计算机科学 ›› 2019, Vol. 46 ›› Issue (11): 267-271.doi: 10.11896/jsjkx.181001861
包宗铭1, 龚声蓉1,2, 钟珊1,2, 燕然1, 戴兴华1
BAO Zong-ming1, GONG Sheng-rong1,2, ZHONG Shan1,2, YAN Ran1, DAI Xing-hua1
摘要: 在跨摄像头的行人再识别任务中,光照、视角以及遮挡物等成像因素导致行人外观在不同视角下呈现出巨大变化,这使得对目标行人的再识别工作变得十分困难。利用重排序算法虽然可以在一定程度上提高行人再识别的准确率,但增加了时间成本和人力成本,且容易引入新的噪声。为此,文中提出了一种基于双向KNN排序优化的行人再识别算法。首先,采用预训练加微调的策略来提取行人的深度特征;然后,利用XQDA和KISSME两种度量学习方法来比较特征间的距离,计算初始排名;最后,根据查询图像和候选图像间的双向KNN关系计算Jaccard距离,并将其与初始距离加权求和作为重排序的参照,计算出新的排名。在CUHK03,Market1501和PRW 3个数据集上的实验表明,文中提出的重排序算法在Rank1和mAP两个评价指标上分别获得了12.2%和13.4%的提升。实验数据充分说明,基于双向KNN排序优化的行人再识别算法可以有效降低重排序时引入噪声的概率,从而提高行人再识别的准确率。
中图分类号:
[1]QI M B,WANG C C,JIANG J G,et al.Pedestrian re-identification with multi-feature fusion and alternating direction multiplier method[J].Chinese Journal of Image and Graphics,2018,23(6):827-836.(in Chinese) 齐美彬,王慈淳,蒋建国,等.多特征融合与交替方向乘子法的行人再识别[J].中国图象图形学报,2018,23(6):827-836. [2]YE M,LIANG C,YU Y,et al.Person Reidentification via Ranking Aggregation of Similarity Pulling and Dissimilarity Pushing[J].IEEE Transactions on Multimedia,2016,18(12):2553-2566. [3]GAO Q Y,FANG H S.HOG Pedestrian Detection Algorithm of Multiple Convolution Feature Fusion[J].Computer Science,2017,44(S2):199-201.(in Chinese) 高琦煜,方虎生.多卷积特征融合的HOG行人检测算法[J].计算机科学,2017,44(S2):199-201. [4]GRAY D,TAO H.Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features[C]∥Proceedings of European Conference on Computer Vision.Marseille:Springer,2008:262-275. [5]CHEN Y C,ZHENG W S,LAI J.Mirror representation formodeling view-specific transform in person re-identification[C]∥Proceedings of International Conference on Artificial Intelligence.Austin:AAAI Press,2015:3402-3408. [6]LIAO S,HU Y,ZHU X,et al.Person Re-identification by Local Maximal Occurrence Representation and Metric Learning[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE Press,2015:2197-2206. [7]DONG H,LU P,ZHONG S,et al.Person Re-identification byEnhanced Local Maximal Occurrence Representation and Genera-lized Similarity Metric Learning[J].Neurocomputing,2018,307:25-37. [8]DONG H,GONG S,LIU C,et al.Large margin relative distance learning for person re-identification[J].IET Computer Vision,2017,11(6):455-462. [9]YI D,LEI Z,LIAO S,et al.Deep Metric Learning for Person Reidentification[C]∥Proceedings of International Conference on Pattern Recognition.Stockholm:IEEE Press,2014:34-39. [10]LI W,ZHAO R,XIAO T,et al.DeepReID:Deep Filter Pairing Neural Network for Person Re-identification[C]∥Proceedings of Computer Vision and Pattern Recognition.Columbus:IEEE Press,2014:152-159. [11]XIAO T,LI H,OUYANG W,et al.Learning deep feature representations with domain guided dropout for person re-identification[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:1249-1258. [12]CHEN Y C,ZHUX T,ZHENG W S,et al.Person Re-Identification by Camera Correlation Aware Feature Augmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(2):392-408. [13]GARCIA J,MARTINEL N,GARDEL A,et al.DiscriminantContext Information Analysis for Post-Ranking Person Re-Identification[J].IEEE Transaction Image Processing,2017,26(4):1650-1665. [14]LENG Q M,HU R M,LIANG C,et al.Person re-identification with content and context re-ranking[J].Multimedia Tools & Applications,2015,74(17):6989-7014. [15]YE M,CHEN J,LENG Q M,et al.Coupled-View Based Ranking Optimization for Person Re-identification[C]∥Proceedings of International Conference on Multimedia Modeling.Sydney:Springer Press,2015:105-117. [16]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:770-778. [17]FELZENSZWALB P,MCALLESTER D,RAMANAN D.A discriminatively trained,multiscale,deformable part model[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Anchorage:IEEE Press,2008:1-8. [18]ZHENG L,YANG Y,HAUPTMANN A G.Person Re-identification:Past,Present and Future[J].arXiv:1610.02984. [19]ZHENG