vcg-uvic / fastmcd Goto Github PK
View Code? Open in Web Editor NEWimplementation of the paper "Detection of Moving Objects with Non-stationary Cameras in 5.8ms: Bringing Motion Detection to Your Mobile Device", CVPRW13
implementation of the paper "Detection of Moving Objects with Non-stationary Cameras in 5.8ms: Bringing Motion Detection to Your Mobile Device", CVPRW13
Can any one help in giving pointers on how the result video can be saved?
Much thanks in advance
Could you please provide an Android version?
Can you comment the code , just few of it. it's hard to cope it with the paper.
Hi
I tried the code and came across two errors. Its clear that the issue has something to do with opencv.
Either the opencv version or the compiler.
Any idea on how to go about this would be highly appreciated.
Below is the error I got:
/home/vip/Documents/Motion Detection Codes/fastMCD-master/src/KLTWrapper.cpp: In member function ‘void KLTWrapper::SwapData(IplImage*)’:
/home/vip/Documents/Motion Detection Codes/fastMCD-master/src/KLTWrapper.cpp:152:34: error: ‘cvCopyImage’ was not declared in this scope
cvCopyImage(imgGray, imgPrevGray);
^
/home/vip/Documents/Motion Detection Codes/fastMCD-master/src/KLTWrapper.cpp: In member function ‘void KLTWrapper::MakeHomoGraphy(int*, int)’:
/home/vip/Documents/Motion Detection Codes/fastMCD-master/src/KLTWrapper.cpp:180:43: error: ‘CV_RANSAC’ was not declared in this scope
if (!cvFindHomography(&_pt1, &_pt2, &_h, CV_RANSAC, 1))
^
/home/vip/Documents/Motion Detection Codes/fastMCD-master/src/KLTWrapper.cpp:180:55: error: ‘cvFindHomography’ was not declared in this scope
if (!cvFindHomography(&_pt1, &_pt2, &_h, CV_RANSAC, 1))
^
CMakeFiles/fastMCD.dir/build.make:110: recipe for target 'CMakeFiles/fastMCD.dir/src/KLTWrapper.cpp.o' failed
make[2]: *** [CMakeFiles/fastMCD.dir/src/KLTWrapper.cpp.o] Error 1
CMakeFiles/Makefile2:67: recipe for target 'CMakeFiles/fastMCD.dir/all' failed
make[1]: *** [CMakeFiles/fastMCD.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2
Great job! But when I test this project, it takes almost 22ms per frame, which is slower than that in paper.
If I only need prob_model.hpp to embed the motion detector in my test application, where can I can get the values for the double h[9] array parameter needed for motionCompensate
Thanks
Edit: I'm not using OpenCV at all
OpenCV4 support ?
i have used vs 2012 and vs 2015, opencv 3.2, cmake 3.8 in win 10 operation system. But i am getting some error.
when i click configure button via CMAKE i am getting the message below :
<<
CMake Warning at C:/opencv/build/OpenCVConfig.cmake:138 (message):
Found OpenCV Windows Pack but it has no binaries compatible with your
configuration.
You should manually point CMake variable OpenCV_DIR to your build of OpenCV
library.
Call Stack (most recent call first):
CMakeLists.txt:11 (find_package)
when building project on Visual Studio, i am getting many errors.
i wonder which version of vs ,opencv, and cmake should i use?
Thanks
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.