《電子技術應用》
您所在的位置:首頁 > 其他 > 設計應用 > 基于YOLOv7-RS的遙感圖像目標檢測研究
基于YOLOv7-RS的遙感圖像目標檢測研究
網(wǎng)絡安全與數(shù)據(jù)治理
梁琦1,2,楊曉文2,3,4
1 武警山西總隊參謀部,山西太原030012;2 中北大學計算機科學與技術學院,山西太原030051;3 機器視覺與虛擬現(xiàn)實山西省重點實驗室,山西太原030051; 4 山西省視覺信息處理及智能機器人工程研究中心,山西太原030051
摘要: 針對遙感圖像目標檢測過程中存在的背景復雜、目標特征不明顯、小目標排列密集的問題,基于YOLOv7算法,提出了一種改進的遙感圖像目標檢測算法YOLOv7-RS(YOLOv7 Remote Sensing),提高了遙感圖像的目標檢測精度。首先,向特征提取網(wǎng)絡中融合SimAM減少背景噪聲的干擾;其次,提出了D ELAN網(wǎng)絡增強遙感目標的特征提取能力;再次,利用SIOU損失函數(shù)以提高算法模型的收斂速度;最后,優(yōu)化了正負樣本分配策略,改善了遙感圖像中小目標密集排列時的漏檢問題。實驗結果表明,YOLOv7-RS在NWPU VHR 10和DOTA數(shù)據(jù)集上的mAP達到95.4%和74.1%,相較于其他主流算法有了明顯提升。
中圖分類號:TP391文獻標識碼:ADOI:10.19358/j.issn.2097-1788.2024.01.005
引用格式:梁琦,楊曉文. 基于YOLOv7-RS的遙感圖像目標檢測研究[J].網(wǎng)絡安全與數(shù)據(jù)治理,2023,43(1):33-41.
Research on object detection in remote sensing image based on YOLOv7-RS
Liang Qi 1,2,Yang Xiaowen 2,3,4
1 General Staff of Shanxi PAP, Taiyuan 030012, China; 2 College of Computer Science and Technology, North University of China, Taiyuan 030051, China;3 Shanxi Key Laboratory of Machine Vision and Virtual Reality, Taiyuan 030051, China; 4 Shanxi Province′s Vision Information Processing and Intelligent Robot Engineering Research Center, Taiyuan 030051, China
Abstract: Aiming at the problems of complex background, obscure object features and dense array of small targets in remote sensing image target detection, we propose an improved remote sensing image target detection algorithm Yolov7-RS (Yolov7 Remote Sensing) based on the YOLOv7 algorithm, which improves the target detection accuracy of remote sensing image. Firstly, SimAM is integrated into feature extraction network to reduce the interference of background noise. Secondly, D-ELAN network enhanced feature extraction capability of remote sensing objects is proposed. Thirdly, SIOU loss function is used to improve the convergence rate of the algorithm model. Finally, the allocation strategy of positive and negative samples is optimized to improve the problem of missing detection when small objects are densely arranged in remote sensing images. Experimental results show that the mAP of YOLOv7-RS on NWPU VHR 10 data sets and DOTA data sets reaches 95.4% and 74.1%, which is significantly improved compared with other mainstream algorithms.
Key words : remote sensing image; target detection; YOLOv7-RS; SimAM; D-ELAN; SIOU

引言

遙感圖像目標檢測任務旨在從復雜多樣的遙感圖像中提取用戶關注的目標,并對其進行位置和類別的標注?;谶b感圖像的目標檢測廣泛應用于城市交通[1]、應急響應[2]和國防軍事[3-4]等方面。如何在海量的遙感圖像中精確識別并定位目標仍是現(xiàn)階段研究的重點。由于遙感圖像與自然圖像的成像方式不同,遙感目標尺度差異大而且具有旋轉不變性,加之遙感圖像背景復雜多樣,使得遙感圖像的目標檢測任務更加具有挑戰(zhàn)性。因此提高遙感圖像的目標檢測精度有著重要的研究意義。隨著卷積神經(jīng)網(wǎng)絡的發(fā)展,當前基于深度學習的目標檢測算法主要分為雙階段目標檢測和單階段目標檢測。YOLO系列算法是典型的單階段目標檢測算法。YOLOv1[5]在2015年首次提出來,有效解決了兩階段檢測網(wǎng)絡推理速度慢的問題。


作者信息:

梁琦1,2,楊曉文2,3,4

(1 武警山西總隊參謀部,山西太原030012;2 中北大學計算機科學與技術學院,山西太原030051;

3 機器視覺與虛擬現(xiàn)實山西省重點實驗室,山西太原030051;

4 山西省視覺信息處理及智能機器人工程研究中心,山西太原030051)


文章下載地址:http://ihrv.cn/resource/share/2000005889


weidian.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權禁止轉載。