Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai, People's Republic of China.
PLoS One. 2024 Feb 28;19(2):e0298739. doi: 10.1371/journal.pone.0298739. eCollection 2024.
With the rapid development of ocean observation technology, underwater object detection has begun to occupy an essential position in the fields of aquaculture, environmental monitoring, marine science, etc. However, due to the problems unique to underwater images such as severe noise, blurred objects, and multi-scale, deep learning-based target detection algorithms lack sufficient capabilities to cope with these challenges. To address these issues, we improve DETR to make it well suited for underwater scenarios. First, a simple and effective learnable query recall mechanism is proposed to mitigate the effect of noise and can significantly improve the detection performance of the object. Second, for underwater small and irregular object detection, a lightweight adapter is designed to provide multi-scale features for the encoding and decoding stages. Third, the regression mechanism of the bounding box is optimized using the combination loss of smooth L1 and CIoU. Finally, we validate the designed network against other state-of-the-art methods on the RUOD dataset. The experimental results show that the proposed method is effective.
随着海洋观测技术的飞速发展，水下目标检测开始在水产养殖、环境监测、海洋科学等领域占据重要地位。然而，由于水下图像所特有的问题，如严重的噪声、模糊的物体和多尺度等，基于深度学习的目标检测算法缺乏足够的能力来应对这些挑战。为了解决这些问题，我们对 DETR 进行了改进，使其非常适合水下场景。首先，提出了一种简单而有效的可学习查询召回机制，以减轻噪声的影响，并显著提高目标的检测性能。其次，对于水下小而不规则的目标检测，设计了一个轻量级适配器，为编码和解码阶段提供多尺度特征。第三，使用平滑 L1 和 CIoU 的组合损失来优化边界框的回归机制。最后，我们在 RUOD 数据集上验证了所设计的网络与其他最先进方法的比较。实验结果表明，所提出的方法是有效的。
