Visual SLAM Lecture 14 CH11 code analysis and detailed explanation of exercises after class

If DBoW3 is not installed, the following error will be reported when compiling directly:

fatal error: DBoW3/DBoW3.h: No such file or directory
 #include "DBoW3/DBoW3.h"
          ^~~~~~~~~~~~~~~
compilation terminated.
CMakeFiles/gen_vocab.dir/build.make:82: recipe for target 'CMakeFiles/gen_vocab.dir/gen_vocab_large.cpp.o' failed
make[2]: *** [CMakeFiles/gen_vocab.dir/gen_vocab_large.cpp.o] Error 1
CMakeFiles/Makefile2:99: recipe for target 'CMakeFiles/gen_vocab.dir/all' failed
make[1]: *** [CMakeFiles/gen_vocab.dir/all] Error 2
Makefile:103: recipe for target 'all' failed
make: *** [all] Error 2

Before compiling the program, you need to install DBoW. The download link of the second version of the installation file is as follows:

https://github.com/rmsalinas/DBow3https://github.com/rmsalinas/DBow3 After downloading, the installation method is very simple. Store the files in the folder you want to store and enter the dbow master folder:

mkdir build
cd build
cmake ..

make -j4
sudo make install

When compiling CH11, the following error occurred:

make[2]: *** No rule to make target '/usr/local/lib/libDBoW3.a', needed by 'loop_closure'.  Stop.
make[1]: *** [CMakeFiles/Makefile2:80: CMakeFiles/loop_closure.dir/all] Error 2
make: *** [Makefile:84: all] Error 2

The problem is that libdbow3.0 was not found A this file, so I used dbow3 in / home/liqiang/slambook/3rdparty in the first version tar. GZ. The download link is as follows:

GitHub - gaoxiang12/slambook

The installation method is the same as above.

feature_training.cpp

#include "DBoW3/DBoW3.h" / / word bag support header file
#include <opencv2/core/core. HPP > / / opencv core module
#include <opencv2/highgui/highgui. HPP > / / GUI module
#include <opencv2/features2d/features2d. HPP > / / feature file
#include <iostream>
#include <vector>
#include <string>

using namespace cv;
using namespace std;

/***************************************************
 * This section demonstrates how to train a dictionary according to ten figures in the data / directory
 * ************************************************/

int main( int argc, char** argv ) 
{
    // read the image 
    cout<<"reading images... "<<endl;//Outputting reading images 
    vector<Mat> images; //image
    for ( int i=0; i<10; i++ )//Traverse and read ten images
    {
        string path = "./data/"+to_string(i+1)+".png";
        images.push_back( imread(path) );
    }
    // detect ORB features
    cout<<"detecting ORB features ... "<<endl;//Output detecting ORB features
    Ptr< Feature2D > detector = ORB::create();
    vector<Mat> descriptors;//descriptor 
    for ( Mat& image:images )
    {
        vector<KeyPoint> keypoints; //Key points
        Mat descriptor;//descriptor 
        detector->detectAndCompute( image, Mat(), keypoints, descriptor );//Detection and calculation
        descriptors.push_back( descriptor );
    }
    
    // Create dictionary
    cout<<"creating vocabulary ... "<<endl;//Output (creating vocabulary...) Create dictionary
    DBoW3::Vocabulary vocab;//Default constructor k=10,d=5
    vocab.create( descriptors );
    cout<<"vocabulary info: "<<vocab<<endl;//Dictionary information
    vocab.save( "vocabulary.yml.gz" );//Save dictionary package
    cout<<"done"<<endl;//Output done
    
    return 0;
}

CMakeLists.txt

cmake_minimum_required( VERSION 2.8 )
project( loop_closure )

set( CMAKE_BUILD_TYPE "Release" )
set( CMAKE_CXX_FLAGS "-std=c++14 -O3" )

# opencv 
find_package( OpenCV 3.1 REQUIRED )
include_directories( ${OpenCV_INCLUDE_DIRS} )

# dbow3 
# dbow3 is a simple lib so I assume you installed it in default directory 
set( DBoW3_INCLUDE_DIRS "/usr/local/include" )
set( DBoW3_LIBS "/usr/local/lib/libDBoW3.a" )

add_executable( feature_training feature_training.cpp )
target_link_libraries( feature_training ${OpenCV_LIBS} ${DBoW3_LIBS} )

add_executable( loop_closure loop_closure.cpp )
target_link_libraries( loop_closure ${OpenCV_LIBS} ${DBoW3_LIBS} )

add_executable( gen_vocab gen_vocab_large.cpp )
target_link_libraries( gen_vocab ${OpenCV_LIBS} ${DBoW3_LIBS} )

Execution results:

 ./feature_training ../data/
reading images... 
detecting ORB features ... 
creating vocabulary ... 
vocabulary info: Vocabulary: k = 10, L = 5, Weighting = tf-idf, Scoring = L1-norm, Number of words = 0
done

Number of words = 0 appears here, which is obviously wrong. Through the inspection program, there is a small problem in reading the data path in the data folder. Modify:

Add one more in the path That's it.

The execution results after modifying the program are as follows:

reading images... 
detecting ORB features ... 
creating vocabulary ... 
vocabulary info: Vocabulary: k = 10, L = 5, Weighting = tf-idf, Scoring = L1-norm, Number of words = 4981
done

Where weight is the weight and Scoring is the score.

loop_closure.cpp

#include "DBoW3/DBoW3.h" / / word bag support header file
#include <opencv2/core/core. HPP > / / opencv core module
#include <opencv2/highgui/highgui. HPP > / / GUI module
#include <opencv2/features2d/features2d. HPP > / / feature file
#include <iostream>
#include <vector>
#include <string>

using namespace cv;
using namespace std;

/***************************************************
 * This section demonstrates how to calculate the similarity score based on the previously trained dictionary
 * ************************************************/
int main(int argc, char **argv) {
    // Read the images and database  
    cout << "reading database" << endl;//Outputting Reading database
    DBoW3::Vocabulary vocab("../vocabulary.yml.gz");//vocabulary.yml.gz path
    // DBoW3::Vocabulary vocab("./vocab_larger.yml.gz");  // use large vocab if you want: 
    if (vocab.empty()) {
        cerr << "Vocabulary does not exist." << endl;//Output volatile does not exist
        return 1;
    }
    cout << "reading images... " << endl;//Outputting reading images
    vector<Mat> images;
    for (int i = 0; i < 10; i++) {
        string path = "../data/" + to_string(i + 1) + ".png";//Image reading path
        images.push_back(imread(path));
    }

    // NOTE: in this case we are comparing images with a vocabulary generated by themselves, this may lead to overfit.  Here we use the dictionaries they generate to compare their own similarities, which may produce over fitting
    // detect ORB features
    cout << "detecting ORB features ... " << endl;//Outputting detecting ORB features (testing ORB characteristics)
    Ptr<Feature2D> detector = ORB::create();//The default image has 500 feature points
    vector<Mat> descriptors;//The descriptor extracts ORB features from 10 images and stores them in the vector container
    for (Mat &image:images) {
        vector<KeyPoint> keypoints;//Key points
        Mat descriptor;//descriptor 
        detector->detectAndCompute(image, Mat(), keypoints, descriptor);//Detection and calculation
        descriptors.push_back(descriptor);
    }

    // we can compare the images directly or we can compare one image to a database 
    // images :
    cout << "comparing images with images " << endl;//Outputting comparing images with images
    for (int i = 0; i < images.size(); i++) 
    {
        DBoW3::BowVector v1;
        //descriptors[i] represents all the sub sets of ORB descriptions in image I. the function transform() calculates the word vector described by the previous dictionary. The value of the element in each vector is either 0, indicating that there is no word in image I; Or the weight of the word
        //The BoW description vector contains the ID and weight of each word, which constitute the whole sparse vector
        //When comparing two vectors, DBoW3 calculates a score for us
        vocab.transform(descriptors[i], v1);
        for (int j = i; j < images.size(); j++) 
        {
            DBoW3::BowVector v2;
            vocab.transform(descriptors[j], v2);
            double score = vocab.score(v1, v2);//p296 formula (11.9)
            cout << "image " << i << " vs image " << j << " : " << score << endl;//Output the similarity score between one image and another image
        }
        cout << endl;
    }

    // or with database 
    //During database query, DBoW sorts the above scores and gives the most similar results
    cout << "comparing images with database " << endl;
    DBoW3::Database db(vocab, false, 0);
    for (int i = 0; i < descriptors.size(); i++) 
        db.add(descriptors[i]);
    cout << "database info: " << db << endl;//Output database info as
    for (int i = 0; i < descriptors.size(); i++) 
    {
        DBoW3::QueryResults ret;
        db.query(descriptors[i], ret, 4);      // max result=4
        cout << "searching for image " << i << " returns " << ret << endl << endl;
    }
    cout << "done." << endl;
}

CMakeLists.txt

Same as above.

