Computer Science ›› 2019, Vol. 46 ›› Issue (11): 267-271.doi: 10.11896/jsjkx.181001861

• Graphics ,Image & Pattern Recognition • Previous Articles     Next Articles

Person Re-identification Algorithm Based on Bidirectional KNN Ranking Optimization

BAO Zong-ming1, GONG Sheng-rong1,2, ZHONG Shan1,2, YAN Ran1, DAI Xing-hua1   

  1. (School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China)1
    (School of Computer Science and Engineering,Changshu Institute of Technology,Suzhou,Jiangsu 215500,China)2
  • Received:2018-10-08 Online:2019-11-15 Published:2019-11-14

Abstract: The imaging factors such as illumination,view,obstruction and noise would bring great changes to pedes-trian’s appearance under the cross-view condition in person re-identification,then it becomes very difficult to identify the target from candidates.Using the re-ranking algorithm can optimize the re-identification’s result,but it can make the task time-consuming and expensive.What’s more,it is easy to introduce the noise during the process of re-ranking,which in turn affects the accuracy of re-identification.To solve the problem,this paper presented a re-ranking method based on bidirectional KNN for person re-identification.First,it utilized the pre-training and fine-tuning strategy to extract the deep features of pedestrian.Then,it choosed an appropriate metric function (XQDA,KISSME) to measure the distance of features.Finally,accor-ding to the bidirectional KNN relation between the query and candidates,the Jaccard distance was calculated and aggregated with the original distance to guide the re-ranking.Experiments on the datasets of CUHK03,Market1501 and PRW show that the re-ranking algorithm proposed in this paper can improve the accuracy of re-identification on the basis of the original method,and the improvements are 12.2% and 13.4% in the two evaluation indexes of Rank1 and mAP respectively.The experimental data indicates that the re-identification algorithm based on bidirectional KNN can effectively reduce the probability of noise during the re-ranking,and then improve the accuracy of re-identification.

Key words: Bidirectional KNN, Deep feature, Metric learning, Person re-identification, Re-ranking

CLC Number: 

  • TP391
[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)
[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)
[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] CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin. Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation [J]. Computer Science, 2022, 49(8): 165-171.
[2] MENG Yue-bo, MU Si-rong, LIU Guang-hui, XU Sheng-jun, HAN Jiu-qiang. Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism [J]. Computer Science, 2022, 49(7): 142-147.
[3] HOU Xia-ye, CHEN Hai-yan, ZHANG Bing, YUAN Li-gang, JIA Yi-zhen. Active Metric Learning Based on Support Vector Machines [J]. Computer Science, 2022, 49(6A): 113-118.
[4] YANG Xiao-yu, YIN Kang-ning, HOU Shao-qi, DU Wen-yi, YIN Guang-qiang. Person Re-identification Based on Feature Location and Fusion [J]. Computer Science, 2022, 49(3): 170-178.
[5] ZHANG Xin-feng, SONG Bo. A Person Re-identification Method Based on Improved Triple Loss and Feature Fusion [J]. Computer Science, 2021, 48(9): 146-152.
[6] DONG Hu-sheng, ZHONG Shan, YANG Yuan-feng, SUN Xun, GONG Sheng-rong. Person Re-identification by Region Correlated Deep Feature Learning with Multiple Granularities [J]. Computer Science, 2021, 48(12): 269-277.
[7] TANG Yi-xing, LIU Xue-liang, HU She-jiao. Multi-orientation Partitioned Network for Person Re-identification [J]. Computer Science, 2021, 48(10): 204-211.
[8] PEI Jia-zhen, XU Zeng-chun, HU Ping. Person Re -identification Fusing Viewpoint Mechanism and Pose Estimation [J]. Computer Science, 2020, 47(6): 164-169.
[9] ZHOU Peng-cheng,GONG Sheng-rong,ZHONG Shan,BAO Zong-ming,DAI Xing-hua. Image Semantic Segmentation Based on Deep Feature Fusion [J]. Computer Science, 2020, 47(2): 126-134.
[10] LI Hao, TANG Min, LIN Jian-wu, ZHAO Yun-bo. Cross-modality Person Re-identification Framework Based on Improved Hard Triplet Loss [J]. Computer Science, 2020, 47(10): 180-186.
[11] ZHANG Yan-hong, ZHANG Chun-guang, ZHOU Xiang-zhen, WANG Yi-ou. Diverse Video Recommender Algorithm Based on Multi-property Fuzzy Aggregate of Items [J]. Computer Science, 2019, 46(8): 78-83.
[12] LI Yin-min, XUE Kai-xin, GAO Zan, XUE Yan-bin, XU Guang-ping, ZHANG Hua. 3-D Model Retrieval Algorithm Based on Residual Network [J]. Computer Science, 2019, 46(3): 148-153.
[13] YU Cheng, ZHU Wan-ning, YOU Kun, ZHU Jin-fu. Prediction Model of E-sports Behavior Pattern Based on Attention Mechanism and LRUA Module [J]. Computer Science, 2019, 46(11A): 76-79.
[14] WEN Jun-hao, DAI Da-wen, YU Jun-liang, GAO Min, ZHANG Yi-hao. Social Recommendation Method Integrating Matrix Factorization and Distance Metric Learning [J]. Computer Science, 2018, 45(10): 196-201.
[15] LIANG Lu, GONG Ben-long, LI Jian and TENG Shao-hua. Diffusion Method of Sample Points for Alleviating Staggered Situation of Classification [J]. Computer Science, 2017, 44(9): 286-289.
Full text



No Suggested Reading articles found!