Performance of an image analysis processing system for hen tracking in an environmental preference chamber

Mohammad Amin Kashiha, Angela R. Green, Tatiana Glogerley Sales, Claudia Bahr, Daniel Berckmans, Richard S. Gates

Research output: Contribution to journalArticle

Abstract

Image processing systems have been widely used in monitoring livestock for many applications, including identification, tracking, behavior analysis, occupancy rates, and activity calculations. The primary goal of this work was to quantify image processing performance when monitoring laying hens by comparing length of stay in each compartment as detected by the image processing system with the actual occurrences registered by human observations. In this work, an image processing system was implemented and evaluated for use in an environmental animal preference chamber to detect hen navigation between 4 compartments of the chamber. One camera was installed above each compartment to produce top-view images of the whole compartment. An ellipse-fitting model was applied to captured images to detect whether the hen was present in a compartment. During a choice-test study, mean ± SD success detection rates of 95.9 ± 2.6% were achieved when considering total duration of compartment occupancy. These results suggest that the image processing system is currently suitable for determining the response measures for assessing environmental choices. Moreover, the image processing system offered a comprehensive analysis of occupancy while substantially reducing data processing time compared with the time-intensive alternative of manual video analysis. The above technique was used to monitor ammonia aversion in the chamber. As a preliminary pilot study, different levels of ammonia were applied to different compartments while hens were allowed to navigate between compartments. Using the automated monitor tool to assess occupancy, a negative trend of compartment occupancy with ammonia level was revealed, though further examination is needed.

Original languageEnglish (US)
Pages (from-to)2439-2448
Number of pages10
JournalPoultry science
Volume93
Issue number10
DOIs
StatePublished - Jan 1 2014

Keywords

  • Animal behavior
  • Choice test
  • Image processing
  • Laying hen
  • Occupancy analysis

ASJC Scopus subject areas

  • Animal Science and Zoology

Fingerprint Dive into the research topics of 'Performance of an image analysis processing system for hen tracking in an environmental preference chamber'. Together they form a unique fingerprint.

  • Cite this