Execution results:

At Ubuntu 20 04 when executing:

reading database
reading images... 
detecting ORB features ... 
comparing images with images 
image 0 vs image 0 : 1
image 0 vs image 1 : 0.0322942
image 0 vs image 2 : 0.0348326
image 0 vs image 3 : 0.0292106
image 0 vs image 4 : 0.0307606
image 0 vs image 5 : 0.0386504
image 0 vs image 6 : 0.0267389
image 0 vs image 7 : 0.0254779
image 0 vs image 8 : 0.041301
image 0 vs image 9 : 0.0501515

image 1 vs image 1 : 1
image 1 vs image 2 : 0.041587
image 1 vs image 3 : 0.034046
image 1 vs image 4 : 0.0318553
image 1 vs image 5 : 0.0354084
image 1 vs image 6 : 0.0221539
image 1 vs image 7 : 0.0296462
image 1 vs image 8 : 0.0397894
image 1 vs image 9 : 0.0306703

image 2 vs image 2 : 1
image 2 vs image 3 : 0.0322172
image 2 vs image 4 : 0.0371113
image 2 vs image 5 : 0.0338423
image 2 vs image 6 : 0.0360772
image 2 vs image 7 : 0.044198
image 2 vs image 8 : 0.0354693
image 2 vs image 9 : 0.0351865

image 3 vs image 3 : 1
image 3 vs image 4 : 0.0278296
image 3 vs image 5 : 0.0338019
image 3 vs image 6 : 0.0349277
image 3 vs image 7 : 0.0294855
image 3 vs image 8 : 0.0299692
image 3 vs image 9 : 0.0469051

image 4 vs image 4 : 1
image 4 vs image 5 : 0.0630388
image 4 vs image 6 : 0.0355424
image 4 vs image 7 : 0.0294301
image 4 vs image 8 : 0.0295447
image 4 vs image 9 : 0.026492

image 5 vs image 5 : 1
image 5 vs image 6 : 0.0365682
image 5 vs image 7 : 0.0275375
image 5 vs image 8 : 0.0309867
image 5 vs image 9 : 0.0337013

image 6 vs image 6 : 1
image 6 vs image 7 : 0.0297398
image 6 vs image 8 : 0.0345615
image 6 vs image 9 : 0.0337139

image 7 vs image 7 : 1
image 7 vs image 8 : 0.0182667
image 7 vs image 9 : 0.0225071

image 8 vs image 8 : 1
image 8 vs image 9 : 0.0432488

image 9 vs image 9 : 1

The following error message appears. I don't know why. I changed a computer, Ubuntu 18 04 is OK. It's the same code (I haven't figured it out yet)

comparing images with database 
terminate called after throwing an instance of 'std::length_error'
  what():  cannot create std::vector larger than max_size()
Aborted (core dumped)

Here is Ubuntu 18 Results from 04:

./loop_closure 

reading database
reading images... 
detecting ORB features ... 
comparing images with images 
image 0 vs image 0 : 1
image 0 vs image 1 : 0.0322942
image 0 vs image 2 : 0.0348326
image 0 vs image 3 : 0.0292106
image 0 vs image 4 : 0.0307606
image 0 vs image 5 : 0.0386504
image 0 vs image 6 : 0.0267389
image 0 vs image 7 : 0.0254779
image 0 vs image 8 : 0.041301
image 0 vs image 9 : 0.0501515

image 1 vs image 1 : 1
image 1 vs image 2 : 0.041587
image 1 vs image 3 : 0.034046
image 1 vs image 4 : 0.0318553
image 1 vs image 5 : 0.0354084
image 1 vs image 6 : 0.0221539
image 1 vs image 7 : 0.0296462
image 1 vs image 8 : 0.0397894
image 1 vs image 9 : 0.0306703

image 2 vs image 2 : 1
image 2 vs image 3 : 0.0322172
image 2 vs image 4 : 0.0371113
image 2 vs image 5 : 0.0338423
image 2 vs image 6 : 0.0360772
image 2 vs image 7 : 0.044198
image 2 vs image 8 : 0.0354693
image 2 vs image 9 : 0.0351865

image 3 vs image 3 : 1
image 3 vs image 4 : 0.0278296
image 3 vs image 5 : 0.0338019
image 3 vs image 6 : 0.0349277
image 3 vs image 7 : 0.0294855
image 3 vs image 8 : 0.0299692
image 3 vs image 9 : 0.0469051

image 4 vs image 4 : 1
image 4 vs image 5 : 0.0630388
image 4 vs image 6 : 0.0355424
image 4 vs image 7 : 0.0294301
image 4 vs image 8 : 0.0295447
image 4 vs image 9 : 0.026492

image 5 vs image 5 : 1
image 5 vs image 6 : 0.0365682
image 5 vs image 7 : 0.0275375
image 5 vs image 8 : 0.0309867
image 5 vs image 9 : 0.0337013

image 6 vs image 6 : 1
image 6 vs image 7 : 0.0297398
image 6 vs image 8 : 0.0345615
image 6 vs image 9 : 0.0337139

image 7 vs image 7 : 1
image 7 vs image 8 : 0.0182667
image 7 vs image 9 : 0.0225071

image 8 vs image 8 : 1
image 8 vs image 9 : 0.0432488

image 9 vs image 9 : 1

comparing images with database 
database info: Database: Entries = 10, Using direct index = no. Vocabulary: k = 10, L = 5, Weighting = tf-idf, Scoring = L1-norm, Number of words = 4983
searching for image 0 returns 4 results:
<EntryId: 0, Score: 1>
<EntryId: 9, Score: 0.0501515>
<EntryId: 8, Score: 0.041301>
<EntryId: 5, Score: 0.0386504>

searching for image 1 returns 4 results:
<EntryId: 1, Score: 1>
<EntryId: 2, Score: 0.041587>
<EntryId: 8, Score: 0.0397894>
<EntryId: 5, Score: 0.0354084>

searching for image 2 returns 4 results:
<EntryId: 2, Score: 1>
<EntryId: 7, Score: 0.044198>
<EntryId: 1, Score: 0.041587>
<EntryId: 4, Score: 0.0371113>

searching for image 3 returns 4 results:
<EntryId: 3, Score: 1>
<EntryId: 9, Score: 0.0469051>
<EntryId: 6, Score: 0.0349277>
<EntryId: 1, Score: 0.034046>

searching for image 4 returns 4 results:
<EntryId: 4, Score: 1>
<EntryId: 5, Score: 0.0630388>
<EntryId: 2, Score: 0.0371113>
<EntryId: 6, Score: 0.0355424>

searching for image 5 returns 4 results:
<EntryId: 5, Score: 1>
<EntryId: 4, Score: 0.0630388>
<EntryId: 0, Score: 0.0386504>
<EntryId: 6, Score: 0.0365682>

searching for image 6 returns 4 results:
<EntryId: 6, Score: 1>
<EntryId: 5, Score: 0.0365682>
<EntryId: 2, Score: 0.0360772>
<EntryId: 4, Score: 0.0355424>

searching for image 7 returns 4 results:
<EntryId: 7, Score: 1>
<EntryId: 2, Score: 0.044198>
<EntryId: 6, Score: 0.0297398>
<EntryId: 1, Score: 0.0296462>

searching for image 8 returns 4 results:
<EntryId: 8, Score: 1>
<EntryId: 9, Score: 0.0432488>
<EntryId: 0, Score: 0.041301>
<EntryId: 1, Score: 0.0397894>

searching for image 9 returns 4 results:
<EntryId: 9, Score: 1>
<EntryId: 0, Score: 0.0501515>
<EntryId: 3, Score: 0.0469051>
<EntryId: 8, Score: 0.0432488>

done.

