• Laser & Optoelectronics Progress
  • Vol. 58, Issue 2, 0215005 (2021)
Sha Liu1, Jianwu Dang1、2、*, Song Wang1、2, and Yangping Wang2、3
Author Affiliations
  • 1School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, China
  • 2Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphic & Image Processing, Lanzhou, Gansu 730070, China;
  • 3National Experimental Teaching Demonstration Center on Computer Science and Technology, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, China
  • show less
    DOI: 10.3788/LOP202158.0215005 Cite this Article Set citation alerts
    Sha Liu, Jianwu Dang, Song Wang, Yangping Wang. Person Re-Identification Based on First-Order and Second-Order Spatial Information[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0215005 Copy Citation Text show less
    Architecture of person re-identification network based on first-order and second-order spatial information
    Fig. 1. Architecture of person re-identification network based on first-order and second-order spatial information
    Structure of the first-order spatial mask
    Fig. 2. Structure of the first-order spatial mask
    Schematic diagram of the second-order spatial mask
    Fig. 3. Schematic diagram of the second-order spatial mask
    Structure of the second-order spatial mask
    Fig. 4. Structure of the second-order spatial mask
    Two-dimensional visualization of sample distribution supervised by different losses. (a) Label smoothed cross entropy loss and basic triplet loss; (b) label smoothed cross entropy loss and center triplet loss
    Fig. 5. Two-dimensional visualization of sample distribution supervised by different losses. (a) Label smoothed cross entropy loss and basic triplet loss; (b) label smoothed cross entropy loss and center triplet loss
    Sample heat map. (a) Sample heat map obtained using only SOM; (b) sample heat map obtained using OM and SOM
    Fig. 6. Sample heat map. (a) Sample heat map obtained using only SOM; (b) sample heat map obtained using OM and SOM
    Visualization results of Market-1501 data set. (a) Baseline network algorithm; (b) our algorithm
    Fig. 7. Visualization results of Market-1501 data set. (a) Baseline network algorithm; (b) our algorithm
    Visualization results of DukeMTMC-reID data set. (a) Baseline network algorithm; (b) our algorithm
    Fig. 8. Visualization results of DukeMTMC-reID data set. (a) Baseline network algorithm; (b) our algorithm
    NO.ModelLossMarket-1501DukeMTMC-reID
    Rank-1mAPRank-1mAP
    1BaselineS+BT95.3687.6288.2876.93
    2Baseline+ SOMS+BT95.5388.6389.5578.18
    3Baseline+SOM+ OMS+BT95.9488.9090.0878.49
    4Baseline+ SOM+ OMS+CT96.1989.7190.3779.23
    Table 1. Experimental results of different models unit: %
    AlgorithmRank-1mAP
    GAN[26]78.1256.25
    SVDNet[27]82.3062.10
    AACN[28]85.9066.87
    HA-CNN[14]89.0071.25
    GLAD[29]89.9073.90
    PCB+RPP[11]93.8081.60
    MGN[30]95.7086.90
    Pyramid-Net[31]95.7088.20
    Our algorithm96.1989.71
    Table 2. Recognition results of different algorithms on the Market-1501 data set unit: %
    AlgorithmRank-1mAP
    GAN[26]67.6847.13
    SVDNet[27]76.7056.80
    AACN[28]76.8458.25
    HA-CNN[14]78.5060.25
    GLAD[29]80.0062.20
    PCB+RPP[11]83.3069.20
    MGN[30]88.7078.40
    Pyramid-Net[31]89.0079.00
    Our algorithm90.3779.23
    Table 3. Recognition results of different algorithms on the DukeMTMC-reID data set unit: %
    Sha Liu, Jianwu Dang, Song Wang, Yangping Wang. Person Re-Identification Based on First-Order and Second-Order Spatial Information[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0215005
    Download Citation