基于DATE-FCOS的空中目标检测研究  

Research on Air Target Detection Based on DATE-FCOS

作　　者：陈钊阳 王玉玫[1] CHEN Zhaoyang;WANG Yumei(North China Institute of Computing Technology,Beijing 100083,China)

机构地区：[1]华北计算技术研究所,北京100083

出　　处：《计算机测量与控制》2024年第2期78-84,共7页Computer Measurement &Control

摘　　要：航空图像中目标的检测是当前研究的热点之一,高效、准确的探测在军事和民用领域具有很高的价值;但由于高空环境复杂和空中目标尺度形状多变,不同用途的飞行器进行改装和涂装使得空中目标在检测中难度较大;所以提出了一种改进的一阶端到端的空中目标检测算法;算法采用DATE-FCOS为基本框架,用CIoU替代GIoU加入到边界框回归损失函数中,并在此基础上,利用可形变卷积模块对其骨干网络进行了改进并且在FPN结构之后加入CBAM模块;通过实际实验测试,所提方法在FGVC aircraft数据集上提高了检测的平均检测精度,达到77.8%,对比原模型提升11%,满足空中目标检测的应用。Target detection in aerial images is one of the current research hotspots,and efficient and accurate detection has high value in military and civilian fields.However,due to the complex high-altitude environment and the variable scale and shape of air targets,the modification and coating of aircraft for different purposes make it difficult to detect air targets.Therefore,an improved first-order end-to-end air target detection algorithm is proposed.The algorithm adopts dual assignment for end-to-end fully convolutional one-stage object detection(DATE-FCOS)as the basic framework,replaces the generalizedi intersection over union(GIoU)with the complete intersection over union(CIoU),and adds it to the bounding box regression loss function.On this basis,the deformable convolutional module is used to improve its backbone network and add the convolutional block attention module(CBAM)after the FPN structure.Through practical experimental tests,the proposed method improves the average detection accuracy of the fine-grained visual cassification of aircraft(FGVC)aircraft dataset by 77.8%,and the average detection accuracy of the proposed method is 11%higher than that of the original model,which meets the application of aerial target detection.

关 键 词：目标检测 FCOS 空中目标 CIoU 可形变卷积 注意力机制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]