Appearance model update based on online learning and soft‐biometrics traits for people re‐identification in multi‐camera environments. Issue 12 (17th September 2019)

• Record Type: Journal Article
• Authors: Moctezuma, Daniela; Tellez, Eric S.; Miranda‐Jiménez, Sabino; Graff, Mario
• Is Part Of: IET image processing. Volume 13:Issue 12(2019)
• Page Start: 2162
• Page End: 2168
• Publication Date: 2019-09-17
• Subjects: learning (artificial intelligence) -- surveillance -- biometrics (access control) -- video surveillance -- cameras -- object detection -- computer vision; camera change -- slight change -- objective traits -- multicamera surveillance environment -- update process -- time lapses -- video surveillance environments -- cameras -- surveillance area -- continuous appearance model -- appearance model update -- online learning -- soft‐biometrics traits -- multicamera environments -- intelligent surveillance systems -- hard‐open problem -- re‐identification task -- time advances -- surveillance videos; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0083
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Intelligent surveillance systems in multi‐camera environments pose a hard‐open problem for computer vision. The way the people look changes inside and also among cameras, so people re‐identification task can be largely improved collecting data about people already identified and take advantage of it as time advances in surveillance video. Furthermore, a camera change or a slight change in the objective traits may require the complete re‐formulation of the appearance models. In this paper, we propose several heuristics for updating the appearance model in a multi‐camera surveillance environment. Through these heuristics, the subject's appearance model is updated across different time and environmental conditions. The update process is carried out primarily in three different aspects: 1) based on time lapses, 2) based on the change of camera, and 3) based on the automatic selection of the most representative samples selected through decision functions of the classifier. The proposed system focuses on video surveillance environments, that is, the objective is to identify an individual across the set of cameras in the surveillance area, the comparison considers only those people that share time and space. We used four public benchmarks to test our claims; the results confirm the importance of continuous appearance model's updating.