重庆交通大学学报(自然科学版) ›› 2022, Vol. 41 ›› Issue (09): 9-17.DOI: 10.3969/j.issn.1674-0696.2022.09.02
蓝章礼,王超,杨晴晴,金豪
收稿日期:
2021-06-28
修回日期:
2021-08-19
发布日期:
2022-09-30
作者简介:
蓝章礼(1973—),男,重庆人,教授,博士,主要从事图像处理、交通信息化的研究。E-mail: lzl7309@126.com
通信作者:王超(1997—),男,重庆人,硕士研究生,主要从事图像处理与机器视觉的研究。E-mail: w_allen@mails.cqjtu.edu.cn
基金资助:
LAN Zhangli, WANG Chao, YANG Qingqing, JIN Hao
Received:
2021-06-28
Revised:
2021-08-19
Published:
2022-09-30
摘要: 针对车辆重识别任务中局部特征提取不充分和潜在显著性局部特征易被掩盖的问题,提出一种基于多粒度特征分割的算法。该算法采用可实现跨通道间信息交互的ResNeSt-50作为骨干网络提取初级特征,并将骨干网络复制成三个独立的分支,对输出的特征图分别沿纵向、横向和通道方向进行多粒度分割以提取到区分性局部特征。为进一步增强网络提取判别性特征信息的能力,又在ResNeSt-50的每个split-attention block中嵌入了空间注意力模块。研究结果表明:算法在VeRi-776数据集上的mAP、Rank-1、Rank-5指标分别达到85.92%、97.67%、98.53%;在VehicleID数据集的三个测试集上,Rank-1指标分别达到了88.36%、84.19%、78.89%,优于现有大部分主流算法,研究结果表明该算法具有先进性和有效性。
中图分类号:
蓝章礼,王超,杨晴晴,金豪. 基于多粒度特征分割的车辆重识别算法[J]. 重庆交通大学学报(自然科学版), 2022, 41(09): 9-17.
LAN Zhangli, WANG Chao, YANG Qingqing, JIN Hao. Vehicle Re-identification Algorithm Based on Multi-granularity Feature Segmentation[J]. Journal of Chongqing Jiaotong University(Natural Science), 2022, 41(09): 9-17.
[1] 刘凯,李浥东,林伟鹏.车辆再识别技术综述[J].智能科学与技术学报,2020,2(1):10-25. LIU Kai, LI Yidong, LIN Weipeng. A survey on vehicle reidenti-fication[J]. Chinese Journal of Intelligent Science and Technology, 2020, 2 (1): 10-25. [2] LIU X, LIU W, MA H. Large-scale vehicle re-identification in urban surveillance videos [C]∥The 2016 IEEE International Conference on Multimedia and Expo (ICME). Piscataway: IEEE Press, 2016: 1-6. [3] ZAPLETAL D, HEROUT A. Vehicle re-identification for automatic video traffic surveillance [C]∥ 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops. [S.l.]:[s.n.], 2016: 1568-1574. [4] LIU H, TIAN Y, WANG Y, et al. Deep relative distance learning: Tell the difference between similar vehicles [C]∥ 2016 IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]:[s.n.], 2016: 2167-2175. [5] BAI Y, LOU Y, GAO F, et al. Group-sensitive triplet embedding for vehicle reidentification [J]. IEEE Transactions on Multimedia, 2018, 20(9): 2385-2399. [6] PENG J, WANG H, ZHAO T, et al. Learning multi-region features for vehicle re-identification with context-based ranking method [J]. Neurocomputing, 2019, 359(24): 427-437. [7] CHEN H, LAGADEC B, BREMOND F. Partition and reunion: A two-branch neural network for vehicle re-identification [C]∥CVPR Workshops. Long Beach: IEEE, 2019: 184-192. [8] QIAN J, JIANG W, LUO H, et al. Stripe-based and attribute-aware network: A two-branch deep model for vehicle re-identification [J]. Measurement Science and Technology, 2020, 31(9): 1-11. [9] WANG H, PENG J, JIANG G, et al. Discriminative feature and dictionary learning with part-aware model for vehicle re-identification [J]. Neurocomputing, 2020: arXiv:2003.07139. [10] SUPREM A, PU C. Looking GLAMORous: Vehicle re-id in hetero-geneous cameras networks with global and local attention[J/OL]. (2020-02-06)[2021-06-28]. https:∥doi.org/10.48550/arXiv.2002.02256. [11] YANG J, XING D, HU Z, et al. A two-branch network with pyramid-based local and spatial attention global feature learning for vehicle re-identification [J]. CAAI