在YOLOv12-LSE中的自适应的多尺度注意力网络融合:一个轻量级的框架,用于高效和强大的水下物体检测
Applied optics
|September 22, 2025
概括
这项研究介绍了YOLOv12-LSE,这是一种用于水下物体检测的轻量级框架. 它提高了准确性和效率,在边缘设备的复杂水下条件下优于YOLOv12.
科学领域:
- 计算机视觉 计算机视觉
- 机器人技术 机器人技术 机器人技术
- 海洋技术 海洋技术
背景情况:
- 水下物体检测面临的挑战包括光学干扰和有限的边缘设备计算能力.
- 像YOLOv12这样的现有模型在水生环境中与多尺度特征建模和高计算复杂性作斗争.
研究的目的:
- 开发一个轻量级的框架,YOLOv12-LSE,优化水下物体检测的性能和效率.
- 解决在水下场景中的精度效率权衡问题,用于诸如自动水下车辆 (AUV) 等应用.
主要方法:
- 提出了C2PSA_LSKA模块的联合注意力和分解策略,以改善多尺度检测和抑制模糊.
- 引入了一个Slim Neck架构,使用稀疏的卷积和特征聚合来减少冗余并保留细节.
- 集成到检测头部的高效频道注意力,以更好地区分低对比度目标.
主要成果:
- 在DUO数据集上,YOLOv12-LSE实现了mAP50 (0.681) 与YOLOv12 (0.652) 相比的4.45%的增加.
- 将计算复杂度降低到19.7 GFLOPs,下降7.08%,是该系列中最低的.
- 在具有挑战性的低照明和密集的目标场景中,其精度提高了6.3%,并且具有稳定性.
结论:
- YOLOv12-LSE提供了高精度的实时水下检测解决方案,打破了边缘设备的精度效率瓶.
- 轻量级的设计和集成的注意力机制促进了人工智能在水下移动机器人的深度整合.
- 这一框架为AUV和其他需要高效准确检测能力的水下移动平台提供了重大进展.
相关概念视频
01:11Buoyancy and Stability for Submerged and Floating Bodies
2.5K
In fluid mechanics, buoyancy and stability are key concepts for understanding the behavior of submerged and floating bodies. When a stationary body is fully or partially submerged in a fluid, the fluid exerts a force on the body known as the buoyant force. This force acts vertically upward through a point called the center of buoyancy, which is the center of the displaced fluid volume. According to Archimedes' principle, the magnitude of the buoyant force is equal to the weight of the fluid...
2.5K
01:18Uniform Depth Channel Flow: Problem Solving
442
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
442