skip to main content
10.1145/3366194.3366268acmotherconferencesArticle/Chapter ViewAbstractPublication PagesricaiConference Proceedingsconference-collections
research-article

Research on pedestrian occlusion detection based on SSD algorithm

Published: 20 September 2019 Publication History

Abstract

As a basic identification technology, pedestrian detection provides technical support for many areas such as security monitoring and autonomous driving, and has a wide range of application scenarios. Based on the Single Shot MultiBox Detector (SSD) target detection algorithm, this paper trains a pedestrian detection system based on the SSD target detection framework with a self-built occlusion pedestrian dataset for the specific target of occlusion pedestrians. The test set and the re-annotated INRIA test set were used to compare the HOG+SVM based pedestrian detection system and the trained SSD model in OpenCV. The experimental results show that the detection effect of the SSD model is significantly better than the traditional pedestrian detection system based on HOG+SVM. The features learned by the deep convolutional neural network are more robust.

References

[1]
Wang W H, Gao L, Wu S B, Zhao Y M. Pedestrian Detection Review [J]. Motorcycle Technology, 2019(01):29--32.
[2]
Li Dan. Overview of Target Detection Based on Deep Learning[J]. Science and Technology Economics Guide, 2019, 27(13):1--2+31.
[3]
Wu G L, Wang M M. Pedestrian Detection Based on HOG Features and SVM Classifier [J]. China Cable Television, 2017(12):1413--1415.
[4]
Liu X N, Wang Z P, He Y T, Liu Q. A review of small target detection based on in-depth learning [J]. Tactical missile technology, 2019(01):100--107.
[5]
Research and Improvement on Target Detection Algorithms of Single Shot MultiBox Detector [J]. Industrial Control Computer, 2019, 32(04): 103--105.
[6]
Zhang S, Benenson R, Schiele B. CityPersons: A Diverse Dataset for Pedestrian Detection [C]. Proceedings-30th IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4457--4465.
[7]
Zhang C F, Song J T, Wang W L. Review of Pedestrian Detection Technology [J]. Television Technology.2014, 38(03):157--162.
[8]
Li W, Wang P J, Song H Y.A Survey of Pedestrian Detection Methods Based on Statistical Classification[J]. Journal of System Simulation, 2016, 28(09): 2186--2194.
[9]
Antonio Brunetti, Domenico Buongiorno, Gianpaolo Francesco Trotta, Vitoantonio Bevilacqua. Computer vision and deep learning techniques for pedestrian detection and tracking: A survey[J]. Neurocomputing, 2018, 300.
[10]
Zhu M. Pedestrian Detection Method Based on SSD[J]. Science and Technology Innovation, 2017(36):75--76.
[11]
Xing H Q, Du Z Q, Su B. Pedestrian Detection Method Based on Improved SSD [J]. Computer Engineering, 2018, 44(11):228--233+238.
[12]
André Mateus, David Ribeiro, Pedro Miraldo, Jacinto C. Nascimento. Efficient and robust pedestrian detection using deep learning for Human-Aware Navigation[J]. Robotics and Autonomous Systems, 2018.
[13]
SSD:Single Shot MultiBox Detector. Liu W, Anguelov D, Erhan D, et al. European Conference on Computer Vision. 2016

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
RICAI '19: Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence
September 2019
803 pages
ISBN:9781450372985
DOI:10.1145/3366194
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: 20 September 2019

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Deep learning
  2. Occlusion pedestrian detection
  3. SSD algorithm
  4. Self-built pedestrian database

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

RICAI 2019

Acceptance Rates

RICAI '19 Paper Acceptance Rate 140 of 294 submissions, 48%;
Overall Acceptance Rate 140 of 294 submissions, 48%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 106
    Total Downloads
  • Downloads (Last 12 months)4
  • Downloads (Last 6 weeks)1
Reflects downloads up to 27 Jan 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

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media