Detecting Darting Out Pedestrians With Occlusion Aware Sensor Fusion of Radar and Stereo Camera

Early and accurate detection of crossing pedestrians is crucial in automated driving in order to perform timely emergency manoeuvres. However, this is a difficult task in urban scenarios where pedestrians are often occluded (not visible) behind objects, e.g., other parked vehicles. The authors propose an occlusion aware fusion of stereo camera and radar sensors to address scenarios with crossing pedestrians behind such parked vehicles. The authors' proposed method adapts both the expected rate and properties of detections in different areas according to the visibility of the sensors. In the authors' experiments on a real-world dataset, the authors show that the proposed occlusion aware fusion of radar and stereo camera detects the crossing pedestrians on average 0.26 seconds earlier than using the camera alone, and 0.15 seconds earlier than fusing the sensors without occlusion information. The authors' dataset containing 501 relevant recordings of pedestrians behind vehicles will be publicly available on their website for non-commercial, scientific use.

• Record URL:
  http://dx.doi.org/10.1109/TIV.2022.3220435
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/23798858
• Supplemental Notes:
  • Copyright © 2023, IEEE.
• Authors:
  • Palffy, Andras
  • Kooij, Julian F P
  • Gavrila, Dariu M
• Publication Date: 2023-2

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 1459-1472
• Serial:
  • IEEE Transactions on Intelligent Vehicles
  • Volume: 8
  • Issue Number: 2
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 2379-8858
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7274857

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Data fusion; Detection and identification technologies; Pedestrians; Radar; Stereoscopic cameras; Urban areas; Visibility
• Subject Areas: Data and Information Technology; Highways; Pedestrians and Bicyclists; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01884262
• Record Type: Publication
• Files: TRIS
• Created Date: May 31 2023 10:58AM