高斯Wasserstein距离改进轻量YOLOv7模型的遥感影像道路交叉口检测

YOLOv7是目前目标检测任务中性能较优的模型，但在处理遥感影像中的道路交叉口时，出现目标背景复杂、先验框定位误差以及模型训练参数量增多的问题。本文针对复杂场景的道路交叉口提出一种结合归一化高斯Wasserstein距离与轻量级YOLOv7的遥感影像道路交叉口检测模型。首先，使用归一化高斯Wasserstein距离与CIOU进行先验框定位损失函数的改进，以提高网络模型对于目标尺寸的鲁棒性；其次，在加强网络特征提取模块中加入三维注意力机制，实现网络处理的特征优化；最后，在主干特征提取网络与加强特征提取网络中加入改进的FasterNet模块，提升网络模型的训练速度，减少了模型训练的参数。实验结果表明，改进后的 YOLOv7 网络模型相比原网络模型，漏检测情况得到明显改善，P、R、AP及F1值分别提升了6.2%，4.9%，6.7%，6.5%，对道路交叉口的检测效果优于原网络模型。其成果对不同环境的影像具有较强适应能力，为道路交叉口检测的发展提供了参考。

Gaussian Wasserstein Distance Improvement of Lightweight YOLOv7 Model for Remote Sensing Image Road Intersection Detection

YOLOv7 is a better-performing model in the current target detection task. However, when dealing with road intersections in remote sensing images, the problems of complex target backgrounds, significant positioning errors in the first frame, and the number of model training parameters increase. This paper proposes a road intersection detection model for remote sensing images that combines normalized Gaussian Wasserstein distance with lightweight YOLOv7 for road intersections in complex scenarios. Firstly, the transcendental box localization loss function is improved by normalized Gauss Wasserstein distance and CIOU to enhance the robustness of the network model to target size. Secondly, a three-dimensional attention mechanism is added to the enhanced network feature extraction module to achieve feature optimization. Finally, an improved FasterNet module is added to the backbone feature extraction network and enhanced feature extraction network to improve the network model''s training speed and reduce the model training parameters. The results show that the improved YOLOv7 network model showed significant improvement in leakage detection compared to the original network model, with P, R, AP, and F1 values increasing by 6.2%, 4.9%, 6.7%, and 6.5%, respectively. It is concluded that solid adaptability to different environmental images provides a reference for developing road intersection detection.