Target Re-detection and Tracking Based on Correlated Filter

Visual object tracking is a key research field in computer vision. Correlation filter tracker (CFT) based methods have shown the strong ability to track objects. However, they did not consider re-detecting the target when tracking failed, which leads to the bad performance. In order to solve this challenge, we propose a novel tracking algorithm that combines the correlation filter tracker and particle filter tracker to re-detect the target. Our algorithm consists three steps: First, we use the correlation filter tracker to track the target and calculate the average peak correlation energy (APCE). Then, we compare the APCE with the default threshold value to determine whether the tracking target misses. When the target missed, particle filter algorithm is used to re-detect the target and the location of the target is obtained in the current frame based on the location of the target in the previous frame. Compared with the staple tracking algorithm, experimental results show that the proposed algorithm is superior to the staple algorithm in distance precision and success rate. Besides, out algorithm operates fast and can meet the real-time requirement.

[1]  Luc Van Gool,et al.  Robust tracking-by-detection using a detector confidence particle filter , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Hanqing Lu,et al.  MC-HOG Correlation Tracking with Saliency Proposal , 2016, AAAI.

[4]  Michael Felsberg,et al.  Convolutional Features for Correlation Filter Based Visual Tracking , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

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

[6]  Luca Bertinetto,et al.  Staple: Complementary Learners for Real-Time Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yong Liu,et al.  Large Margin Object Tracking with Circulant Feature Maps , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[9]  Ming-Hsuan Yang,et al.  Long-term correlation tracking , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Simone Calderara,et al.  Visual Tracking: An Experimental Survey , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Michael Felsberg,et al.  Accurate Scale Estimation for Robust Visual Tracking , 2014, BMVC.

[12]  Arnold W. M. Smeulders,et al.  Fast occluded object tracking by a robust appearance filter , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.