Please wait a minute...
Remote Sensing for Natural Resources    2022, Vol. 34 Issue (4) : 97-104     DOI: 10.6046/zrzyyg.2021377
Classification and detection of radiation anomalies in Chinese optical satellite images by integrating multi-scale features
TAN Hai1(), ZHANG Rongjun1,2(), FAN Wenfeng1, ZHANG Yifang1, XU Hang1
1. Land Satellite Remote Sensing Application Center, MNR, Beijing 100048, China
2. School of Geomatics, Liaoning Technical University, Fuxin 123000, China
Download: PDF(4689 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

With the rapid development of China’s aerospace remote sensing industry, the types of Chinese civilian optical remote sensing satellites have continuously increased. Consequently, the data volume of optical images shows a leapfrogging growth. This brings huge challenges to the daily quality inspection of the calibration products for optical remote sensing image sensors. The inspection of image radiation anomalies is a key step in image quality inspection. However, the inspection faces many problems such as a lack of automated inspection technical capabilities, high manual participation, and low efficiency. To address the above problems, this study proposed a deep learning network model that integrates multi-scale features for the classification and detection of radiation anomaly data. This network model employed a hollow space convolutional pooling pyramid based on the EfficientNet-B0 model. The features of radiation anomaly data on different scales were collected by setting different expansion rates and then processed through channel splicing, pooling, and convolution. Furthermore, they were merged with the features extracted using the EfficientNet-B0 model to improve the precision of the classification and detection model. The experimental results show that the proposed classification and detection model has a higher classification precision for the detection and classification of radiation anomaly data of optical images than other models. Therefore, this study will help to improve the automation level of radiation quality inspection of remote sensing images.

Keywords EfficientNet      deep learning      radiation anomaly      classification detection     
ZTFLH:  TP79  
Issue Date: 27 December 2022
E-mail this article
E-mail Alert
Articles by authors
Rongjun ZHANG
Wenfeng FAN
Yifang ZHANG
Hang XU
Cite this article:   
Hai TAN,Rongjun ZHANG,Wenfeng FAN, et al. Classification and detection of radiation anomalies in Chinese optical satellite images by integrating multi-scale features[J]. Remote Sensing for Natural Resources, 2022, 34(4): 97-104.
URL:     OR
Fig.1  Examples of CCD stitching problem data
Fig.2  Examples of garbled problem data
Fig.3  Examples of tap problem data
Fig.4  Examples of missing problem data
Fig.5  Examples of color cast problem data
Fig.6  EfficientNet-B0 structure diagram
Fig.7  Improved EfficientNet-B0 network model
Fig.8  Receptive field size of dilated convolution
Fig.9  Change curve of overal classification accuracy and loss value during training
分类方法 CCD拼接 乱码 抽头 缺失 偏色 正常
本文方法 0.970 0.952 0.968 0.975 0.962 0.973
EfficientNet-B0 0.965 0.946 0.952 0.961 0.957 0.968
ResNet 0.901 0.925 0.913 0.930 0.912 0.940
VGG16 0.908 0.944 0.910 0.903 0.932 0.937
GoogLeNet 0.937 0.928 0.925 0.918 0.929 0.930
Tab.1  Comparison of classification accuracy of different models for different problems
分类方法 Precisionmacro Recallmacro F1
本文方法 0.193 3 0.191 6 0.192 4
EfficientNet-B0 0.190 1 0.188 9 0.187 5
ResNet 0.180 3 0.182 0 0.182 5
VGG16 0.183 9 0.183 4 0.183 7
GoogLeNet 0.185 6 0.184 5 0.185 0
Tab.2  Comprehensive performance comparison of different classification models
[1] 李德仁. 论21世纪遥感与GIS的发展[J]. 武汉大学学报(信息科学版), 2003, 28(2):127-131.
[1] Li D R. Towards the development of remote sensing and GIS in the 21st century[J]. Geomatics and Information Science of Wuhan University, 2003, 28(2):127-131.
[2] 梁晓珩, 梁秀娟, 柯蓓. 我国遥感卫星系统发展进阶路径探讨[J]. 航天器环境工程, 2021, 38(1):100-105.
[2] Liang X H, Liang X J, Ke B. The development path of romote sensing satellite system in China[J]. Spacecraft Environment Engineering, 2021, 38(1):100-105.
[3] 廖小罕. 中国对地观测20年科技进步和发展[J]. 遥感学报, 2021, 25(1):267-275.
[3] Liao X H. Scientific and technological progress and development prospect of the earth observation in China in the past 20 years[J]. National Remote Sensing Bulletin, 2021, 25(1):267-275.
