skip to main content
10.1145/3007669.3007745acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicimcsConference Proceedingsconference-collections
short-paper

Deep People Counting with Faster R-CNN and Correlation Tracking

Published: 19 August 2016 Publication History

Abstract

Crowd counting is a key problem for many computer vision tasks while most existing methods try to count people based on regression with hand-crafted features. Recently, the fast development of deep learning has resulted in many promising detectors of generic object classes. In this paper, to effective leverage the discriminability of convolutional neural networks, we propose a method to people counting based on Faster R-CNN[9] head-shoulder detection and correlation tracking. Firstly, we train a Faster R-CNN head-shoulder detector with Zeiler model to detect people with multiple poses and views. Next, we employ kernelized correlation filter(KCF)[7] to track the people and obtain the trajectory. Considering the results of the detection and tracking, we fuse the two bounding box to obtain a continuous and stable trajectory. Extensive experiments and comparison show the promise of the proposed approach.

References

[1]
O. Barinova, V. Lempitsky, and P. Kohli. On detection of multiple object instances using hough transform. In CVPR, 2010.
[2]
D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui. Visual object tracking using adaptive correlation filters. In CVPR, pages 2544--2550, 2010.
[3]
K. Chen, S. Gong, T. Xiang, and C. C. Loy. Cumulative attribute space for age and crowd density estimation. In CVPR, pages 2467--2474, 2013.
[4]
W. Gao, H. Ai, and S. Lao. Adaptive contour features in oriented granular space for human detection and segmentation. In CVPR, 2009.
[5]
W. Ge and R. Collins. Marked point processes for crowd counting. In CVPR, pages 2913--2920, 2009.
[6]
R. B. Girshick. Fast r-cnn. In ICCV, 2015.
[7]
J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. Highspeed tracking with kernelized correlation filters. In PAMI, 2015.
[8]
I. Loshchilov and F. Hutter. Online batch selection for faster training of neural networks. arXiv preprint arXiv:1511.06343, 2015.
[9]
S. Ren, K. He, R. B. Girshick, and J. Sun. Faster r-cnn: towards real-time object detection with region proposal networks. In NIPS, pages 91--99, 2015.
[10]
A. Shrivastava, A. Gupta, and R. Girshick. Training region-based object detectors with online hard example mining. arXiv preprint arXiv:1604.03540, 2016.
[11]
R. Stewart and M. Andriluka. End-to-end people detection in crowded scenes. In NIPS, 2015.
[12]
J. Xing, H. Ai, L. Liu, and S. Lao. Robust crowd counting using detection flow. In ICIP, 2011.

Cited By

View all
  • (2024)Mask focal loss: a unifying framework for dense crowd counting with canonical object detection networksMultimedia Tools and Applications10.1007/s11042-024-18134-x83:27(70571-70593)Online publication date: 31-Jan-2024
  • (2023)Target-centered context-detection technique using dual R-CNNJournal of Advanced Marine Engineering and Technology10.5916/jamet.2023.47.6.40547:6(405-410)Online publication date: 31-Dec-2023
  • (2023)Passenger Flow Detection in Subway Stations Based on Improved You Only Look Once AlgorithmTransportation Research Record: Journal of the Transportation Research Board10.1177/036119812311591282677:9(397-409)Online publication date: 22-Mar-2023
  • Show More Cited By

Index Terms

  1. Deep People Counting with Faster R-CNN and Correlation Tracking

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICIMCS'16: Proceedings of the International Conference on Internet Multimedia Computing and Service
    August 2016
    360 pages
    ISBN:9781450348508
    DOI:10.1145/3007669
    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 ACM 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]

    In-Cooperation

    • Xidian University

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 19 August 2016

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Head-shoulder Detector
    2. Kernelized Correlation Filter
    3. People Counting

    Qualifiers

    • Short-paper
    • Research
    • Refereed limited

    Funding Sources

    Conference

    ICIMCS'16

    Acceptance Rates

    ICIMCS'16 Paper Acceptance Rate 77 of 118 submissions, 65%;
    Overall Acceptance Rate 163 of 456 submissions, 36%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)11
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 15 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Mask focal loss: a unifying framework for dense crowd counting with canonical object detection networksMultimedia Tools and Applications10.1007/s11042-024-18134-x83:27(70571-70593)Online publication date: 31-Jan-2024
    • (2023)Target-centered context-detection technique using dual R-CNNJournal of Advanced Marine Engineering and Technology10.5916/jamet.2023.47.6.40547:6(405-410)Online publication date: 31-Dec-2023
    • (2023)Passenger Flow Detection in Subway Stations Based on Improved You Only Look Once AlgorithmTransportation Research Record: Journal of the Transportation Research Board10.1177/036119812311591282677:9(397-409)Online publication date: 22-Mar-2023
    • (2023)Character Detection in First Person Shooter Game Scenes Using YOLO-v5 and YOLO-v7 Networks2023 2nd International Conference on Data Analytics, Computing and Artificial Intelligence (ICDACAI)10.1109/ICDACAI59742.2023.00160(825-831)Online publication date: 17-Oct-2023
    • (2023)Human Detection in crowd using One-stage and Two-stage object detection models2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)10.1109/ICCCNT56998.2023.10307765(1-5)Online publication date: 6-Jul-2023
    • (2023)Convolutional neural network for human crowd analysis: a reviewMultimedia Tools and Applications10.1007/s11042-023-16841-583:22(62307-62331)Online publication date: 25-Sep-2023
    • (2022)Distillation Remote Sensing Object Counting via Multi-Scale Context Feature AggregationIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2021.312524960(1-12)Online publication date: 2022
    • (2022)NAPC: A Neural Algorithm for Automated Passenger Counting in Public Transport on a Privacy-Friendly DatasetIEEE Open Journal of Intelligent Transportation Systems10.1109/OJITS.2021.31393933(33-44)Online publication date: 2022
    • (2022)PDDNet: lightweight congested crowd counting via pyramid depth-wise dilated convolutionApplied Intelligence10.1007/s10489-022-03967-653:9(10472-10484)Online publication date: 19-Aug-2022
    • (2021)Passenger Flow Estimation with Bipartite Matching on Bus Surveillance Cameras2021 IEEE 4th International Conference on Multimedia Information Processing and Retrieval (MIPR)10.1109/MIPR51284.2021.00038(206-212)Online publication date: Sep-2021
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media