OpenCV Color Segmentation and Tracking on DragonBoard 820c

Posted by Charbax – October 5, 2018

This demo is based and tested on the DragonBoard 820c, but should be able to work on varying platforms. In summary, it counts objects by color passing in the same direction through the camera field of view. It can count multiple objects simultaneously. The OpenCV functionality leveraged by this demo includes the following:

- Object segmentation using color
- Valid object identification by size
- Frame stitching to track and count multiple simultaneous moving objects by color
- Provides hooks to monitor performance when algorithm changes to - - OpenCV library calls are made for identification tuning
- Provides hooks to export results to the cloud