首页|基于改进YOLOX的遥感目标检测算法

基于改进YOLOX的遥感目标检测算法

扫码查看
遥感目标检测是环境监测、电路巡检等领域中的一个重要的环节.针对遥感图像存在的目标尺度差异大、目标模糊、背景复杂度高等难点,提出了一种基于YOLOX的遥感目标检测算法.首先,提出区域上下文聚合模块,利用不同扩张率的空洞卷积扩大感受野,获取多尺度上下文信息,从而有利于小目标的检测;其次,提出特征融合模块,采用两种不同的尺度变换模块实现对不同尺度特征的融合,从而充分融合浅层位置信息与深层语义信息,提高网络对不同尺度目标的检测性能;最后在多尺度特征融合网络部分引入特征增强模块,并将其与注意力机制CAS[CA(coordinate attention)+SimAM(simple parameter-free attention module)]结合,使网络更加关注目标信息,忽略复杂背景的干扰,同时,将浅层特征层与深层检测层进行特征融合,防止由特征信息丢失造成的预测端检测性能降低.实验结果表明:改进后的算法在DIOR和RSOD遥感数据集上分别取得了 73.87%和 96.22%的检测精度,与原YOLOX算法相比检测精度分别提高了 4.08和1.34个百分点;与其他先进算法相比,改进后的算法在检测精度与检测速度上都具有一定的优越性.
Object Detection Algorithm in Remote Sensing Images Based on Improved YOLOX
Remote sensing target detection is an important aspect in the fields of environmental monitoring and circuit patrol.A remote sensing target detection algorithm based on YOLOX is proposed for the difficulties of remote sensing images with large target scale differences,blurred targets and high background complexity.First,a regional context aggregation module is proposed to expand the perceptual field using the dalited convolutions with different expansion rates to obtain multi-scale contextual information,which is beneficial to the detection of the small targets.Second,the feature fusion module is proposed,and two different scale transformation modules are used to achieve the fusion of features at different scales,fully fusing shallow location information with deep semantic information to improve the detection performance of the network for targets at different scales.Finally,a feature enhancement module is introduced to the multi-scale feature fusion network part and combined with the attention mechanism CAS[CA(coordinate attention)with SimAM(simple parameter-free attention module)]to make the network pay more attention to the target information and ignore the interference of complex background,while the shallow feature layer is fused with the deep detection layer for feature fusion to prevent the low detection performance affected by the loss of feature information at the prediction end.The experimental results show that the improved algorithm achieves 73.87%and 96.22%detection accuracy on DIOR and RSOD remote sensing datasets,which is 4.08 and 1.34 percentage points higher than the original YOLOX algorithm,and has superiority in both detection accuracy and detection speed compared with other advanced algorithms.

object detectionYOLOXfeature fusionattention mechanismregional context

胡昭华、李昱辉

展开 >

南京信息工程大学电子与信息工程学院,江苏 南京 210044

南京信息工程大学江苏省大气环境与装备技术协同创新中心,江苏 南京 210044

目标检测 YOLOX 特征融合 注意力机制 区域上下文

国家自然科学基金江苏省自然科学基金

61601230BK20141004

2024

激光与光电子学进展
中国科学院上海光学精密机械研究所

激光与光电子学进展

CSTPCD北大核心
影响因子:1.153
ISSN:1006-4125
年,卷(期):2024.61(12)