A Single-Scan Algorithm for Connected Components Labelling in a Traffic Monitoring Application

This paper presents a fast algorithm based on sequential local operations which aims at labelling connected components in binary images. While classical algorithms scan the image twice and utilize an equiv alencetable to store and resolve lable redundancies, our method performs just a single scan, relying on the idea of labelling a whole blob at a time. In this way, we avoid label redundancies. As a consequence, the use od both equivalence tables and algorithms to resolve them becomes unnecessary. This leads our labelling algorithm to attain even more significant performances in the case of image characterized by blobs generating a large number of label equivalences. The proposed labelling algorithm has been successfully utilized in our visual surveillance system.

[1]  Patrick Garda,et al.  Motion detection, labeling, data association and tracking, in real-time on RISC computer , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[2]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[3]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[4]  Alessandro Bevilacqua Effective Object Segmentation in a Traffic Monitoring Application , 2002, ICVGIP.

[5]  Azriel Rosenfeld,et al.  Sequential Operations in Digital Picture Processing , 1966, JACM.

[6]  T. Hattori A high-speed pipeline processor for regional labelling based on a new algorithm , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[7]  Carl G. Looney,et al.  Fast connected component labeling algorithm using a divide and conquer technique , 2000, CATA.

[8]  Kenji Suzuki,et al.  Fast connected-component labeling based on sequential local operations in the course of forward raster scan followed by backward raster scan , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[9]  Alessandro Bevilacqua,et al.  Effective Shadow Detection in Traffic Monitoring Applications , 2003, WSCG.

[10]  Luigi di Stefano,et al.  A simple and efficient connected components labeling algorithm , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[11]  Alessandro Bevilacqua A Novel Background Initialization Method in Visual Surveillance , 2002, MVA.

[12]  Reinhard Klette,et al.  Handbook of image processing operators , 1996 .

[13]  Alessandro Bevilacqua,et al.  Robust denoising and moving shadows detection in traffic scenes , 2001 .