gen_vocab_large.cpp

When the code in the book is executed, the following errors will be reported. The txt file described in the code is not under the folder. It is not clear where there is a problem.

terminate called after throwing an instance of 'std::logic_error'
  what():  basic_string::_M_construct null not valid
Aborted (core dumped)

Make a little change to the code:

#include "DBoW3/DBoW3.h" / / word bag support header file
#include <opencv2/core/core. HPP > / / opencv core module
#include <opencv2/highgui/highgui. HPP > / / GUI module
#include <opencv2/features2d/features2d. HPP > / / feature file
#include <iostream>
#include <vector>
#include <string>

using namespace cv;
using namespace std;


int main( int argc, char** argv )
{
    String directoryPath = "/home/liqiang/slambook2/ch11/rgbd_dataset_freiburg1_desk2/rgb";//Image path
    vector<String> imagesPath;
    glob(directoryPath, imagesPath);
    // string dataset_dir = argv[1];
    // ifstream fin ( dataset_dir+"/home/liqiang/slambook2/ch11/rgbd_dataset_freiburg1_desk2/rgb" );
    // if ( !fin )
    // {
    //     cout<<"please generate the associate file called associate.txt!"<<endl;
    //     return 1;
    // }

    // vector<string> rgb_files, depth_files;
    // vector<double> rgb_times, depth_times;
    // while ( !fin.eof() )
    // {
    //     string rgb_time, rgb_file, depth_time, depth_file;
    //     fin>>rgb_time>>rgb_file>>depth_time>>depth_file;
    //     rgb_times.push_back ( atof ( rgb_time.c_str() ) );
    //     depth_times.push_back ( atof ( depth_time.c_str() ) );
    //     rgb_files.push_back ( dataset_dir+"/"+rgb_file );
    //     depth_files.push_back ( dataset_dir+"/"+depth_file );

    //     if ( fin.good() == false )
    //         break;
    // }
    // fin.close();
    
    cout<<"generating features ... "<<endl;//Output generating features
    vector<Mat> descriptors;//descriptor 
    Ptr< Feature2D > detector = ORB::create();
    int index = 1;
    for ( String path : imagesPath )
    {
        Mat image = imread(path);
        vector<KeyPoint> keypoints; //Key points
        Mat descriptor;//descriptor 
        detector->detectAndCompute( image, Mat(), keypoints, descriptor );
        descriptors.push_back( descriptor );
        cout<<"extracting features from image " << index++ <<endl;//Outputting extracting features from image
    }
    cout<<"extract total "<<descriptors.size()*500<<" features."<<endl;
    
    // create vocabulary 
    cout<<"creating vocabulary, please wait ... "<<endl;//Output creating dictionary, please wait
    DBoW3::Vocabulary vocab;
    vocab.create( descriptors );
    cout<<"vocabulary info: "<<vocab<<endl;
    vocab.save( "vocab_larger.yml.gz" );//Save dictionary
    cout<<"done"<<endl;
    
    return 0;
}

The data set needs to be downloaded from the image path, and the download address is as follows:

Computer Vision Group - Dataset Download

CMakeLists.txt

Same as above.

Execution results:

./gen_vocab
generating features ... 
extracting features from image 1
extracting features from image 2
extracting features from image 3
extracting features from image 4
extracting features from image 5
extracting features from image 6
extracting features from image 7
extracting features from image 8
extracting features from image 9
extracting features from image 10
.....
extracting features from image 634
extracting features from image 635
extracting features from image 636
extracting features from image 637
extracting features from image 638
extracting features from image 639
extracting features from image 640
extract total 320000 features.
creating vocabulary, please wait ... 
vocabulary info: Vocabulary: k = 10, L = 5, Weighting = tf-idf, Scoring = L1-norm, Number of words = 89315
done

After execution, a vocab will be generated under the build folder_ larger. yml. GZ, and then you can use this dictionary to execute loop_closure.cpp, just add loop_ closure. It's ok to modify the dictionary in CPP.

Execute loop again_ closure. CPP, the execution results are as follows:

reading database
reading images... 
detecting ORB features ... 
comparing images with images 
image 0 vs image 0 : 1
image 0 vs image 1 : 0.00401522
image 0 vs image 2 : 0.00575911
image 0 vs image 3 : 0.0057625
image 0 vs image 4 : 0.00516026
image 0 vs image 5 : 0.00289918
image 0 vs image 6 : 0.00280098
image 0 vs image 7 : 0.00329088
image 0 vs image 8 : 0.00869696
image 0 vs image 9 : 0.0304572

image 1 vs image 1 : 1
image 1 vs image 2 : 0.0241793
image 1 vs image 3 : 0.00553848
image 1 vs image 4 : 0.00522892
image 1 vs image 5 : 0.00702649
image 1 vs image 6 : 0.00331991
image 1 vs image 7 : 0.0035423
image 1 vs image 8 : 0.00950168
image 1 vs image 9 : 0.00598861

image 2 vs image 2 : 1
image 2 vs image 3 : 0.00634031
image 2 vs image 4 : 0.00541992
image 2 vs image 5 : 0.0149133
image 2 vs image 6 : 0.00789202
image 2 vs image 7 : 0.00498983
image 2 vs image 8 : 0.00329779
image 2 vs image 9 : 0.00490939

image 3 vs image 3 : 1
image 3 vs image 4 : 0.00195016
image 3 vs image 5 : 0.0150889
image 3 vs image 6 : 0.0073025
image 3 vs image 7 : 0.00476159
image 3 vs image 8 : 0.0110854
image 3 vs image 9 : 0.00516915

image 4 vs image 4 : 1
image 4 vs image 5 : 0.0105219
image 4 vs image 6 : 0.00596558
image 4 vs image 7 : 0.00467202
image 4 vs image 8 : -0
image 4 vs image 9 : 0.00676682

image 5 vs image 5 : 1
image 5 vs image 6 : 0.0015908
image 5 vs image 7 : 0.00508986
image 5 vs image 8 : 0.00442575
image 5 vs image 9 : 0.00177321

image 6 vs image 6 : 1
image 6 vs image 7 : 0.00579406
image 6 vs image 8 : 0.0069873
image 6 vs image 9 : 0.00166793

image 7 vs image 7 : 1
image 7 vs image 8 : 0.00720273
image 7 vs image 9 : 0.00174475

image 8 vs image 8 : 1
image 8 vs image 9 : 0.00937256

image 9 vs image 9 : 1

comparing images with database 
database info: Database: Entries = 10, Using direct index = no. Vocabulary: k = 10, L = 5, Weighting = tf-idf, Scoring = L1-norm, Number of words = 99566
searching for image 0 returns 4 results:
<EntryId: 0, Score: 1>
<EntryId: 9, Score: 0.0304572>
<EntryId: 8, Score: 0.00869696>
<EntryId: 3, Score: 0.0057625>

searching for image 1 returns 4 results:
<EntryId: 1, Score: 1>
<EntryId: 2, Score: 0.0241793>
<EntryId: 8, Score: 0.00950168>
<EntryId: 5, Score: 0.00702649>

searching for image 2 returns 4 results:
<EntryId: 2, Score: 1>
<EntryId: 1, Score: 0.0241793>
<EntryId: 5, Score: 0.0149133>
<EntryId: 6, Score: 0.00789202>

searching for image 3 returns 4 results:
<EntryId: 3, Score: 1>
<EntryId: 5, Score: 0.0150889>
<EntryId: 8, Score: 0.0110854>
<EntryId: 6, Score: 0.0073025>

searching for image 4 returns 4 results:
<EntryId: 4, Score: 1>
<EntryId: 5, Score: 0.0105219>
<EntryId: 9, Score: 0.00676682>
<EntryId: 6, Score: 0.00596558>

searching for image 5 returns 4 results:
<EntryId: 5, Score: 1>
<EntryId: 3, Score: 0.0150889>
<EntryId: 2, Score: 0.0149133>
<EntryId: 4, Score: 0.0105219>

searching for image 6 returns 4 results:
<EntryId: 6, Score: 1>
<EntryId: 2, Score: 0.00789202>
<EntryId: 3, Score: 0.0073025>
<EntryId: 8, Score: 0.0069873>

searching for image 7 returns 4 results:
<EntryId: 7, Score: 1>
<EntryId: 8, Score: 0.00720273>
<EntryId: 6, Score: 0.00579406>
<EntryId: 5, Score: 0.00508986>

searching for image 8 returns 4 results:
<EntryId: 8, Score: 1>
<EntryId: 3, Score: 0.0110854>
<EntryId: 1, Score: 0.00950168>
<EntryId: 9, Score: 0.00937256>

searching for image 9 returns 4 results:
<EntryId: 9, Score: 1>
<EntryId: 0, Score: 0.0304572>
<EntryId: 8, Score: 0.00937256>
<EntryId: 4, Score: 0.00676682>

done.

