Reservoirs are fundamental infrastructures for the management of water resources. Constructions around them can negatively impact their water quality. Such constructions can be detected by segmenting man-made objects around reservoirs in the remote sensing (RS) images. Deep learning (DL) has attracted considerable attention in recent years as a method for segmenting the RS imagery into different land covers/uses and has achieved remarkable success. We develop an approach based on DL and image processing techniques for man-made object segmentation around the reservoirs. In order to segment man-made objects around the reservoirs in an end-to-end procedure, segmenting reservoirs and identifying the region of interest (RoI) around them are essential. In the proposed two-phase workflow, the reservoir is initially segmented using a DL model, and a postprocessing stage is proposed to remove errors, such as floating vegetation in the generated reservoir map. In the second phase, the RoI around the reservoir (RoIaR) is extracted using the proposed image processing techniques. Finally, the man-made objects in the RoIaR are segmented using a DL model. To illustrate the proposed approach, our task of interest is segmenting man-made objects around some of the most important reservoirs in Brazil. Therefore, we trained the proposed workflow using collected Google Earth images of eight reservoirs in Brazil over two different years. The U-Net-based and SegNet-based architectures are trained to segment the reservoirs. To segment man-made objects in the RoIaR, we trained and evaluated four architectures: U-Net, feature pyramid network, LinkNet, and pyramid scene parsing network. Although the collected data are highly diverse (for example, they belong to different states, seasons, resolutions, etc.), we achieved good performances in both phases. The F1-score of phase-1 and phase-2 highest performance models in segmenting test sets are 96.53% and 90.32%, respectively. Furthermore, applying the proposed postprocessing to the output of reservoir segmentation improves the precision in all studied reservoirs except two cases. We validated the prepared workflow with a reservoir dataset outside the training reservoirs. The F1-scores of the phase-1 segmentation stage, postprocessing stage, and phase-2 segmentation stage are 92.54%, 94.68%, and 88.11%, respectively, which show high generalization ability of the prepared workflow.
{"title":"Man-made object segmentation around reservoirs by an end-to-end two-phase deep learning-based workflow","authors":"Nayereh Hamidishad, Roberto Marcondes Cesar Jr.","doi":"10.1117/1.jrs.18.018502","DOIUrl":"https://doi.org/10.1117/1.jrs.18.018502","url":null,"abstract":"Reservoirs are fundamental infrastructures for the management of water resources. Constructions around them can negatively impact their water quality. Such constructions can be detected by segmenting man-made objects around reservoirs in the remote sensing (RS) images. Deep learning (DL) has attracted considerable attention in recent years as a method for segmenting the RS imagery into different land covers/uses and has achieved remarkable success. We develop an approach based on DL and image processing techniques for man-made object segmentation around the reservoirs. In order to segment man-made objects around the reservoirs in an end-to-end procedure, segmenting reservoirs and identifying the region of interest (RoI) around them are essential. In the proposed two-phase workflow, the reservoir is initially segmented using a DL model, and a postprocessing stage is proposed to remove errors, such as floating vegetation in the generated reservoir map. In the second phase, the RoI around the reservoir (RoIaR) is extracted using the proposed image processing techniques. Finally, the man-made objects in the RoIaR are segmented using a DL model. To illustrate the proposed approach, our task of interest is segmenting man-made objects around some of the most important reservoirs in Brazil. Therefore, we trained the proposed workflow using collected Google Earth images of eight reservoirs in Brazil over two different years. The U-Net-based and SegNet-based architectures are trained to segment the reservoirs. To segment man-made objects in the RoIaR, we trained and evaluated four architectures: U-Net, feature pyramid network, LinkNet, and pyramid scene parsing network. Although the collected data are highly diverse (for example, they belong to different states, seasons, resolutions, etc.), we achieved good performances in both phases. The F1-score of phase-1 and phase-2 highest performance models in segmenting test sets are 96.53% and 90.32%, respectively. Furthermore, applying the proposed postprocessing to the output of reservoir segmentation improves the precision in all studied reservoirs except two cases. We validated the prepared workflow with a reservoir dataset outside the training reservoirs. The F1-scores of the phase-1 segmentation stage, postprocessing stage, and phase-2 segmentation stage are 92.54%, 94.68%, and 88.11%, respectively, which show high generalization ability of the prepared workflow.","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":"20 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139554459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wenzheng Ye, Tinghuai Ma, Zilong Jin, Huan Rong, Benjamin Kwapong Osibo, Mohamed Magdy Abdel Wahab, Yuming Su, Bright Bediako-Kyeremeh
Timely and accurate prediction of winter wheat yield contributes to ensuring national food security. We propose a CNN- bidirectional gated recurrent unit method with triple attention for winter wheat yield prediction, named CBTA. This deep learning model uses convolutional neural networks to mine the spatial spectral information in hyperspectral remote sensing images. Furthermore, the bidirectional gated recurrent unit is used to adaptively learn the time dependence between the various stages of winter wheat growth. Data from Henan Province, China, is used in this study to train the model and also verify its prediction performance and stability. The results from our experiment show that our proposed model has an excellent effect on yield prediction in the county, with root-mean-square-error, mean absolute error, and R2 of 0.469 t/ha, 0.336 t/ha, and 0.827, respectively. Moreover, our findings suggested that the precision of our model using the data from sowing to heading-flowering stage was very close to that from sowing to ripening stage, which proves that the CBTA model can accurately predict the yield of winter wheat 1 to 2 months in advance.
