An Improved ViBe Algorithm for Shadow Removal in Different Backgrounds
Conference: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
12/17/2021 - 12/19/2021 at Shenyang, China
Proceedings: ICMLCA 2021
Pages: 5Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Wang, Yanmei; Zhang, Zhao (School of Information Science and Engineering, Shenyang Ligong University, Shen yang, China)
Zhang, Yanzhu (School of Automation and Electrical Engineering Shenyang Ligong University, Shen yang, China)
Abstract:
Due to the strict requirements of accuracy and efficiency in target detection, intelligent target detection algorithms require a lot of manpower and resources to satisfy the need of huge data volume. Therefore, it is very necessary to continue the research on traditional target detection algorithms. Typically, there are two types of image background, pure background and complex background. The traditional ViBe algorithm produces shadows in the detection of targets under complex backgrounds, especially with interference such as reflections and jitter. This paper proposes two methods to solve the problem of shadows generated by the traditional ViBe algorithm when detecting targets, and compares the shadow removal effects of the two improved algorithms under different backgrounds.