Clothing mark index system with image saliency in surveillance videos

Lili Jia; Wenbin Liu; Wei Chen

doi:10.1117/12.2553063

31 January 2020 Clothing mark index system with image saliency in surveillance videos

Lili Jia, Wenbin Liu, Wei Chen

Proceedings Volume 11427, Second Target Recognition and Artificial Intelligence Summit Forum; 114273Q (2020) https://doi.org/10.1117/12.2553063
Event: Second Target Recognition and Artificial Intelligence Summit Forum, 2019, Changchun, China

Abstract

In order to strengthen the management and control of special crowd and increase the application effectiveness of video as a typical unstructured data, this paper focuses on how to effectively extract and utilize the rich content contained in it to transform into intelligence information and build an effective personnel-specific tracking system. The experimental results show that the combination of video motion region extraction and personnel image features can more accurately complete person detection, and the introduction of multi-feature fusion to extract special person regions, such as clothing logo identification and other areas, for specific person to carry out feature labeling to index, improve the accuracy of personnel tracking. From the perspective of police technology innovation, this paper introduces the method of personnel characteristics analysis, comparison, retrieval, data mining and intelligent early warning to improve the application level of valuable personnel characteristics data in video images, and establish a feature analysis system to achieve continuous tracking of targets.

Citation Download Citation

Lili Jia, Wenbin Liu, and Wei Chen "Clothing mark index system with image saliency in surveillance videos", Proc. SPIE 11427, Second Target Recognition and Artificial Intelligence Summit Forum, 114273Q (31 January 2020); https://doi.org/10.1117/12.2553063

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available