Automatic segmentation of veterinary infrared images with the active shape approach

  • Authors:

  • Tom Wirthgen;Stephan Zipser;Ulrike Franze;Steffi Geidel;Franz Dietel;Theophile Alary

  • Affiliations:

  • Fraunhofer Institute for Transportation and Infrastructure Systems, Dresden, Germany;Fraunhofer Institute for Transportation and Infrastructure Systems, Dresden, Germany;HTW Dresden, Pillnitzer Platz, Dresden, Germany;HTW Dresden, Pillnitzer Platz, Dresden, Germany;HTWK Leipzig, Postfach, Leipzig, Germany;Universite de technologie de Troyes, France

  • Venue:
  • SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Modern livestock farming follows a trend to higher automation and monitoring standards. Novel systems for a health monitoring of animals like dairy cows are under development. The application of infrared thermography (IRT) for medical diagnostics was suggested long ago, but the lack of suitable technical solutions still prevents an efficient use. Within the R&D project VIONA new solutions are developed to provide veterinary IRT based diagnostic procedures with precise absolute temperature values of the animal surface. Amongst others this requires a reliable object detection and segmentation of the IR images. Due to the significant shape variation of interest objects advanced segmentation methods are necessary. The "active shape" approach introduced by Cootes and Taylor [7] is applied to veterinary IR images for the first time. The special features of the thermal infrared spectrum require a comprehensive adaptation of this approach. The modified algorithm and first results of the successful application on approximately two million IR images of dairy cows are presented.