An automatic underwater object recognition system is essential to reduce the costs of underwater inspection. In this study, we propose a novel convolutional neural network architecture that is trained on underwater video frames. This method is based on a modified residual neural network (ResNet) for underwater object detection. Multi-scale ResNet (M-ResNet), the modified method, improves efficiency by utilizing multi-scale operations for the accurate detection of objects of various sizes, especially small objects. The experimental results show that the proposed method yields an accuracy of 96.5% (mAP) in recognition performance. As a consequence, we propose a novel system for automatic object detection as an application for marine environments.

中文翻译：

---

用于实时水下目标检测的多尺度 ResNet

自动水下物体识别系统对于降低水下检查成本至关重要。在这项研究中，我们提出了一种新颖的卷积神经网络架构，该架构在水下视频帧上进行训练。该方法基于改进的残差神经网络 (ResNet)，用于水下物体检测。改进后的多尺度 ResNet (M-ResNet) 方法通过利用多尺度操作来准确检测各种尺寸的物体，尤其是小物体，提高了效率。实验结果表明，所提出的方法在识别性能上产生了96.5%（mAP）的准确率。因此，我们提出了一种新的自动物体检测系统，作为海洋环境的应用。