The Use of Vanishing Point for the Classification of Reflections From Foreground Mask in Videos

• Published in: IEEE transactions on image processing Vol. 18; no. 6; pp. 1366 - 1372
• Main Authors: Havasi, L., Szlavik, Z., Sziranyi, T.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.06.2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Exact sciences and technology; Extraction; Image and video processing; Image processing; Information theory; Information, signal and communications theory; Layout; Masks; Mirrors; Motion estimation; Optical reflection; Performance analysis; Reflection; robust estimation; scene analysis; Shadows; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Solid modeling; Statistics; Surveillance; Tasks; Telecommunications and information theory; Transmission line matrix methods; Videos; Performance evaluation; Image processing; Shadow; Robust estimation; Information extraction; Image and video processing; Geometrical model; Video signal processing; Image analysis; Accuracy; Asymmetry; Symmetric matrix; Scene analysis; Point estimation; Information processing; Foreground; Monitoring
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2009.2017137

Extraction of foreground is a basic task in surveillance video analysis. In most real cases, its performance is heavily based on the efficiency of shadow detection and on the analysis of lighting conditions and reflections caused by mirrors or other reflective surfaces. This correspondence is focused on the improvement of foreground extraction in the case of planar reflective surfaces. We show that the geometric model of a scene with a planar reflective surface is reduced to the estimation of vanishing-point for the case of an auto-epipolar (skew-symmetric) fundamental matrix. The correspondences for the vanishing-point estimation are extracted from motion statistics. The knowledge of the position of the vanishing point allows us to integrate the geometric model and the motion statistics into image foreground-extraction to separate foreground from reflections, and thus to achieve better performance. The experiments confirm the accuracy of the vanishing point and the improvement of the foreground image mask by removing reflected object parts.