[4] 孙伟伟, 杨刚, 陈超, 等. 中国地球观测遥感卫星发展现状及文献分析[J]. 遥感学报, 2020, 24(5):479-510.
[4] Sun W W, Yang G, Chen C, et al. Development status and literature analysis of China’s earth observation remote sensing satellites[J]. Journal of Remote Sensing, 2020, 24(5):479-510.
[5] 许和鱼, 张黎明, 李鑫, 等. 基于太阳漫反射板线阵CCD相对辐射定标方法研究[J]. 光学学报, 2020, 40(6):179-187.
[5] Xu H Y, Zhang L M, Li X, et al. A relative radiometric calibration method based on solar diffuser research for a linear array CCD detector[J]. Acta Optica Sinica, 2020, 40(6):179-187.
[6] 曹红业, 张天棋. 基于辐射传输模型的高分二号影像大气校正方法研究[J]. 红外技术, 2020, 42(6):534-541.
[6] Cao H Y, Zhang T Q. Atmospheric correction algorithm for GF-2 image based on a radiative transfer model[J]. Infrared Technology, 2020, 42(6):534-541.
[7] He K, Zhang X, Ren S, et al. Deep residual learning for image reco-gnition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.
[8] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]// The 3rd International Conference on Learning Representations (ICLR2015), 2015:1-14.
[9] 胡杰, 张莹, 谢仕义. 国产遥感影像分类技术应用研究进展综述[J]. 计算机工程与应用, 2021, 57(3):1-13.
doi: 10.3778/j.issn.1002-8331.2007-0101
[9] Hu J, Zhang Y, Xie S Y. Summary of research progress on application of domestic remote sensing image classification technology[J]. Computer Engineering and Applications, 2021, 57(3):1-13.
doi: 10.3778/j.issn.1002-8331.2007-0101
[10] 周培诚, 程塨, 姚西文, 等. 高分辨率遥感影像解译中的机器学习范式[J]. 遥感学报, 2021, 25(1):182-197.
[10] Zhou P C, Cheng G, Yao X W, et al. Machine learning paradigms in high-resolution remote sensing image interpretation[J]. National Remote Sensing Bulletin, 2021, 25(1):182-197.
[11] 谭琨, 王雪, 杜培军. 结合深度学习和半监督学习的遥感影像分类进展[J]. 中国图象图形学报, 2019, 24(11):1823-1841.
[11] Tan K, Wang X, Du P J. Research progress of the remote sensing classification combining deep learning and semi-supervised learning[J]. Journal of Image and Graphics, 2019, 24(11):1823-1841.
[12] 王智敏, 谭海, 郭正胜, 等. 基于CNN的高分辨率遥感影像多级云检测[J]. 测绘与空间地理息, 2020, 43(9):139-142,145,151.
[12] Wang Z M, Tan H, Guo Z S, et al. Multi-level cloud detection in high-resolution remote sensing images based on CNN[J]. Geomatics and Spatial Information Technology, 2020, 43(9):139-142,145,151.
[13] 蔡之灵, 翁谦, 叶少珍, 等. 基于Inception-V3模型的高分遥感影像场景分类[J]. 国土资源遥感, 2020, 32(3):80-89.doi:10.6046/gtzyyg.2020.03.11.
doi: 10.6046/gtzyyg.2020.03.11
[13] Cai Z L, Weng Q, Ye S Z, et al. Remote sensing image scene classification based on Inception-V3[J]. Remote Sensing for Land and Resources, 2020, 32(3):80-89.doi:10.6046/gtzyyg.2020.03.11.
doi: 10.6046/gtzyyg.2020.03.11
[14] Tan M, Le Q V. EfficientNet:Rethinking model scaling for convolutional neural networks[C]// International Conference on Machine Learning.Long Beach, USA:ICML, 2019:6105-6114.
[15] Wang K R, Yu X B. MobileNet and EfficientNet demonstration on Google landmark recognition dataset[J]. International Core Journal of Engineering, 2021, 7(3):313-319.
[16] 张敏, 赵雪青. 基于EfficientNets的织物疵点图像分类方法[J]. 纺织高校基础科学学报, 2020, 33(4):64-70.
[16] Zhang M, Zhao X Q. EfficientNets-based method for fabric defect image classification[J]. Basic Sciences Journal of Textile Universities, 2020, 33(4):64-70.
[17] 赵鹏菲, 黄丽佳. 一种基于EfficientNet与BiGRU的多角度SAR图像目标识别方法[J]. 雷达学报, 2021, 10(6):895-904.
[17] Zhao P F, Huang L J. Target recognition method for multi-aspect synthetic aperture Radar images based on EfficientNet and BiGRU[J]. Journal of Radars, 2021, 10(6):895-904.
