[RotNet self supervised learning] predict image rotation angle
Thesis Guide
RotNet performs self supervised learning by predicting image rotation
This is a paper published by ICLR in 2018, which has been cited more than 1100 times. The idea of this paper comes from: if someone does not understand the concept of the object depicted in the image, he cannot recognize the rotation applied to the image.
...
Added by Jona on Wed, 29 Dec 2021 07:16:31 +0200
The binocular camera is calibrated by Zhang Zhengyou calibration method based on Matlab
1, Working environment
Operating system: Win10
Development environment: Matlab 2019b (camera driver package required)
Camera: USB binocular camera, supporting UVC standard protocol
1. Install the OS Generic Video Interface
Plug in the camera and enter the command (webcam) in the Matlab command line window. If the following interface app ...
Added by endlyss on Tue, 28 Dec 2021 00:50:09 +0200
mmdetection construction of one-stage detection model for disassembly of each module (taking FCOS as an example)
introduction
For the author, the most important thing to learn mmdetection is to learn how to DIY your own model, so it is very important to understand how the classical model is built step by step. This chapter will start from scratch and deconstruct the construction process of the one-stage detection model (taking FCOS as an example) in ...
Added by davidz on Sun, 26 Dec 2021 01:47:10 +0200
Learn OpenCV to understand the data types of OpenCV - 3
catalogue
Tool function
cv::alignPtr()
cv::alignSize()
cv::allocate()
cv::deallocate()
cv::fastAtan2()
cv::cubeRoot()
cv::CV_Assert() & cv::CV_DbgAsser()
cv::error()
cv::CV_Error() & cv::CV_Error_()
cv::fastFree()
cv::fastMalloc()
cv::format()
cv::getCPUTickCount()
cv::getNumThreads()
cv::getOptimalDFTSize()
cv::getTh ...
Added by zoooj on Thu, 23 Dec 2021 09:30:52 +0200
Fundamentals of digital image and machine vision #2
1, Digital image processing
1.1 converting color image files to grayscale files
gray image Gray image is an image with only one sampling color per pixel. This kind of image is usually displayed as a gray scale from the darkest black to the brightest white. In theory, this sampling can be different in the depth of any color, or even differ ...
Added by steelerman99 on Wed, 22 Dec 2021 23:58:48 +0200
Color planet image generation 3: fine tuning of code details (pytorch version)
Previous episode:
Color planet image generation 2: using both traditional Gan discriminator and Markov discriminator (pytorch version)
Based on the previous set of code, some detailed modifications are made to improve the generation effect.
1. Modification
1.1 preprocessing scaling
The code for preprocessing training set pictures is mod ...
Added by gx30uk on Wed, 22 Dec 2021 22:02:50 +0200
opencv/c + + simple number / floating point recognition
Tip: after the article is written, the directory can be generated automatically. Please refer to the help document on the right for how to generate it
preface
Tip: the project needs to identify the real-time collected pictures and identify the floating-point numbers in the pictures The idea is as follows: CV is used to process the image ...
Added by dips_007 on Tue, 21 Dec 2021 18:22:44 +0200
Actual combat PP tinypose + picodet: application of new intelligent body measurement mode
Actual combat PP tinypose + picodet: application of new intelligent body measurement mode
Introduction to PP tinypose
PP tinypose is a real-time attitude detection model optimized by paddedetection for mobile devices, which can smoothly perform multi person attitude estimation tasks on mobile devices. Excellent lightweight detection model d ...
Added by Lahloob on Tue, 21 Dec 2021 11:18:21 +0200
PspNet successfully trained Pascal VOC2012 data set and pit stepping record under MMsegmentation framework
Time: 2021 / 08 / 29 / 05:45:28 It's been a night. I can't believe I'm not sleepy and have the impulse to organize my blog. Just this week, the ability to stay up late suddenly broke through in the absence of a home for several nights. After one night, there is a world of difference. I can stay up night by night. Before, I was worried about my ...
Added by bizshop on Mon, 20 Dec 2021 13:14:06 +0200
SAR Target Classification Based on full convolution network
SAR Target Classification Based on full convolution network
1. MSTAR dataset expansion
In the original SAR image (128) × 128) random clipping 88 × 88 slices, each slice can contain the target area, and the number of samples can reach (128-88 + 1) after random sampling × (128-88 + 1) = 1681 times, each SAR image of each c ...
Added by salih0vicX on Mon, 20 Dec 2021 07:29:15 +0200