Object Detection and Recognition using YOLO

Prerequisites

YOLOv3 config: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov3.cfg
YOLOv3 weights: https://pjreddie.com/media/files/yolov3.weights
Class names: https://github.com/pjreddie/darknet/blob/master/data/coco.names

Copy the above config, weights and class names files into the same folder as this source code.

To detect object in image, just run:

python yolo_detect_image.py --image name_of_your_image_here

For example, with this input image:

The output will be:

Similarly, to detect object in video, just run:

python yolo_detect_video.py --video name_of_your_video_here

An video example can be seen below:

Please feel free to adjust CONF_THRESHOLD and NMS_THRESHOLD constants to suit your needs.