Transactions on Intelligence Technology, 2021, 6(1): 46-54. [12] MENG D, LI L, LIU X, et al. Parsing-based view-aware embedding network for vehicle re-identification [C]∥ 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. [S.l.]:[s.n.], 2020: 7103-7112. [13] ZHANG H, WU C, ZHANG Z, et al. Resnest: Split-attention networks[J/OL]. (2020-12-30)[2021-06-28].https:∥doi.org/10.48550/arXiv.2004.08955. [14] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition [C]∥ 2016 IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]:IEEE, 2016: 770-778. [15] 杨红,韩鹏,刘畅,等.基于多任务学习的船舶行为识别与轨迹预测[J].重庆交通大学学报(自然科学版),2022,41(4):1-7. YANG Hong, HAN Peng, LIU Chang, et al. Vessel behavior recogni-tion and trajectory prediction based on multi-task learning model [J]. Journal of Chongqing Jiaotong University (Natural Science), 2022, 41 (4): 1-7. [16] WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module [C]∥Proceedings of the European Conference on Computer Vision. [S.l.]:[s.n.], 2018: 3-19. [17] HERMANS A, BEYER L, LEIBE B. In defense of the triplet loss for person re-identification[J/OL]. (2017-05-17)[2021-06-28]. https:∥doi.org/10.48550 /arXiv.1703.07737. [18] LIU X, LIU W, MEI T, et al. Provid: Progressive and multimodal vehicle reidentification for large-scale urban surveillance [J]. IEEE Transactions on Multimedia, 2017, 20(3): 645-658. [19] LIU H, TIAN Y, YANG Y, et al. Deep relative distance learning: Tell the difference between similar vehicles [C]∥ 2016 IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]:[s.n.], 2016: 2167-2175. [20] ZHENG A, LIN X, LI C, et al. Attributes guided feature learning for vehicle re-identification[J/OL]. (2019-05-22)[2021-06-28]. https:∥doi.org/10.48550/ arXiv.1905.08997. |
[1] | 韩宝睿, 濮海建, 朱震军. 基于改进Lotka-Volterra模型的城市轨道交通与常规公交竞合关系演变研究[J]. 重庆交通大学学报(自然科学版), 2023, 42(2): 106-112. |
[2] | 何烈云, 周妍, 黄少泽, 刘强. 叠加放行信号控制方式适用条件及效益评价[J]. 重庆交通大学学报(自然科学版), 2023, 42(1): 113-119. |
[3] | 李振龙, 董爱华, 杨磊. 基于群决策和熵权法的换道轨迹评价研究[J]. 重庆交通大学学报(自然科学版), 2023, 42(1): 120-127. |
[4] | 赵欣, 酆磊, 林皓博, 陈曦, 肖宇舟. 相邻T型路口非直线路径绿波控制方法研究[J]. 重庆交通大学学报(自然科学版), 2022, 41(09): 16-23. |
[5] | 张智勇, 黄鑫灿, 邵越. 礼让行人条件下右转保护型相位设置阈值研究[J]. 重庆交通大学学报(自然科学版), 2022, 41(09): 24-33. |
[6] | 冯天军, 杨夏玉, 夏春亭, 梁春岩, 李赫楠. 基于分隔设施的寒区城市道路行车安全间距研究[J]. 重庆交通大学学报(自然科学版), 2022, 41(09): 34-38. |
[7] | 潘义勇, 吴静婷, 施颖. 交叉口处老年人碰撞事故伤害严重程度分析[J]. 重庆交通大学学报(自然科学版), 2022, 41(09): 39-44. |
[8] | 吕贞, 戚春华, 朱守林. 草原公路不同分心状态下驾驶人动态视觉特性[J]. 重庆交通大学学报(自然科学版), 2022, 41(09): 45-52. |
[9] | 张玲玉, 王力, 张立立, 张骁, 孙德辉. 智能汽车的切换型人机共驾研究进展与展望[J]. 重庆交通大学学报(自然科学版), 2022, 41(09): 130-139. |
[10] | 赵树恩, 刘伟. 基于改进VGG模型的低照度道路交通标志识别[J]. 重庆交通大学学报(自然科学版), 2021, 40(10): 178-184. |
[11] | 李英帅1,闫琦若1,赵聪2. 基于公交车右转内轮差效应的范围研究[J]. 重庆交通大学学报(自然科学版), 2021, 40(09): 43-48. |
[12] | 阎莹1,刘革1,田敏1,刘佳乐1,穆岩2. 基于Trucksim的弯坡组合路段临界车速确定方法[J]. 重庆交通大学学报(自然科学版), 2021, 40(09): 49-54. |
[13] | 胡明伟1,2,3,施小龙1,翟素云4,刘鹏1. 自动驾驶混合交通流的交通和环境效益评估[J]. 重庆交通大学学报(自然科学版), 2021, 40(08): 7-14. |
[14] | 李佳1,王雪松2. 密集路网中城市主干路中观安全分析模型[J]. 重庆交通大学学报(自然科学版), 2021, 40(08): 34-41. |
[15] | 焦柳丹1,朱影含1,吴雅2,宋向南3. 基于演化博弈理论的城市轨道交通高峰票价定价研究[J]. 重庆交通大学学报(自然科学版), 2021, 40(08): 42-49. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||