Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849335
Guangtong Sun, Xiaoyang Liu, P. Song, Hongda Jia
The Beijing plain area with serious land subsidence is selected as the study area. The data of 26 scenic Sentinel-1A in this area from January 2020 to March 2021 are processed by SBAS-InSAR technology. Through the steps of small baseline combination, differential interference processing, track refining and re leveling, SBAS inversion and geological coding, the time series cumulative settlement and homogeneous strain rate in Beijing during January 2020 to March 2021 are finally inversed, The monitoring results show that the settlement in the east of Beijing is more serious, followed by the south. The settlement develops in the form of multi center funnel, and a relatively continuous settlement area has been formed. The subsidence areas are mainly distributed in Chaoyang, Shunyi and TongZhou areas, of which Chaoyang TongZhou area has the most serious subsidence, with the maximum annual average subsidence rate of 155.9mm/y, which is consistent with the current situation of rapid construction of groundwater demand in this area. Finally, the monitoring results are compared with the existing research results, and the consistency between them is high, which verifies the reliability and accuracy of sbas-insar technology in monitoring regional settlement.
{"title":"Monitoring and analysis of land subsidence in Beijing based on SBAS-InSAR Technology","authors":"Guangtong Sun, Xiaoyang Liu, P. Song, Hongda Jia","doi":"10.1109/ICGMRS55602.2022.9849335","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849335","url":null,"abstract":"The Beijing plain area with serious land subsidence is selected as the study area. The data of 26 scenic Sentinel-1A in this area from January 2020 to March 2021 are processed by SBAS-InSAR technology. Through the steps of small baseline combination, differential interference processing, track refining and re leveling, SBAS inversion and geological coding, the time series cumulative settlement and homogeneous strain rate in Beijing during January 2020 to March 2021 are finally inversed, The monitoring results show that the settlement in the east of Beijing is more serious, followed by the south. The settlement develops in the form of multi center funnel, and a relatively continuous settlement area has been formed. The subsidence areas are mainly distributed in Chaoyang, Shunyi and TongZhou areas, of which Chaoyang TongZhou area has the most serious subsidence, with the maximum annual average subsidence rate of 155.9mm/y, which is consistent with the current situation of rapid construction of groundwater demand in this area. Finally, the monitoring results are compared with the existing research results, and the consistency between them is high, which verifies the reliability and accuracy of sbas-insar technology in monitoring regional settlement.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126394330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849323
Mengxu Zhu, Guohong Li, Wenhao Zhang
UAV remote sensing multispectral image has become more and more popular because of its high temporal and spatial resolution. However, multispectral image has the characteristics of large number of bands, large amount of data, spatial and spectral redundancy. These characteristics bring great challenges to image storage and transmission. According to the characteristics of multispectral images, an end-to-end multispectral image compression framework based on CNN is adopted. The whole framework is composed of self-encoder, quantization structure, entropy coding and rate distortion optimization. The innovation of this paper is to propose a new multi-source data preprocessing method, which uniformly converts the DN value of multispectral image into reflectivity, and the multispectral image compression framework uses 1 * 1 convolution to reduce the inter spectral redundancy of the image, self-encoder to reduce the dimension of the image, Gaussian mixture entropy coding to estimate the code rate, rate distortion optimization to jointly optimize the code rate and distortion. The experimental results show that under the same bit rate, the image compression effect of this method model is significantly better than the traditional image compression method, and the quality of the reconstructed image is significantly improved.
