A real-time object recognition application using Google's TensorFlow Object Detection API and OpenCV.
conda env create -f environment.yml
python object_detection_app.py /
Optional arguments (default value):
- Device index of the camera
- Width of the frames in the video stream
- Height of the frames in the video stream
- Number of workers
- Size of the queue
- Get video from HLS stream rather than webcam '--stream-input=http://somertmpserver.com/hls/live.m3u8'
- Send stream to livestreaming server '--stream-output=--stream=http://somertmpserver.com/hls/live.m3u8'
pytest -vs utils/
- OpenCV 3.1 might crash on OSX after a while, so that's why I had to switch to version 3.0. See open issue and solution here.
- Moving the
.read() part of the video stream in a multiple child processes did not work. However, it was possible to move it to a separate thread.
See LICENSE for details.
Copyright (c) 2017 Dat Tran.