摘要
高分辨率的遥感图像与普通图像相比,遥感图像目标具有方向多样性和尺度变化较大等特点。针对遥感图像目标检测问题,提出一种R-CenterNet遥感图像目标检测算法。首先,对CenterNet网络重新设计,在网络结构中加入旋转因子为检测框提供角度信息;其次,增加网络深度,提高网络检测性能;最后,为聚合不同区域的信息,进一步提取目标的多尺度信息,提出一种将目标特征注意力信息与多尺度池化信息相融合的注意力金字塔池化模块。实验结果表明R-CenterNet的检测结果比原始CenterNet提升了8%的平均精度值(mAP),具有更好的检测效果。
Compared with ordinary images,high-resolution remote sensing images have the characteristics of diverse directions and large scale changes.Aiming at the problem of remote sensing image object detection,this paper proposes an R-CenterNet remote sensing image object detection algorithm.First,redesign the CenterNet network and add a rotation factor to the network structure to provide angle information for the detection frame;secondly,increase the network depth and improve the network detection performance;finally,to aggregate the information of different regions,further extract the multi-scale information of the object.This paper proposes an attention pyramid pooling module that combines the object feature attention information with multi-scale pooling information.The experimental results show that R-CenterNet has a better detection effect,and the mAP value is increased by 8%compared with the original CenterNet detection results.
作者
王明阳
王江涛
刘琛
Wang Mingyang;Wang Jiangtao;Liu Chen(School of Physics and Electronic Information,Huaibei Normal University,Huaibei 235000,China;Anhui Key Laboratory of Pollutant Sensitive Materials and Environmental Remediation,Huaibei 235000,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2021年第6期102-108,共7页
Journal of Electronic Measurement and Instrumentation
基金
国家自然科学基金项目(61976101)
安徽省高校自然科学研究重大项目(KJ2018ZD038)
安徽省高校自然科学研究一般项目(KJ2019B15)资助。
关键词
遥感图像
目标检测
深度学习
remote sensing image
object detection
deep learning