{"title":"Research on UAV remote sensing multispectral image compression based on CNN","authors":"Mengxu Zhu, Guohong Li, Wenhao Zhang","doi":"10.1109/ICGMRS55602.2022.9849323","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849323","url":null,"abstract":"UAV remote sensing multispectral image has become more and more popular because of its high temporal and spatial resolution. However, multispectral image has the characteristics of large number of bands, large amount of data, spatial and spectral redundancy. These characteristics bring great challenges to image storage and transmission. According to the characteristics of multispectral images, an end-to-end multispectral image compression framework based on CNN is adopted. The whole framework is composed of self-encoder, quantization structure, entropy coding and rate distortion optimization. The innovation of this paper is to propose a new multi-source data preprocessing method, which uniformly converts the DN value of multispectral image into reflectivity, and the multispectral image compression framework uses 1 * 1 convolution to reduce the inter spectral redundancy of the image, self-encoder to reduce the dimension of the image, Gaussian mixture entropy coding to estimate the code rate, rate distortion optimization to jointly optimize the code rate and distortion. The experimental results show that under the same bit rate, the image compression effect of this method model is significantly better than the traditional image compression method, and the quality of the reconstructed image is significantly improved.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114175408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849313
Xin Wang, RenZhong Yang, Xinzhu Liu
Aiming at the shortcomings of the existing remote sensing satellite data preprocessing system, such as slow speed, weak universality, poor scalability, weak automation and unfriendly interface, a visual and self customized general system for remote sensing satellite data preprocessing process based on MPI + CUDA is designed. Based on MPI + GPU, CUDA technology is used to realize the accelerated processing of various services in two levels in parallel, Greatly improve the system processing efficiency. A three-tier system architecture is adopted to solve the problem of dense coupling of the original system. The business modules of the data layer are implemented based on WCF (Windows communication foundation) to improve the scalability and portability of the system. Automatic preprocessing of satellite data based on WWF (Windows workflow foudation). The visual editing of processing flow is realized through WPF (Windows Presentation Foundation), which provides users with a friendly interactive interface.
{"title":"Research on General System of Remote Sensing Satellite Data Preprocessing Based on MPI + CUDA","authors":"Xin Wang, RenZhong Yang, Xinzhu Liu","doi":"10.1109/ICGMRS55602.2022.9849313","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849313","url":null,"abstract":"Aiming at the shortcomings of the existing remote sensing satellite data preprocessing system, such as slow speed, weak universality, poor scalability, weak automation and unfriendly interface, a visual and self customized general system for remote sensing satellite data preprocessing process based on MPI + CUDA is designed. Based on MPI + GPU, CUDA technology is used to realize the accelerated processing of various services in two levels in parallel, Greatly improve the system processing efficiency. A three-tier system architecture is adopted to solve the problem of dense coupling of the original system. The business modules of the data layer are implemented based on WCF (Windows communication foundation) to improve the scalability and portability of the system. Automatic preprocessing of satellite data based on WWF (Windows workflow foudation). The visual editing of processing flow is realized through WPF (Windows Presentation Foundation), which provides users with a friendly interactive interface.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121069565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849222
Li Chen, Xian Zhang, Wei Li, Yu Li
Recently, high spatial resolution remote sensing images have been widely used to classify in the mining area. However, the information extraction and dynamic change analysis of typical open-pit laterites nickel mine by using high spatial resolution remote sensing images is less studied. The openpit Tagaung Taung nickel mine is one of the famous laterites nickel ore in Myanmar. In this paper, based on the data of Pleiades and GF-2 image, we used the method of object-oriented classification with hierarchical multi-scale segmentation to extract ground object information and analyze the dynamic change in the Tagaung Taung nickel mine. The qualitatively and quantitatively relative analysis show that identification results with hierarchical multi-scale segmentation has better effect and the precise. The overall accuracies of Pleiades and GF-2 image are 94.24% and 89.02% respectively. Accordingly, this method is more suitable to be utilized to the information extraction of openpit laterites nickel mine. Through dynamic change analysis, the mining scale of Tagaung Taung Nickel mine continues to expand from 2015 to 2017, and the mining speed is fast. Consequently, the deposit has good resource development potential and broad development prospects in the future.
