Stereo-Vision-Based Pedestrian's Intention Detection in a Moving Vehicle

The authors present a method to detect starting, stopping and bending in intentions of pedestrians from a moving vehicle based on stereo-vision. The method focuses on urban scenarios where these pedestrian movements are common and may result in critical situations. Pedestrian intentions are determined by means of an image-based motion contour histogram of oriented gradient descriptor. It is based on silhouettes gathered from stereo data and does not require any compensation of appearance changes resulting from the ego-motion of a vehicle. Nevertheless, it covers small movements indicating a pedestrian's intention. A linear support vector machine with probabilistic estimates is used for classification. The authors evaluated their method on the publicly available Daimler Pedestrian Path Prediction Benchmark Dataset containing detections of a state-of-the-art pedestrian detector. The authors detect a pedestrian's stopping intention from 125 ms to 500 ms before standing still within an accuracy range of 80% to 100%. Bending in is detected from 320 ms to 570 ms after a first visible lateral body movement in the same accuracy range. The intention to cross the road from standing still (starting) is detected 250 ms after the first visible motion and, therefore, within the first step with an accuracy of 100%.

• Record URL:
  • https://doi.org/10.1109/ITSC.2015.374
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9781467365956
• Supplemental Notes:
  • Abstract reprinted with permission of IEEE.
• Corporate Authors:

  Institute of Electrical and Electronics Engineers (IEEE)

  3 Park Avenue, 17th Floor
  New York, NY  United States  10016-5997
• Authors:
  • Köhler, Sebastian
  • Goldhammer, Michael
  • Zindler, Klaus
  • Doll, Konrad
  • Dietmeyer, Klaus
• Conference:
  • 18th International IEEE Conference on Intelligent Transportation Systems (ITSC)
  • Location: Canary Islands , Spain
  • Date: 2015-9-15 to 2015-9-18
• Publication Date: 2015

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 2317-2322
• Monograph Title: 18th International IEEE Conference on Intelligent Transportation Systems (ITSC 2015)

Subject/Index Terms

• TRT Terms: Accuracy; Detection and identification; Image processing; Intelligent vehicles; Pedestrians
• Uncontrolled Terms: Intentions; Stereo vision; Support vector machines
• Subject Areas: Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01601917
• Record Type: Publication
• ISBN: 9781467365956
• Files: TRIS
• Created Date: Jun 15 2016 12:05PM