Citation

Tzamali E, Akoumianakis G, Argyros A, Stephanedes YJ. J. Transp. Eng. 2006; 132(11): 837-844.

Affiliation

Institute of Computer Science, Foundation of Research and Technology - Hellas (FORTH), Athens 15341, Greece

Copyright

(Copyright © 2006, American Society of Civil Engineers)

DOI

unavailable

PMID

unavailable

Abstract

Advances in machine vision techniques have led to algorithms and integrated systems that can be applied in transportation engineering to improve surveillance and control. Despite these advances, certain problems in the effective integration of machine-vision based systems at complex intersections and complex freeway sections still remain. These are related to increasing system performance in the identification, analysis, and detection of the traffic state in real time. This work examines the feasibility of providing transformed visual input to existing machine-vision based systems, in order to gain increased efficiency and cost effectiveness of integrated transportation systems. Two transformations are developed, homography-based transformation and panoramic image reprojection. Homography-based transformation operates on video of the road scene, provided by classical cameras, and seeks to transform any view to a top-down view. This transforms the three-dimensional problem of image analysis for, e.g., road event detection to a two-dimensional one. Panoramic image reprojection employs panoramic cameras to reduce required hardware, and the complexity and cost incurred in obtaining the desired road view. The image reprojection technique allows the reconstruction of undistorted, perspectively correct views from panoramic images in real time. Tests at sites in Spain, the United Kingdom, and Greece are performed on-line and off-line in combination with operating machine-vision based incident detection systems. Test results indicate that the two methods simplify the input provided to machine vision, and reduce the workload and amount of hardware in implementing complex machine-vision based systems for incident detection. Both modules can be integrated into incident detection systems to improve their overall efficiency and ease of application.