Optical flow-based bird tracking and counting for congregating flocks

  • Authors:

  • Jing Yi Tou;Chen Chuan Toh

  • Affiliations:

  • Centre for Computing and Intelligent Systems (CCIS), Faculty of Information and Communication Technology (FICT), Universiti Tunku Abdul Rahman (UTAR), Perak, Kampar, Malaysia;Centre for Computing and Intelligent Systems (CCIS), Faculty of Information and Communication Technology (FICT), Universiti Tunku Abdul Rahman (UTAR), Perak, Kampar, Malaysia

  • Venue:
  • ACIIDS'12 Proceedings of the 4th Asian conference on Intelligent Information and Database Systems - Volume Part III
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Bird flock counting is not deeply studied yet, but there are applications of bird flock counting that would provide benefits to different parties, such as the population estimation of swiftlets for swiftlet farmers and migratory raptors for ornithologists. The methodology involved two stages: 1. segmentation phase to segment the birds out from the video and; 2. tracking phase to track the birds using optical flow and count them. The raptor flocks are used in this paper because they are bigger and easier to be filmed at congregation sites during migration. The experimental results show an average hit rate of 88.1% for video of 500 × 400 but only achieve 6.17 fps while the video of 320 × 200 had a lower hit rate of 73.3% but achieving 16.98 fps. Both are not capable of achieving real-time processing but show possibility of tracking and counting a flock of flying birds.