Vehicle Re-Identification Based on Multi-Scale and Wavelet Spatial Attention

doi:10.13438/j.cnki.jdzk.2021.06.003

Abstract

Abstract: For the problem that the multi-scale vehicle re-identification model is short of extracted detail features, a re-identification model combining multi-scale vehicle features and wavelet attention mechanism is designed. Firstly, spatial wavelet attention module is embedded into the model to obtain more details for the network. Secondly, a hierarchical fusion network is proposed, which integrates the features of different scales to improve the ability of global feature aggregation. Finally, TriHard and CrossEntropy Loss functions are used to construct the object function of vehicle identification. Experimental results of this model compared with other excellent models on VeRi and VehicleID datasets show that vehicle re-identification accuracy can be improved by embedding spatial wavelet attention into multi-scale networks.

Key words: vehicle re-identification, spatial attention mechanism, wavelet transform, multi-scale, characteristics , fusion

LIAO Guangkai, ZHANG Zheng, NIU Yibo, SONG Zhiguo. Vehicle Re-Identification Based on Multi-Scale and Wavelet Spatial Attention[J]. Journal of Jishou University(Natural Sciences Edition), 2021, 42(6): 15-22.

References

[1] LIAO Shengcai, HU Yang, ZHU Xiangyu, et al. Person Re-Identification by Local Maximal Occurrence Representation and Metric Learning[C/OL]. 2015 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. (2015-05-06)[2021-07-05]. https:∥arxiv.org/abs/1406.4216.
[2] ZHENG Liang, SHEN Liyue, TIAN Lu, et al. Scalable Person Re-Identification: A Benchmark[C/OL]. 2015 IEEE International Conference on Computer Vision (ICCV). (2015-12-07)[2021-07-05]. https:∥ieeexplore.ieee.org/document/7410490/authors#authors.
[3] LIU Xinchen, LIU Wu, MA Huadong, et al. Large-Scale Vehicle Re-Identification in Urban Surveillance Videos[C/OL]. 2016 IEEE International Conference on Multimedia and Expo (ICME). (2016-07-11)[2021-07-05]. https:∥ieeexplore.ieee.org/document/7553002.
[4] LIU Hongye, TIAN Yonghong, WANG Yaowei, et al. Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles[C/OL]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2016-06-01)[2021-07-05] https:∥ieeexplore.ieee.org/document/7780607.
[5] KRIZHEVSKY ALEX, SUTSKEVER I, HINTON G, et al. Image Net Classification with Deep Convolutional Neural Networks[C/OL]. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2012-01-01)[2021-07-05]. https:∥sci-hub.se/10.1145/3065386.
[6] SIMONYAN KAREN, ZISSERMAN ANDREW. Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. International Conference on Learning Representations（ICLR）. (2015-04-10)[2021-07-05]. https:∥arxiv.org/abs/1409.1556.
[7] SZEGEDY CHRISTIAN, LIU Wei, JIA Yangqing, et al. Going Deeper with Convolutions[C/OL]. 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2014-09-17)[2021-07-05]. https:∥arxiv.org/abs/1409.4842.
[8] HE Kaiming, ZHANG Xiangyu, REN Shaoqing. Deep Residual Learning for Image Recognition[C/OL].2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2015-10-15)[2021-07-05]. https:∥arxiv.org/abs/1512.03385.
[9] WU Songtao, ZHONG Shenghua, LIU Yan. Deep Residual Learning for Image Steganalysis[J]. Multimedia Tools and Applications, 2018, 77(9): 10437-10453.
[10] LIU Xinchen, LIU Wu, MEI Tao, et al. PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance[J]. IEEE Transactions on Multimedia, 2017, 20(3): 645-658.
[11] LIU H, TIAN Y, WANG Y, et al. Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles[C/OL]. IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. (2016-06-27)[2021-07-05]. https:∥sci-hub.se/10.1109/cvpr.2016.238.
