The Multimodal Motion Detector is a Computer Vision model which detects faces and poses of entities through a video input of a webcam or a video file and maps out the various poses and motions of the entity.
We have implemented this detector using the cvzone module of opencv-python and it utilises the methods of FaceDetector and PoseDetector from the mentioned module
The individual modules consist of two models a face detection and a pose detection model,which we then integrate into a one cohesive model which performs the Multimodal Motion Detection