After class exercises

1. Please write a small program to calculate PR curve. It may be easier to use MATLAB or Python because they are good at drawing.

Before testing, you need to install scikit learn and matplotlib:

To install scikit learn: Installing scikit-learn — scikit-learn 1.0.1 documentation

pip3 install -U scikit-learn

matplotlib: 

 pip install matplotlib

The following code is reproduced in: Three minutes will take you to understand roc curve and PR curve_ Guo_Python blog - CSDN blog_ roc curve and PR curve

 pr.py: 

import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import precision_recall_curve,roc_curve
 
 
def draw_pr(confidence_scores, data_labels):
    plt.figure()
    plt.title('PR Curve')
    plt.xlabel('Recall')
    plt.ylabel('Precision')
    plt.grid()
 
    #Accuracy, recall, threshold
    precision,recall,thresholds = precision_recall_curve(data_labels,confidence_scores)
 
    from sklearn.metrics import average_precision_score
    AP = average_precision_score(data_labels, confidence_scores) # Calculate AP
    plt.plot(recall, precision, label = 'pr_curve(AP=%0.2f)' % AP)
    plt.legend()
    plt.show()
 
def draw_roc(confidence_scores, data_labels):
    #True rate
    fpr, tpr, thresholds = roc_curve(data_labels, confidence_scores)
    plt.figure()
    plt.grid()
    plt.title('Roc Curve')
    plt.xlabel('FPR')
    plt.ylabel('TPR')
 
    from sklearn.metrics import auc
    auc=auc(fpr, tpr) #AUC calculation
    plt.plot(fpr,tpr,label = 'roc_curve(AUC=%0.2f)' % auc)
    plt.legend()
    plt.show()
 
 
if __name__ == '__main__':
    # The confidence of positive samples, that is, the probability that the model is identified as 1
    confidence_scores = np.array([0.9, 0.78, 0.6, 0.46, 0.4, 0.37, 0.2, 0.16])
    # Real label
    data_labels = np.array([1,1,0,1,0,0,1,1])
 
    draw_pr(confidence_scores, data_labels)
    draw_roc(confidence_scores, data_labels)

When running under Ubuntu, I put the python file under the ch11 folder:

python pr.py

Execution results:

Reproduced at:
Roc curve and pr curve understanding and simple code implementation_ JMU-HZH blog - CSDN blog_ Realization of pr curve
 

 pr1.py:

import matplotlib
import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import precision_recall_curve,roc_curve

plt.figure()
plt.title('PR Curve')
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.grid()

#Just understand the meaning of the two curves, so the data is simple to construct
confidence_scores = np.array([0.9,0.46,0.78,0.37,0.6,0.4,0.2,0.16])
confidence_scores=sorted(confidence_scores,reverse=True)#Confidence ranking from large to small
print(confidence_scores)

data_labels = np.array([1,1,0,1,0,0 ,1,1])#Label corresponding to confidence

#Accuracy, recall, threshold
precision,recall,thresholds = precision_recall_curve(data_labels,confidence_scores)
print(precision)
print(recall)
print(thresholds)
plt.plot(recall,precision)
plt.show()

#True rate
fpr, tpr, thresholds = roc_curve(data_labels, confidence_scores)
#print(fpr)
#print(tpr)
plt.figure()
plt.grid()
plt.title('Roc Curve')
plt.xlabel('FPR')
plt.ylabel('TPR')

from sklearn.metrics import auc
auc=auc(fpr, tpr)#AUC calculation
plt.plot(fpr,tpr,label='roc_curve(AUC=%0.2f)'%auc)
plt.legend()
plt.show()

Execution results:

python pr1.py 

[0.9, 0.78, 0.6, 0.46, 0.4, 0.37, 0.2, 0.16]
[0.625      0.57142857 0.5        0.6        0.75       0.66666667
 1.         1.         1.        ]
[1.  0.8 0.6 0.6 0.6 0.4 0.4 0.2 0. ]
[0.16 0.2  0.37 0.4  0.46 0.6  0.78 0.9 ]

 

2. To verify the loopback detection algorithm, it is necessary to manually mark the loopback data set, such as [103]. However, it is inconvenient to mark the loop manually. We will consider calculating the loop according to the standard trajectory. That is, if the pose of two frames in the track is very similar, they are considered loop. Please calculate the loop in a data set according to the standard trajectory given by the TUM data set. Are the images of these loops really similar?

Reproduced at: Visual SLAM Lecture 14 (Second Edition) lesson 11 problem solving - Zhihu

#include <pangolin/pangolin.h>
#include <Eigen/Core>
#include <Eigen/Geometry> 
#include <unistd.h>

using namespace std;
using namespace Eigen;

// path to groundtruth file
string groundtruth_file = "/home/liqiang/slambook2/ch11/rgbd_dataset_freiburg2_rpy/groundtruth.txt";
// Set the detection interval so that the detection has sparsity and covers the whole environment at the same time
int delta = 50; 
// Norm of difference of homogeneous transformation matrix

// Less than this value, the pose is considered very close
double threshold = 0.4; 

int main(int argc, char **argv) {

  vector<Isometry3d, Eigen::aligned_allocator<Isometry3d>> poses;
  vector<string> times;
  
  ifstream fin(groundtruth_file);
  if (!fin) {
    cout << "cannot find trajectory file at " << groundtruth_file << endl;
    return 1;
  }
  
  int num = 0;
  
  while (!fin.eof()) 
  {
    string time_s;
    double tx, ty, tz, qx, qy, qz, qw;
    fin >> time_s >> tx >> ty >> tz >> qx >> qy >> qz >> qw;
    Isometry3d Twr(Quaterniond(qw, qx, qy, qz));
    Twr.pretranslate(Vector3d(tx, ty, tz));
    // It is equivalent to starting from the 150th pose, because the standard trajectory is recorded earlier than the photos (there is no corresponding photo for the first 120 poses)
    if (num > 120 && num % delta == 0){
      times.push_back(time_s);
      poses.push_back(Twr);
    }
    num++;
  }
  cout << "read total " << num << " pose entries" << endl;
  cout << "selected total " << poses.size() << " pose entries" << endl;
  

  //Set the number of picture intervals to restart detection after loop detection
  cout << "**************************************************" << endl;
  cout << "Detection Start!!!" << endl;
  cout << "**************************************************" << endl;
  for (size_t i = 0 ; i < poses.size() - delta; i += delta){
    for (size_t j = i + delta ; j < poses.size() ; j++){
      Matrix4d Error = (poses[i].inverse() * poses[j]).matrix() - Matrix4d::Identity();
      if (Error.norm() < threshold){
	cout << "The first" << i << "Photo and page" << j << "This photo forms a loop" << endl;
	cout << "The pose error is" << Error.norm() << endl;
	cout << "The first" << i << "The timestamp of this photo is" << endl << times[i] << endl;
	cout << "The first" << j << "The timestamp of this photo is" << endl << times[j] << endl;
	cout << "**************************************************" << endl;
	break;
      }
    } 
  }
  cout << "Detection Finish!!!" << endl;
  cout << "**************************************************" << endl;
  return 0;
}

I tried this code, but it didn't run through. The error message was killed. I didn't understand what it meant. There may be insufficient memory or too much computation. If you want to try, run it.


3. Learn DBoW3 or DBoW2 library, find some pictures by yourself, and see if the loop can be detected correctly.

The datasets I use are: Computer Vision Group - Dataset Download

Then create a new folder data1 under ch11 and select 21 pictures to put in.

