Correlation Filter Network Model Performance Analysis

Object tracking is an significant field of computer vision, which is extensive used in the fields of automatic driving and intelligent monitoring. However, target tracking still has difficulties in tracking caused by factors such as occlusion, illumination, and scale changes. In order to accurately track the target and increase the tracking performance of the model, the paper reproduces the two goals of the full convolution twin neural network and the correlation filtering neural network. The tracking algorithm is tested using the OTB100 data set. The target tracking overlap rate differs by 1.3%, and the success rate differs by 1.5%. Experiments show that, in the face of complex environments, the relevant filtering neural network updates the model in time and shows excellent tracking results.

[1]  Qiang Wang,et al.  Fast Online Object Tracking and Segmentation: A Unifying Approach , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Shiguang Shan,et al.  Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking , 2018, ECCV.

[3]  Luca Bertinetto,et al.  Fully-Convolutional Siamese Networks for Object Tracking , 2016, ECCV Workshops.

[4]  Ruchi Pandey,et al.  Deep Learning For Computer Vision Tasks: A review , 2018, ArXiv.

[5]  Wei Wu,et al.  High Performance Visual Tracking with Siamese Region Proposal Network , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Luca Bertinetto,et al.  End-to-End Representation Learning for Correlation Filter Based Tracking , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Chong Luo,et al.  A Twofold Siamese Network for Real-Time Object Tracking , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Ankita Kalra,et al.  A scalable and robust framework for intelligent real-time video surveillance , 2016, 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[9]  Bohyung Han,et al.  Learning Multi-domain Convolutional Neural Networks for Visual Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Song Wang,et al.  Learning Dynamic Siamese Network for Visual Object Tracking , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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