Detecting occluded objects is a crucial exercise in many spheres of application. For example in Strafing (attacking ground targets from low flying aircrafts) or vehicular tracking, continuous detection of the object even when it is occluded by another object is essential. Failing to track the occluded object may result in completely losing its location or another object to be mistakenly tracked. Both of which will result in disastrous consequences. There are various methods to handle occlusions. In a previous research which was done by the author, a novel noise filtration mechanism based on the corrector equation of the Kalman filter which can be used with greater accuracy to handle lengthy occlusions was made. In this presentation, a further analysis of the error of the algorithm will be presented. The algorithm when compared with existing algorithms under the same test conditions gives promising results.
References
[1]
Shu, G., et al. (2012) Part-Based Multiple-Person Tracking with Partial Occlusion Handling. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, 16-21 June 2012, 1815-1821.
[2]
Dinh, T.B. and Medioni, G. (2011) Co-Training Framework of Generative and Discriminative Trackers with Partial Occlusion Handling. IEEE Workshop on Applications of Computer Vision (WACV), Kona, HI, 5-7 January 2011, 13-15.
[3]
Enzweiler, M., et al. (2010) Multi-Cue Pedestrian Classification with Partial Occlusion Handling. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, 13-18 June 2010, 990-997.
[4]
Ouyang, W. and Wang, X. (2012) A Discriminative Deep Model for Pedestrian Detection with Occlusion Handling. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, 16-21 June 2012, 3258-3265.
[5]
Fleuret, F., Lengagne, R. and Fua, P. (2005) Fixed Point Probability Field for Complex Occlusion Handling. 10th IEEE International Conference on Computer Vision (ICCV), Washington DC, 17-20 October 2005, 694-700.
[6]
Schick, A. and Stiefelhagen, R. (2009) Real-Time GPU-Based Voxel Carving with Systematic Occlusion Handling. Pattern Recognition, 5748, 372-381.
https://doi.org/10.1007/978-3-642-03798-6_38
[7]
Caillette, F. and Howard, T. (2004) Real-Time Marker Less Human Body Tracking Using Colored Voxels and 3-D Blobs. 3rd IEEE and ACM International Symposium on Mixed and Augmented Reality, Arlington, VA, 5-5 November 2004, 266-267.
https://doi.org/10.1109/ISMAR.2004.50
[8]
Sun, J., Kang, S.B. and Shum, H.-Y. (2005) Symmetric Stereo Matching for Occlusion Handling. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, 20-26 June, 2005, 399-406.
[9]
Senior, A., et al. (2006) Appearance Models for Occlusion Handling. Image and Vision Computing, 24, 1233-1243.
[10]
Pan, J. and Hu, B. (2007) Robust Occlusion Handling in Object Tracking. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, 17-22 June 2007, 1-8. https://doi.org/10.1109/CVPR.2007.383453
[11]
Guha, P., Mukerjee, A. and Venkatesh, K. (2005) Efficient Occlusion Handling for Multiple Agent Tracking by Reasoning with Surveillance Event Primitives. 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, Beijing, 49-56.
[12]
Yang, T., Pan, Q. and Li, J. (2005) Real-Time Multiple Objects Tracking with Occlusion Handling in Dynamic Scenes. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, 970-975.
[13]
Zhong, D., Lu, H. and Yang, M.-H. (2012) Robust Object Tracking via Sparsity Based Collaborative Model. IEEE Conference on Computer Vision and Pattern Recognition, Providence, 1838-1845.
[14]
Schulz, W., Burgard, W. and Craemers, A.B. (2001) Tracking Multiple Moving Targets with a Mobile Robot Using Particle Filters and Statistical Data Association. IEEE International Conference on Robotics and Automation, Seoul, 1665-1670.
[15]
Zhou, S.K., Chellappa, R. and Moghaddam, B. (2004) Visual Tracking and Recognition Using Appearance-Adaptive Models in Particle Filters. IEEE Transactions on Image Processing, 13, 1491-1506.
[16]
Zhang, C., Xu, J., Goto, S. and Beaugendre, A. (2012) A KLT-Based Approach for Occlusion Handling in Human Tracking. Picture Coding Symposium, Krakow, 337-340.
[17]
Panahi, R., Gholampour, I. and Jamzad, M. (2013) Real Time Occlusion Handling Using Kalman Filter and Mean-Shift. 8th Iranian Conference on Machine Vision and Image Processing, Zanjan, 320-323.
[18]
Ramos, O.E., Mirzaei, M.A. and Merienne, F. (2011) Tracking in Presence of Total Occlusion and Size Variation using Mean Shift and Kalman Filter. IEEE/SICE International Symposium on System Integration, Kyoto, 401-406.
[19]
De Villiers, B.Z., Clarke, W.A. and Robinson, P.E. (2012) Mean Shift Object Tracking with Occlusion Handling. 23rd Annual Symposium of the Pattern Recognition Association, Johannesburg, 348-354.
[20]
Gnanasekera, M. and Kulasekere, E. (2016) Kalman Filter Based Occlusion Handler for Lengthy Occlusions. International Conference on Microelectronics, Computing and Communications, Durgapur, 1-4.
https://doi.org/10.1109/MicroCom.2016.7522545
[21]
Welch, G. and Bishop, G. (1996) An Introduction to the Kalman Filter. University of North Carolina at Chapel Hill, Chapel Hill.
