计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (1): 207-216.DOI: 10.3778/j.issn.1002-8331.2303-0375

• 图形图像处理 • 上一篇    下一篇

注意力特征融合的快速遥感图像目标检测算法

吴建成,郭荣佐,成嘉伟,张浩   

  1. 四川师范大学 计算机科学学院,成都 610101
  • 出版日期:2024-01-01 发布日期:2024-01-01

Fast Remote Sensing Image Object Detection Algorithm Based on Attention Feature Fusion

WU Jiancheng, GUO Rongzuo, CHENG Jiawei, ZHANG Hao   

  1. College of Computer Science, Sichuan Normal University, Chengdu 610101, China
  • Online:2024-01-01 Published:2024-01-01

摘要: 针对遥感图像背景复杂、小目标多、特征提取难等问题,提出了一种注意力特征融合的快速遥感图像目标检测算法——YOLO-Aff。该算法设计了一种带通道注意力的主干网络模块(ECALAN)以及模糊池(BP)模块来减小下采样带来的损失。此外,采用了一种无跨步卷积的特征金字塔网络(SPD-FPN)结合SimAM注意力特征融合模块(CBSA)来增强特征的跨尺度融合能力。最后,通过使用Wise-IoU作为网络的坐标损失来优化样本不均衡问题。实验结果表明,改进的YOLO-Aff算法在NWPU VHR-10数据集上的mAP值达到96%,较原算法mAP提高了2.9个百分点,为遥感图像的快速、高精度目标检测提供了新的解决方案。

关键词: 遥感图像, 目标检测, YOLO, 注意力机制, 特征融合

Abstract: Aiming at the challenges of complex backgrounds, numerous small targets, and difficulty in feature extraction in remote sensing images, a fast remote sensing image object detection algorithm based on attention feature fusion—YOLO-Aff is proposed. This algorithm designs a backbone network module (ECALAN) with channel attention and a blur pool (BP) module to reduce the loss caused by downsampling. In addition, a feature pyramid network (SPD-FPN) with no stride convolution is used to combine the SimAM attention feature fusion module (CBSA) to enhance the cross-scale feature fusion performance of the features. Finally, Wise-IoU is used as the coordinate loss of the network to optimize the sample imbalance problem. The experimental results show that YOLO-Aff achieves an mAP value of 96% on the NWPU VHR-10 dataset, which is 2.9 percentage points higher than the original algorithm, and provides a new solution for fast and high-precision object detection of remote sensing images.

Key words: remote sensing image, object detection, YOLO, attention mechanism, feature pyramid