skip to main content
10.1145/3697467.3697633acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiotmlConference Proceedingsconference-collections
research-article

Pedestrian Re-identification Method Based on ParNet Network

Published: 08 November 2024 Publication History

Abstract

Pedestrian re-recognition refers to the search and analysis of surveillance objects from video or images. However, this task faces multiple challenges. Firstly, in the case of cross-camera and cross-environment, the characteristics of pedestrian images will change. Secondly, it is difficult for traditional methods to capture the diversity features in pedestrian images, which further reduces the accuracy of recognition. To this end, we employ ParNet, a network enhanced by parallel substructures, as the foundational architecture to derive features from pedestrian images of varying resolutions, and perform hierarchical fusion after feature extraction to improve the capability of multi-level feature modeling. In addition, the CBAM is introduced to capture the fine-grained features in the image more accurately, thus increasing the expressive capacity of the model. During the training period, we employ both the triplet loss function and the cross-entropy loss function, while employing data enhancement techniques to enhancing the robustness and generalization of the model. The experimental outcomes demonstrate that the suggested model achieves commendable performance on both the Market1501 and DukeMTMC-reID datasets.

References

[1]
Ankit Goyal, Alexey Bochkovskiy. NON-DEEP NETWORKS. https://arxiv.org/abs/2110.07641, Thu, 14 Oct 2021.
[2]
LUO H, GU Y, LIAO X, et al. Bag of tricks and a strong baseline for deep person re-identifi-cation[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019; 4321-4329.
[3]
Xie G, Su H, Luo Y, et al. Person re-identification by utilizing hierarchical spatial relation reasoning [J]. Image and Vision Computing, 2024, 148 105111-105111.
[4]
Santana J O, Navarro L J, Obregón F D, et al. Applying deep learning image enhancement methods to improve person re-identification [J]. Neurocomputing, 2024, 598 128011-128011.
[5]
Fu Y, Wei Y, Zhou Y, et al. Horizontal pyramid matching for person re-identification[C]//Proceedings of the AAAI conference on artificial intelligence. 2019, 33(01): 8295-8302.
[6]
Zhang Z, Lan C, Zeng W, et al. Relation-aware global attention for person re-identification[C]//Proceedings of the ieee/cvf conference on computer vision and pattern recognition. 2020: 3186-3195.
[7]
ZHANG Z Y, DING J W, WEI H W, et al. Cascaded Multi-level Features Learning For Attention Based Person Re-Identification [J]. Laser& Optoelectronics Progress, 2021, 58(22):221500.
[8]
Sumeyye A, Ozlem I D. On the Use of a Convolutional Block Attention Module in Deep Learning-Based Human Activity Recognition with Motion Sensors. [J]. Diagnostics (Basel, Switzerland), 2023, 13 (11):
[9]
P S V P R, C C, Ghousiya K B, et al. Deep Learning-Based Skin Lesion Multi-class Classification with Global Average Pooling Improvement. [J]. Journal of digital imaging, 2023, 36 (5): 2227-2248.
[10]
Bo Y, Yao S, Rui P, et al. A feature extraction method for person re-identification based on a two-branch CNN [J]. Multimedia Tools and Applications, 2022, 81 (27): 39169-39184.
[11]
Chenrui W, Xinhao Y, Ke Z, et al. Improved Loss Function for Image Classification [J]. Computational Intelligence and Neuroscience, 2021, 2021
[12]
Zhang Y, Song H, Wei J. Cross-Domain Person Re-Identification Based on Feature Fusion Invariance [J]. Applied Sciences, 2024, 14 (11).

Index Terms

  1. Pedestrian Re-identification Method Based on ParNet Network

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    IoTML '24: Proceedings of the 2024 4th International Conference on Internet of Things and Machine Learning
    August 2024
    443 pages
    ISBN:9798400710353
    DOI:10.1145/3697467
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 08 November 2024

    Check for updates

    Author Tags

    1. CBAM
    2. ParNet network
    3. Pedestrian re-identification
    4. hierarchical fusion
    5. parallel network

    Qualifiers

    • Research-article

    Conference

    IoTML 2024

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 11
      Total Downloads
    • Downloads (Last 12 months)11
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    Full Text

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media