Infrared target tracking via weighted correlation filter

Abstract Design of an effective target tracker is an important and challenging task for many applications due to multiple factors which can cause disturbance in infrared video sequences. In this paper, an infrared target tracking method under tracking by detection framework based on a weighted correlation filter is presented. This method consists of two parts: detection and filtering. For the detection stage, we propose a sequential detection method for the infrared target based on low-rank representation. For the filtering stage, a new multi-feature weighted function which fuses different target features is proposed, which takes the importance of the different regions into consideration. The weighted function is then incorporated into a correlation filter to compute a confidence map more accurately, in order to indicate the best target location based on the detection results obtained from the first stage. Extensive experimental results on different video sequences demonstrate that the proposed method performs favorably for detection and tracking compared with baseline methods in terms of efficiency and accuracy.

[1]  Andrea Sanna,et al.  Improving Robustness of Infrared Target Tracking Algorithms Based on Template Matching , 2011, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Hong Li,et al.  Small infrared target detection based on harmonic and sparse matrix decomposition , 2013 .

[3]  Zhenmin Tang,et al.  Modified particle filter-based infrared pedestrian tracking , 2010 .

[4]  Yong Yu,et al.  Robust Subspace Segmentation by Low-Rank Representation , 2010, ICML.

[5]  Lei Zhang,et al.  Fast Compressive Tracking , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  David Zhang,et al.  Fast Visual Tracking via Dense Spatio-temporal Context Learning , 2014, ECCV.

[7]  Xuelong Li,et al.  Track infrared point targets based on projection coefficient templates and non-linear correlation combined with Kalman prediction , 2013 .

[8]  Yi Yang,et al.  Infrared Patch-Image Model for Small Target Detection in a Single Image , 2013, IEEE Transactions on Image Processing.

[9]  Bruce A. Draper,et al.  Visual object tracking using adaptive correlation filters , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Yunli Long,et al.  Track-before-detect algorithm for maneuvering infrared weak multiple targets via particle filter , 2014 .

[11]  Bruce A. Draper,et al.  Average of Synthetic Exact Filters , 2009, CVPR.

[12]  Tianqi Zhang,et al.  Small infrared target detection using sparse ring representation , 2012, IEEE Aerospace and Electronic Systems Magazine.

[13]  Rui Caseiro,et al.  Exploiting the Circulant Structure of Tracking-by-Detection with Kernels , 2012, ECCV.

[14]  Haibin Ling,et al.  Real time robust L1 tracker using accelerated proximal gradient approach , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Philip H. S. Torr,et al.  Struck: Structured output tracking with kernels , 2011, ICCV.

[16]  Yang Lu,et al.  Online Object Tracking, Learning, and Parsing with And-Or Graphs , 2014, CVPR.

[17]  Ying Li,et al.  Real-time infrared target tracking based on ℓ1 minimization and compressive features. , 2014, Applied optics.

[18]  Xinsheng Huang,et al.  Infrared dim and small target detecting and tracking method inspired by Human Visual System , 2014 .

[19]  Yong Yu,et al.  Robust Recovery of Subspace Structures by Low-Rank Representation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Michael Felsberg,et al.  Adaptive Color Attributes for Real-Time Visual Tracking , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.