This paper seeks a synthesis of Bayesian and geostatistical approaches to combining categorical data in the context of remote sensing classification. By experiment with aerial photographs and Landsat TM data, accuracy...This paper seeks a synthesis of Bayesian and geostatistical approaches to combining categorical data in the context of remote sensing classification. By experiment with aerial photographs and Landsat TM data, accuracy of spectral, spatial, and combined classification results was evaluated. It was confirmed that the incorporation of spatial information in spectral classification increases accuracy significantly. Secondly, through test with a 5-class and a 3-class classification schemes, it was revealed that setting a proper semantic framework for classification is fundamental to any endeavors of categorical mapping and the most important factor affecting accuracy. Lastly, this paper promotes non-parametric methods for both definition of class membership profiling based on band-specific histograms of image intensities and derivation of spatial probability via indicator kriging, a non-parametric geostatistical technique.展开更多
A topic studied in cartography is to make the extraction of cartographic features that provide the update of cartographic maps more easily. For this reason many automatic routines were created with the intent to perfo...A topic studied in cartography is to make the extraction of cartographic features that provide the update of cartographic maps more easily. For this reason many automatic routines were created with the intent to perform the features extraction. Despite of all studies about this, some features cannot be found by the algorithm or it can extract some pixels unduly. So the current article aims to show the results with the software development that uses the original and reference image to calculate some statistics about the extraction process. Furthermore, the calculated statistics can be used to evaluate the extraction process.展开更多
This research aims to define an efficient and fast quantification of bitumen removal on the road surface by Digital Imaging Processing (DIP) and spectral analysis. The retrieval of bitumen removal is an important issu...This research aims to define an efficient and fast quantification of bitumen removal on the road surface by Digital Imaging Processing (DIP) and spectral analysis. The retrieval of bitumen removal is an important issue for road management and environmental studies related to asphalt wear and environmental pollution. The calculation of the Exposed Aggregate Index (EAI), based on DIP, allows to quantify in each frame the superficial removal of bitumen and the exposure of aggregates. A procedure, based on non-parametric classification process of digital images, gives a fast response of EAI. A correlation among EAI and spectral data, between 390 nm and 900 nm range, is evaluated. Results show a good correlation between spectral data at different wavelength and EAI. Finally, this work evaluates the possibility to retrieve asphalt bitumen removal through remote sensed imagery.展开更多
Monuments and historical centers, because of their particular importance, are studied in multiple ways. The study concerns different scientific disciplines and technology. Photogrammetry and remote sensing contribute ...Monuments and historical centers, because of their particular importance, are studied in multiple ways. The study concerns different scientific disciplines and technology. Photogrammetry and remote sensing contribute essentially to this study, because of the valuable qualitative and quantitative information they offer. In this paper we search through the possibilities of very high resolution satellite imagery on historical centers study, referring to Delphi historical center. The study concerns image enhancement techniques and visual interpretation of Ikonos satellite imagery. Image enhancement techniques facilitate visual interpretation, detection and recognition, of the physiognomy and spatial arrangement of Delphi historical center and offer information about physical and architectural features in the wide area of the historical center.展开更多
[目的/意义]猕猴桃果树生长重叠明显,树冠结构复杂,利用传统方式无法实现果树单木骨架提取与冠层预测,为对密集栽培的猕猴桃果园进行高效无损监测并获取果树生长参数,本研究利用冬季简单树形进行骨架提取,并集成深度学习与数学形态学方...[目的/意义]猕猴桃果树生长重叠明显,树冠结构复杂,利用传统方式无法实现果树单木骨架提取与冠层预测,为对密集栽培的猕猴桃果园进行高效无损监测并获取果树生长参数,本研究利用冬季简单树形进行骨架提取,并集成深度学习与数学形态学方法,提高单木骨架预测精度,提出了一种融合骨架信息的冠层分割方案。[方法方法]采用低成本无人机图像获取高分辨率数据支持,改进PSP-Net语义分割模型,引入数学形态学处理提取单木骨架并优化骨架连续性,以优化单木骨架为先验实现冠层分割。[结果与讨论]优化骨架提取精度可达95%以上,相较于传统方式精度提高约15.71%,像素准确率(Pixel Accuracy,PA)值达95.84%,平均交并比(Mean In-tersection over Union,MIo U)值达95.76%,冠层分割加权得分(Weighted F1 Score,WF1)达94.07%左右;而冠层预测像素准确率PA可达95%以上,冠层分割WF1达95.76%左右,与直接利用原始骨架相比,优化骨架提高了冠层分割的PA为13.2%,MIo U为10.9%,WF1为18.4%,显著改善了分割指标。[结论]该研究为高效监测猕猴桃园以获取果树数据提供了可靠技术支撑,并为高效、低成本的果园精细化管理提供了全新的技术方案,具有重要的应用前景。展开更多
文摘This paper seeks a synthesis of Bayesian and geostatistical approaches to combining categorical data in the context of remote sensing classification. By experiment with aerial photographs and Landsat TM data, accuracy of spectral, spatial, and combined classification results was evaluated. It was confirmed that the incorporation of spatial information in spectral classification increases accuracy significantly. Secondly, through test with a 5-class and a 3-class classification schemes, it was revealed that setting a proper semantic framework for classification is fundamental to any endeavors of categorical mapping and the most important factor affecting accuracy. Lastly, this paper promotes non-parametric methods for both definition of class membership profiling based on band-specific histograms of image intensities and derivation of spatial probability via indicator kriging, a non-parametric geostatistical technique.
