| Autor: |
Tong Li, Bo Jiang, Dihua Wu, Xuqiang Yin, Huaibo Song |
| Jazyk: |
angličtina |
| Rok vydání: |
2019 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 7, Pp 185520-185531 (2019) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2019.2961515 |
| Popis: |
A Cow's ruminant behavior can provide information about a cow's health. Monitoring a cow's ruminant behavior could therefore be of use when assessing its health. However, it is difficult to simultaneously monitor multiple target cows' ruminations simultaneously without any contact-type equipment. A method for monitoring multiple target cows' ruminant behavior based on an optical flow method and an inter-frame difference method is proposed here in. The optical flow method is used to obtain the optical flow fields of the ruminant cows' mouth areas in the first 60 frames of a video. The optical flow values with large changes are selected from the first 60 frames of the test video and these values are superimposed to obtain the candidate ruminant cows' mouth areas. The candidate ruminant cows' mouth areas are magnified 1.5 times, and the inter-frame difference method is used to track the real cows' mouth areas in the new magnified areas. According to the “center error” and “overlap rate” indexes, the tracking result for the 15 videos is evaluated. The results show that the average successful tracking rate reaches 89.12%, demonstrating that the algorithm could be applied for the automatic monitoring of multiple target ruminant cows' mouth areas. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
