Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study
Lameness in horses is a long-known issue influencing the welfare, as well as the use, of a horse. Nevertheless, the detection and classification of lameness mainly occurs on a subjective basis by the owner and the veterinarian. The aim of this study was the development of a lameness detection system...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/12/20/2804 |
| _version_ | 1797475993055657984 |
|---|---|
| author | Ann-Kristin Feuser Stefan Gesell-May Tobias Müller Anna May |
| author_facet | Ann-Kristin Feuser Stefan Gesell-May Tobias Müller Anna May |
| author_sort | Ann-Kristin Feuser |
| collection | DOAJ |
| description | Lameness in horses is a long-known issue influencing the welfare, as well as the use, of a horse. Nevertheless, the detection and classification of lameness mainly occurs on a subjective basis by the owner and the veterinarian. The aim of this study was the development of a lameness detection system based on pose estimation, which permits non-invasive and easily applicable gait analysis. The use of 58 reference points on easily detectable anatomical landmarks offers various possibilities for gait evaluation using a simple setup. For this study, three groups of horses were used: one training group, one analysis group of fore and hindlimb lame horses and a control group of sound horses. The first group was used to train the network; afterwards, horses with and without lameness were evaluated. The results show that forelimb lameness can be detected by visualising the trajectories of the reference points on the head and both forelimbs. In hindlimb lameness, the stifle showed promising results as a reference point, whereas the tuber coxae were deemed unsuitable as a reference point. The study presents a feasible application of pose estimation for lameness detection, but further development using a larger dataset is essential. |
| first_indexed | 2024-03-09T20:51:36Z |
| format | Article |
| id | doaj.art-6ac3c0053a4d4ba7ae7170854d0c74e3 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-09T20:51:36Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-6ac3c0053a4d4ba7ae7170854d0c74e32023-11-23T22:32:09ZengMDPI AGAnimals2076-26152022-10-011220280410.3390/ani12202804Artificial Intelligence for Lameness Detection in Horses—A Preliminary StudyAnn-Kristin Feuser0Stefan Gesell-May1Tobias Müller2Anna May3Equine Hospital in Parsdorf, 85599 Vaterstetten, GermanyAnirec GmbH, Artificial Intelligence Solutions in Veterinary Medicine, 80539 Munich, GermanyAnirec GmbH, Artificial Intelligence Solutions in Veterinary Medicine, 80539 Munich, GermanyEquine Hospital, Ludwig Maximilians University, 85764 Oberschleissheim, GermanyLameness in horses is a long-known issue influencing the welfare, as well as the use, of a horse. Nevertheless, the detection and classification of lameness mainly occurs on a subjective basis by the owner and the veterinarian. The aim of this study was the development of a lameness detection system based on pose estimation, which permits non-invasive and easily applicable gait analysis. The use of 58 reference points on easily detectable anatomical landmarks offers various possibilities for gait evaluation using a simple setup. For this study, three groups of horses were used: one training group, one analysis group of fore and hindlimb lame horses and a control group of sound horses. The first group was used to train the network; afterwards, horses with and without lameness were evaluated. The results show that forelimb lameness can be detected by visualising the trajectories of the reference points on the head and both forelimbs. In hindlimb lameness, the stifle showed promising results as a reference point, whereas the tuber coxae were deemed unsuitable as a reference point. The study presents a feasible application of pose estimation for lameness detection, but further development using a larger dataset is essential.https://www.mdpi.com/2076-2615/12/20/2804artificial intelligencedeep learningpose estimationlamenessequine |
| spellingShingle | Ann-Kristin Feuser Stefan Gesell-May Tobias Müller Anna May Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study Animals artificial intelligence deep learning pose estimation lameness equine |
| title | Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study |
| title_full | Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study |
| title_fullStr | Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study |
| title_full_unstemmed | Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study |
| title_short | Artificial Intelligence for Lameness Detection in Horses—A Preliminary Study |
| title_sort | artificial intelligence for lameness detection in horses a preliminary study |
| topic | artificial intelligence deep learning pose estimation lameness equine |
| url | https://www.mdpi.com/2076-2615/12/20/2804 |
| work_keys_str_mv | AT annkristinfeuser artificialintelligenceforlamenessdetectioninhorsesapreliminarystudy AT stefangesellmay artificialintelligenceforlamenessdetectioninhorsesapreliminarystudy AT tobiasmuller artificialintelligenceforlamenessdetectioninhorsesapreliminarystudy AT annamay artificialintelligenceforlamenessdetectioninhorsesapreliminarystudy |