[18] Duong L T, Nguyen P T, Sipio C D, et al. Automated fruit recognition using EfficientNet and MixNet[J]. Computers and Electronics in Agriculture, 2020, 171:105326.
doi: 10.1016/j.compag.2020.105326 url:
[19] 宝音图, 刘伟, 牛朝阳, 等. 联合集成学习与EfficientNet的光学遥感图像场景分类[J]. 计算机工程, 2021, 47(10):226-235.
[19] Bao Y T, Liu W, Niu C Y, et al. Scene classification of optical remote sensing images joint ensemble learning and EfficientNet[J]. Computer Engineering, 2021, 47(10):226-235.
[20] Chen L C, Papandreou G, Kokkinos I, et al. DeepLab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848.
doi: 10.1109/TPAMI.2017.2699184 url:
[1] LIU Li, DONG Xianmin, LIU Juan. A performance evaluation method for semantic segmentation models of remote sensing images considering surface features[J]. Remote Sensing for Natural Resources, 2023, 35(3): 80-87.
[2] NIU Xianghua, HUANG Wei, HUANG Rui, JIANG Sili. A high-fidelity method for thin cloud removal from remote sensing images based on attentional feature fusion[J]. Remote Sensing for Natural Resources, 2023, 35(3): 116-123.
[3] ZHANG Xian, LI Wei, CHEN Li, YANG Zhaoying, DOU Baocheng, LI Yu, CHEN Haomin. Research progress and prospect of remote sensing-based feature extraction of opencast mining areas[J]. Remote Sensing for Natural Resources, 2023, 35(2): 25-33.
[4] DIAO Mingguang, LIU Yong, GUO Ningbo, LI Wenji, JIANG Jikang, WANG Yunxiao. Mask R-CNN-based intelligent identification of sparse woods from remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(2): 97-104.
[5] QIU Lei, ZHANG Xuezhi, HAO Dawei. VideoSAR moving target detection and tracking algorithm based on deep learning[J]. Remote Sensing for Natural Resources, 2023, 35(2): 157-166.
[6] ZHANG Ke, ZHANG Gengsheng, WANG Ning, WEN Jing, LI Yu, YANG Jun. A forecasting method for water table depths in areas with power transmission lines based on remote sensing and deep learning models[J]. Remote Sensing for Natural Resources, 2023, 35(1): 213-221.
[7] HU Jianwen, WANG Zeping, HU Pei. A review of pansharpening methods based on deep learning[J]. Remote Sensing for Natural Resources, 2023, 35(1): 1-14.
[8] ZHAO Linghu, YUAN Xiping, GAN Shu, HU Lin, QIU Mingyu. An information extraction model of roads from high-resolution remote sensing images based on improved Deeplabv3+[J]. Remote Sensing for Natural Resources, 2023, 35(1): 107-114.
[9] LYU Yanan, ZHU Hong, MENG Jian, CUI Chengling, SONG Qiqi. A review and adaptability study of deep learning models for vehicle detection based on high-resolution remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(4): 22-32.
[10] SU Wei, LIN Yangyang, YUE Wen, CHEN Yingbiao. Identification of mariculture areas in Guangdong Province and remote sensing monitoring of their spatial and temporal changes based on the U-Net convolutional neural network[J]. Remote Sensing for Natural Resources, 2022, 34(4): 33-41.
[11] ZHANG Pengqiang, GAO Kuiliang, LIU Bing, TAN Xiong. Classification of hyperspectral images based on deep Transformer network combined with spatial-spectral information[J]. Remote Sensing for Natural Resources, 2022, 34(3): 27-32.
[12] ERPAN Anwar, MAMAT Sawut, MAIHEMUTI Balati. Recognition of cotton distribution based on GF-2 images and Unet model[J]. Remote Sensing for Natural Resources, 2022, 34(2): 242-250.
[13] SUN Yu, HUANG Liang, ZHAO Junsan, CHANG Jun, CHEN Pengdi, CHENG Feifei. High spatial resolution automatic detection of bridges with high spatial resolution remote sensing images based on random erasure and YOLOv4[J]. Remote Sensing for Natural Resources, 2022, 34(2): 97-104.
[14] WANG Huajun, GE Xiaosan. Lightweight DeepLabv3+ building extraction method from remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(2): 128-135.
[15] XUE Bai, WANG Yizhe, LIU Shuhan, YUE Mingyu, WANG Yiying, ZHAO Shihu. Change detection of high-resolution remote sensing images based on Siamese network[J]. Remote Sensing for Natural Resources, 2022, 34(1): 61-66.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech