Change Detection with Weightless Neural Networks

In this paper a pixel -- based Weightless Neural Network (WNN) method to face the problem of change detection in the field of view of a camera is proposed. The main features of the proposed method are 1) the dynamic adaptability to background change due to the WNN model adopted and 2) the introduction of pixel color histories to improve system behavior in videos characterized by (des)appearing of objects in video scene and/or sudden changes in lightning and background brightness and shape. The WNN approach is very simple and straightforward, and it gives high rank results in competition with other approaches applied to the ChangeDetection.net 2014 benchmark dataset.

[1]  Igor Aleksander,et al.  Introduction to Neural Computing , 1990 .

[2]  Lucia Maddalena,et al.  The SOBS algorithm: What are the limits? , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[3]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[4]  Massimo De Gregorio,et al.  A WiSARD-Based Approach to CDnet , 2013, 2013 BRICS Congress on Computational Intelligence and 11th Brazilian Congress on Computational Intelligence.

[5]  I. Aleksander,et al.  WISARD·a radical step forward in image recognition , 1984 .

[6]  Bruno Siciliano,et al.  Tracking deformable objects with WISARD networks , 2014 .

[7]  Silvia Rossi,et al.  Can you follow that guy? , 2014, ESANN.

[8]  Ashish Ghosh,et al.  Semi-supervised change detection using modified self-organizing feature map neural network , 2014, Appl. Soft Comput..