Real-Time Long-Term Tracking With Prediction-Detection-Correction
- 7 February 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 20 (9) , 2289-2302
Abstract
Real-time long-term visual tracking is one of the most challenging problems in computer vision due to various factors such as occlusion and motion ambiguity. To achieve robust long-term tracking, most state-of-the-art methods typically construct an online detector in each frame. However, they fail to achieve real-time performance due to high computational complexity. In this paper, we propose a novel real-time long-term tracking algorithm by exploiting a joint Prediction-Detection-Correction Tracking framework (PDCT). We utilize superpixel optical flow to construct a predictor to estimate the target motion and internal scale variation. To locate the target at a finer level, we develop an improved kernelized correlation detector with an adaptive online learning rate and translation-scale parameters from the predictor. To refine the tracking result and re-detect the target in the case of tracking failure, we devise a corrector utilizing dual online SVMs with dense sampling and reliable history samples. The SVMs are trained with passive-aggressive learning and online re-training strategies. In addition, we employ a selection mechanism for the correlation responses to maintain reliable samples effectively. As a result, our proposed tracker is able to refine tracking results via the corrector and detector and maintain reliable tracking results for subsequent tracking. Extensive experiments on the widely used Object Tracking Benchmark show that the proposed tracker is superior to state-of-the-art trackers in terms of both effectiveness and efficiency, and the integration of each component is effective under the Prediction-Detection-Correction Tracking framework.Keywords
Funding Information
- National Natural Science Foundation of China (61573151)
- Natural Science Foundation of Guangdong Province (2016A030313468)
- Science and Technology Planning Project of Guangdong Province (2017A010101026)
This publication has 32 references indexed in Scilit:
- Visual Tracking Using Strong Classifier and Structural Local Sparse DescriptorsIEEE Transactions on Multimedia, 2015
- Visual Object Tracking by Structure Complexity CoefficientsIEEE Transactions on Multimedia, 2015
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Locally Orderless TrackingInternational Journal of Computer Vision, 2014
- Adaptive Color Attributes for Real-Time Visual Tracking2014
- Robust Superpixel TrackingIEEE Transactions on Image Processing, 2014
- Visual Tracking: An Experimental SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Exploiting the Circulant Structure of Tracking-by-Detection with Kernels2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009