intel-iot-devkit / people-counter-cpp

Create a smart video application using the Intel Distribution of OpenVINO toolkit. The toolkit uses models and inference to run single-class object detection.

Home Page:https://software.intel.com/content/www/us/en/develop/topics/iot/reference-implementations/people-counter-system.html

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Not Able to see any video on the UI interface

Jeetkarsh opened this issue · comments

Could anybody help me out with this

image

image

Can you please check the error console while loading the page and add the details here?

Thanks for your reply Here you go
image

image

image

@Jeetkarsh I'm referring to the browser's error console, you can find it in Chrome under More Tools -> Developer Tools. I've seen node dependencies break the web interface in the past, so this could be why the stream is not getting loaded. The rest of the application seems to be running fine.

Actually, I can't really tell from the output of the screen running cvservice, did you stop it from running or does it exit right away?

Actually, I can't really tell from the output of the screen running cvservice, did you stop it from running or does it exit right away?

Its actually running,i am running this application on AWS and using Putty to connect to the AWS server i have added the forwarded port which were giving error in the console.After adding all the forwarded port as shown above page is still loading with the web layout but no video playback is being shown.

image

Thanks for the updated info. It seems like the web console is clean, indicating that the problem is more likely network configuration related. Take a quick look at this commit I made for the face-access-control demo. It runs the demo over a network, and a couple of files need to be updated with the right address when doing so. Also, I recently came across instances where AWS cannot open local files due to permission issues which may be related. However I don't have a fix for this, you would have to check AWS documentation for further details. One more thing, try to play the video back with ffplay to ensure it's being streamed properly.

Tried doing it on my local environment but still getting the following error.

(pyhton3.5) jeetendra@ubuntu:~/people-counter/ieservice/bin/intel64/Release$ ./obj_recognition -i Pedestrain_Detect_2_1_1.mp4 -m /opt/intel/computer_vision_sdk/deployment_tools/intel_models/person-detection-retail-0012/FP16/person-detection-retail-0012.xml -l /opt/intel/computer_vision_sdk/deployment_tools/intel_models/person-detection-retail-0012/FP16/person-detection-retail-0012.bin -d GPU -t SSD -thresh 0.7 0 2>/dev/null | ffmpeg -v warning -f rawvideo -pixel_format bgr24 -video_size 544x320 -i - http://localhost:8090/fac.ffm
Output file is empty, nothing was encoded (check -ss / -t / -frames parameters if used)