{"title":"Information Extraction with Hierarchical Multi-scale Segmentation and Dynamic Change Analysis in Myanmar Tagaung Taung Nickel Mine","authors":"Li Chen, Xian Zhang, Wei Li, Yu Li","doi":"10.1109/ICGMRS55602.2022.9849222","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849222","url":null,"abstract":"Recently, high spatial resolution remote sensing images have been widely used to classify in the mining area. However, the information extraction and dynamic change analysis of typical open-pit laterites nickel mine by using high spatial resolution remote sensing images is less studied. The openpit Tagaung Taung nickel mine is one of the famous laterites nickel ore in Myanmar. In this paper, based on the data of Pleiades and GF-2 image, we used the method of object-oriented classification with hierarchical multi-scale segmentation to extract ground object information and analyze the dynamic change in the Tagaung Taung nickel mine. The qualitatively and quantitatively relative analysis show that identification results with hierarchical multi-scale segmentation has better effect and the precise. The overall accuracies of Pleiades and GF-2 image are 94.24% and 89.02% respectively. Accordingly, this method is more suitable to be utilized to the information extraction of openpit laterites nickel mine. Through dynamic change analysis, the mining scale of Tagaung Taung Nickel mine continues to expand from 2015 to 2017, and the mining speed is fast. Consequently, the deposit has good resource development potential and broad development prospects in the future.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121850835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849268
Weiwei Cai, Bo Jiang, Xinhao Jiang
Aiming at the problem of low image resolution that easily occurs in the process of infrared images acquisition, this paper proposes a novel hierarchical distillation network to achieve infrared images super-resolution. By designing a cascaded residual distillation module, the negative impact of the over-deep network model is reduced; meanwhile, a dual-path feature fusion module is constructed to further enhance the feature expression capability of the network model. Experiments were conducted on public datasets and evaluated using two evaluation metrics, Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM). The experimental results show that the method in this paper improves 1.97 and 0.033 in PSNR and SSIM, respectively, compared with RCAN, and generates images with high definition, strong structure and rich detail information.
{"title":"Super-resolution of infrared images based on hierarchical distillation network","authors":"Weiwei Cai, Bo Jiang, Xinhao Jiang","doi":"10.1109/ICGMRS55602.2022.9849268","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849268","url":null,"abstract":"Aiming at the problem of low image resolution that easily occurs in the process of infrared images acquisition, this paper proposes a novel hierarchical distillation network to achieve infrared images super-resolution. By designing a cascaded residual distillation module, the negative impact of the over-deep network model is reduced; meanwhile, a dual-path feature fusion module is constructed to further enhance the feature expression capability of the network model. Experiments were conducted on public datasets and evaluated using two evaluation metrics, Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM). The experimental results show that the method in this paper improves 1.97 and 0.033 in PSNR and SSIM, respectively, compared with RCAN, and generates images with high definition, strong structure and rich detail information.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125180770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849389
Qin Wang, Yibin Yao, Chen Liu, Chaoqian Xu
Global Navigation Satellite System-derived Precipitable Water Vapor (GNSS-PWV) has been applied in numerous meteorological researches due to its high accuracy and all-weather support. This paper explores the coordinated variation characteristics between the PWV and actual precipitation during typhoon "Chanthu." The PWV series, from ten stations of Shanghai Continuously Operating Reference Stations (SHCORS) during Sep. 10th to 14th, 2021, were retrieved by real-time Precise Point Positioning (PPP) technology. We also collected the rainfall records from eleven meteorological stations during the same period. The results show that PWV content was significantly correlated with precipitation, i.e., PWV initially surged before rainfall, then remained stable during rain, and finally fell back to the normal level after rain. Additionally, the spatial changes of PWV could also reveal the water vapor (WV) transport path during the typhoon. It suggests that real-time PWV has the potential capacity for extreme precipitation warnings. The above findings indicate that the CORS system can equip the rainfall warning module to expand its further service field in the future.
