A pedestrian detection method based on PSO and multimodal function

Wei Xing Li, We Liang Ma, Bing Quan, Meng Xin Pei, Xiao Xue Feng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

To solve the problem of heavy time-consuming in real-time pedestrian detection, a pedestrian detection algorithm based on Particle Swarm Optimization (PSO) for multimodal function is developed. This method treats the pedestrian detection problem as the multimodal function in a solution space, and uses PSO to solve the multimodal function. Pedestrians' feature is described by Histogram of Sparse Code (HSC) and classified by linear SVM. In addition, the acceleration constants in PSO are improved by adaptive parameters, and the proposed iteration criterion is given to find the final results efficiently and effectively. Simulation experiments show the effectiveness of the proposed algorithm, and the running time is decreased by 72.9% compared to the sliding window detection methods.

Original languageEnglish
Title of host publicationProceedings of the 28th Chinese Control and Decision Conference, CCDC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6054-6058
Number of pages5
ISBN (Electronic)9781467397148
DOIs
Publication statusPublished - 3 Aug 2016
Event28th Chinese Control and Decision Conference, CCDC 2016 - Yinchuan, China
Duration: 28 May 201630 May 2016

Publication series

NameProceedings of the 28th Chinese Control and Decision Conference, CCDC 2016

Conference

Conference28th Chinese Control and Decision Conference, CCDC 2016
Country/TerritoryChina
CityYinchuan
Period28/05/1630/05/16

Keywords

  • Multimodal function
  • PSO
  • Pedestrian detection
  • Sparse coding

Fingerprint

Dive into the research topics of 'A pedestrian detection method based on PSO and multimodal function'. Together they form a unique fingerprint.

Cite this