In this paper, focusing on the challenges in unique shape dimension and limited training dataset of benthonic organisms, an one-stage CNN detector-based benthonic organisms detection (OSCD-BOD) scheme is proposed. Main contributions are as follows: (1) The regression loss between the predicted bounding box and ground truth box is innovatively measured by the generalized intersection over union (GIoU), such that localization accuracy of benthonic organisms is dramatically enhanced. (2) By devising K-means-based dimension clustering, multiple benthonic organisms anchor boxes (BOAB) sufficiently exploring a priori dimension information can be finely derived from limited training dataset, and thereby significantly promoting the recall ability. (3) Geometric and color transformations (GCT)-based data augmentation technique is further resorted to not only efficiently prevent over-fitting training but also to significantly enhance detection generalization in complex and changeable underwater environments. (4) The OSCD-BOD scheme is eventually established in a modular manner by integrating GIoU, BOAB and GCT functionals. Comprehensive experiments and comparisons sufficiently demonstrate that the proposed OSCD-BOD scheme outperforms typical approaches including Faster R-CNN, SSD, YOLOv2, YOLOv3 and CenterNet in terms of mean average precision by 6.88%, 10.92%, 12.44%, 3.05% and 1.09%, respectively.

在本文中，针对底栖生物独特的形状维度和有限的训练数据集的挑战，提出了一种基于 CNN 检测器的单阶段底栖生物检测（OSCD-BOD）方案。主要贡献如下： (1) 创新性地通过广义交叉联合（GIoU）测量预测边界框和地面实况框之间的回归损失，从而显着提高底栖生物的定位精度。(2) 通过设计基于 K-means 的维度聚类，多个底栖生物锚框 (BOAB) 充分探索先验维度信息可以从有限的训练数据集中精细导出，从而显着提升召回能力。(3) 进一步采用基于几何和颜色变换 (GCT) 的数据增强技术，不仅可以有效防止过拟合训练，还可以显着增强复杂多变水下环境中的检测泛化能力。(4) OSCD-BOD方案最终通过集成GIoU、BOAB和GCT功能以模块化方式建立。综合实验和比较充分表明，所提出的 OSCD-BOD 方案在平均精度方面优于包括 Faster R-CNN、SSD、YOLOv2、YOLOv3 和 CenterNet 在内的典型方法 6.88%、10.92%、12.44%、3.05% 和 1.09% ， 分别。