Hot-Spot Blob Merging for Real-Time Image Segmentation

One of the major, difficult tasks in automated video surveillance is the segmentation of relevant objects in the scene. Current implementations often yield inconsistent results on average from frame to frame when trying to differentiate partly occluding objects. This paper presents an efficient block-based segmentation algorithm which is capable of separating partly occluding objects and detecting shadows. It has been proven to perform in real time with a maximum duration of 47.48 ms per frame (for 8x8 blocks on a 720x576 image) with a true positive rate of 89.2%. The flexible structure of the algorithm enables adaptations and improvements with little effort. Most of the parameters correspond to relative differences between quantities extracted from the image and should therefore not depend on scene and lighting conditions. Thus presenting a performance oriented segmentation algorithm which is applicable in all critical real time scenarios.

Authors:

• K. Kraus
• M. Uiberacker
• O. Martikainen
• R. Reda

Keywords:

• Image segmentation
• Model-based
• Region growing
• Blob Analysis
• Occlusion
• Shadow detection
• Intelligent videosurveillance.

References:

[1] L. Shapiro and G. Stockman: "Computer Vision", pp 279-325, New
Jersey, Prentice-Hall, ISBN 0-13-030796-3, 2001.
[2] S. Osher, N. Paragios: Geometric Level Set Methods in Imaging Vision
and Graphics, Springer Verlag, ISBN 0387954880, 2003
[3] J. Shi, J. Malik: "Normalized Cuts and Image Segmentation", IEEE
Conference on Computer Vision and Pattern Recognition, pp 731-737,
1997
[4] Beucher S, Meyer F. The morphological approach to segmentation:The
watershed transformation. In: Dougherty ER, ed. Mathematical
morphology in image processing.New York: Marcel Dekker, 1993: 433-
481.
[5] Y Cheng: Mean Shift, Mode Seeking, and Clustering, IEEE
Transactions on Pattern Analysis and Machine, 1995.
[6] C. Beleznai, B. Fruhstuck, H. Bischof: Human detection in groups using
a fast mean shift procedure, Image Processing, ICIP '04: International
Conference, 2004.
[7] T. Horprasert, D. Harwood, L. Davis: A statistical approach for Realtime
Robust Background Subtraction and Shadow Detection, EEE
ICCV'99 Frame-Rate Workshop, 1999.
[8] PETS 2006, Ninth IEEE International Workshop on Performance
Evaluation of Tracking and Surveillance: http://www.pets2006.net,
2006.
[9] T. Leung, J Malik: Representing and Recognizing the Visual
Appearance of Materials using Three-dimensional Textons, International
Journal of Computer Vision, 2001.
[10] N Dalai, B Triggs, I Rhone-Alps, F Montbonnot: Histograms of oriented
gradients for human detection, Computer Vision and Pattern
Recognition, 2005.