L,ZHANG H,SUN S,et al.Person Re-identification in the Wild[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:3346-3355. [20]SUN Y,ZHENG L,DENG W,et al.SVDNet for Pedestrian Retrieval[C]∥Proceedings of IEEE International Conference on Computer Vision.Venice:IEEE Press,2017:3820-3828. [21]ZENG M,WU Z,TIAN C,et al.Person re-identification based on a novelmahalanobis distance feature dominated KISS metric learning[J].Electronics Letters,2016,52(14):1223-1225. [22]ZHONG Z,ZHENG L,CAO D,et al.Re-ranking Person Re-identification with k-reciprocal Encoding[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:3652-3661. [23]ZHANG X,LUO H,FAN X,et al.Aligned ReID:Surpassing Human-Level Performance in Person Re-Identification[J].ar-Xiv:1711.08184. [24]BAI S,BAI X.Sparse Contextual Activation for Efficient Visual Re-Ranking[J].IEEE Transactions on Image Processing,2016,25(3):1056-1069. [25]SARFRAZ M S,SCHUMSNN A,EBERLE A,et al.A PoseSensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE Press,2018:420-429. [26]HERMANS A,BEYER L,LEIBE B.In defense of the tripletloss for person re-identification[J].arXiv:1703.07737. [27]ZHONG Z,ZHENG L,ZHENG Z,et al.Camera Style Adaptation for Person Re-identification[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE Press,2018:5157-5166. [28]ZHANG Y,XIANG T,HOSPEDALES T M,et al.Deep Mutual Learning[J].arXiv:1706.00384. [29]HE L,LIANG J,LI H,et al.Deep Spatial Feature Reconstruction for Partial Person Re-identification:Alignment-Free Approach[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE Press,2018:7073-7082. |
[1] | 陈坤峰, 潘志松, 王家宝, 施蕾, 张锦. 基于双目叠加仿生的微换衣行人再识别 Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation 计算机科学, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140 |
[2] | 陆要要, 袁家斌, 何珊, 王天星. 基于超分辨率重建的低质量视频人脸识别方法 Low-quality Video Face Recognition Method Based on Super-resolution Reconstruction 计算机科学, 2021, 48(11A): 295-302. https://doi.org/10.11896/jsjkx.201200159 |
[3] | 唐一星, 刘学亮, 胡社教. 多方向分区网络结构的行人再识别 Multi-orientation Partitioned Network for Person Re-identification 计算机科学, 2021, 48(10): 204-211. https://doi.org/10.11896/jsjkx.210300128 |
[4] | 裴嘉震, 徐曾春, 胡平. 融合视点机制与姿态估计的行人再识别方法 Person Re -identification Fusing Viewpoint Mechanism and Pose Estimation 计算机科学, 2020, 47(6): 164-169. https://doi.org/10.11896/jsjkx.190500013 |
[5] | 周鹏程,龚声蓉,钟珊,包宗铭,戴兴华. 基于深度特征融合的图像语义分割 Image Semantic Segmentation Based on Deep Feature Fusion 计算机科学, 2020, 47(2): 126-134. https://doi.org/10.11896/jsjkx.190100119 |
[6] | 田献珍, 孙立强, 田振中. 基于蚁群算法的图像重建 Image Reconstruction Based on Ant Colony Algorithm 计算机科学, 2020, 47(11A): 231-235. https://doi.org/10.11896/jsjkx.191000128 |
[7] | 李荫民, 薛凯心, 高赞, 薛彦兵, 徐光平, 张桦. 基于残差网络的三维模型检索算法 3-D Model Retrieval Algorithm Based on Residual Network 计算机科学, 2019, 46(3): 148-153. https://doi.org/10.11896/j.issn.1002-137X.2019.03.022 |
[8] | 赵小艳,刘宏哲,袁家政,杨少鹏. 图像重排序技术的研究进展 Advances in Image Reranking 计算机科学, 2018, 45(5): 15-23. https://doi.org/10.11896/j.issn.1002-137X.2018.05.003 |
[9] | 钮晨霄,孙瑾,丁永晖. 融合深度与肤色特征的自适应手部跟踪算法 Adaptive Hand Tracking Based on Fusing Depth and Skin Features 计算机科学, 2016, 43(Z6): 125-129. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.030 |
[10] | 邓莉琼,郝向宁,夏鸣,李中宁. 基于内容检索的图像自动标注方法研究 Image Annotation by Similarity Content-based Image Retrieval 计算机科学, 2014, 41(Z11): 119-122. |
[11] | 陈达智,赵荣彩,韩林,丁锐,赵捷. 基于重排序变换和循环分布的通信优化算法 Communication Optimization Algorithm Using Reordering Transformation and Loop Distribution 计算机科学, 2012, 39(9): 296-301. |
[12] | 刘鑫,陆林生,陈德训. 非结构网格并行计算预处理方法研究 Research on Pre-processing Methods of Unstructured Grids 计算机科学, 2012, 39(3): 308-311. |
[13] | 张霞,王素贞,尹怡欣,赵海龙. 基于模糊粒度计算的K-means文本聚类算法研究 Research of Text Clustering Based on Fuzzy Granular Computing 计算机科学, 2010, 37(2): 209-211. |
[14] | 李绍荣 徐琳琳. 简化BDD的SBDD和变量重排序结合算法 计算机科学, 2007, 34(4): 287-288. |
|