[12] LIUHongye, TIAN Yonghong, WANG Yaowei, et al. Deep Joint Discriminative Learning for Vehicle Re-Identification and Retrieval[C/OL]. International Conference on Learning Representations（ICLR）. (2018-02-22)[2021-07-05]. https:∥sci-hub.se/10.1109/icip.2017.8296310.
[13] ZHANG Yiheng, LIU Dong, ZHA ZHENG-JUN. Improving Triplet-Wise Training of Convolutional Neural Network for Vehicle Re-Identification[C/OL]. 2017 IEEE International Conference on Multimedia and Expo (ICME). (2018-02-22)[2021-07-05]. https:∥www.researchgate.net/publication/319569730_Improving_triplet-wise_training_of_convolutional_neural_network_for_vehicle_re-identification.
[14] SU Chi, LI Jianing, ZHANG Shiliang, et al. Pose-Driven Deep Convolutional Model for Person Re-identification[C/OL]. 2017 IEEE International Conference on Computer Vision (ICCV). (2017-07-25)[2021-07-05]. https:∥ieeexplore.ieee.org/document/8237689.
[15] LI Dangwei, CHEN Xiaotang, ZHANG Zhang, et al. Learning Deep Context-Aware Features Over Body and Latent Parts for Person Re-Identification[C/OL]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2017-07-25)[2021-07-05]. https:∥www.researchgate.net/publication/316034140_Learning_Deep_Context-Aware_Features_over_Body_and_Latent_Parts_for_Person_Re-identification.
[16] HE Kaiming, ZHANG Xiangyu, REN Shaoqing. Deep Residual Learning for Image Recognition[C/OL]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2016-09-15)[2021-07-05]. https:∥arxiv.org/abs/1512.03385.
[17] TENG Shangzhi, LIU Xiaobin, ZHANG Shiliang, et al. SCAN: Spatial and Channel Attention Network for Vehicle Re-Identification[C/OL]. Advances in Multimedia Information Processing-PCM 2018. (2017-07-25)[2021-07-05]. https:∥link.springer.com/chapter/10.1007/978-3-030-00764-5_32.
[18] MALLAT S G. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674-693.
[19] WOO SANGHYUN, PARK JONGCHAN, LEE JOON-YOUNG, et al. CBAM: Convolutional Block Attention Module[C/OL]. 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2018-07-18)[2021-07-05]. https:∥arxiv.org/abs/1807.06521.
[20] LIU Xinchen, LIU Wu, MEI Tao, et al. PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance[J]. IEEE Transactions on Multimedia, 2017,20(3): 645-658.
[21] HOU Jinhui, ZENG Huanqiang, CAI Lei, et al. Multi-label Learning with Multi-label Smoothing Regularization for Vehicle Re-Identification[J]. Neurocomputing, 2019, 345: 15-22.
[22] PIRAZH KHORRAMSHAHI, AMIT KUMAR, PERI NEEHAR, et al. A Dual-Path Model with Adaptive Attention for Vehicle Re-Identification[C/OL]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). (2020-02-27)[2021-07-05]. https:∥ieeexplore.ieee.org/document/9010356/references#references.
[23] ZHU Jianqing, ZENG Huanqing, HUANG Jingchang, et al. Vehicle Re-Identification Using Quadruple Directional Deep Learning Features[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 99:1-11.
[24] ZHENG Aihua, LIN Xianmin, DONG Jiacheng, et al. Multi-Scale Attention Vehicle Re-Identification[J]. Neural Computing and Applications, 2020, 32(6): 17489-17503.
[25] 邱铭凯,李熙莹.用于车辆重识别的基于细节感知的判别特征学习模型[J].中山大学学报(自然科学版),2021,60(4):111-120.
[26] KUMA RATNESH, WEILL EDWIN, AGHDASI FARZIN, et al. Vehicle Re-Identification: An Efficient Baseline Using Triplet Embedding[C/OL]. 2019 International Joint Conference on Neural Networks (IJCNN). (2019-07-14)[2021-07-05]. https:∥sci-hub.se/10.1109/ijcnn.2019.8852059.
[27] XU Yue, JIANG Na, ZHANG Lei, et al. Multi-Scale Vehicle Re-Identification Using Self-Adapting Label Smoothing Regularization[C/OL]. 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (2019-04-17)[2021-07-05]. https:∥ieeexplore.ieee.org/document/8682599.
[28] LOU YIHANG, BAI YAN, LIU JUN, et al. Embedding Adversarial Learning for Vehicle Re-Identification[J]. IEEE Trans Image Process, 2019, 28(8):3794-3807.