Characterization of a machine vision system to access gestating sow space usage

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)Not applicablepeer-review

View graph of relations

Author(s)

  • Suzanne Leonard
  • Hongwei Xin
  • Tami M. Brown-Brandl
  • Brett C. Ramirez
  • J. P. Stinn
  • Anna Johnson

Detail(s)

Original languageEnglish
Title of host publication2019 ASABE Annual International Meeting
PublisherAmerican Society of Agricultural and Biological Engineers
Publication statusPublished - Jul 2019

Conference

Title2019 Annual International Meeting
LocationBoston Marriott Copley Place
PlaceUnited States
CityBoston, Massachusetts
Period7 - 10 July 2019

Abstract

Physical space allocation for animals is an important consideration when designing animal production facilities. This physical space is defined by the length, width, and height of a volume designated to an individual animal. Animals require static space when stationary, but additional space is needed to perform dynamic postural transitions. Inadequate space to perform basic behaviors and postural adjustments can reduce productivity and welfare. Conversely, excess space introduces inefficiencies, resulting in production losses and unnecessary construction expenses. The most commonly used sow space guidelines were published in the 1980s. Therefore, modern commercial sow‘s static and dynamic space requirements must be studied to provide evidence-based guidelines for current producers. Such information can be accurately assessed with the use of time-of-flight depth image sensors. A process to develop calibration equations to convert the depth image pixel measurements into physical dimensions was developed and error was assessed. Sample data collected on structurally sound commercial sows (Landrace x Yorkshire) in late gestation (11-15 weeks) of various parities is described. Length, width, and height of the space utilized by sows were calculated for static positions defined as standing and lateral lying, as well as dynamic sequences defined as standing up and lying down. Results can be used to develop relationships between sow body weight and three dimensional static and dynamic space requirements. This information can be used to inform gestation housing design decisions.

Research Area(s)

  • Kinect®, machine vision, sow, space allocation, welfare

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

Characterization of a machine vision system to access gestating sow space usage. / Leonard, Suzanne ; Xin, Hongwei; Brown-Brandl, Tami M.; Ramirez, Brett C.; Stinn, J. P.; Johnson, Anna ; Liu, Kai.

2019 ASABE Annual International Meeting. American Society of Agricultural and Biological Engineers, 2019. 1900782.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)Not applicablepeer-review