《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 其他 > 設(shè)計應(yīng)用 > 針對遙感影像的MSA-YOLO儲油罐目標檢測
針對遙感影像的MSA-YOLO儲油罐目標檢測
2022年電子技術(shù)應(yīng)用第11期
李 想1,2,特日根1,2,趙宇恒1,2,陳文韜1,2,徐國成3
1.長光衛(wèi)星技術(shù)股份有限公司,吉林 長春130000; 2.吉林省衛(wèi)星遙感應(yīng)用技術(shù)重點實驗室,吉林 長春130000; 3.吉林大學(xué) 材料科學(xué)與工程學(xué)院,吉林 長春130000
摘要: 原油作為一種重要的戰(zhàn)略物資,在我國經(jīng)濟和軍事等多個領(lǐng)域均起到重要作用。提出一種算法MSA-YOLO(MultiScale Adaptive YOLO),該算法在YOLOv4算法的基礎(chǔ)上進行優(yōu)化,并基于以吉林一號光學(xué)遙感衛(wèi)星影像為主的遙感圖像數(shù)據(jù)集進行實驗,對特定監(jiān)控區(qū)域內(nèi)的儲油罐進行識別與分類。算法優(yōu)化內(nèi)容包括:為簡化儲油罐監(jiān)測模型同時保證模型的效率,對YOLOv4的網(wǎng)絡(luò)結(jié)構(gòu)中的多尺度識別模塊進行修剪;使用k-means++聚類算法進行初始錨框的選取,使模型加速收斂;使用基于CIoU-NMS的優(yōu)化,進一步提升推理速度和準確度。實驗結(jié)果表明,與YOLOv4相比,MSA-YOLO模型參數(shù)數(shù)量減少25.84%;模型尺寸減少62.13%;在Tesla V100的GPU環(huán)境下,模型的訓(xùn)練速度提升6 s/epoch,推理速度提升15.76 F/s;平均精度為95.65%。與此同時,MSA-YOLO算法在多種通用目標識別算法進行的對比實驗中均體現(xiàn)出了更高效的特點。MSA-YOLO算法對儲油罐進行準確且實時的識別具有通用可行性,可為遙感數(shù)據(jù)在能源期貨領(lǐng)域提供技術(shù)參考。
中圖分類號: TP75
文獻標識碼: A
DOI:10.16157/j.issn.0258-7998.223191
中文引用格式: 李想,特日根,趙宇恒,等. 針對遙感影像的MSA-YOLO儲油罐目標檢測[J].電子技術(shù)應(yīng)用,2022,48(11):24-32,40
英文引用格式: Li Xiang,Te Rigen,Zhao Yuheng,et al. MSA-YOLO oil storage tank target detection for remote sensing images[J]. Application of Electronic Technique,2022,48(11):24-32,40
MSA-YOLO oil storage tank target detection for remote sensing images
Li Xiang1,2,Te Rigen1,2,Zhao Yuheng1,2,Chen Wentao1,2,Xu Guocheng3
1.Chang Guang Satellite Technology Co.,Ltd.,Changchun 130000,China; 2.Main Laboratory of Satellite Remote Sensing Technology of Jilin Province,Changchun 130000,China; 3.School of Materials Science and Engineering,Jilin University,Changchun 130000,China
Abstract: Crude oil, as an important strategic material, plays an important role in many fields such as my country′s economy and military. This paper proposes an algorithm MSA-YOLO(MultiScale Adaptive YOLO), which is optimized on the basis of the YOLOv4 algorithm, and is experimented based on the remote sensing image dataset mainly based on Jilin-1 optical remote sensing satellite images,to make identification and classification of oil storage tanks. The algorithm optimization contents include: in order to simplify the oil storage tank monitoring model and ensure the efficiency of the model, prune the multi-scale identification module in the network structure of YOLOv4; use the k-means++ clustering algorithm to select the initial anchor frame to accelerate the convergence of the model;use CIoU-NMS-based optimization to further improve inference speed and accuracy. The experimental results show that compared with YOLOv4, the number of parameters of MSA-YOLO model is reduced by 25.84%; the model size is reduced by 62.13%; in the GPU environment of Tesla V100, the training speed of the model is increased by 6 s/epoch, and the inference speed is increased by 15.76 F/s; the average accuracy is 95.65%. At the same time, the MSA-YOLO algorithm shows more efficient characteristics in the comparative experiments of various general target recognition algorithms. The MSA-YOLO algorithm has universal feasibility for accurate and real-time identification of oil storage tanks, and can provide technical reference for remote sensing data in the field of energy futures.
Key words : computer vision;target recognition;deep learning;YOLO;sorage tank detection

0 引言

    近年來,隨著高分辨率光學(xué)衛(wèi)星遙感影像處理技術(shù)的快速發(fā)展,基于遙感影像的目標識別取得了大量成果。其中,對地表自然形成或人造物體進行識別一直是從業(yè)人員的關(guān)注重點之一。儲油罐是在石油、天然氣等石化行業(yè)中使用的設(shè)備,用于儲存在環(huán)境溫度下為液態(tài)的原油或者其他化工產(chǎn)品度下為液態(tài)的原油或者其他化工產(chǎn)品。按照儲油罐的不同用途,分為固定頂型和外浮頂型。利用遙感影像的太陽高度角和內(nèi)外陰影參數(shù),可以對外浮頂儲油罐的滿油率進行估算,通過滿油率數(shù)據(jù)在能源期貨價格的預(yù)測模型中進行回歸分析,不但可以為能源期貨交易機構(gòu)提供參考,還能對我國原油的采購及存儲等起到指導(dǎo)作用。而在上述工作中,首要任務(wù)是在高分辨率遙感影像中實現(xiàn)固定頂和外浮頂儲油罐的高效識別與分類。




本文詳細內(nèi)容請下載:http://ihrv.cn/resource/share/2000005000。




作者信息:

李  想1,2,特日根1,2,趙宇恒1,2,陳文韜1,2,徐國成3

(1.長光衛(wèi)星技術(shù)股份有限公司,吉林 長春130000;

2.吉林省衛(wèi)星遙感應(yīng)用技術(shù)重點實驗室,吉林 長春130000;

3.吉林大學(xué) 材料科學(xué)與工程學(xué)院,吉林 長春130000)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。