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
