Authors:
Kristof Van Beeck
and
Toon Goedemé
Affiliation:
Campus De Nayer - KU Leuven and KU Leuven, Belgium
Keyword(s):
Pedestrian Detection, Tracking, Real-time, Computer Vision, Active Safety Systems.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Human-Computer Interaction
;
Image and Video Analysis
;
Image Understanding
;
Methodologies and Methods
;
Motion and Tracking
;
Motion, Tracking and Stereo Vision
;
Object Recognition
;
Pattern Recognition
;
Physiological Computing Systems
;
Software Engineering
;
Video Analysis
Abstract:
In this paper we present a multi-pedestrian detection and tracking framework targeting a specific application:
detecting vulnerable road users in a truck’s blind spot zone. Research indicates that existing non-vision based
safety solutions are not able to handle this problem completely. Therefore we aim to develop an active safety
system which warns the truck driver if pedestrians are present in the truck’s blind spot zone. Our system solely
uses the vision input from the truck’s blind spot camera to detect pedestrians. This is not a trivial task, since
the application inherently requires real-time operation while at the same time attaining very high accuracy.
Furthermore we need to cope with the large lens distortion and the extreme viewpoints introduced by the blind
spot camera. To achieve this, we propose a fast and efficient pedestrian detection and tracking framework
based on our novel perspective warping window approach. To evaluate our algorithm we recorded several
realistical
ly simulated blind spot scenarios with a genuine blind spot camera mounted on a real truck. We
show that our algorithm achieves excellent accuracy results at real-time performance, using a single core CPU
implementation only.
(More)