{"title":"Coordinated Variation of Precipitable Water Vapor and Rainfall during Typhoon","authors":"Qin Wang, Yibin Yao, Chen Liu, Chaoqian Xu","doi":"10.1109/ICGMRS55602.2022.9849389","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849389","url":null,"abstract":"Global Navigation Satellite System-derived Precipitable Water Vapor (GNSS-PWV) has been applied in numerous meteorological researches due to its high accuracy and all-weather support. This paper explores the coordinated variation characteristics between the PWV and actual precipitation during typhoon \"Chanthu.\" The PWV series, from ten stations of Shanghai Continuously Operating Reference Stations (SHCORS) during Sep. 10th to 14th, 2021, were retrieved by real-time Precise Point Positioning (PPP) technology. We also collected the rainfall records from eleven meteorological stations during the same period. The results show that PWV content was significantly correlated with precipitation, i.e., PWV initially surged before rainfall, then remained stable during rain, and finally fell back to the normal level after rain. Additionally, the spatial changes of PWV could also reveal the water vapor (WV) transport path during the typhoon. It suggests that real-time PWV has the potential capacity for extreme precipitation warnings. The above findings indicate that the CORS system can equip the rainfall warning module to expand its further service field in the future.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122724682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849310
Jingyun Liu, Jun Liu
The Ice, Cloud, and Land Elevation Satellite-2(ICESat-2) is equipped with the advanced topography laser altimeter system (ATLAS). Product data has background noise due to atmospheric scattering, solar radiation, instrument noise, etc. So, data denoising is necessary before processing and applying the product data. This paper experimented with ICESat-2 land data using three methods: the K-nearest neighbor distance algorithm, DBSCAN algorithm, and DRAGANN algorithm. The experimental results show that the DRAGANN algorithm has the best accuracy. The DBSCAN algorithm is suitable for dealing with land areas with much vegetation, and the KNN algorithm is suitable for dealing with land areas with less vegetation. Different surface types greatly affect the accuracy of these methods for denoising.
{"title":"Analysis and comparison of denoising methods for photon-counting laser data","authors":"Jingyun Liu, Jun Liu","doi":"10.1109/ICGMRS55602.2022.9849310","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849310","url":null,"abstract":"The Ice, Cloud, and Land Elevation Satellite-2(ICESat-2) is equipped with the advanced topography laser altimeter system (ATLAS). Product data has background noise due to atmospheric scattering, solar radiation, instrument noise, etc. So, data denoising is necessary before processing and applying the product data. This paper experimented with ICESat-2 land data using three methods: the K-nearest neighbor distance algorithm, DBSCAN algorithm, and DRAGANN algorithm. The experimental results show that the DRAGANN algorithm has the best accuracy. The DBSCAN algorithm is suitable for dealing with land areas with much vegetation, and the KNN algorithm is suitable for dealing with land areas with less vegetation. Different surface types greatly affect the accuracy of these methods for denoising.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116497221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849254
Zequn Hu, Shaohua Jin, Gang Bian, Yang Cui
Geomagnetic daily variation is the main source of error affecting marine magnetic measurements. In this paper, the influence of the geomagnetic daily variation base value on marine magnetic measurements is theoretically analysed in relation to the characteristics of geomagnetic daily variation, and its influence on the calculation of the cross-point difference of the magnetic survey results is discussed and calculated and analysed by means of actual data. The conclusions show that when a survey area is completed by more than one cruise, the different base values of geomagnetic daily variation selected by different cruises will have an impact on the cross-point difference, thus affecting the accuracy of the marine magnetic survey results. With reasonable adjustments, the accuracy of data processing can be improved and the quality of marine magnetic measurements can be improved.
