Sheep Detection, Tracking and counting from aerial images using Deep Learning
Abderrahmane Adjila , Fatima Djekaba, Mohammed Elmehdi Mehaya
كلية العلوم والتكنولوجيا-جامعة غرداية · الجزائر
Object detection is widely used in the field of computer vision. Furthermore, it can be harnessedin agriculture and farming, especially with the new methods that achieve promising results. Nowadays, the problem is tackled using either traditional machine learning methods that use computervision techniques or deep learning methods. In this work, we investigate the deep learning stateof-the-art tools to create a smart system for detecting, tracking and counting sheep using aerialimages captured by a drone. In the process, we gather sufficient data with good quality and use itto train a model dependent on the YOLOv4 network. Next, we tackle the counting stage directlyusing an innovative method that uses an imaginary line cutting the processed frame incrementingthe counter whenever an intersection between the bounding box and the gate happens. However, we had to introduce an intermediate stage because of low performance. That intermediary is called tracking. The results obtained by the experiment are highly promising in detection with an mAPof 71% and 16.1274 % of avg loss function.