JiaoJiao Xing
ABSTRACT
ECO based trackers have achieved excellent performance on visual object tracking. However, Illumination variation and other factors still are challenging research problems in the process of tracking. Moreover, traditional neural networks also face information loss during the transmission process. In this paper, we introduce a new feature fusion (HE, FHOG-Encoder) and update strategy of learning rate. We propose an encoder network to extract features, which consists of two convolutional layers and three residual units. In addition, we design an updating strategy of learning rate, by computing absolute difference of inter-frame pixel, to effectively update sample space model. Experiments on challenging benchmarks OTB-100 are carried out. Experimental results show that our tracker achieves superior performance in some special cases, compared with the original ECO tracker.
- D. S. Bolme, J. R. Beveridge, B. A. Draper, Visual object tracking using adaptive correlation filters. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, 2010, 2544-2550.Google Scholar
Cross Ref
- Henriques J F, Caseiro R, Martins P, Exploiting the circulant structure of tracking-by-detection with kernels. In ECCV, 2012.Google ScholarDigital Library
- Henriques, João F., High-speed tracking with kernelized correlation filters. In Pattern Analysis and Machine Intelligence, IEEE Transactions ,2015, 583-596.Google Scholar
- Martin Danelljan, Gustav Häger, Fahad Khan, Accurate Scale Estimation for Robust Visual Tracking. In Proceedings of the British Machine Vision Conference (BMVC), 2014.Google Scholar
- Li Y., Zhu J. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration. In Agapito L., Bronstein M., Rother C. (eds) Computer Vision - ECCV 2014 Workshops, 2014.Google Scholar
- H. Nam and B. Han. Learning multi-domain convolutional neural networks for visual tracking. In CVPR, 2016.Google ScholarCross Ref
- Held D , Thrun S , Savarese S . Learning to Track at 100 FPS with Deep Regression Networks. In European Conference on Computer Vision, Springer, Cham, 2016.Google ScholarCross Ref
- Luca Bertinetto, Jack Valmadre, Joao F Henriques, Fully-convolutional siamese networks for object tracking. In ECCV, 2016.Google ScholarCross Ref
- Zhang Z , Peng H . Deeper and Wider Siamese Networks for Real-Time Visual Tracking. 2019.Google ScholarCross Ref
- Danelljan M , Robinson A , Khan F S, Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking. In Springer International Publishing, 2016.Google Scholar
- Danelljan, M., ECO: Efficient Convolution Operators for Tracking. In arXiv preprint arXiv:1611.09224, 2016.Google Scholar
- Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, ECO: Efficient convolution operators for tracking. In CVPR, 2017, volume 1, page 3.Google Scholar
- Y. Wu, J. Lim, and M.-H. Yang. Object tracking benchmark. In TPAMI, 2015, 37(9):1834–1848.Google ScholarDigital Library
- J. F. Henriques, R. Caseiro, P. Martins, High speed tracking with kernelized correlation fifilters. In TPAMI, 2015, 37(3):583–596.Google ScholarDigital Library
- Z. Kalal, J. Matas, and K. Mikolajczyk. P-n learning: Bootstrapping binary classifiers by structural constraints. In CVPR, 2010.Google ScholarCross Ref
- S. Hare, A. Saffari, and P. Torr. Struck: Structured output tracking with kernels. In ICCV, 2011.Google ScholarDigital Library
- M. Danelljan, G. H¨ager, F. Shahbaz Khan, Accurate scale estimation for robust visual tracking. In BMVC, 2014.Google ScholarCross Ref
- B.Luca, V.Jack, G.Stuart, Staple: Complementary learners for real-time tracking. In CVPR, 2016.Google Scholar
- Tianyu Yang and Antoni B. Chan. Learning Dynamic Memory Networks for Object Tracking. In ECCV, 2018.Google Scholar
- Bo Li, Junjie Yan, Wei Wu,et al. High performance visual tracking with siamese region proposal network. In CVPR, 2018.Google ScholarCross Ref
- Zheng Zhu, Qiang Wang, Bo Li, Distractor-aware siamese networks for visual object tracking. In ECCV, 2018.Google ScholarDigital Library
- Yang T, Xu P, Hu R, ROAM: Recurrently Optimizing Tracking Model. 2019.Google Scholar
- Xiankai Lu, Chao Ma, Bingbing Ni, Deep Regression Tracking with Shrinkage Loss. In ECCV, 2018.Google ScholarDigital Library
Index Terms
- Target tracking by improved ECO
Recommendations
Robust pedestrian tracking using improved tracking-learning-detection algorithm
ICVGIP '16: Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image ProcessingManual analysis of pedestrians for surveillance of large crowds in real time applications is not practical. Tracking-Learning-Detection suggested by Kalal, Mikolajczyk and Matas [1] is one of the most prominent automatic object tracking system. TLD can ...
Hierarchical multi-modal fusion FCN with attention model for RGB-D tracking
Highlights- We propose a RGB-D tracker based on hierarchical multi-modal fusion FCN with attention model.
AbstractIn this paper, we propose a RGB-D tracking algorithm, built upon hierarchical multi-modal fusion fully convolutional neural network (FCN) with attention model. First, we encode the depth images into three channels using the HHA ...
Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph
Incorporating multiple cameras is an effective solution to improve the performance and robustness of multi-target tracking to occlusion and appearance ambiguities. In this paper, we propose a new multi-camera multi-target tracking method based on a ...
Comments