《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 針對(duì)遙感影像的MSA-YOLO儲(chǔ)油罐目標(biāo)檢測(cè)
針對(duì)遙感影像的MSA-YOLO儲(chǔ)油罐目標(biāo)檢測(cè)
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(guó)成3
1.長(zhǎng)光衛(wèi)星技術(shù)股份有限公司,,吉林 長(zhǎng)春130000; 2.吉林省衛(wèi)星遙感應(yīng)用技術(shù)重點(diǎn)實(shí)驗(yàn)室,,吉林 長(zhǎng)春130000,; 3.吉林大學(xué) 材料科學(xué)與工程學(xué)院,吉林 長(zhǎng)春130000
摘要: 原油作為一種重要的戰(zhàn)略物資,,在我國(guó)經(jīng)濟(jì)和軍事等多個(gè)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(jìn)行優(yōu)化,,并基于以吉林一號(hào)光學(xué)遙感衛(wèi)星影像為主的遙感圖像數(shù)據(jù)集進(jìn)行實(shí)驗(yàn),,對(duì)特定監(jiān)控區(qū)域內(nèi)的儲(chǔ)油罐進(jìn)行識(shí)別與分類。算法優(yōu)化內(nèi)容包括:為簡(jiǎn)化儲(chǔ)油罐監(jiān)測(cè)模型同時(shí)保證模型的效率,,對(duì)YOLOv4的網(wǎng)絡(luò)結(jié)構(gòu)中的多尺度識(shí)別模塊進(jìn)行修剪,;使用k-means++聚類算法進(jìn)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(jìn)一步提升推理速度和準(zhǔn)確度,。實(shí)驗(yàn)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(shí),,MSA-YOLO算法在多種通用目標(biāo)識(shí)別算法進(jìn)行的對(duì)比實(shí)驗(yàn)中均體現(xiàn)出了更高效的特點(diǎn)。MSA-YOLO算法對(duì)儲(chǔ)油罐進(jìn)行準(zhǔn)確且實(shí)時(shí)的識(shí)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(hào): TP75
文獻(xiàn)標(biāo)識(shí)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(duì)遙感影像的MSA-YOLO儲(chǔ)油罐目標(biāo)檢測(cè)[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(lái),,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(biāo)識(shí)別取得了大量成果。其中,,對(duì)地表自然形成或人造物體進(jìn)行識(shí)別一直是從業(yè)人員的關(guān)注重點(diǎn)之一,。儲(chǔ)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(chǔ)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(chǔ)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(yáng)高度角和內(nèi)外陰影參數(shù),可以對(duì)外浮頂儲(chǔ)油罐的滿油率進(jìn)行估算,,通過(guò)滿油率數(shù)據(jù)在能源期貨價(jià)格的預(yù)測(cè)模型中進(jìn)行回歸分析,,不但可以為能源期貨交易機(jī)構(gòu)提供參考,還能對(duì)我國(guó)原油的采購(gòu)及存儲(chǔ)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(shí)現(xiàn)固定頂和外浮頂儲(chǔ)油罐的高效識(shí)別與分類。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/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(guó)成3

(1.長(zhǎng)光衛(wèi)星技術(shù)股份有限公司,吉林 長(zhǎng)春130000,;

2.吉林省衛(wèi)星遙感應(yīng)用技術(shù)重點(diǎn)實(shí)驗(yàn)室,,吉林 長(zhǎng)春130000;

3.吉林大學(xué) 材料科學(xué)與工程學(xué)院,,吉林 長(zhǎng)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。