RETRACTED ARTICLE: Efficient object analysis by leveraging deeply-trained object proposals prediction model

• Published in: Multimedia tools and applications Vol. 79; no. 13-14; p. 9695
• Main Authors: Dai, Bo, Yao, Yiyang, Ye, Wenjing, Zheng, Jing
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2020; Springer Nature B.V
• Subjects: Computer Communication Networks; Computer Science; Data Structures and Information Theory; Multimedia Information Systems; Special Purpose and Application-Based Systems; Deep Feature Representation; Information Theory; Security Surveillance Systems; RETRACTED ARTICLE; Proposed Prediction
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-017-5390-6

In this paper, a learned motion target detection algorithm combining background estimation and Bing (binary specification gradient) objects is proposed in video surveillance. A simple background estimation method for detecting rough images of a set of moving foreground objects. The foreground setting in the foreground will estimate another set of candidate window, and the target (pedestrian / vehicle) coming from the cross region comes from the first two steps. In addition, the time cost is reduced by the estimated area. Experiments on outdoor datasets show that this method can not only achieve higher detection rate, but also reduce false positive rate and time overhead.