Human Segmentation and Tracking Survey on Masks for MADS Dataset

Abstract

Human segmentation and tracking often use the outcome of person detection in the video. Thus, the results of segmentation and tracking depend heavily on human detection results in the video. With the advent of Convolutional Neural Networks (CNNs), there are excellent results in this field. Segmentation and tracking of the person in the video have significant applications in monitoring and estimating human pose in 2D images and 3D space. In this paper, we performed a survey of many studies, methods, datasets, and results for human segmentation and tracking in video. We also touch upon detecting persons as it affects the results of human segmentation and human tracking. The survey is performed in great detail up to source code paths. The MADS (Martial Arts, Dancing and Sports) dataset comprises fast and complex activities. It has been published for the task of estimating human posture. However, before determining the human pose, the person needs to be detected as a segment in the video. Moreover, in the paper, we publish a mask dataset to evaluate the segmentation and tracking of people in the video. In our MASK MADS dataset, we have prepared 28 k mask images. We also evaluated the MADS dataset for segmenting and tracking people in the video with many recently published CNNs methods.

Computer Vision and Machine Learning for Intelligent Sensing Systems

“…• Le and Scherer [6] performed a comprehensive survey of many studies, methods, datasets, and results for human segmentation and tracking in video.…”

Unified End-to-End YOLOv5-HR-TCM Framework for Automatic 2D/3D Human Pose Estimation for Real-Time Applications

“… Illustration of computing movement scores in women’s artistic gymnastics ( a ) and weightlifting ( b ). Images ( c ) and ( d ) are an illustration of a dancer performing jazz and hip hop dances [ 95 , 96 ]. …”

A Real-Time Dance Analysis Program to Assist in Dance Practice Using Pose Estimation

“…HDVR captures comprehensive gesture data, but may face challenges in complex, fast movements. The MADS dataset enhances 3D pose estimation, but may encounter difficulties in subtle, fast movements [10].…”