Then modify the image path:

gen_vocab_large3.cpp

#include "DBoW3/DBoW3.h" / / word bag support header file
#include <opencv2/core/core. HPP > / / opencv core module
#include <opencv2/highgui/highgui. HPP > / / GUI module
#include <opencv2/features2d/features2d. HPP > / / feature file
#include <iostream>
#include <vector>
#include <string>

using namespace cv;
using namespace std;


int main( int argc, char** argv )
{
    String directoryPath = "/home/liqiang/slambook2/ch11/data1";//Image path
    vector<String> imagesPath;
    glob(directoryPath, imagesPath);
    // string dataset_dir = argv[1];
    // ifstream fin ( dataset_dir+"/home/liqiang/slambook2/ch11/rgbd_dataset_freiburg1_desk2/rgb" );
    // if ( !fin )
    // {
    //     cout<<"please generate the associate file called associate.txt!"<<endl;
    //     return 1;
    // }

    // vector<string> rgb_files, depth_files;
    // vector<double> rgb_times, depth_times;
    // while ( !fin.eof() )
    // {
    //     string rgb_time, rgb_file, depth_time, depth_file;
    //     fin>>rgb_time>>rgb_file>>depth_time>>depth_file;
    //     rgb_times.push_back ( atof ( rgb_time.c_str() ) );
    //     depth_times.push_back ( atof ( depth_time.c_str() ) );
    //     rgb_files.push_back ( dataset_dir+"/"+rgb_file );
    //     depth_files.push_back ( dataset_dir+"/"+depth_file );

    //     if ( fin.good() == false )
    //         break;
    // }
    // fin.close();
    
    cout<<"generating features ... "<<endl;//Output generating features
    vector<Mat> descriptors;//descriptor 
    Ptr< Feature2D > detector = ORB::create();
    int index = 1;
    for ( String path : imagesPath )
    {
        Mat image = imread(path);
        vector<KeyPoint> keypoints; //Key points
        Mat descriptor;//descriptor 
        detector->detectAndCompute( image, Mat(), keypoints, descriptor );
        descriptors.push_back( descriptor );
        cout<<"extracting features from image " << index++ <<endl;//Outputting extracting features from image
    }
    cout<<"extract total "<<descriptors.size()*500<<" features."<<endl;
    
    // create vocabulary 
    cout<<"creating vocabulary, please wait ... "<<endl;//Output creating dictionary, please wait
    DBoW3::Vocabulary vocab;
    vocab.create( descriptors );
    cout<<"vocabulary info: "<<vocab<<endl;
    vocab.save( "vocab_larger3.yml.gz" );//Save dictionary
    cout<<"done"<<endl;
    
    return 0;
}

CMakeLists.txt 

cmake_minimum_required( VERSION 2.8 )
project( loop_closure )

set( CMAKE_BUILD_TYPE "Release" )
set( CMAKE_CXX_FLAGS "-std=c++14 -O3" )

# opencv 
find_package( OpenCV 3.1 REQUIRED )
include_directories( ${OpenCV_INCLUDE_DIRS} )

# Add Pangolin dependency
find_package( Pangolin )
include_directories( ${Pangolin_INCLUDE_DIRS} )

# Add Eigen header file
include_directories("/usr/include/eigen3")
add_executable( 2 2.cpp )
target_link_libraries( 2 ${OpenCV_LIBS} ${DBoW3_LIBS} ${Pangolin_LIBRARIES} )


# dbow3 
# dbow3 is a simple lib so I assume you installed it in default directory 
set( DBoW3_INCLUDE_DIRS "/usr/local/include" )
set( DBoW3_LIBS "/usr/local/lib/libDBoW3.a" )

add_executable( feature_training feature_training.cpp )
target_link_libraries( feature_training ${OpenCV_LIBS} ${DBoW3_LIBS} )

add_executable( loop_closure loop_closure.cpp )
target_link_libraries( loop_closure ${OpenCV_LIBS} ${DBoW3_LIBS} )


add_executable( loop_closure1 loop_closure1.cpp )
target_link_libraries( loop_closure1 ${OpenCV_LIBS} ${DBoW3_LIBS} )

add_executable( loop_closure3 loop_closure3.cpp )
target_link_libraries( loop_closure3 ${OpenCV_LIBS} ${DBoW3_LIBS} )


add_executable( gen_vocab gen_vocab_large.cpp )
target_link_libraries( gen_vocab ${OpenCV_LIBS} ${DBoW3_LIBS} )

add_executable( gen_vocab1 gen_vocab_large1.cpp )
target_link_libraries( gen_vocab1 ${OpenCV_LIBS} ${DBoW3_LIBS} )

add_executable( gen_vocab2 gen_vocab_large2.cpp )
target_link_libraries( gen_vocab2 ${OpenCV_LIBS} ${DBoW3_LIBS} )

add_executable( gen_vocab3 gen_vocab_large3.cpp )
target_link_libraries( gen_vocab3 ${OpenCV_LIBS} ${DBoW3_LIBS} )

Execution results:

./gen_vocab3
generating features ... 
extracting features from image 1
extracting features from image 2
extracting features from image 3
extracting features from image 4
extracting features from image 5
extracting features from image 6
extracting features from image 7
extracting features from image 8
extracting features from image 9
extracting features from image 10
extracting features from image 11
extracting features from image 12
extracting features from image 13
extracting features from image 14
extracting features from image 15
extracting features from image 16
extracting features from image 17
extracting features from image 18
extracting features from image 19
extracting features from image 20
extracting features from image 21
extract total 10500 features.
creating vocabulary, please wait ... 
vocabulary info: Vocabulary: k = 10, L = 5, Weighting = tf-idf, Scoring = L1-norm, Number of words = 10381
done

After execution, a vocab will be generated in the build folder_ larger3. yml. GZ compressed package. Finally, put the compressed package under ch11 and execute loop_closure3.

Modify the following two places:

loop_closure3.cpp

#include "DBoW3/DBoW3.h" / / word bag support header file
#include <opencv2/core/core. HPP > / / opencv core module
#include <opencv2/highgui/highgui. HPP > / / GUI module
#include <opencv2/features2d/features2d. HPP > / / feature file
#include <iostream>
#include <vector>
#include <string>

using namespace cv;
using namespace std;

/***************************************************
 * This section demonstrates how to calculate the similarity score based on the previously trained dictionary
 * ************************************************/
int main(int argc, char **argv) {
    // Read the images and database  
    cout << "reading database" << endl;//Outputting Reading database
    DBoW3::Vocabulary vocab("../vocab_larger3.yml.gz");//vocabulary.yml.gz path
    // DBoW3::Vocabulary vocab("./vocab_larger.yml.gz");  // use large vocab if you want: 
    if (vocab.empty()) {
        cerr << "Vocabulary does not exist." << endl;//Output volatile does not exist
        return 1;
    }
    cout << "reading images... " << endl;//Outputting reading images
    vector<Mat> images;
    for (int i = 0; i < 21; i++) {
        string path = "../data1/" + to_string(i + 1) + ".png";//Image reading path
        images.push_back(imread(path));
    }

    // NOTE: in this case we are comparing images with a vocabulary generated by themselves, this may lead to overfit.  Here we use the dictionaries they generate to compare their own similarities, which may produce over fitting
    // detect ORB features
    cout << "detecting ORB features ... " << endl;//Outputting detecting ORB features (testing ORB characteristics)
    Ptr<Feature2D> detector = ORB::create();//The default image has 500 feature points
    vector<Mat> descriptors;//The descriptor extracts ORB features from 10 images and stores them in the vector container
    for (Mat &image:images) {
        vector<KeyPoint> keypoints;//Key points
        Mat descriptor;//descriptor 
        detector->detectAndCompute(image, Mat(), keypoints, descriptor);//Detection and calculation
        descriptors.push_back(descriptor);
    }

    // we can compare the images directly or we can compare one image to a database 
    // images :
    cout << "comparing images with images " << endl;//Outputting comparing images with images
    for (int i = 0; i < images.size(); i++) 
    {
        DBoW3::BowVector v1;
        //descriptors[i] represents all the sub sets of ORB descriptions in image I. the function transform() calculates the word vector described by the previous dictionary. The value of the element in each vector is either 0, indicating that there is no word in image I; Or the weight of the word
        //The BoW description vector contains the ID and weight of each word, which constitute the whole sparse vector
        //When comparing two vectors, DBoW3 calculates a score for us
        vocab.transform(descriptors[i], v1);
        for (int j = i; j < images.size(); j++) 
        {
            DBoW3::BowVector v2;
            vocab.transform(descriptors[j], v2);
            double score = vocab.score(v1, v2);//p296 formula (11.9)
            cout << "image " << i << " vs image " << j << " : " << score << endl;//Output the similarity score between one image and another image
        }
        cout << endl;
    }

    // or with database 
    //During database query, DBoW sorts the above scores and gives the most similar results
    cout << "comparing images with database " << endl;
    DBoW3::Database db(vocab, false, 0);
    for (int i = 0; i < descriptors.size(); i++) 
        db.add(descriptors[i]);
    cout << "database info: " << db << endl;//Output database info as
    for (int i = 0; i < descriptors.size(); i++) 
    {
        DBoW3::QueryResults ret;
        db.query(descriptors[i], ret, 4);      // max result=4
        cout << "searching for image " << i << " returns " << ret << endl << endl;
    }
    cout << "done." << endl;
}

CMakeLists.txt  

Refer to the above, cmakelists Txt has added the relevant cpp execution file.

