Chapter 18: The use of 3D imaging technology in animal management, with a special emphasis on ruminant production
In: Practical Precision Livestock FarmingSearch for other papers by Y. Le Cozler in
Current site
Google Scholar
PubMed
Search for other papers by C. Allain in
Current site
Google Scholar
PubMed
Search for other papers by A. Fischer in
Current site
Google Scholar
PubMed
Search for other papers by A. Caillot in
Current site
Google Scholar
PubMed
Search for other papers by L. Depuille in
Current site
Google Scholar
PubMed
Agroscope, Ruminant Research Unit, Route de la Tioleyre 4, 1725 Posieux, Switzerland.
Search for other papers by C. Xavier in
Current site
Google Scholar
PubMed
Search for other papers by J.M. Delouard in
Current site
Google Scholar
PubMed
Search for other papers by L. Delattre in
Current site
Google Scholar
PubMed
Search for other papers by T. Luginbuhl in
Current site
Google Scholar
PubMed
Search for other papers by S. Lerch in
Current site
Google Scholar
PubMed
Search for other papers by A. Lebreton in
Current site
Google Scholar
PubMed
Search for other papers by P. Faverdin in
Current site
Google Scholar
PubMed
Purchase instant access (PDF download and unlimited online access):
An important aspect of livestock management consists of carefully observing the animals, which, depending on the species and type of farming operation, can be extremely time-consuming for farmers. To assist in these activities, researchers have begun investigating the use of 3D imaging. Among its many advantages, the most beneficial is that it enables easy and safe measurement of traits of interest, both those that have historically been used as well as new traits that until now have not been obtainable from living animals. With recent developments, image-based approaches are becoming increasingly accessible to farms, regardless of scale or method of production (e.g. conventional or organic). This article reviews the principles of this technology and its current applications, mainly in dairy farms, but also presents some promising future perspectives. Imaging technology can already provide access to rapid and repeated measurements of body condition score, surface area, volume, and morphological traits from a large number of individuals. However, further development is needed to improve the efficiency of data processing and interpretation, particularly with respect to automation and image analysis. To date, applications of imaging data have been limited by constraints on the frequency of monitoring. In the future, the use of machine learning will probably help to identify new body areas or traits of interest. However, even if most technical and technological obstacles have been removed (or will soon be removed), improvements are still needed with respect to data transfer and storage capacity, the type of information stored, and analysis and communication of reliable and usable information in real time. The application of high-throughput monitoring to these indicators opens new possibilities which thus far remain largely unknown. Finally, much work remains on determining the best use of these data, the advice to give to breeders, and the training needed by farmers.