By Topic

Real time detection of the back view of a preceding vehicle for automated heterogeneous platoons in unstructured environment using video

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

6 Author(s)
Alfraheed, M. ; Inst. of Inf. Manage. in Mech. Eng. (IMA), RWTH Aachen Univ., Aachen, Germany ; Droge, A. ; Kunze, R. ; Klingender, M.
more authors

Due to the increase in road transportation several projects concerning automated highway systems were initiated to optimize highway capacity. In the future, the developed techniques should be applicable in unstructured environment (e.g. desert) and adaptable for heterogeneous vehicles. But before, several challenges, i.e. independency of lane markings, have to be overcome. Our solution is to consider the back view of the preceding vehicle as a reference point for the lateral and longitudinal control of the following vehicle. This solution is independent from the environmental structure as well as additional equipment like infrared emitters. Thus, both the detection and tracking process of the back view are needed to provide automated highway systems with the distance and the deviation degree of the preceding vehicle. In this paper the first step, the detection and location of the back view on video streams, is discussed. For a definite detection in a heterogeneous platoon several features of the back view are detected. A method is proposed to run rejection cascades generated by the AdaBoost classifier theory on the video stream. Compared to other methods related to object detection, the proposed method reduces the running time for the detection of the back view to 0.03-0.08 s/frame. Furthermore, the method enables a more accurate detection of the back view.

Published in:

Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on

Date of Conference:

9-12 Oct. 2011