针对水下视觉退化问题，提升目标检测分类跟踪性能。
AquaFeat+: an Underwater Vision Learning-based Enhancement Method for Object Detection, Classification, and Tracking
- 基于端到端训练的特征增强管道，专注优化感知任务
- 在FishTrack23数据集上显著提升检测、分类与追踪指标
- 可直接嵌入机器人系统，适合水下自主作业场景
由于光照不足、色彩失真和浑浊度高等因素，水下视频分析极具挑战性，严重影响视觉数据质量并直接制约机器人感知模块的性能。本文提出AquaFeat+，一种专为自动化视觉任务设计的即插即用增强方法，而非提升人眼观感。该架构包含色彩校正、分层特征增强及自适应残差输出模块，所有组件端到端训练，并由最终应用任务的损失函数直接引导。在FishTrack23数据集上进行训练与评估，AquaFeat+在目标检测、分类与跟踪指标上均取得显著提升，验证了其在水下机器人感知任务中的有效性。
原文摘要 · Abstract (English)
Underwater video analysis is particularly challenging due to factors such as low lighting, color distortion, and turbidity, which compromise visual data quality and directly impact the performance of perception modules in robotic applications. This work proposes AquaFeat+, a plug-and-play pipeline designed to enhance features specifically for automated vision tasks, rather than for human perceptual quality. The architecture includes modules for color correction, hierarchical feature enhancement, and an adaptive residual output, which are trained end-to-end and guided directly by the loss function of the final application. Trained and evaluated in the FishTrack23 dataset, AquaFeat+ achieves significant improvements in object detection, classification, and tracking metrics, validating its effectiveness for enhancing perception tasks in underwater robotic applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。