{"title":"CBTA: a CNN-BiGRU method with triple attention for winter wheat yield prediction","authors":"Wenzheng Ye, Tinghuai Ma, Zilong Jin, Huan Rong, Benjamin Kwapong Osibo, Mohamed Magdy Abdel Wahab, Yuming Su, Bright Bediako-Kyeremeh","doi":"10.1117/1.jrs.18.014507","DOIUrl":"https://doi.org/10.1117/1.jrs.18.014507","url":null,"abstract":"Timely and accurate prediction of winter wheat yield contributes to ensuring national food security. We propose a CNN- bidirectional gated recurrent unit method with triple attention for winter wheat yield prediction, named CBTA. This deep learning model uses convolutional neural networks to mine the spatial spectral information in hyperspectral remote sensing images. Furthermore, the bidirectional gated recurrent unit is used to adaptively learn the time dependence between the various stages of winter wheat growth. Data from Henan Province, China, is used in this study to train the model and also verify its prediction performance and stability. The results from our experiment show that our proposed model has an excellent effect on yield prediction in the county, with root-mean-square-error, mean absolute error, and R2 of 0.469 t/ha, 0.336 t/ha, and 0.827, respectively. Moreover, our findings suggested that the precision of our model using the data from sowing to heading-flowering stage was very close to that from sowing to ripening stage, which proves that the CBTA model can accurately predict the yield of winter wheat 1 to 2 months in advance.","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":"8 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139578001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Forestry pests pose a significant threat to forest health, making precise extraction of infested trees a vital aspect of forest protection. In recent years, deep learning has achieved substantial success in detecting infestations. However, when applying existing deep learning methods to infested tree detection, challenges arise, such as limited training samples and confusion between forest areas and artificial structures. To address these issues, this work proposes a two-stage hierarchical semi-supervised deep learning approach based on unmanned aerial vehicle visible images to achieve the individual extraction of each pine wilt disease (PWD). The approach can automatically detect the positions and crown extents of each infested tree. The comprehensive framework includes the following key steps: (a) considering the disparities in global image representation between forest areas and artificial structures, a scene classification network named MobileNetV3 is trained to effectively differentiate between forested regions and other artificial structures. (b) Considering the high cost of manually annotating and incomplete labeling of infested tree samples, a semi-supervised infested tree samples mining method is introduced, significantly reducing the workload of sample annotation. Ultimately, this method is integrated into the YOLOv7 object detection network, enabling rapid and reliable detection of infested trees. Experimental results demonstrate that, with a confidence threshold of 0.15 and using the semi-supervised sample mining framework, the number of samples increases from 53,046 to 93,544. Precision evaluation metrics indicate a 5.8% improvement in recall and a 2.6% increase in mean average precision@.5. The final test area prediction achieves an overall accuracy of over 80% and the recall rate of over 90%, indicating the effectiveness of the proposed method in PWD detection.