./loop_closure3
reading database
reading images... 
detecting ORB features ... 
comparing images with images 
image 0 vs image 0 : 1
image 0 vs image 1 : 0.0179514
image 0 vs image 2 : 0.0257712
image 0 vs image 3 : 0.0248006
image 0 vs image 4 : 0.0215647
image 0 vs image 5 : 0.00544075
image 0 vs image 6 : 0.0224883
image 0 vs image 7 : 0.0172719
image 0 vs image 8 : 0.0177548
image 0 vs image 9 : 0.0362582
image 0 vs image 10 : 0.0162675
image 0 vs image 11 : 0.0222014
image 0 vs image 12 : 0.0204588
image 0 vs image 13 : 0.0170047
image 0 vs image 14 : 0.0165957
image 0 vs image 15 : 0.0241384
image 0 vs image 16 : 0.0131228
image 0 vs image 17 : 0.0231237
image 0 vs image 18 : 0.0126125
image 0 vs image 19 : 0.0264222
image 0 vs image 20 : 0.0319604

image 1 vs image 1 : 1
image 1 vs image 2 : 0.0225294
image 1 vs image 3 : 0.0291438
image 1 vs image 4 : 0.024401
image 1 vs image 5 : 0.0427242
image 1 vs image 6 : 0.00947695
image 1 vs image 7 : 0.0336035
image 1 vs image 8 : 0.0554665
image 1 vs image 9 : 0.0313537
image 1 vs image 10 : 0.0127257
image 1 vs image 11 : 0.0170929
image 1 vs image 12 : 0.024939
image 1 vs image 13 : 0.0188714
image 1 vs image 14 : 0.0191085
image 1 vs image 15 : 0.0482948
image 1 vs image 16 : 0.0242885
image 1 vs image 17 : 0.0134153
image 1 vs image 18 : 0.017274
image 1 vs image 19 : 0.0283448
image 1 vs image 20 : 0.00922942

image 2 vs image 2 : 1
image 2 vs image 3 : 0.0159252
image 2 vs image 4 : 0.0253237
image 2 vs image 5 : 0.0118317
image 2 vs image 6 : 0.0571594
image 2 vs image 7 : 0.0189714
image 2 vs image 8 : 0.0155815
image 2 vs image 9 : 0.0195412
image 2 vs image 10 : 0.0184117
image 2 vs image 11 : 0.0152941
image 2 vs image 12 : 0.0178018
image 2 vs image 13 : 0.0233106
image 2 vs image 14 : 0.0168851
image 2 vs image 15 : 0.0137194
image 2 vs image 16 : 0.0498792
image 2 vs image 17 : 0.0240186
image 2 vs image 18 : 0.0219548
image 2 vs image 19 : 0.0209176
image 2 vs image 20 : 0.0140803

image 3 vs image 3 : 1
image 3 vs image 4 : 0.0234056
image 3 vs image 5 : 0.0284397
image 3 vs image 6 : 0.02011
image 3 vs image 7 : 0.0216389
image 3 vs image 8 : 0.0176086
image 3 vs image 9 : 0.0155744
image 3 vs image 10 : 0.0170962
image 3 vs image 11 : 0.0225567
image 3 vs image 12 : 0.0234662
image 3 vs image 13 : 0.0182703
image 3 vs image 14 : 0.01482
image 3 vs image 15 : 0.020363
image 3 vs image 16 : 0.0176234
image 3 vs image 17 : 0.0233771
image 3 vs image 18 : 0.0155559
image 3 vs image 19 : 0.016011
image 3 vs image 20 : 0.0177395

image 4 vs image 4 : 1
image 4 vs image 5 : 0.0119718
image 4 vs image 6 : 0.0274229
image 4 vs image 7 : 0.0149015
image 4 vs image 8 : 0.0252062
image 4 vs image 9 : 0.0127473
image 4 vs image 10 : 0.0123496
image 4 vs image 11 : 0.0234471
image 4 vs image 12 : 0.0255185
image 4 vs image 13 : 0.018047
image 4 vs image 14 : 0.0397562
image 4 vs image 15 : 0.0105365
image 4 vs image 16 : 0.0148716
image 4 vs image 17 : 0.0347258
image 4 vs image 18 : 0.0131217
image 4 vs image 19 : 0.0191835
image 4 vs image 20 : 0.0211236

image 5 vs image 5 : 1
image 5 vs image 6 : 0.0141552
image 5 vs image 7 : 0.0205087
image 5 vs image 8 : 0.023158
image 5 vs image 9 : 0.0193337
image 5 vs image 10 : 0.0187104
image 5 vs image 11 : 0.025994
image 5 vs image 12 : 0.0196689
image 5 vs image 13 : 0.0257136
image 5 vs image 14 : 0.0124622
image 5 vs image 15 : 0.0692064
image 5 vs image 16 : 0.0210536
image 5 vs image 17 : 0.0252288
image 5 vs image 18 : 0.0119623
image 5 vs image 19 : 0.0251428
image 5 vs image 20 : 0.0231639

image 6 vs image 6 : 1
image 6 vs image 7 : 0.0176295
image 6 vs image 8 : 0.0157532
image 6 vs image 9 : 0.0177508
image 6 vs image 10 : 0.0141089
image 6 vs image 11 : 0.0116931
image 6 vs image 12 : 0.0177043
image 6 vs image 13 : 0.0113189
image 6 vs image 14 : 0.0165114
image 6 vs image 15 : 0.0238359
image 6 vs image 16 : 0.0286878
image 6 vs image 17 : 0.0242205
image 6 vs image 18 : 0.0238473
image 6 vs image 19 : 0.0183829
image 6 vs image 20 : 0.0160894

image 7 vs image 7 : 1
image 7 vs image 8 : 0.0484327
image 7 vs image 9 : 0.0799389
image 7 vs image 10 : 0.0140699
image 7 vs image 11 : 0.0353015
image 7 vs image 12 : 0.0162742
image 7 vs image 13 : 0.0123849
image 7 vs image 14 : 0.0155762
image 7 vs image 15 : 0.0236286
image 7 vs image 16 : 0.021078
image 7 vs image 17 : 0.00994403
image 7 vs image 18 : 0.0104469
image 7 vs image 19 : 0.00981495
image 7 vs image 20 : 0.0793399

image 8 vs image 8 : 1
image 8 vs image 9 : 0.0242055
image 8 vs image 10 : 0.0144976
image 8 vs image 11 : 0.0289231
image 8 vs image 12 : 0.0134452
image 8 vs image 13 : 0.0107451
image 8 vs image 14 : 0.013121
image 8 vs image 15 : 0.0440592
image 8 vs image 16 : 0.023649
image 8 vs image 17 : 0.0226309
image 8 vs image 18 : 0.0167086
image 8 vs image 19 : 0.0163815
image 8 vs image 20 : 0.019543

image 9 vs image 9 : 1
image 9 vs image 10 : 0.0196453
image 9 vs image 11 : 0.0360537
image 9 vs image 12 : 0.0216228
image 9 vs image 13 : 0.00905572
image 9 vs image 14 : 0.0117925
image 9 vs image 15 : 0.0203327
image 9 vs image 16 : 0.0124184
image 9 vs image 17 : 0.014915
image 9 vs image 18 : 0.0190471
image 9 vs image 19 : 0.0135781
image 9 vs image 20 : 0.136697

