基于Faster R-CNN改进的光学遥感图像飞机检测  

Improved Aircraft Detection of Optical Remote Sensing Image Based on Faster R-CNN

作　　者：杨鑫 王琼[1] 姚亚洲 唐振民[1] Yang Xin;Wang Qiong;Yao Yazhou;Tang Zhenmin(School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,Jiangsu,China)

机构地区：[1]南京理工大学计算机科学与工程学院,江苏南京210094

出　　处：《激光与光电子学进展》2023年第12期417-427,共11页Laser & Optoelectronics Progress

摘　　要：针对光学遥感图像飞机检测任务中超大图像尺寸、小目标检测、复杂背景干扰等问题,提出一种轻量化特征提取网络与注意力机制融合的改进型Faster R-CNN飞机检测算法。通过删去对检测小目标冗余的深层特征层,所提算法对小目标的检测能力得到有效提升,且网络参数量减少38.4%,实现了轻量化处理,推理速度也有显著提升;为强化特征提取能力、弱化背景干扰,创造性地仅在特征提取网络的主干部分引入卷积块注意力模块,有效增加模型对飞机目标的检测能力;在测试推理阶段,采用中线单帧预测后处理方式,对重叠区域内的飞机目标进行单帧预测,避免重复推理、预测结果不一致现象。实验证明,改进后的算法在光学遥感数据集上的mF1分数比改进前算法提升3.5%,最终达到88.97。To address the issues of extremely large image size,small target detection,and complex background interference in aircraft detection task of optical remote sensing image,an improved Faster R-CNN aircraft detection algorithm based on the fusion of lightweight feature extraction network and attention mechanism is proposed.The proposed algorithm’s ability to detect small targets is significantly enhanced by removing the deep feature layer of small target detection redundancy,which also results in a 38.4%reduction in the number of network parameters,enabling lightweight processing and significantly improving the reasoning speed.To strengthen the feature extraction ability and weaken the background interference,convolutional block attention module is creatively presented only in the backbone of the feature extraction network,which successfully increases the detection ability of the model to aircraft targets.To avoid repeated reasoning and inconsistent prediction results,the midline single frame prediction post-processing mode is used in the test reasoning stage to predict the aircraft target in the overlapping area in a single frame.The experiment demonstrates that the improved algorithm achieves a final mF1 score of 88.97,which is 3.5%higher than the original algorithm on the optical remote sensing dataset.

关 键 词：遥感 飞机检测 注意力机制 轻量化 遥感图像 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]