A Comparison of Deep Learning Approach for Underwater Object Detection

Abstract

In recent years, marine ecosystems and fisheries have become potential resources. Therefore, monitoring these objects will be essential to ensure their existence. One of the computer vision techniques is object detection, utilized to recognize and localize objects in underwater scenery. Many studies have been conducted to investigate various deep learning methods implemented in underwater object detection; however, only a few investigations have been performed to compare mainstream object detection algorithms in these circumstances. This article examines various state-of-the-art deep learning methods applied to underwater object detection, including Faster-RCNN, SSD, RetinaNet, YOLOv3, and YOLOv4. We trained five models on the RUIE dataset. The average detection time was used to compare how fast a model can detect an object within an image, and mAP was also applied to measure detection accuracy. All trained models have costs and benefits; SSD was fast but had poor performance; RetinaNet had consistent performance across different thresholds, but the detection speed was slow; YOLOv3 was the fastest and had acceptable performance comparable with RetinaNet; YOLOv4 was good at first, but performance dropped as threshold enlargement; also, YOLOv4 needed extra time to detect objects compared to YOLOv3. There are no models that are fully suited for underwater object detection; nonetheless, when the mAP and average detection time of the five models were compared, we determined that YOLOv3 is the best acceptable model among the evaluated underwater object detection models.

Keywords

• underwater object detection
• faster-rcnn
• ssd
• retinanet
• yolov3
• yolov4