Use MAT frames for feature tracking

[apoorvasinhazxc]

I have an already written program that displays frames in the MAT format. I wish to use these for tracking features instead of giving a video file location to the feature tracking algorithm. Is there any way I can pass the MAT images as input so that the algorithm uses them to obtain and track features?

[Honey_Patouceul]

You may have a look to these 2 examples (one in C++, one in python):

TX2 OpenCV tracking Segfault

This example works fine on my TX2. I use the KCF tracker with the onboard camera video : #include <opencv2/core/utility.hpp> #include <opencv2/tracking.hpp> #include <opencv2/videoio.hpp> #include <opencv2/highgui.hpp> #include <iostream> #include <cstring> using namespace std; using namespace cv; int main( int argc, char** argv ){ // Gstreamer pipeline for accessing on board camera, rotate image 180° writing to CPU mem and convert to BGR for opencv input const char* gst = "nvcameras…

Multi-object tracker tx1

Update: I took some time to test your code and adapt to opencv (main.py below). I’ve used opencv4.2 (pre 4.3.0). You would need an opencv build with gstreamer support installed and available from python (uncomment #cv2.getBuildInformation() to be sure). As input, it uses a gstreamer pipeline in order to read the AVI file TownCentreXVID.avi and provide frames in BGR format, with decodebin that should use nvv4l2decoder for HW(NVDEC) H264 decoding and nvvidconv for NV12 to BGRx HW(ISP) conversio…

[apoorvasinhazxc]

@Honey_Patouceul Thank you for the reply. But my issue is not with getting OpenCV to work, it’s just the particular problem I mentioned of how exactly to modify the feature tracking sample given (what code to insert/change), such that it takes MAT frames as input.

[Honey_Patouceul]

@apoorvasinhazxc

But my issue is not with getting OpenCV to work, it’s just the particular problem I mentioned of how exactly to modify the feature tracking sample given (what code to insert/change), such that it takes MAT frames as input.

Sorry, but I fail to understand your case. You may explain further.
The two samples I’ve posted are using opencv mat frames for tracking, not about getting opencv working.
Glad you’re familiar and got opencv working, but please tell your use case and expectation. Also tell if using C++ or Python.
Not sure I can help further, but you may get better advice explaining in more details.

[apoorvasinhazxc]

@Honey_Patouceul I’m using C++. I’ll explain my problem in detail.
The sample code in main_feature_tracker.cpp takes a string source location as input, and creates a frame source using it →
…
std::string sourceUri = app.findSampleFilePath(argv[1]);
…
std::unique_ptrovxio::FrameSource source(
ovxio::createDefaultFrameSource(context, sourceUri));
…

I would like to modify this or the surrounding code such that I can run a loop and send it frames of the video in the form of MAT images as the input, instead of the current string file location.

[Honey_Patouceul]

Now I understand you’re referring to VisionWorks.
I have no experience with VisionWorks. Someone else would better advise.

[snarky]

You should post the question in the VisionWorks forum, not the Jetson Nano forum, if you’re using VisionWorks.