Vehicle re-identification supports cross-camera tracking and the location of specific vehicles in a smart city. The gallery images of vehicles are ranked based on the similarities in the appearance of objects to a vehicle query image. Previous work on vehicle re-identification has mainly focused on global or local analyses of predefined regions of vehicles to classify the vehicle images with a softmax loss function. On the one hand, separate global or predefined local regions of vehicles are often sensitive to perspective and occlusions. On the other hand, the embedding space supervised by the softmax loss function is not sufficiently compact for the object class. To solve these problems, we propose an end-to-end distance-based global and partial multi-regional deep network (DGPM) that combines multi-regional features to identify global and local differences. We exploit a three-branch architecture to learn the global and partial features from coarsely partitioned regions. A global similarity module is introduced to reduce the background information interference in the local branches. Unlike general classification, we design a distance-based classification layer that maintains consistency among criteria for similarity evaluation. Furthermore, we use spatiotemporal vehicle information to improve the vehicle re-identification results when the camera and shooting time are available. Systematic comparative evaluations performed on the large-scale VeRi and VehicleID datasets showed that our approach robustly achieved state-of-the-art performance. For instance, for the VeRi dataset, we achieve (79.39 + 2.78)% mAP and (96.19 + 2.26)% Rank-1 accuracy.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vehicle Re-Identification Using Distance-Based Global and Partial Multi-Regional Feature Learning


    Beteiligte:
    Chen, Xu (Autor:in) / Sui, Haigang (Autor:in) / Fang, Jian (Autor:in) / Feng, Wenqing (Autor:in) / Zhou, Mingting (Autor:in)


    Erscheinungsdatum :

    2021-02-01


    Format / Umfang :

    5120575 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Abnormal vehicle distance identification method based on multi-source information

    DING HUA / JIANG CHAO / ZHANG XIAONA et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Vehicle occupancy detection using passenger to driver feature distance

    XU BEILEI / PAUL PETER / PERRONNIN FLORENT | Europäisches Patentamt | 2017

    Freier Zugriff

    A Partial-Fréchet-Distance-Based Framework for Bus Route Identification

    Lyu, Cheng / Wu, Xinhua / Liu, Yang et al. | IEEE | 2022


    VEHICLE OCCUPANCY DETECTION USING PASSENGER TO DRIVER FEATURE DISTANCE

    XU BEILEI / PAUL PETER / PERRONNIN FLORENT | Europäisches Patentamt | 2015

    Freier Zugriff

    Vehicle display comprising focal distance correction feature

    WELLER ANDREW D / VANDERPLOEG JOHN A | Europäisches Patentamt | 2020

    Freier Zugriff