{"title":"Extraction of pine wilt disease based on a two-stage unmanned aerial vehicle deep learning method","authors":"Xin Huang, Weilin Gang, Jiayi Li, Zhili Wang, Qun Wang, Yuegang Liang","doi":"10.1117/1.jrs.18.014503","DOIUrl":"https://doi.org/10.1117/1.jrs.18.014503","url":null,"abstract":"Forestry pests pose a significant threat to forest health, making precise extraction of infested trees a vital aspect of forest protection. In recent years, deep learning has achieved substantial success in detecting infestations. However, when applying existing deep learning methods to infested tree detection, challenges arise, such as limited training samples and confusion between forest areas and artificial structures. To address these issues, this work proposes a two-stage hierarchical semi-supervised deep learning approach based on unmanned aerial vehicle visible images to achieve the individual extraction of each pine wilt disease (PWD). The approach can automatically detect the positions and crown extents of each infested tree. The comprehensive framework includes the following key steps: (a) considering the disparities in global image representation between forest areas and artificial structures, a scene classification network named MobileNetV3 is trained to effectively differentiate between forested regions and other artificial structures. (b) Considering the high cost of manually annotating and incomplete labeling of infested tree samples, a semi-supervised infested tree samples mining method is introduced, significantly reducing the workload of sample annotation. Ultimately, this method is integrated into the YOLOv7 object detection network, enabling rapid and reliable detection of infested trees. Experimental results demonstrate that, with a confidence threshold of 0.15 and using the semi-supervised sample mining framework, the number of samples increases from 53,046 to 93,544. Precision evaluation metrics indicate a 5.8% improvement in recall and a 2.6% increase in mean average precision@.5. The final test area prediction achieves an overall accuracy of over 80% and the recall rate of over 90%, indicating the effectiveness of the proposed method in PWD detection.","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":"72 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139103035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Renxiong Zhuo, Yunfei Guo, Baofeng Guo, Baoyang Liu, Fan Dai
{"title":"Two-dimensional compact variational mode decomposition for effective feature extraction and data classification in hyperspectral imaging","authors":"Renxiong Zhuo, Yunfei Guo, Baofeng Guo, Baoyang Liu, Fan Dai","doi":"10.1117/1.jrs.17.044517","DOIUrl":"https://doi.org/10.1117/1.jrs.17.044517","url":null,"abstract":"","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":" 37","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138963675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luis Zea, Aldo Aguilar-Nadalini, Marvin Martínez, Johan Birnie, Emilio Miranda, Fredy España, Kuk Chung, Dan Álvarez, J. Bagur, Carlo Estrada, Rony Herrarte, V. Ayerdi
{"title":"Academic development and space operations of a multispectral imaging payload for 1U CubeSats","authors":"Luis Zea, Aldo Aguilar-Nadalini, Marvin Martínez, Johan Birnie, Emilio Miranda, Fredy España, Kuk Chung, Dan Álvarez, J. Bagur, Carlo Estrada, Rony Herrarte, V. Ayerdi","doi":"10.1117/1.jrs.17.047501","DOIUrl":"https://doi.org/10.1117/1.jrs.17.047501","url":null,"abstract":"","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":"38 11","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138596247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Variational pansharpening based on high-pass injection fidelity with local dual-scale coefficient estimation","authors":"Lingxin GongYe, Kyongson Jon, Jianhua Guo","doi":"10.1117/1.jrs.17.046510","DOIUrl":"https://doi.org/10.1117/1.jrs.17.046510","url":null,"abstract":"","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":"40 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138595569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zachary J. Landicini, Jeffrey Barber, James C. Weatherall, Duane C. Karns, Peter R. Smith, Joaquín Aparicio-Bolaño, Wendy Ruiz
Dielectric measurements of plastic explosives using a loaded waveguide technique via vector network analyzer and banded millimeter wave extender modules operating at V-band (50 to 75 GHz) are performed. A portion of an explosive sample is inserted into a waveguide shim 2 mm in length and trimmed flush with the faces of the shim. Two-port S-parameter measurements are conducted on the explosive; the empty shim is similarly characterized. Using standard waveguide equations and the measured length of the shim, the complex S-parameter data obtained with the filled shim is optimized to four free parameters—complex permittivity and distance offsets for the two sample faces relative to the calibration planes. Permittivity data obtained from measurements of the plastic explosives C-4, Primasheet 1000, Primasheet 2000 and Semtex 10 are presented. Results obtained for C-4 and Primasheet 1000 are comparable to other data in the literature, and the data on Primasheet 2000 and Semtex 10 are the first known published permittivity values in this range. Excellent agreement between the experiment and the fit is obtained using a constant permittivity across the waveguide band, indicating that dispersion is not significant for these materials.
