Spatial and Channel Attention Mechanism Method for Object Tracking

Jiamin LIU; Wenjie XIE; Hong HUANG; Yiming TANG

doi:10.11999/JEIT200687

Volume 43 Issue 9

Sep. 2021

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2021 > 43(9): 2569-2576

Jiamin LIU, Wenjie XIE, Hong HUANG, Yiming TANG. Spatial and Channel Attention Mechanism Method for Object Tracking[J]. Journal of Electronics & Information Technology, 2021, 43(9): 2569-2576. doi: 10.11999/JEIT200687

Citation:

Jiamin LIU, Wenjie XIE, Hong HUANG, Yiming TANG. Spatial and Channel Attention Mechanism Method for Object Tracking[J]. Journal of Electronics & Information Technology, 2021, 43(9): 2569-2576. doi: 10.11999/JEIT200687

Citation:

PDF( 3423 KB)

Spatial and Channel Attention Mechanism Method for Object Tracking

doi: 10.11999/JEIT200687

Key Laboratory of Optoelectronic Technique System of the Ministry of Education, Chongqing University, Chongqing 400044, China

Funds: The National Natural Science Foundation of China (41371338), Chongqing Basic and Frontier Research Program (cstc2018jcyjAX0093), Chongqing Returned Overseas Students’ Entrepreneurship and Innovation Support Program (cx2019144), Chongqing Graduate Research and Innovation Project (CYB19039, CYB18048)

Received Date: 2020-08-05
Rev Recd Date: 2021-03-20

Available Online: 2021-04-16

Publish Date: 2021-09-16

Abstract

Abstract

Object tracking is one of the important research fields in computer vision. However, most tracking algorithm can not effectively learn the features suitable for tracking scene, which limits the performance improvement of tracking algorithm. To overcome this problem, this paper proposes a target tracking algorithm based on CNN Spatial and Channel Attention Mechanisms (CNNSCAM). The method consists of an off-line training apparent model and an adaptive updating classifier layer. In the offline training, the spatial and channel attention mechanism module is introduced to recalibrate the original features, and the space and channel weights are obtained respectively. The key features are selected by normalizing the weights to the corresponding original features. In online tracking, the network parameters of the full connection layer and classifier layer are trained, and the boundary box regression is used. Secondly, samples are collected according to the set threshold, and the negative sample with the highest classifier score is selected for each iteration to fine tune the network layer parameters. The experimental results on OTB2015 dataset show that compared with other mainstream tracking algorithms, the proposed method achieves better tracking accuracy. The overlap success rate and error success rate are 67.6% and 91.2% respectively.
- Object tracking,
- Deep learning,
- Spatial attention,
- Channel attention,
- Online learning

FullText(HTML)

References(15)

References

[1]	蒲磊, 冯新喜, 侯志强, 等. 基于自适应背景选择和多检测区域的相关滤波算法[J]. 电子与信息学报, 2020, 42(12): 3061–3067. doi: 10.11999/JEIT190931 PU Lei, FENG Xinxi, HOU Zhiqiang, et al. Correlation filter algorithm based on adaptive context selection and multiple detection areas[J]. Journal of Electronics &Information Technology, 2020, 42(12): 3061–3067. doi: 10.11999/JEIT190931
[2]	李康, 李亚敏, 胡学敏, 等. 基于卷积神经网络的鲁棒高精度目标跟踪算法[J]. 电子学报, 2018, 46(9): 2087–2093. doi: 10.3969/j.issn.0372-2112.2018.09.007 LI Kang, LI Yamin, HU Xuemin, et al. A robust and accurate object tracking algorithm based on convolutional neural network[J]. Acta Electronica Sinica, 2018, 46(9): 2087–2093. doi: 10.3969/j.issn.0372-2112.2018.09.007
[3]	王鹏, 孙梦宇, 王海燕, 等. 一种目标响应自适应的通道可靠性跟踪算法[J]. 电子与信息学报, 2020, 42(8): 1950–1958. doi: 10.11999/JEIT190569 WANG Peng, SUN Mengyu, WANG Haiyan, et al. An object tracking algorithm with channel reliability and target response adaptation[J]. Journal of Electronics &Information Technology, 2020, 42(8): 1950–1958. doi: 10.11999/JEIT190569
[4]	HONG S, YOU T, KWAK S, et al. Online tracking by learning discriminative saliency map with convolutional neural network[C]. Proceedings of the 32nd International Conference on Machine Learning, Lille, France, 2015: 597–606.
[5]	ZHU Zheng, WANG Qiang, LI Bo, et al. Distractor-aware Siamese networks for visual object tracking[C]. Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, 2018: 104–119. doi: 10.1007/978-3-030-01240-3_7.
[6]	LI Xin, MA Chao, WU Baoyuan, et al. Target-aware deep tracking[C]. Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 1369–1378. doi: 10.1109/CVPR.2019.00146.
[7]	WANG Ning, SONG Yibing, MA Chao, et al. Unsupervised deep tracking[C]. Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 1308–1317.
[8]	HU Jie, SHEN Li, and SUN Gang. Squeeze-and-excitation networks[C]. Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 7132–7141. doi: 10.1109/CVPR.2018.00745.
[9]	WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]. Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, 2018: 1352–1368. doi: 10.1007/978-3-030-01234-2_1.
[10]	WANG Qiang, TENG Zhu, XING Junliang, et al. Learning attentions: Residual attentional Siamese network for high performance online visual tracking[C]. Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 4854–4863. doi: 10.1109/CVPR.2018.00510.
[11]	CHEN Boyu, LI Peixia, CHONG Sun, et al. Multi attention module for visual tracking[J]. Pattern Recognition, 2019, 87: 80–93. doi: 10.1016/j.patcog.2018.10.005
[12]	张文明, 姚振飞, 高雅昆, 等. 一种平衡准确性以及高效性的显著性目标检测深度卷积网络模型[J]. 电子与信息学报, 2020, 42(5): 1201–1208. doi: 10.11999/JEIT190229 ZHANG Wenming, YAO Zhenfei, GAO Yakun, et al. A deep convolutional network for saliency object detection with balanced accuracy and high efficiency[J]. Journal of Electronics &Information Technology, 2020, 42(5): 1201–1208. doi: 10.11999/JEIT190229
[13]	WU Yi, LIM J, and YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834–1848. doi: 10.1109/TPAMI.2014.2388226
[14]	ZHANG Tianzhu, XU Changsheng, and YANG M H. Multi-task correlation particle filter for robust object tracking[C]. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 4819–4827. doi: 10.1109/CVPR.2017.512.
[15]	GALOOGAHI H K, FAGG A, and LUCEY S. Learning background-aware correlation filters for visual tracking[C]. Proceedings of 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 1144–1152. doi: 10.1109/ICCV.2017.129.