Automatic Body Condition Scoring on Dairy Cows of the Swedish red breed
The objective of this MSc thesis was to investigate parameters reported to be associated with dairy cows’ body condition and its changes. A valid reference of a dairy cow’s body condition was to be suggested and investigated for suitability in the development of a 3D imaging based automatic body...
| Autor principal: | |
|---|---|
| Formato: | Second cycle, A2E |
| Lenguaje: | sueco Inglés |
| Publicado: |
2016
|
| Materias: | |
| Acceso en línea: | https://stud.epsilon.slu.se/9038/ |
| _version_ | 1855571450925154304 |
|---|---|
| author | Foschi Lundmark, Gabriella Eva |
| author_browse | Foschi Lundmark, Gabriella Eva |
| author_facet | Foschi Lundmark, Gabriella Eva |
| author_sort | Foschi Lundmark, Gabriella Eva |
| collection | Epsilon Archive for Student Projects |
| description | The objective of this MSc thesis was to investigate parameters reported to be associated
with dairy cows’ body condition and its changes. A valid reference of a dairy cow’s body
condition was to be suggested and investigated for suitability in the development of a 3D
imaging based automatic body condition scoring model. Furthermore, it was important to
accumulate data to use in training (adjustment of the algorithm mathematics) of the 3D
imaging based automatic body condition scoring model. The study included 21 dairy cows of
the Swedish Red breed from the herd at the Kungsängen Research Centre in Uppsala. The
cows had access to an exercise pen and were fed silage and concentrates indoors according to
the Swedish feeding recommendations, based on individual milk yields. Data was collected
weekly from May to August 2009 and included live weight, manual body condition score,
backfat thickness, 3D images, milk yield, content of fat, protein and lactose in milk and the
plasma metabolites non esterified fatty acids and β-hydroxybutyrate. Data was analysed by
linear correlation and regression analysis. Of all individually investigated collected
parameters, backfat thickness was found to have the highest correlation with manual body
condition scores and this parameter was therefore suggested and used as an alternative true
reference of body condition in the training of the 3D imaging based automatic body condition
scoring model. Results were promising and it was concluded that it is possible to train and
calibrate the 3D imaging based automatic body condition scoring model both with manual
body condition scores and with backfat thickness as reference, to predict the dairy cow’s body
condition. The advantage in using backfat thickness would be that it is a more objective
measure and that it gives continuous data instead of the categorical data obtained from manual
body condition scoring. If sufficient sensitivity is obtained in the automatic body condition
scoring model it could alert the farmer to changes in the cow’s body condition, instead of only
recording the body condition after a change. Future studies should focus on developing this
function in the automatic body condition scoring models since it would add significant value
to dairy management systems. |
| format | Second cycle, A2E |
| id | RepoSLU9038 |
| institution | Swedish University of Agricultural Sciences |
| language | Swedish Inglés |
| publishDate | 2016 |
| publishDateSort | 2016 |
| record_format | eprints |
| spelling | RepoSLU90382016-11-09T12:35:42Z https://stud.epsilon.slu.se/9038/ Automatic Body Condition Scoring on Dairy Cows of the Swedish red breed Foschi Lundmark, Gabriella Eva Animal physiology - Nutrition Veterinary science and hygiene - General aspects The objective of this MSc thesis was to investigate parameters reported to be associated with dairy cows’ body condition and its changes. A valid reference of a dairy cow’s body condition was to be suggested and investigated for suitability in the development of a 3D imaging based automatic body condition scoring model. Furthermore, it was important to accumulate data to use in training (adjustment of the algorithm mathematics) of the 3D imaging based automatic body condition scoring model. The study included 21 dairy cows of the Swedish Red breed from the herd at the Kungsängen Research Centre in Uppsala. The cows had access to an exercise pen and were fed silage and concentrates indoors according to the Swedish feeding recommendations, based on individual milk yields. Data was collected weekly from May to August 2009 and included live weight, manual body condition score, backfat thickness, 3D images, milk yield, content of fat, protein and lactose in milk and the