Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 7; p. 1651
• Main Authors: Hong, Suk-Ju, Han, Yunhyeok, Kim, Sang-Yeon, Lee, Ah-Yeong, Kim, Ghiseok
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI 06.04.2019; MDPI AG
• Subjects: Animals; bird detection; Birds; convolutional neural networks; Deep Learning; Machine Learning; Neural Networks (Computer); Remote Sensing Technology - methods; unmanned aerial vehicle; deep learning; bird detection; unmanned aerial vehicle; convolutional neural networks
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s19071651

Wild birds are monitored with the important objectives of identifying their habitats and estimating the size of their populations. Especially in the case of migratory bird, they are significantly recorded during specific periods of time to forecast any possible spread of animal disease such as avian influenza. This study led to the construction of deep-learning-based object-detection models with the aid of aerial photographs collected by an unmanned aerial vehicle (UAV). The dataset containing the aerial photographs includes diverse images of birds in various bird habitats and in the vicinity of lakes and on farmland. In addition, aerial images of bird decoys are captured to achieve various bird patterns and more accurate bird information. Bird detection models such as Faster Region-based Convolutional Neural Network (R-CNN), Region-based Fully Convolutional Network (R-FCN), Single Shot MultiBox Detector (SSD), Retinanet, and You Only Look Once (YOLO) were created and the performance of all models was estimated by comparing their computing speed and average precision. The test results show Faster R-CNN to be the most accurate and YOLO to be the fastest among the models. The combined results demonstrate that the use of deep-learning-based detection methods in combination with UAV aerial imagery is fairly suitable for bird detection in various environments.