《电子技术应用》
您所在的位置:首页 > 其他 > 设计应用 > 针对遥感影像的MSA-YOLO储油罐目标检测
针对遥感影像的MSA-YOLO储油罐目标检测
2022年电子技术应用第11期
李 想1,2,特日根1,2,赵宇恒1,2,陈文韬1,2,徐国成3
1.长光卫星技术股份有限公司,吉林 长春130000; 2.吉林省卫星遥感应用技术重点实验室,吉林 长春130000; 3.吉林大学 材料科学与工程学院,吉林 长春130000
摘要: 原油作为一种重要的战略物资,在我国经济和军事等多个领域均起到重要作用。提出一种算法MSA-YOLO(MultiScale Adaptive YOLO),该算法在YOLOv4算法的基础上进行优化,并基于以吉林一号光学遥感卫星影像为主的遥感图像数据集进行实验,对特定监控区域内的储油罐进行识别与分类。算法优化内容包括:为简化储油罐监测模型同时保证模型的效率,对YOLOv4的网络结构中的多尺度识别模块进行修剪;使用k-means++聚类算法进行初始锚框的选取,使模型加速收敛;使用基于CIoU-NMS的优化,进一步提升推理速度和准确度。实验结果表明,与YOLOv4相比,MSA-YOLO模型参数数量减少25.84%;模型尺寸减少62.13%;在Tesla V100的GPU环境下,模型的训练速度提升6 s/epoch,推理速度提升15.76 F/s;平均精度为95.65%。与此同时,MSA-YOLO算法在多种通用目标识别算法进行的对比实验中均体现出了更高效的特点。MSA-YOLO算法对储油罐进行准确且实时的识别具有通用可行性,可为遥感数据在能源期货领域提供技术参考。
中图分类号: TP75
文献标识码: A
DOI:10.16157/j.issn.0258-7998.223191
中文引用格式: 李想,特日根,赵宇恒,等. 针对遥感影像的MSA-YOLO储油罐目标检测[J].电子技术应用,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

    近年来,随着高分辨率光学卫星遥感影像处理技术的快速发展,基于遥感影像的目标识别取得了大量成果。其中,对地表自然形成或人造物体进行识别一直是从业人员的关注重点之一。储油罐是在石油、天然气等石化行业中使用的设备,用于储存在环境温度下为液态的原油或者其他化工产品度下为液态的原油或者其他化工产品。按照储油罐的不同用途,分为固定顶型和外浮顶型。利用遥感影像的太阳高度角和内外阴影参数,可以对外浮顶储油罐的满油率进行估算,通过满油率数据在能源期货价格的预测模型中进行回归分析,不但可以为能源期货交易机构提供参考,还能对我国原油的采购及存储等起到指导作用。而在上述工作中,首要任务是在高分辨率遥感影像中实现固定顶和外浮顶储油罐的高效识别与分类。




本文详细内容请下载:https://www.chinaaet.com/resource/share/2000005000




作者信息:

李  想1,2,特日根1,2,赵宇恒1,2,陈文韬1,2,徐国成3

(1.长光卫星技术股份有限公司,吉林 长春130000;

2.吉林省卫星遥感应用技术重点实验室,吉林 长春130000;

3.吉林大学 材料科学与工程学院,吉林 长春130000)




wd.jpg

此内容为AET网站原创,未经授权禁止转载。