This project is the implementation of Real-time Object detection in video with deep learning and OpenCV.
--prototxt : The path to the Caffe prototxt file.
--model : The path to the pre-trained model.
--confidence : The minimum probability threshold to filter weak detections. The default is 20%.
To build our deep learning-based real-time object detector with OpenCV we’ll need to
- access our webcam/video stream in an efficient manner and
- apply object detection to each frame.
The command to run the program:
python real_time_object_detection.py --prototxt MobileNetSSD_deploy.prototxt.txt --model MobileNetSSD_deploy.caffemodel
