Bio-Inspired Neuromorphic Vision by CMOS Conductance for Intelligent Monitoring of Passenger Emergency

This paper presents a system of neuromorphic vision which analyzes the passenger status in an emergency situation for post management of an accident (e-POST). The system relies on the bio-inspired robust vision of visual cortex, tunable to the selective stimulus of orientation and movement. The CMOS spiking neurons by MOS transistors’ conductance are able to implement the bio-inspired neuromorphic vision sensors based on the visual cortex experimentation of Hubel and Wiesel. This approach is demonstrated by the robust object detection of particular visual shape features. The authors have evaluated the effectiveness of the neuromorphic vision sensor by applying it to the occupancy and pose detection of passengers in the vehicle and the vehicle detection on the road, as well as the feasibility of analog-mixed CMOS VLSI implementation.

• Corporate Authors:

  ITS Japan

  Tokyo,   Japan 

  ITS America

  1100 17th Street, NW, 12th Floor
  Washington, DC  United States  20036

  ERTICO

  326 Avenue Louis
  Brussels,   Belgium  B-1050
• Authors:
  • Han, Woo Joon
  • Shin, Jae Kon
  • Lee, Jae Wan
  • Han, Il Song
• Conference:
  • 17th ITS World Congress
  • Location: Busan , Korea, South
  • Date: 2010-10-25 to 2010-10-29
• Publication Date: 2010

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; Photos; References;
• Pagination: 12p
• Monograph Title: 17th ITS World Congress, Busan, 2010: Proceedings

Subject/Index Terms

• TRT Terms: CMOS devices; Computer vision; Detection and identification systems; Passengers; Sensors
• Subject Areas: Data and Information Technology; Highways; Vehicles and Equipment; I90: Vehicles;

Filing Info

• Accession Number: 01365999
• Record Type: Publication
• Files: TRIS
• Created Date: Mar 23 2012 8:44AM