A bio-inspired multi-camera topology for crowd analysis

Dimitrios Chrysostomou, Georgios Ch. Sirakoulis, Antonios Gasteratos

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

This paper presents a bio-inspired method for introducing an adequate multi-camera topology aiming to maximize the coverage of the available space for sufficient crowd analysis. More specifically, a twofold bio-inspired approach is proposed, taking into advantage the emergent computation that arrives from swarms able to find solutions to complex mathematical problems which keep computers busy for days. In the proposed approach, artificial bumblebees are used to determine the number of requested cameras needed to maximize the coverage of an available space subject under the safety specifications dictated by the crowd analysis application, while artificial spiders following the way they wave their webs indicate the exact positions of the aforementioned cameras in the under study crowd environment. Experimental results show that the algorithm is capable of producing promising results where 95% coverage of the given room is possible
Original languageEnglish
Title of host publicationProceedings of the 1st International Workshop on Pattern Recognition and Crowd Analysis (PRCA '12)
Number of pages6
Publication date5 Oct 2012
Publication statusPublished - 5 Oct 2012
Externally publishedYes

Keywords

  • bee colony
  • bio-inspired
  • crowd analysis
  • multi-camera systems

Fingerprint Dive into the research topics of 'A bio-inspired multi-camera topology for crowd analysis'. Together they form a unique fingerprint.

Cite this