通过矢量网络分析仪和工作在 V 波段（50 至 75 千兆赫）的带状毫米波扩展器模块，使用加载波导技术对塑料炸药进行介电测量。将爆炸物样品的一部分插入长度为 2 毫米的波导垫片，并与垫片表面齐平。对爆炸物进行双端口 S 参数测量；对空垫片进行类似表征。利用标准波导方程和测量的垫片长度，将填充垫片获得的复 S 参数数据优化为四个自由参数--复介电常数和两个样品面相对于校准平面的距离偏移。本文展示了通过测量塑料炸药 C-4、Primasheet 1000、Primasheet 2000 和 Semtex 10 获得的介电常数数据。C-4 和 Primasheet 1000 的测量结果与文献中的其他数据相当，而 Primasheet 2000 和 Semtex 10 的数据则是首次公布的该范围内的脆率值。使用整个波导波段的恒定介电常数，实验与拟合之间获得了极好的一致性，表明这些材料的色散并不严重。
{"title":"Loaded waveguide measurements of plastic explosives at V-band","authors":"Zachary J. Landicini, Jeffrey Barber, James C. Weatherall, Duane C. Karns, Peter R. Smith, Joaquín Aparicio-Bolaño, Wendy Ruiz","doi":"10.1117/1.jrs.18.014501","DOIUrl":"https://doi.org/10.1117/1.jrs.18.014501","url":null,"abstract":"Dielectric measurements of plastic explosives using a loaded waveguide technique via vector network analyzer and banded millimeter wave extender modules operating at V-band (50 to 75 GHz) are performed. A portion of an explosive sample is inserted into a waveguide shim 2 mm in length and trimmed flush with the faces of the shim. Two-port S-parameter measurements are conducted on the explosive; the empty shim is similarly characterized. Using standard waveguide equations and the measured length of the shim, the complex S-parameter data obtained with the filled shim is optimized to four free parameters—complex permittivity and distance offsets for the two sample faces relative to the calibration planes. Permittivity data obtained from measurements of the plastic explosives C-4, Primasheet 1000, Primasheet 2000 and Semtex 10 are presented. Results obtained for C-4 and Primasheet 1000 are comparable to other data in the literature, and the data on Primasheet 2000 and Semtex 10 are the first known published permittivity values in this range. Excellent agreement between the experiment and the fit is obtained using a constant permittivity across the waveguide band, indicating that dispersion is not significant for these materials.","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":"7 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139063547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01Epub Date: 2022-06-06DOI: 10.1177/15266028221098707
Anna L Driessen, Carla K Scott, Gerardo G Guardiola, Mirza S Baig, Melissa L Kirkwood, Carlos H Timaran
Failed fenestrated-branched endovascular aortic repair (F-BEVAR) requiring a redo F-BEVAR is a rare event. In this study, we report 2 cases of a failed F-BEVAR secondary to a type IIIb endoleak from tears on the fabric graft successfully treated with redo F-BEVAR. This is a technically challenging procedure that requires meticulous planning, advanced imaging technologies and experienced operators. Redo F-BEVAR appears to be a feasible and safe treatment option. However, larger series and long-term follow-up are needed to confirm effectiveness and durability.
{"title":"Redo Fenestrated-Branched Endovascular Aortic Repair (F-BEVAR) for Failed F-BEVAR.","authors":"Anna L Driessen, Carla K Scott, Gerardo G Guardiola, Mirza S Baig, Melissa L Kirkwood, Carlos H Timaran","doi":"10.1177/15266028221098707","DOIUrl":"10.1177/15266028221098707","url":null,"abstract":"<p><p>Failed fenestrated-branched endovascular aortic repair (F-BEVAR) requiring a redo F-BEVAR is a rare event. In this study, we report 2 cases of a failed F-BEVAR secondary to a type IIIb endoleak from tears on the fabric graft successfully treated with redo F-BEVAR. This is a technically challenging procedure that requires meticulous planning, advanced imaging technologies and experienced operators. Redo F-BEVAR appears to be a feasible and safe treatment option. However, larger series and long-term follow-up are needed to confirm effectiveness and durability.</p>","PeriodicalId":54879,"journal":{"name":"Journal of Applied Remote Sensing","volume":"15 1","pages":"964-970"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76780223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","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：