A Novel Scale Insensitive KCF Tracker Based on HOG and Color Features
Authors:
- 19 February 2020
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 29 (11)
Abstract
Kernelized Correlation Filters (KCF) for visual tracking have received much attention due to their fast speed and outstanding performances in real scenarios. However, the KCF sometimes still fails to track the targets with different scales, and it may drift because the target response is fixed and the original histogram of orientation gradient (HOG) features cannot represent the targets well. In this paper, we propose a novel fast tracker, which is based on KCF and insensitive to scale changes by learning two independent correlation filters (CFs) where one filter is designed for position estimation and the other is for scale estimation. In addition, it can adaptively change the target response and multiple features are integrated to improve the performance for our tracker. Finally, we employ an adaptive high confidence filters updating scheme to avoid errors. Evaluated on the popular OTB50 and OTB100 datasets, our proposed trackers show superior performances in terms of efficiency and accuracy compared to the existing methods.Keywords
Funding Information
- Basic Research Program of Jiangsu Province (BK20150784)
- Fundamental Research Funds for the Central Universities (30917011324)
- Postdoctoral Research Foundation of China (2015M581800)
- National Key Research and Development Program of China under Grant (2016YFF0103604)
- Jiangsu Key Laboratory of Spectral Imaging and Intelligence Sense (3091801410410)
- Nanjing Key Technologies Breakthrough Project in Advantageous Industrials (2108002)
- Jiangsu Provincial Key Research and Development Program (BE2016768)
This publication has 14 references indexed in Scilit:
- An effective semi-cross-validation model selection method for extreme learning machine with ridge regressionNeurocomputing, 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
- Constructive multi-output extreme learning machine with application to large tanker motion dynamics identificationNeurocomputing, 2013
- Coloring Action Recognition in Still ImagesInternational Journal of Computer Vision, 2013
- Exploiting the Circulant Structure of Tracking-by-Detection with Kernels2012
- Modulating Shape Features by Color Attention for Object RecognitionInternational Journal of Computer Vision, 2011
- A fast and accurate online self-organizing scheme for parsimonious fuzzy neural networksNeurocomputing, 2009
- Sparse Basis Selection: New Results and Application to Adaptive Prediction of Video Source TrafficIEEE Transactions on Neural Networks, 2005
- Learning with Kernels: Support Vector Machines, Regularization, Optimization, and BeyondIEEE Transactions on Neural Networks, 2005