8 March 2017 Hand and goods judgment algorithm based on depth information
Author Affiliations +
Proceedings Volume 10255, Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016; 102550B (2017) https://doi.org/10.1117/12.2268129
Event: Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016, 2016, Jinhua, Suzhou, Chengdu, Xi'an, Wuxi, China
Abstract
A tablet computer with a depth camera and a color camera is loaded on a traditional shopping cart. The inside information of the shopping cart is obtained by two cameras. In the shopping cart monitoring field, it is very important for us to determine whether the customer with goods in or out of the shopping cart. This paper establishes a basic framework for judging empty hand, it includes the hand extraction process based on the depth information, process of skin color model building based on WPCA (Weighted Principal Component Analysis), an algorithm for judging handheld products based on motion and skin color information, statistical process.

Through this framework, the first step can ensure the integrity of the hand information, and effectively avoids the influence of sleeve and other debris, the second step can accurately extract skin color and eliminate the similar color interference, light has little effect on its results, it has the advantages of fast computation speed and high efficiency, and the third step has the advantage of greatly reducing the noise interference and improving the accuracy.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mingzhu Li, Jinsong Zhang, Dan Yan, Qin Wang, Ruiqi Zhang, Jing Han, "Hand and goods judgment algorithm based on depth information", Proc. SPIE 10255, Selected Papers of the Chinese Society for Optical Engineering Conferences held October and November 2016, 102550B (8 March 2017); doi: 10.1117/12.2268129; https://doi.org/10.1117/12.2268129
PROCEEDINGS
6 PAGES


SHARE
Back to Top