Efficient and high‐performance pedestrian detector implementation for intelligent vehicles. Issue 6 (1st August 2016)

• Record Type: Journal Article
• Authors: Said, Yahia; Atri, Mohamed
• Is Part Of: IET intelligent transport systems. Volume 10:Issue 6(2016)
• Page Start: 438
• Page End: 444
• Publication Date: 2016-08-01
• Subjects: intelligent transportation systems -- covariance matrices -- field programmable gate arrays -- computer vision; high‐performance pedestrian detector implementation -- intelligent vehicles -- human detection -- pedestrian detection system -- sliding covariance matrix feature descriptor -- support vector machine classifier -- field programmable gate array prototyping boards -- standard INRIA pedestrian benchmark dataset; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2015.0239
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : Human detection is exploited as a key operation in many applications such as automotive safety, intelligent vehicles, assisted living, and video surveillance. Consequently, there is a significant advancement in this area of research in the past years and a vast literature. In this study, the authors propose a pedestrian detection system which relies on sliding covariance matrix feature descriptor combined with a support vector machine classifier. The proposed framework is implemented onto field programmable gate array prototyping boards. Experimental results using the standard Institut National de Recherche en Informatique et en Automatique (INRIA) pedestrian benchmark dataset show that the proposed architecture achieved outstanding processing performances with high detection accuracy when compared with state‐of‐the‐art methods.