plstcharles / litiv Goto Github PK
View Code? Open in Web Editor NEWC++ implementation pool for computer vision R&D projects.
Home Page: http://www.polymtl.ca/litiv/en/
License: Other
C++ implementation pool for computer vision R&D projects.
Home Page: http://www.polymtl.ca/litiv/en/
License: Other
Hello~
I want to use your algorithm to detect stationary obj(like the cargo that fell from truck to the ground ),so I make the learningRateOverride=0(not update the bg model at all) to detect the stationary foreground.But the staionary foreground still get into the bg model which lead the stationary foreground can't be detect.So sincerely hope you to help me,can you give me some advice about stationary objection?
Thanks!
Kind regard.
Hello,I‘m still study your PAWCS,I want to find a way to skip the bg model update,but I’m getting in trouble with the code......I use the PAWCS with bgslibrary,can you give me some annotations about the function “void BackgroundSubtractorPAWCS::apply()”? or some simple explain of the Looping statements?Please,need your help
Hi:
I use DASC descriptor for learning,but I found your example is hand to understand.
can you give me an example?
etc:
My input is an image , output is DASC descritpr,
I use this function in your library:
void DASC::compute2(const cv::Mat& oImage, cv::Mat& oDescMap_)
but the output type is
oDescMap_.type()==CV_32FC1,
So how can I get the descritpr? Can you give me another example?
Thanks
Building the framework on Windows using MSVC2015 and CUDA may cause a unit test to fail in release mode. The test in question:
65> Start 17: litiv_utest_imgproc_global
65> 17/30 Test #17: litiv_utest_imgproc_global .......***Failed 9.13 sec
65> [----------] 1 test from descriptor_affinity
65> [ RUN ] descriptor_affinity.regression_L2_sc
65>E:\develop\litiv\modules\imgproc\test\global.cpp(358): error : Expected: oAffMap(i,j,k)
65> Which is: -1
65> To be equal to: oAffMapTmp(i,j,k)
65> Which is: 0
65> ijk=[0,0,0]
65> [ FAILED ] descriptor_affinity.regression_L2_sc (475 ms)
65> [----------] 1 test from descriptor_affinity (475 ms total)
Will have to investigate further later on.
Hi, I'm testing the library in MSVS2015.
When I run litiv_sample_changedet with some sample image sequences (build is all fine, no errors, no warning, build under Debug x64), the program crashes on this line..
and the debugger brought me to this file and said illegal instruction (something related to the memory)
How can I fix it? Or is there other way to get the instance of the background subtraction method.
( and BTW, when I compile the code using Release x64, the program crashes without running a single line of code, do i need some extra configuration?)
I think we should
change "http://bitbucket.org/eigen/eigen/get/3.3.4.zip" in 3rdparty/eigen3/CMakeLists.txt to
"https://gitlab.com/libeigen/eigen/-/archive/3.3.4/eigen-3.3.4.zip" .
Because, the first address respond "Repository eigen/eigen not found".
the image origina size is 1920 x 1080,I make it risize to 320x240 (QVGA),the it about 0.8 second per frame at Intel i7 CPU,the paper said that the speed is 22 frames per second Intel i5 CPU,can you help me to enhance the processing speed?
Attempted to build without any bells or whistles:
$ mkdir build
$ cd build
$ cmake ..
$ make
But fails with:
[ 46%] Building CXX object modules/datasets/CMakeFiles/litiv_datasets.dir/src/impl/BSDS500.cpp.o
/tmp/build/litiv/modules/datasets/src/impl/BSDS500.cpp:42:32: error: ‘-pedantic-errors’ is not an option that controls warnings [-Werror=pragmas]
#pragma GCC diagnostic ignored "-pedantic-errors"
^~~~~~~~~~~~~~~~~~
compilation terminated due to -Wfatal-errors.
cc1plus: all warnings being treated as errors
make[2]: *** [modules/datasets/CMakeFiles/litiv_datasets.dir/build.make:159: modules/datasets/CMakeFiles/litiv_datasets.dir/src/impl/BSDS500.cpp.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:219: modules/datasets/CMakeFiles/litiv_datasets.dir/all] Error 2
make: *** [Makefile:128: all] Error 2
This is related to a dataset issue, forgive me if this is not the right place to ask.
I have compiled and installed this repository with no issue.
I am now trying to run something which calls this library and acts on the LITIV2018 dataset (Online Mutual Foreground Segmentation for Multispectral Stereo Videos) located here from the datasets page.
For vid04, I am getting this assertion error found in include/litiv/datasets/impl/litiv-stcharles2018.hpp
:
lvAssert__(vsLWIRFramePaths.size()>0u && vsLWIRMaskPaths.size()<=vsLWIRFramePaths.size() && vsLWIRGTPaths.size()<=vsLWIRFramePaths.size(),"bad input lwir packet count for sequence '%s'",this->getName().c_str());
I found the following:
Particularly, the lwir_masks
folder has all 0-1835 images, but the lwir
folder is immediately missing 0, 7, 16 etc.
Am I missing something?
Bonjour,
Thanks a lot for your great contribution.
I notice that opencv >= 3.0.0 is required, but I failed to cmake with a version 4.5.2 of opencv. I would like to know if it supports opencv 4.
Merci!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.