Browse by author
Lookup NU author(s): Dr Richard Stafford
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
In this paper a bioinspired algorithm for collision detection is proposed, based on previous models of the locust (Locusta migratoria) visual system reported by F.C. Rind and her group, in the University of Newcastle-upon-Tyne. The algorithm is intended for its VLSI implementation in standard CMOS technologies as a system-on-chip for automotive applications. The working principle of the algorithm is to process a video stream that represents the current scenario, and to fire a collision alarm if an object approaches in collision course. Moreover, it establishes a scale of warning states, from no danger to collision alarm, depending on the activity it detects in the current scenario. In the worst case, the minimum time before collision at which the model would fire the collision alarm is 40 msec (1 frame before, at 25 frames per second). The average time to successfully fire an airbag system is 2 msec. So, even in the worst case, this algorithm would be very helpful to more efficiently arm the airbag system, or even take some kind of collision avoidance countermeasures. Furthermore, we have included an additional module called “Topological Feature Estimator” that takes into account the shape of the approaching object to decide whether it is a person, a road line or a car. This is very helpful in rejecting false alarms fired by stripes and horizontal lines on the road, complementing the information the algorithm offers as a result of the processing.
Author(s): Cuadri J, Linan G, Keil MS, Stafford R, Roca E
Editor(s): Carmona, R.A., Linan-Cembrano, G.
Publication type: Book Chapter
Publication status: Published
Book Title: Bioengineered and Bioinspired Systems II
Year: 2005
Volume: 5839
Pages: 238-248
Series Title: Proceedings of SPIE
Publisher: SPIE
Place Published: London, UK
Library holdings: Search Newcastle University Library for this item
ISBN: 9780819458346