{"title":"Analysis of the effect of differences in the base value of geomagnetic daily variation on marine magnetometry","authors":"Zequn Hu, Shaohua Jin, Gang Bian, Yang Cui","doi":"10.1109/ICGMRS55602.2022.9849254","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849254","url":null,"abstract":"Geomagnetic daily variation is the main source of error affecting marine magnetic measurements. In this paper, the influence of the geomagnetic daily variation base value on marine magnetic measurements is theoretically analysed in relation to the characteristics of geomagnetic daily variation, and its influence on the calculation of the cross-point difference of the magnetic survey results is discussed and calculated and analysed by means of actual data. The conclusions show that when a survey area is completed by more than one cruise, the different base values of geomagnetic daily variation selected by different cruises will have an impact on the cross-point difference, thus affecting the accuracy of the marine magnetic survey results. With reasonable adjustments, the accuracy of data processing can be improved and the quality of marine magnetic measurements can be improved.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121874570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849329
Feng Wang, Yang Zhou
Based on the MIKE21 SW wave numerical model, taking Typhoon Talim as an example, the sensitivity analysis of the influence of wave physical processes such as bottom friction, wave breaking and wave-wave nonlinear interaction on typhoon waves is carried out. The optimal parameters are selected to simulate the wave changes in Sanmen Bay under the influence of typhoon Talim and compared with the measured data. The results show that different wave physical process parameters have certain influence on the simulation results, and the simulation results are in good agreement with the measured data. The established model has reference significance for typhoon wave prediction in Sanmen Bay.
{"title":"Numerical simulation of typhoon waves in Sanmen Bay","authors":"Feng Wang, Yang Zhou","doi":"10.1109/ICGMRS55602.2022.9849329","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849329","url":null,"abstract":"Based on the MIKE21 SW wave numerical model, taking Typhoon Talim as an example, the sensitivity analysis of the influence of wave physical processes such as bottom friction, wave breaking and wave-wave nonlinear interaction on typhoon waves is carried out. The optimal parameters are selected to simulate the wave changes in Sanmen Bay under the influence of typhoon Talim and compared with the measured data. The results show that different wave physical process parameters have certain influence on the simulation results, and the simulation results are in good agreement with the measured data. The established model has reference significance for typhoon wave prediction in Sanmen Bay.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127804396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849267
W. Zhang, Zhiheng Liu, Hang Yu, Suiping Zhou, Haoran Jiang, Yuru Guo
Complex terrain and landscape, and mountains in China are prone to landslide disasters, and causing great potential danger to social stability, people's life and property safety, which makes landslide detection be a hot spot of research. With the advent of remote sensing images, landslide data are growing explosively, which provides conditions for landslide detection by applying deep learning algorithms. Firstly, to broaden the landslide identification method, we created a landslide dataset based on open-source Google Earth images. Secondly, we applied a series of object detection algorithms, such as YOLOV5, Faster RCNN, EfficientDet, SSD, and the improved YOLOV5 by embedding CBAM and Ghost module in the backbone, for detecting landslides from landslide dataset. Finally, we analyzed and compared the experimental results. The results show that the SSD algorithm detects landslides with an accuracy of 97.86%, and the training time for each epoch is only 57s. When there is only one landslide target in the image, SSD is advantageous; The improved YOLOV5 in this paper can identify multiple landslides well while reducing the number of model parameters when detecting images containing multiple landslides.
{"title":"Comparison of landslide detection based on different deep learning algorithms","authors":"W. Zhang, Zhiheng Liu, Hang Yu, Suiping Zhou, Haoran Jiang, Yuru Guo","doi":"10.1109/ICGMRS55602.2022.9849267","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849267","url":null,"abstract":"Complex terrain and landscape, and mountains in China are prone to landslide disasters, and causing great potential danger to social stability, people's life and property safety, which makes landslide detection be a hot spot of research. With the advent of remote sensing images, landslide data are growing explosively, which provides conditions for landslide detection by applying deep learning algorithms. Firstly, to broaden the landslide identification method, we created a landslide dataset based on open-source Google Earth images. Secondly, we applied a series of object detection algorithms, such as YOLOV5, Faster RCNN, EfficientDet, SSD, and the improved YOLOV5 by embedding CBAM and Ghost module in the backbone, for detecting landslides from landslide dataset. Finally, we analyzed and compared the experimental results. The results show that the SSD algorithm detects landslides with an accuracy of 97.86%, and the training time for each epoch is only 57s. When there is only one landslide target in the image, SSD is advantageous; The improved YOLOV5 in this paper can identify multiple landslides well while reducing the number of model parameters when detecting images containing multiple landslides.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133210815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：