Tracking of multiple objects with time-adjustable composite correlation filters

An algorithm for tracking of multiple objects in video based on time-adjustable adaptive composite correlation filtering is proposed. For each frame a bank of composite correlation filters are designed in such a manner to provide invariance to pose, occlusion, clutter, and illumination changes. The filters are synthesized with the help of an iterative algorithm, which optimizes the discrimination capability for each object. The filters are adapted to the objects changes online using information from the current and past scene frames. Results obtained with the proposed algorithm using real-life scenes are presented and compared with those obtained with state-of-the-art tracking methods in terms of detection efficiency, tracking accuracy, and speed of processing.

[1]  Vitaly Kober,et al.  Facial recognition using composite correlation filters designed with multiobjective combinatorial optimization , 2014, Optics & Photonics - Optical Engineering + Applications.

[2]  Wang Shen-shen.  A Robust Tracking Algorithm for Multiple-Sensor , 2011 .

[3]  Vitaly Kober,et al.  Real-Time Tracking Based on Rotation-Invariant Descriptors , 2015, 2015 International Conference on Computational Science and Computational Intelligence (CSCI).

[4]  Vitaly Kober,et al.  A Robust Tracking Algorithm Based on HOGs Descriptor , 2014, CIARP.

[5]  Vitaly Kober,et al.  A robust HOG-based descriptor for pattern recognition , 2016, Optical Engineering + Applications.

[6]  Vitaly Kober,et al.  Accurate three-dimensional pose recognition from monocular images using template matched filtering , 2016 .

[7]  Serdar Korukoglu,et al.  Performance Evaluation Software , 2013, SpringerBriefs in Computer Science.

[8]  Vitaly Kober,et al.  Robust illumination-invariant tracking algorithm based on HOGs , 2015, SPIE Optical Engineering + Applications.

[9]  Ming-Hsuan Yang,et al.  Object Tracking Benchmark , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  A. Ruchay,et al.  A new predicting method based on estimate of holder exponent by continuous wavelet transform , 2016, 2016 2nd International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM).

[11]  Ilya Sochenkov,et al.  Face recognition based on a matching algorithm with recursive calculation of oriented gradient histograms , 2016 .

[12]  Vitaly Kober,et al.  Adaptive composite filters for pattern recognition in linearly degraded and noisy scenes , 2008 .

[13]  Vitaly Kober,et al.  Objects tracking with adaptive correlation filters and Kalman filtering , 2015, SPIE Optical Engineering + Applications.

[14]  A. Vokhmintsev,et al.  Visual Duplicates Image Search for a Non-cooperative Person Recognition at a Distance , 2015 .

[15]  Vitaly Kober,et al.  An efficient algorithm for matching of SLAM video sequences , 2016, Optical Engineering + Applications.

[16]  Huchuan Lu,et al.  Robust object tracking via sparsity-based collaborative model , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Vitaly Kober,et al.  Adaptive composite filters for pattern recognition in nonoverlapping scenes using noisy training images , 2014, Pattern Recognit. Lett..

[18]  A. Sochenkova,et al.  Effective indexing for face recognition , 2016, Optical Engineering + Applications.

[19]  Victor H. Diaz-Ramirez,et al.  Target tracking with dynamically adaptive correlation , 2016 .

[20]  Vitaly Kober,et al.  Real-time tracking of multiple objects using adaptive correlation filters with complex constraints , 2013 .

[21]  Vitaly Kober,et al.  Text Detection in Digital Images Captured with Low Resolution Under Nonuniform Illumination Conditions , 2016, MCPR.

[22]  Vitaly Kober,et al.  Conformal Parameterization and Curvature Analysis for 3D Facial Recognition , 2015, 2015 International Conference on Computational Science and Computational Intelligence (CSCI).

[23]  Vitaly Kober,et al.  3D face recognition based on matching of facial surfaces , 2015, SPIE Optical Engineering + Applications.

[24]  Bahadir Karasulu,et al.  Performance Evaluation Software: Moving Object Detection and Tracking in Videos , 2013 .

[25]  Vitaly Kober,et al.  A correlation-based algorithm for recognition and tracking of partially occluded objects , 2016, Optical Engineering + Applications.

[26]  Vitaly Kober,et al.  Multiple objects tracking with HOGs matching in circular windows , 2014, Optics & Photonics - Optical Engineering + Applications.

[27]  Artyom Makovetskii,et al.  A modified iterative closest point algorithm for shape registration , 2016, Optical Engineering + Applications.

[28]  Vitaly Kober,et al.  Target tracking in nonuniform illumination conditions using locally adaptive correlation filters , 2014 .

[29]  Vitaly Kober,et al.  Object Tracking in Nonuniform Illumination Using Space-Variant Correlation Filters , 2013, CIARP.

[30]  Vitaly Kober,et al.  Correlation-based tracking using tunable training and Kalman prediction , 2016, Optical Engineering + Applications.

[31]  Vitaly Kober,et al.  Robust Face Tracking with Locally-Adaptive Correlation Filtering , 2014, CIARP.