image 10 vs image 10 : 1
image 10 vs image 11 : 0.0150776
image 10 vs image 12 : 0.0147019
image 10 vs image 13 : 0.0437288
image 10 vs image 14 : 0.0212159
image 10 vs image 15 : 0.0175276
image 10 vs image 16 : 0.0244171
image 10 vs image 17 : 0.0173673
image 10 vs image 18 : 0.0180583
image 10 vs image 19 : 0.0198632
image 10 vs image 20 : 0.0186188

image 11 vs image 11 : 1
image 11 vs image 12 : 0.0145951
image 11 vs image 13 : 0.00686832
image 11 vs image 14 : 0.0105737
image 11 vs image 15 : 0.0193443
image 11 vs image 16 : 0.0145832
image 11 vs image 17 : 0.0164647
image 11 vs image 18 : 0.0173467
image 11 vs image 19 : 0.0160974
image 11 vs image 20 : 0.0500313

image 12 vs image 12 : 1
image 12 vs image 13 : 0.00650131
image 12 vs image 14 : 0.0809155
image 12 vs image 15 : 0.0164976
image 12 vs image 16 : 0.0315461
image 12 vs image 17 : 0.0174517
image 12 vs image 18 : 0.029972
image 12 vs image 19 : 0.0157822
image 12 vs image 20 : 0.0115077

image 13 vs image 13 : 1
image 13 vs image 14 : 0.0190167
image 13 vs image 15 : 0.0269287
image 13 vs image 16 : 0.0171848
image 13 vs image 17 : 0.0151769
image 13 vs image 18 : 0.0242274
image 13 vs image 19 : 0.00725557
image 13 vs image 20 : 0.00889539

image 14 vs image 14 : 1
image 14 vs image 15 : 0.0181876
image 14 vs image 16 : 0.03296
image 14 vs image 17 : 0.0200591
image 14 vs image 18 : 0.0362168
image 14 vs image 19 : 0.0128257
image 14 vs image 20 : 0.0160966

image 15 vs image 15 : 1
image 15 vs image 16 : 0.0233746
image 15 vs image 17 : 0.0147329
image 15 vs image 18 : 0.0240136
image 15 vs image 19 : 0.0301395
image 15 vs image 20 : 0.0211014

image 16 vs image 16 : 1
image 16 vs image 17 : 0.0128384
image 16 vs image 18 : 0.0139085
image 16 vs image 19 : 0.0200746
image 16 vs image 20 : 0.0090532

image 17 vs image 17 : 1
image 17 vs image 18 : 0.018697
image 17 vs image 19 : 0.017062
image 17 vs image 20 : 0.0147481

image 18 vs image 18 : 1
image 18 vs image 19 : 0.0196678
image 18 vs image 20 : 0.0187427

image 19 vs image 19 : 1
image 19 vs image 20 : 0.0131965

image 20 vs image 20 : 1

comparing images with database 
database info: Database: Entries = 21, Using direct index = no. Vocabulary: k = 10, L = 5, Weighting = tf-idf, Scoring = L1-norm, Number of words = 10381
searching for image 0 returns 4 results:
<EntryId: 0, Score: 1>
<EntryId: 9, Score: 0.0362582>
<EntryId: 20, Score: 0.0319604>
<EntryId: 19, Score: 0.0264222>

searching for image 1 returns 4 results:
<EntryId: 1, Score: 1>
<EntryId: 8, Score: 0.0554665>
<EntryId: 15, Score: 0.0482948>
<EntryId: 5, Score: 0.0427242>

searching for image 2 returns 4 results:
<EntryId: 2, Score: 1>
<EntryId: 6, Score: 0.0571594>
<EntryId: 16, Score: 0.0498792>
<EntryId: 0, Score: 0.0257712>

searching for image 3 returns 4 results:
<EntryId: 3, Score: 1>
<EntryId: 1, Score: 0.0291438>
<EntryId: 5, Score: 0.0284397>
<EntryId: 0, Score: 0.0248006>

searching for image 4 returns 4 results:
<EntryId: 4, Score: 1>
<EntryId: 14, Score: 0.0397562>
<EntryId: 17, Score: 0.0347258>
<EntryId: 6, Score: 0.0274229>

searching for image 5 returns 4 results:
<EntryId: 5, Score: 1>
<EntryId: 15, Score: 0.0692064>
<EntryId: 1, Score: 0.0427242>
<EntryId: 3, Score: 0.0284397>

searching for image 6 returns 4 results:
<EntryId: 6, Score: 1>
<EntryId: 2, Score: 0.0571594>
<EntryId: 16, Score: 0.0286878>
<EntryId: 4, Score: 0.0274229>

searching for image 7 returns 4 results:
<EntryId: 7, Score: 1>
<EntryId: 9, Score: 0.0799389>
<EntryId: 20, Score: 0.0793399>
<EntryId: 8, Score: 0.0484327>

searching for image 8 returns 4 results:
<EntryId: 8, Score: 1>
<EntryId: 1, Score: 0.0554665>
<EntryId: 7, Score: 0.0484327>
<EntryId: 15, Score: 0.0440592>

searching for image 9 returns 4 results:
<EntryId: 9, Score: 1>
<EntryId: 20, Score: 0.136697>
<EntryId: 7, Score: 0.0799389>
<EntryId: 0, Score: 0.0362582>

searching for image 10 returns 4 results:
<EntryId: 10, Score: 1>
<EntryId: 13, Score: 0.0437288>
<EntryId: 16, Score: 0.0244171>
<EntryId: 14, Score: 0.0212159>

searching for image 11 returns 4 results:
<EntryId: 11, Score: 1>
<EntryId: 20, Score: 0.0500313>
<EntryId: 9, Score: 0.0360537>
<EntryId: 7, Score: 0.0353015>

searching for image 12 returns 4 results:
<EntryId: 12, Score: 1>
<EntryId: 14, Score: 0.0809155>
<EntryId: 16, Score: 0.0315461>
<EntryId: 18, Score: 0.029972>

searching for image 13 returns 4 results:
<EntryId: 13, Score: 1>
<EntryId: 10, Score: 0.0437288>
<EntryId: 15, Score: 0.0269287>
<EntryId: 5, Score: 0.0257136>

searching for image 14 returns 4 results:
<EntryId: 14, Score: 1>
<EntryId: 12, Score: 0.0809155>
<EntryId: 4, Score: 0.0397562>
<EntryId: 18, Score: 0.0362168>

searching for image 15 returns 4 results:
<EntryId: 15, Score: 1>
<EntryId: 5, Score: 0.0692064>
<EntryId: 1, Score: 0.0482948>
<EntryId: 8, Score: 0.0440592>

searching for image 16 returns 4 results:
<EntryId: 16, Score: 1>
<EntryId: 2, Score: 0.0498792>
<EntryId: 14, Score: 0.03296>
<EntryId: 12, Score: 0.0315461>

searching for image 17 returns 4 results:
<EntryId: 17, Score: 1>
<EntryId: 4, Score: 0.0347258>
<EntryId: 5, Score: 0.0252288>
<EntryId: 6, Score: 0.0242205>

searching for image 18 returns 4 results:
<EntryId: 18, Score: 1>
<EntryId: 14, Score: 0.0362168>
<EntryId: 12, Score: 0.029972>
<EntryId: 13, Score: 0.0242274>

searching for image 19 returns 4 results:
<EntryId: 19, Score: 1>
<EntryId: 15, Score: 0.0301395>
<EntryId: 1, Score: 0.0283448>
<EntryId: 0, Score: 0.0264222>

searching for image 20 returns 4 results:
<EntryId: 20, Score: 1>
<EntryId: 9, Score: 0.136697>
<EntryId: 7, Score: 0.0793399>
<EntryId: 11, Score: 0.0500313>

done.

Pick out several with high matching scores

(note that the image sequence number in the execution program is different from that under the data1 folder: 9 corresponds to png, and 10 and 20 correspond to 21. Everyone who has learned the basic syntax of c + + here should be able to understand.)