plasma metabolites non esterified fatty acids and β-hydroxybutyrate. Data was analysed by linear correlation and regression analysis. Of all individually investigated collected parameters, backfat thickness was found to have the highest correlation with manual body condition scores and this parameter was therefore suggested and used as an alternative true reference of body condition in the training of the 3D imaging based automatic body condition scoring model. Results were promising and it was concluded that it is possible to train and calibrate the 3D imaging based automatic body condition scoring model both with manual body condition scores and with backfat thickness as reference, to predict the dairy cow’s body condition. The advantage in using backfat thickness would be that it is a more objective measure and that it gives continuous data instead of the categorical data obtained from manual body condition scoring. If sufficient sensitivity is obtained in the automatic body condition scoring model it could alert the farmer to changes in the cow’s body condition, instead of only recording the body condition after a change. Future studies should focus on developing this function in the automatic body condition scoring models since it would add significant value to dairy management systems. Syftet med detta examensarbete var att undersöka parametrar kopplade till mjölkors hull och förändring i hull. En referens för mjölkkors hull skulle föreslås och dess lämplighet undersökas i utvecklingen av en 3D-bild baserad automatisk hullbedömningsmodell. Därutöver var det viktigt att samla data för att använda i träningen (justering av algoritmens matematik) av den 3D-bild baserade automatiska hullbedömningsmodellen. Studien inkluderade 21 kor av Svensk röd och vit boskap och utfördes vid Kungsängens Forskningscentrum i Uppsala. Under studien hade korna tillgång till en rastfålla och de utfodrades inomhus med ensilage och kraftfoder. Data samlades in en gång per vecka från Maj till Augusti 2009 och innefattade mätningar av levande vikt, manuell hullbedömning, underhudsfetts tjocklek, 3D bilder, mjölkavkastning, mjölkens sammansättning (protein, fett och laktos) och plasmametaboliterna fria fettsyror och β-hydroxybutyrat. Insamlade data analyserades genom linjär korrelation och regressionsanalys. Av alla parametrar visade sig underhudsfettets tjocklek vara starkast korrelerad med manuell hullbedömning och föreslogs därför som referens för mjölkkors hull. Underhudsfettets tjocklek användes som referens i träningen av den 3D-bild baserade automatiska hullbedömningsmodellen. Resultaten var lovande och slutsatsen drogs att det är möjlig att träna och kalibrera den 3D-bild baserade automatiska hullbedömningsmodellen för att uppskatta mjölkkors hull med underhudsfettstjocklek som referens. Fördelen med att använda underhudsfettets tjocklek som referens för mjölkkors hull, istället för manuell hullbedömning, är att den erbjuder en mer objektiv och kontinuerlig typ av data. Automatiseringen av hullbedömningen avlägsnar subjektivitet och minskar arbetsbördan samt möjligen ger tillfället att tidigare upptäcka när förändringar i mjölkkors hull inträffar, tack vare högre känslighet. Detta skulle underlätta beslutsfattandet kring djurens skötsel för bonden. 2016-05-12 Second cycle, A2E NonPeerReviewed application/pdf sv https://stud.epsilon.slu.se/9038/1/foschi_g_20161109.pdf Foschi Lundmark, Gabriella Eva, 2016. Automatic Body Condition Scoring on Dairy Cows of the Swedish red breed. Second cycle, A2E. Uppsala: (VH) > Dept. of Animal Nutrition and Management (until 231231) <https://stud.epsilon.slu.se/view/divisions/OID-650.html> urn:nbn:se:slu:epsilon-s-5359 eng |
| spellingShingle | Animal physiology - Nutrition Veterinary science and hygiene - General aspects Foschi Lundmark, Gabriella Eva Automatic Body Condition Scoring on Dairy Cows of the Swedish red breed |
| title | Automatic Body Condition Scoring on Dairy Cows of
the Swedish red breed |
| title_full | Automatic Body Condition Scoring on Dairy Cows of
the Swedish red breed |
| title_fullStr | Automatic Body Condition Scoring on Dairy Cows of
the Swedish red breed |
| title_full_unstemmed | Automatic Body Condition Scoring on Dairy Cows of
the Swedish red breed |
| title_short | Automatic Body Condition Scoring on Dairy Cows of
the Swedish red breed |
| title_sort | automatic body condition scoring on dairy cows of
the swedish red breed |
| topic | Animal physiology - Nutrition Veterinary science and hygiene - General aspects |
| url | https://stud.epsilon.slu.se/9038/ https://stud.epsilon.slu.se/9038/ |