文摘A topic studied in cartography is to make the extraction of cartographic features that provide the update of cartographic maps more easily. For this reason many automatic routines were created with the intent to perform the features extraction. Despite of all studies about this, some features cannot be found by the algorithm or it can extract some pixels unduly. So the current article aims to show the results with the software development that uses the original and reference image to calculate some statistics about the extraction process. Furthermore, the calculated statistics can be used to evaluate the extraction process.
文摘This research aims to define an efficient and fast quantification of bitumen removal on the road surface by Digital Imaging Processing (DIP) and spectral analysis. The retrieval of bitumen removal is an important issue for road management and environmental studies related to asphalt wear and environmental pollution. The calculation of the Exposed Aggregate Index (EAI), based on DIP, allows to quantify in each frame the superficial removal of bitumen and the exposure of aggregates. A procedure, based on non-parametric classification process of digital images, gives a fast response of EAI. A correlation among EAI and spectral data, between 390 nm and 900 nm range, is evaluated. Results show a good correlation between spectral data at different wavelength and EAI. Finally, this work evaluates the possibility to retrieve asphalt bitumen removal through remote sensed imagery.
文摘Monuments and historical centers, because of their particular importance, are studied in multiple ways. The study concerns different scientific disciplines and technology. Photogrammetry and remote sensing contribute essentially to this study, because of the valuable qualitative and quantitative information they offer. In this paper we search through the possibilities of very high resolution satellite imagery on historical centers study, referring to Delphi historical center. The study concerns image enhancement techniques and visual interpretation of Ikonos satellite imagery. Image enhancement techniques facilitate visual interpretation, detection and recognition, of the physiognomy and spatial arrangement of Delphi historical center and offer information about physical and architectural features in the wide area of the historical center.
文摘[目的/意义]猕猴桃果树生长重叠明显,树冠结构复杂,利用传统方式无法实现果树单木骨架提取与冠层预测,为对密集栽培的猕猴桃果园进行高效无损监测并获取果树生长参数,本研究利用冬季简单树形进行骨架提取,并集成深度学习与数学形态学方法,提高单木骨架预测精度,提出了一种融合骨架信息的冠层分割方案。[方法方法]采用低成本无人机图像获取高分辨率数据支持,改进PSP-Net语义分割模型,引入数学形态学处理提取单木骨架并优化骨架连续性,以优化单木骨架为先验实现冠层分割。[结果与讨论]优化骨架提取精度可达95%以上,相较于传统方式精度提高约15.71%,像素准确率(Pixel Accuracy,PA)值达95.84%,平均交并比(Mean In-tersection over Union,MIo U)值达95.76%,冠层分割加权得分(Weighted F1 Score,WF1)达94.07%左右;而冠层预测像素准确率PA可达95%以上,冠层分割WF1达95.76%左右,与直接利用原始骨架相比,优化骨架提高了冠层分割的PA为13.2%,MIo U为10.9%,WF1为18.4%,显著改善了分割指标。[结论]该研究为高效监测猕猴桃园以获取果树数据提供了可靠技术支撑,并为高效、低成本的果园精细化管理提供了全新的技术方案,具有重要的应用前景。
