基于多尺度特征融合的地理测绘影像目标检测
Target Detection of Geographic Mapping Image Based on Multi-scale Feature Fusion
李睿 1李亚洲 1赵建文 1周卫波1
作者信息
- 1. 国网山东省电力公司建设公司,山东 济南 250000
- 折叠
摘要
为了提高对地理测绘目标的检测准确度,设计了基于多尺度特征融合的地理测绘影像目标检测方法.初步提取地理测绘遥感影像的边缘信息,并计算其边缘密度与边缘分布情况,通过增强边缘信息实现对遥感影像的预处理,得到更明确的影像边缘信息;利用梯度采样法建立下降金字塔影像,并融合多尺度特征,为后续的目标提取提供更准确、特征更明显的信息;根据特征融合结果,采用深度卷积网络实现对地理测绘影像目标的有效检测.结果表明,应用该方法,检测结果的准确率、召回率和F1 分数数值均较高,检测耗时也维持在较低的数值范围,该方法可明显提高目标检测效果.
Abstract
In order to improve the detection accuracy of geographic mapping targets,a target detection method of geographic mapping images based on multi-scale feature fusion was designed.The edge infor-mation of the remote sensing image of geographical mapping was preliminarily extracted,and its edge density and edge distribution were calculated.Through enhancing the edge information,the remote sens-ing image was preprocessed to obtain more clear image edge information.Gradient sampling method was used to establish the descending pyramid image to provide more accurate and distinct information for sub-sequent target extraction by integrating multi-scale feature.According to the feature fusion results,the deep convolution network was used to effectively detect the geographic mapping image objects.The exper-imental results showed that the accuracy,recall and F1 score of the detection results were high after the application of this method,and the detection time was also maintained in a lower numerical range,indi-cating that the method significantly improved the detection effect for targets.
关键词
目标检测/地理测绘影像/边缘信息/多尺度特征/深度卷积网络/检测耗时Key words
target detection/geographic mapping image/edge information/multi-scale feature/deep convolution network/detection time引用本文复制引用
基金项目
山东省电力公司科技项目(520632220002)
出版年
2024
NETL
NSTL
万方数据