This is a side project I haven been working on for crowd counting and tracking. I use the ImageAI object detection library to track and count the crowd in the video. Thanks to the wonderful creators of ImageAI library you also can get the detection analytics for each frame, minute, and seconds of the video. The detection analytics for each second can be found in the "analytics" directory. The video used for detection is a random stock video I found to use for this project to perform object detection.
Creator: Moses Olafenwa
https://github.com/OlafenwaMoses/ImageAI
Built with simplicity in mind, ImageAI supports a list of state-of-the-art Machine Learning algorithms for image prediction, custom image prediction, object detection, video detection, video object tracking and image predictions trainings. ImageAI currently supports image prediction and training using 4 different Machine Learning algorithms trained on the ImageNet-1000 dataset. ImageAI also supports object detection, video detection and object tracking using RetinaNet, YOLOv3 and TinyYOLOv3 trained on COCO dataset. Eventually, ImageAI will provide support for a wider and more specialized aspects of Computer Vision including and not limited to image recognition in special environments and special fields.