Deep Learning for Shark Detection Tasks

• Published in: 2021 IEEE Green Energy and Smart Systems Conference (IGESSC) pp. 1 - 6
• Main Authors: Zhang, Wenlu, Chen, Xinyi, Bhadani, Dhara, Rex, Patrick, Yang, Yu, Lowe, Christopher G., Yeh, Hen-Geul
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2021
• Subjects: Convolutional Neural Network; Data models; Deep learning; Face recognition; Feature extraction; Object detection; Pipelines; Shark Recognition; Unmanned aerial vehicles
• ISSN: 2640-0138
• DOI: 10.1109/IGESSC53124.2021.9618703

Automatic detection of free-ranging sharks from beach areas is of great importance in maintaining a safe humans-hark interaction. The task is especially challenging due to most existing shark detection methods and the sparsity features of field images collected from Unmanned Aerial Vehicle (UAV). Recently, deep learning has been tremendously successful in various real-world applications such as automatic driving system, object detection, face recognition, medical diagnosis, etc. In this paper, we propose an automated pipeline of shark detection tasks. In specific, we implement several state-of-the-art object detection models into our shark field data set. These algorithms are Faster R-CNN, Mask R-CNN, Feature Pyramid Network (FPN) and RetinaNet. We report the quantitative comparison results on the above mentioned object detection models and we also provide some detection example images. The experiments show that the models are capable of making a fast and efficient detection among shark and non-shark objects.