Utilizing Biomimetic Image Processing to Detect the Road Edge of Off-Road Terrain
Abstract
Soldiers incurred injuries or even lost their lives due to rollovers while driving military vehicles. A recent report identified that the one cause of rollovers is the driver's inability to assess rollover threats, such as a cliff, soft ground, water, or a culvert on the passenger side of the vehicle, due to the vehicle's width. To reduce the number of rollover accidents, a road-edge detection and driver warning system is being developed to detect the rollover threats on the passenger side of the vehicle and warn the driver. This system utilizes a unique, ultra-fast image processing algorithm based on the neurobiology of insect vision and the study of fly vision. The system consists of a camera system, a long-range, planar laser scanner, a processing module in which a biomimetic image processor detects edges present in the images in real-time, and a Driver Vision Enhancer (DVE) which displays the current road image, detected boundaries, and road side terrain steepness.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2007
- Accession Number
- ADA484745
Entities
People
- Nancy Truong
- William Agassounon
Organizations
- United States Army Tank Automotive Research, Development and Engineering Center