Integration of MapReduce with an Interactive Boosting Mechanism for Image Background Subtraction in Cultural Sightseeing

Background subtraction is widely used in multimedia applications, such as traffic monitoring, video surveillance, and object tracking. Several methods with different advantages in different applications have been proposed. The advent of cloud computing also has made possible of the combination of various background subtraction techniques and the processing of large amounts of images. In this paper, an integrated algorithm for background subtraction is implemented and analyzed. The proposed AdaBoost algorithm combines weak classifiers: pixel-based background subtraction methods, block-based background subtraction methods, and graph-cut segmentation methods. After training, the program adjusts the weight of each weak classifier. The algorithm is accelerated using Hadoop cloud-computing architecture. By using a MapReduce framework, this system can parallel-processing on multiple servers in order to reduce computing time. When the system completes its task, the user can see the combined results on the screen and then choose the preferred result. The system can obtain user feedback and tune the combination mechanism.

[1]  Marko Heikkilä,et al.  A texture-based method for modeling the background and detecting moving objects , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Axel Pinz,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[3]  Jimmy J. Lin,et al.  Web-scale computer vision using MapReduce for multimedia data mining , 2010, MDMKDD '10.

[4]  Vladimir Kolmogorov,et al.  "GrabCut": interactive foreground extraction using iterated graph cuts , 2004, ACM Trans. Graph..

[5]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[6]  Harry Shum,et al.  Background Cut , 2006, ECCV.

[7]  Christopher M. Bishop,et al.  Non-linear Bayesian Image Modelling , 2000, ECCV.

[8]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[9]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[10]  Cong Wang,et al.  MRKDSBC: A Distributed Background Modeling Algorithm Based on MapReduce , 2012, ISNN.

[11]  Marios M. Polycarpou,et al.  Advances in Neural Networks – ISNN 2012 , 2012, Lecture Notes in Computer Science.

[12]  P. KaewTrakulPong,et al.  An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection , 2002 .

[13]  Larry S. Davis,et al.  Non-parametric Model for Background Subtraction , 2000, ECCV.