Pedestrian Detection Based on Improved Mask R-CNN Algorithm

  • Wenjun Yu
  • , Sumi Kim
  • , Fei Chen
  • , Jaeho Choi*
  • *Corresponding author for this work

Research output: Contribution to conferenceConference paperpeer-review

Abstract

As the modern society evolves around digital media, object recognition becomes one of the important areas for computer vision. Pedestrian detection particularly draws much attention because it is closely related to everyday life. Recently, pedestrian detection has achieved great success in intelligent monitoring, intelligent driving, and environmental protection. Although, there are several pedestrian detection algorithms based on deep learning, the pedestrian detection is still a huge challenge. Background occlusion, pedestrians’ various changing postures and objects’ occlusion give significant impact on the recognition results; it still brings up much attention. In this paper, to reduce the influence of external factors, we propose a new method based on Mask R-CNN algorithm. The proposed system was evaluated on the Daimler pedestrian dataset for training and on the public Caltech and INRIA pedestrian datasets for testing. The experimental results have showed that the proposed algorithm achieves better detection accuracy than the conventional ones.

Original languageEnglish
Title of host publicationIntelligent and Fuzzy Techniques
Subtitle of host publicationSmart and Innovative Solutions - Proceedings of the INFUS 2020 Conference
EditorsCengiz Kahraman, Sezi Cevik Onar, Basar Oztaysi, Irem Ucal Sari, Selcuk Cebi, A. Cagri Tolga
PublisherSpringer
Pages1515-1522
Number of pages8
ISBN (Print)9783030511555
DOIs
StatePublished - 2021
EventInternational Conference on Intelligent and Fuzzy Systems, INFUS 2020 - Istanbul, Turkey
Duration: 2020.07.212020.07.23

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1197 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceInternational Conference on Intelligent and Fuzzy Systems, INFUS 2020
Country/TerritoryTurkey
CityIstanbul
Period20.07.2120.07.23

Keywords

  • Feature concatenation
  • Hard negative mining
  • Mask R-CNN
  • Pedestrian detection

Quacquarelli Symonds(QS) Subject Topics

  • Computer Science & Information Systems

Fingerprint

Dive into the research topics of 'Pedestrian Detection Based on Improved Mask R-CNN Algorithm'. Together they form a unique fingerprint.

Cite this