Pedestrian Detection Based on Clustered Poselet Models and Hierarchical <sc>and</sc>–<sc>or</sc> Grammar

In this paper, a novel part-based pedestrian detection algorithm is proposed for complex traffic surveillance environments. To capture posture and articulation variations of pedestrians, the authors define a hierarchical grammar model with the and-or graphical structure to represent the decomposition of pedestrians. Thus, pedestrian detection is converted to a parsing problem. Next, they propose clustered poselet models, which use the affinity propagation clustering algorithm to automatically select representative pedestrian part patterns in keypoint space. Trained clustered poselets are utilized as the terminal part models in the grammar model. Finally, after all clustered poselet activations in the input image are detected, one bottom-up inference is performed to effectively search maximum a posteriori (MAP) solutions in the grammar model. Thus, consistent poselet activations are combined into pedestrian hypotheses, and their bounding boxes are predicted. Both appearance scores and geometry constraints among pedestrian parts are considered in inference. A series of experiments is conducted on images, both from the public TUD-Pedestrian data set and collected in real traffic crossing scenarios. The experimental results demonstrate that the algorithm outperforms other successful approaches with high reliability and robustness in complex environments.

• Record URL:
  • https://doi.org/10.1109/TVT.2014.2331314
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00189545
• Supplemental Notes:
  • Abstract reprinted with permission of IEEE.
• Authors:
  • Li, B
  • Chen, Y
  • Wang, F
• Publication Date: 2015-4

Language

• English

Media Info

• Media Type: Web
• Pagination: pp 1435-1444
• Serial:
  • IEEE Transactions on Vehicular Technology
  • Volume: 64
  • Issue Number: 4
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 0018-9545
  • Serial URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=25

Subject/Index Terms

• TRT Terms: Algorithms; Cluster analysis; Pedestrian detectors; Pedestrian movement; Reliability; Traffic surveillance
• Subject Areas: Data and Information Technology; Highways; Pedestrians and Bicyclists; Safety and Human Factors; I85: Safety Devices used in Transport Infrastructure;

Filing Info

• Accession Number: 01564567
• Record Type: Publication
• Files: TRIS
• Created Date: May 26 2015 4:12PM