中山大学智能工程学院 / 广东省智能交通系统重点实验室 / 视频图像智能分析与应用技术公安部重点实验室,广东 广州 510006
邱铭凯(1996年生),男;研究方向:交通视频图像分析;E-mail: qiumk@mail2.sysu.edu.cn
李熙莹(1972年生),女;研究方向:交通视频图像分析;E-mail: stslxy@mail.sysu.edu.cn
纸质出版日期:2021-07-25,
网络出版日期:2020-09-15,
收稿日期:2020-03-16,
录用日期:2020-05-07
扫 描 看 全 文
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(04):111-120.
QIU Mingkai,LI Xiying.Detail-aware discriminative feature learning model for vehicle re-identification[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2021,60(04):111-120.
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(04):111-120. DOI: 10.13471/j.cnki.acta.snus.2020.03.16.2020B023.
QIU Mingkai,LI Xiying.Detail-aware discriminative feature learning model for vehicle re-identification[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2021,60(04):111-120. DOI: 10.13471/j.cnki.acta.snus.2020.03.16.2020B023.
在多摄像头下拍摄的车辆图片集合中,对属于目标车辆的图片进行匹配为车辆重识别。如何有效的区分具有相似外观的不同车辆的图片,是车辆重识别的一大挑战。考虑到不同车辆之间的差异集中于车窗等区域的细节,文章提出了一个基于细节感知的判别特征学习模型;设计了一个指导式的车辆局部特征提取流程,将局部特征与骨干网络提取的全局特征联合作为车辆的提取特征,不同车辆联合特征之间的欧式距离作为相似度衡量。在算法实验中,所提出的算法在公开数据集VehicleID与VeRi上都取得领先于现有车辆重识别算法的结果,验证了算法的有效性。
Vehicle re-identification (Re-ID) aims to identify a target vehicle from multiple non-overlapping cameras. Vehicle Re-ID is a challenging work because it's hard to distinguish vehicles of the same model with similar appearance. Since the differences between these vehicles are concentrated in some small local regions, a detail-aware discriminative feature learning model is proposed in this paper, based on the assumption that features of network's middle layer is helpful in extracting discriminative feature representation of local regions. In the proposed model, a guided vehicle local feature extraction process is designed, and the final feature representation of vehicle consist of the extracted local feature and the global feature extracted by the backbone network. Extensive experiments over benchmark datasets VehicleID and VeRi have shown that the proposed methods could achieve superior performance than state-of-the-art methods.
车辆重识别神经网络局部特征提取判别特征学习
vehicle re-identificationneural networklocal feature extractiondiscriminative feature learning
LIU H Y, TIAN Y H, WANG Y W, et al. Deep relative distance learning: Tell the difference between similar vehicles[C] // In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016:2167-2175.
BAI Y, LOU Y H, GAO F, et al. Group-sensitive triplet embedding for vehicle reidentification[J]. IEEE Transactions on Multimedia, 2018, 20(9):2385-2399.
CHU R H, SUN Y F, LI Y D, et al. Vehicle re-identification with viewpoint-aware metric learning[C] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019:8281-8290.
ZHOU Y, SHAO L . Vehicle re-identification by adversarial bi-directional LSTM network[C] // In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018:653-662.
KHORRAMSHAHI P, KUMAR A, et al. A dual-path model with adaptive attention for vehicle re-identification[C] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019:6131-6140.
GUO H Y ,ZHU K, TANG M, et al. Two-level attention network with multi-grain ranking loss for vehicle re-identification[J]. IEEE Transactions on Image Processing, 2019, 28(9): 4328-4338.
LIN G S, MILAN A, SHEN C H, et al. Reid refinenet: multi-path refinement networks for high-resolution semantic segmentation[C] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017:5168-5177.
YOSINSKI J, CLUNE J, NGUYEN A, et al. Understanding neural networks through deep visualization[J/OL]. [2015-06-22]. https://arxiv.org/abs/1506.06579v1https://arxiv.org/abs/1506.06579v1.
SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C] // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015:1-9.
LIU X C, LIU W, MEI T, et al. PROVID: Progressive and multimodal vehicle reidentification for large-scale urban surveillance[J]. IEEE Transactions on Multimedia, 2018, 20(3):645-658.
SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J/OL].[2015-04-10].https://arxiv.org/abs/1409.1556https://arxiv.org/abs/1409.1556.
HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016:770-778.
ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[J/OL]. [2013-11-28]. https://arxiv.org/abs/1311.2901https://arxiv.org/abs/1311.2901.
DENG J, DONG W, SOCHER R, et al. Imagenet: a large-scale hierarchical image database[C] // IEEE Computer Vision & Pattern Recognition, 2009:248-255.
ZHU J Q, ZENG H Q, DU Y Z, et al. Joint feature and similarity deep learning for vehicle re-identification[J]. IEEE Access, 2018(6): 43724-43731.
ZHOU Y, LIU L, SHAO L . Vehicle re-identification by deep hidden multi-view inference[J]. IEEE Transactions on Image Processing, 2018, 27(7): 3275-3287.
LOU Y H, BAI Y, LIU J, et al. Embedding adversarial learning for vehicle re-identification[J]. IEEE Transactions on Image Processing, 2019, 28(8): 3794-3807.
0
浏览量
0
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构