Object Tracking in UAV Videos by Multifeature Correlation Filters With Saliency Proposals
Open Access
- 5 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 5538-5548
Abstract
The purpose of object tracking is to locate a given target in image sequence, such as people and vehicles. In recent years, with the development of UAV technology, object tracking in UAV videos has engaged many scholars. It has been widely used in traffic control, water quality inspection, wildlife census and other fields. However, low resolution, scale change, occlusion and other challenges have been restricting the development of the tracker. To solve the aforementioned problems, we put forward multi-feature correlation filters with saliency proposals. First, we use histogram of oriented gradient (HOG) features, gray (I) features and color names (CN) features to heighten the representation information of target, so that our algorithm can accurately locate small targets. Then, we introduce saliency proposals to reposition the occluded target. Finally, we use dynamic update weights instead of the fixed update weights to mitigate the adverse effects caused by template degradation. Experiments demonstrate that our tracker has achieved satisfactory tracking accuracy and AUC scores have reached 0.462, 0.417, and 0.425 on UAV123@10FPS, UAV20L, and UAVDT datasets respectively.Keywords
Funding Information
- Natural Science Foundation of Jiangsu Province (BK20211539)
- National Natural Science Foundation of China (U20B2065, U22B2056)
- Qinglan Project of Jiangsu Province of China
- Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX23_1372)
This publication has 47 references indexed in Scilit:
- A Benchmark and Simulator for UAV Tracking2016
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking2016
- Discriminative Scale Space TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Learning Spatially Regularized Correlation Filters for Visual Tracking2015
- Hierarchical Convolutional Features for Visual Tracking2015
- A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Accurate Scale Estimation for Robust Visual Tracking2014
- Exploiting the Circulant Structure of Tracking-by-Detection with Kernels2012
- Adaptive Thresholding using the Integral ImageJournal of Graphics Tools, 2007