| Title |
Detecting Abnormal Behavior of Cattle based on Object Detection Algorithm |
| Authors |
채정우(Jung-woo Chae) ; 조현종(Hyun-chong Cho) |
| DOI |
https://doi.org/10.5370/KIEE.2020.69.3.468 |
| Keywords |
Abnormal Behavior; Activity Recognition; Cattle; Deep Learning Model; Estrus; Object Detection |
| Abstract |
Detection of abnormal behavior and unusual signs of cattle has been an important factor for managers in the livestock farming.
Among them, it is of great interest for livestock farmers to detect estrus of cattle, which are unusual behaviors related to breeding management. Most studies on detecting estrus combined with IT technologies have been based on sensors attached to the neck or leg of cattle. But sensor-type devices have the potential to cause stress on the cattle by attaching them, and there are additional cost issues for maintenance. In this study, to solve the above problems, we present a estrus detection system which used regular CCTV and applied the object detection algorithm based on the deep learning model. To run real-time detection in video stream, the activity detection is performed within a single image frame and makes prediction with a single network evaluation. The results of the proposed system showed 97% precision and 96% accuracy. |