In this project, I tried to detect objects in real time.
In order to achieve this goal, I used:
- OpenCV to capture my webcam,
- and YOLOv5 to detect object.
How to improve this code:
- by using GPU acceleration and get more fps (decrease of computation time),
- and by testing other object detection algorithms (YOLOv4, a more complexe version of YOLOv5, a faster R-CNN algorithm with TensorFlow Hub, etc).