UTD-Yolov5: A Real-time Underwater Targets Detection Method based on Attention Improved YOLOv5

TL;DR

This paper introduces UTD-Yolov5, an enhanced real-time underwater target detection algorithm that improves accuracy and efficiency for detecting COTS in challenging marine environments using attention mechanisms and network optimizations.

Contribution

The paper presents a novel underwater detection method based on YOLOv5 with architectural modifications and optimization techniques for better accuracy and real-time performance.

Findings

Achieved 78.54% average accuracy on CSIRO dataset

Enhanced detection of COTS in underwater images

Improved network efficiency through WBF and iterative refinement

Abstract

As the treasure house of nature, the ocean contains abundant resources. But the coral reefs, which are crucial to the sustainable development of marine life, are facing a huge crisis because of the existence of COTS and other organisms. The protection of society through manual labor is limited and inefficient. The unpredictable nature of the marine environment also makes manual operations risky. The use of robots for underwater operations has become a trend. However, the underwater image acquisition has defects such as weak light, low resolution, and many interferences, while the existing target detection algorithms are not effective. Based on this, we propose an underwater target detection algorithm based on Attention Improved YOLOv5, called UTD-Yolov5. It can quickly and efficiently detect COTS, which in turn provides a prerequisite for complex underwater operations. We adjusted the original network architecture of YOLOv5 in multiple stages, including: replacing the original Backbone with a two-stage cascaded CSP (CSP2); introducing the visual channel attention mechanism module SE; designing random anchor box similarity calculation method etc. These operations enable UTD-Yolov5 to detect more flexibly and capture features more accurately. In order to make the network more efficient, we also propose optimization methods such as WBF and iterative refinement mechanism. This paper conducts a lot of experiments based on the CSIRO dataset [1]. The results show that the average accuracy of our UTD-Yolov5 reaches 78.54%, which is a great improvement compared to the baseline.