Detecting sheep in UAV images

• Published in: Computers and electronics in agriculture 2021-08, Vol.187, p.106219, Article 106219
• Main Authors: Sarwar, Farah, Griffin, Anthony, Rehman, Saeed Ur, Pasang, Timotius
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Centroids; Deep learning; Image segmentation; Livestock; Machine learning; Object detection; Object recognition; Performance evaluation; UAV; Unmanned aerial vehicles
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2021.106219

•The use of a UAV is proposed for livestock detection and counting.•A dataset of images of sheep from a UAV at 80 m and 120 m is compiled and tested.•A variety of CNN networks are trained and tested for sheep detection.•The U-Net-MS network achieves an excellent F1-score of about 98%. In the last decade, researchers have focused more on deep convolutional neural networks (CNNs) than other machine learning algorithms for object detection, localization, classification and segmentation. Such CNNs have achieved remarkable results in these fields and use the bounding boxes as the ground truth data. In this research article, we have used a fully connected network (FCN) for livestock detection in aerial images captured by an unmanned aerial vehicle (UAV), that used centroids as ground truth data. For performance evaluation and comparison, we have proposed a single-layered and a seven-layered CNN network in this article. These proposed networks are trained using state-of-the-art method, Region-based CNN. In addition, AlexNet, GoogLeNet, VGG16, VGG19 and ResNet50 were also fine-tuned for livestock detection. The results of the FCN and one of our proposed networks are then merged to improve the recall of the complete system from 90% to 98%.