Research status and prospect of visual image feature point detection in body measurements

Abstract

To improve visual image feature point detection with two-dimensional human body circumference measurements, this paper analyzes and compares several feature point detection algorithms, algorithm based on human body proportion, and deep-learning-based convolutional neural network algorithms. Among them, the principles and application of the Harris corner detection algorithm are described in detail. The progress in image feature points detection based on human body proportions and regions is then summarized and reviewed. Based on the convolutional neural network method, a method of calculating feature points based on the relatively mature human joint point recognition algorithm is proposed, so as to solve the problem of inaccurate positioning in traditional algorithms. Finally, the challenge of feature point detection for clothing volumes is explained. Feature point detection from visual images has significant development prospects in the two-dimensional measurement of body circumference. Related research provides a reliable theoretical reference for realizing the accurate and rapid detection of human feature points in visual images.

KEYWORDS:

• Feature point detection
• Harris algorithm
• human body proportion
• convolutional neural network
• human joint points

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

Funding support by National key R & D Program of China to this research work is gratefully acknowledged, Project No. 2018YFB1308801.