Group I: form a loop

 

                                  10.png                                                            21.png

Group II: form a loop

 

                                15.png                                                            13.png

Group III: form a loop

                      8.png                                            10.png

Group 4: form a loop

 

                     3.png                                        7.png

Summary: because my pictures are randomly selected, basically those with high matching scores constitute loopback, but sometimes detection errors occur. If the computer performance, you can try the whole data set or select more images from it for loopback detection.


4. What are the common measurement methods of research similarity score?

Please refer to the following articles for specific common measurement methods:

Similarity Measurement in machine learning - there are many methods to describe the similarity between samples. Generally speaking, the commonly used methods are correlation coefficient and Euclidean distance. This paper summarizes the common Similarity Measurement methods in machine learning. In classification, it is often necessary to estimate the Similarity Measurement between different samples, whichhttps://zhuanlan.zhihu.com/p/55493039There are nine common distance measurement methods in data science, including Euclidean distance, Chebyshev distance, etc. - it is known that in data mining, we often need to calculate the similarity between samples. The usual method is to calculate the distance between samples. In this paper, data scientist Maarten Grootendorst introduces us nine distance measurement methods, including Euclidean distance, cosine similarity and so on. From towardsdahttps://zhuanlan.zhihu.com/p/350744027

(1) Euclidean distance

The matlab program is as follows:

Reproduced at: [data mining] Euclidean distance calculation with matlab_ Lamb Baa Baa blog - CSDN blog_ Calculating Euclidean distance with matlab

% Method 1
function dist = dist_E(x,y)
dist = [];
if(length(x)~=length(y))
    disp('length of input vectors must agree')  % disp The function outputs the content directly to the Matlab In the command window
else
    z =(x-y).*(x-y);
    dist = sqrt(sum(z));
end
end

% Method 2: formula method
function dist = dist_E(x,y)
[m,n] = size(x);
dist = 0;
for i=1:max(m,n)
    dist = dist+(x(i)-y(i))^2;
end
dist = sqrt(dist);
end
% Method 3: use pdist function
function dist = dist_E(x,y)
dist = [x;y];
dist = pdist(dist); % Calculate the Euclidean distance between each row of vectors
end

On the command line, enter:

x=[1,3,0,2]; 
y=[2,3,2,0];  
dist=dist_E(x,y)​​​​​​​

Press enter, and then you can calculate the Euclidean distance between the two vectors.

(2) Manhattan distance

import numpy as np

a=[8,2]
b=[5,10]
a_np = np.array(a)
b_np = np.array(b)

dist3 = np.sum(np.abs(a_np-b_np))
print(f"Manhattan Distance = {dist3}\n")

python manhatta.py 
Manhattan Distance = 11

The following codes are reproduced in: [369]python implementation of various distance formulas_ Zhou Xiaodong - CSDN blog_ python Euclidean distance

(3) Chebyshev distance

# -*- coding: utf-8 -*-
from numpy import *

vector1 = mat([1,2,3])
vector2 = mat([4,7,5])
print (abs(vector1-vector2).max())

import numpy as np

x=np.random.random(10)
y=np.random.random(10)
#Method 1: solve according to the formula
d1=np.max(np.abs(x-y))
print('d1:',d1)

#Method 2: solve according to scipy library
from scipy.spatial.distance import pdist

X=np.vstack([x,y])
d2=pdist(X,'chebyshev')[0]
print('d2:',d2)

python Chebyshev.py 

5
d1: 0.7956039912699736
d2: 0.7956039912699736

(3) Hamming distance

# -*- coding: utf-8 -*-
from numpy import *

matV = mat([[1,1,0,1,0,1,0,0,1],[0,1,1,0,0,0,1,1,1]])
smstr = nonzero(matV[0]-matV[1])
print(shape(smstr[0])[0])


import numpy as np
from scipy.spatial.distance import pdist

x=np.random.random(10)>0.5
y=np.random.random(10)>0.5
x=np.asarray(x,np.int32)
y=np.asarray(y,np.int32)
#Method 1: solve according to the formula
d1=np.mean(x!=y)
print('d1:', d1)

#Method 2: solve according to scipy library
X=np.vstack([x,y])
d2=pdist(X,'hamming')[0]
print('d2:', d2)

 python hamming.py 

6
d1: 0.4
d2: 0.4

(4) Normalized Euclidean distance

# -*- coding: utf-8 -*-
import numpy as np
x=np.random.random(10)
y=np.random.random(10)

X=np.vstack([x,y])

#Method 1: solve according to the formula
sk=np.var(X,axis=0,ddof=1)
d1=np.sqrt(((x - y) ** 2 /sk).sum())
print('d1:',d1)

#Method 2: solve according to scipy library
from scipy.spatial.distance import pdist
d2=pdist(X,'seuclidean')[0]
print('d2:',d2)

python Standardized_Euclidean.py 
d1: 4.47213595499958
d2: 4.47213595499958

(5) Included angle cosine

# -*- coding: utf-8 -*-
import numpy as np
from scipy.spatial.distance import pdist

'''
x: [0.05627679 0.80556938 0.48002662 0.24378563 0.75763754 0.15353348
 0.54491664 0.1775408  0.50011986 0.55041845]
y: [0.50068882 0.12200178 0.79041352 0.07332715 0.017892   0.57880032
 0.56707591 0.48390753 0.631051   0.20035466]
'''
x = np.random.random(10)
y = np.random.random(10)
# solution1
dist1 = 1 - np.dot(x, y) / (np.linalg.norm(x) * np.linalg.norm(y))
# solution2
dist2 = pdist(np.vstack([x, y]), 'cosine')[0]
print('x', x)
print('y', y)
print('dist1:', dist1)
print('dist2:', dist2)

python Cosine.py 
x [0.59758063 0.40859383 0.98186786 0.01670254 0.33830128 0.06095993
 0.80674537 0.90611795 0.08119071 0.24229608]
y [0.43176033 0.2846342  0.41233185 0.37309159 0.24177945 0.68055469
 0.36115457 0.3278653  0.57811011 0.13355709]
dist1: 0.31572330152121986
dist2: 0.31572330152121975

(6) Jackard distance & jackard similarity coefficient

# -*- coding: utf-8 -*-
from numpy import *
from scipy.spatial.distance import pdist # Import scipy distance formula

matV = mat([[1,1,0,1,0,1,0,0,1],[0,1,1,0,0,0,1,1,1]])
print ("dist.jaccard:", pdist(matV,'jaccard'))

import numpy as np
from scipy.spatial.distance import pdist

x = np.random.random(10) > 0.5
y = np.random.random(10) > 0.5
x = np.asarray(x, np.int32)
y = np.asarray(y, np.int32)
# Method 1: solve according to the formula
up = np.double(np.bitwise_and((x != y), np.bitwise_or(x != 0, y != 0)).sum())
down = np.double(np.bitwise_or(x != 0, y != 0).sum())
d1 = (up / down)
print('d1:', d1)
# Method 2: solve according to scipy library
X = np.vstack([x, y])
d2 = pdist(X, 'jaccard')[0]
print('d2:', d2)

python Jaccard.py 

dist.jaccard: [0.75]
d1: 1.0
d2: 1.0

(7) Correlation coefficient & correlation distance

# -*- coding: utf-8 -*-
import numpy as np

x=np.random.random(10)
y=np.random.random(10)

#Method 1: solve according to the formula
x_=x-np.mean(x)
y_=y-np.mean(y)
d1=np.dot(x_,y_)/(np.linalg.norm(x_)*np.linalg.norm(y_))
print('d1:', d1)

#Method 2: solve according to numpy library
X=np.vstack([x,y])
d2=np.corrcoef(X)[0][1]
print('d2:', d2)

python correlation.py 

d1: 0.2479989126873464
d2: 0.24799891268734642

5. What is the principle of chow Liu tree? How is it used to build dictionaries and loop detection?

Refer to the following article: Graduation thesis arrangement (2): approximate discrete probability distribution with dependency tree | article | BEWINDOWEB

6. Read [118], in addition to the word bag model, what other methods are used for loop detection?

Refer to the following two articles:

Visual SLAM Lecture 14 (Second Edition) lesson 11 problem solving - Zhihu

Overview | SLAM loop detection methods

Keywords: C++ Computer Vision

Added by wilsonodk on Thu, 09 Dec 2021 18:35:36 +0200

Popular Keywords

©2024 Programming VIP