HAVPTAT: A Human Activity Video Pose Tracking Annotation Tool

Abstract

We propose a new semi-automatic annotation software: Human Activity Video Pose Tracking Annotation Tool (HAVPTAT). It can automatically detect and track multiple people and their pose in the video to improve work efficiency. HAVPTAT also provides the dynamical visualization of human pose, bounding boxes, person tracking ID, and possible prediction results together. The lightweight software can be launched in a few seconds and easily distributed. Its ease of use will allow non-professionals to get started quickly. This software will accelerate the development of human activity recognition models and service robots.