Xiao Zhanhao, Li Zhenpeng, Li Huihui, Li Mengting, Liu Xiaoyong, Kong Yinying
School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China.
Guangdong Provincial Key Laboratory of Intellectual Property and Big Data, Guangdong Polytechnic Normal University, Guangzhou 510665, China.
Sensors (Basel). 2024 Nov 11;24(22):7201. doi: 10.3390/s24227201.
Underwater object detection (UOD) presents substantial challenges due to the complex visual conditions and the physical properties of light in underwater environments. Small aquatic creatures often congregate in large groups, further complicating the task. To address these challenges, we develop Aqua-DETR, a tailored end-to-end framework for UOD. Our method includes an align-split network to enhance multi-scale feature interaction and fusion for small object identification and a distinction enhancement module using various attention mechanisms to improve ambiguous object identification. Experimental results on four challenging datasets demonstrate that Aqua-DETR outperforms most existing state-of-the-art methods in the UOD task, validating its effectiveness and robustness.
由于水下环境中复杂的视觉条件和光的物理特性，水下目标检测（UOD）面临着巨大挑战。小型水生生物常常成群聚集，这使得任务进一步复杂化。为应对这些挑战，我们开发了Aqua-DETR，这是一个专门用于UOD的端到端框架。我们的方法包括一个对齐分割网络，用于增强多尺度特征交互和融合以识别小目标，以及一个使用各种注意力机制的区分增强模块，以改善模糊目标的识别。在四个具有挑战性的数据集上的实验结果表明，Aqua-DETR在UOD任务中优于大多数现有的最先进方法，验证了其有效性和鲁棒性。
