This paper examines the utility of high-resolution airborne RGB orthophotos and LiDAR data for mapping residential land uses within the spatial limits of suburb of Athens, Greece. Modem remote sensors deliver ample in...This paper examines the utility of high-resolution airborne RGB orthophotos and LiDAR data for mapping residential land uses within the spatial limits of suburb of Athens, Greece. Modem remote sensors deliver ample information from the AOI （area of interest） for the estimation of 2D indicators or with the inclusion of elevation data 3D indicators for the classification of urban land. In this research, two of these indicators, BCR （building coverage ratio） and FAR （floor area ratio） are automatically evaluated. In the pre-processing step, the low resolution elevation data are fused with the high resolution optical data through a mean-shift based discontinuity preserving smoothing algorithm. The outcome is an nDSM （normalized digital surface model） comprised of upsampled elevation data with considerable improvement regarding region filling and ＂straightness＂ of elevation discontinuities. Following this step, a MFNN （multilayer feedforward neural network） is used to classify all pixels of the AOI into building or non-building categories. The information derived from the BCR and FAR building indicators, adapted to landscape characteristics of the test area is used to propose two new indices and an automatic post-classification based on the density of buildings.展开更多
地球的及时、精确的变化察觉“ s 表面特征为更好计划，管理和环境研究提供基础。在这个学习 ANN 变化，察觉被用来执行植被变化察觉，并且与分类以后的方法相比。以前分类以后被执行 ANN 分类被用来产出多时间的植被地图。ANN 也被用来...地球的及时、精确的变化察觉“ s 表面特征为更好计划，管理和环境研究提供基础。在这个学习 ANN 变化，察觉被用来执行植被变化察觉，并且与分类以后的方法相比。以前分类以后被执行 ANN 分类被用来产出多时间的植被地图。ANN 也被用来在 2003 和 2004 为图象执行一个一个通行证分类。DEM 和斜坡被用作二条额外的隧道。在训练阶段期间，训练数据包括 36 个变化子类和 46 个没有变化子类被分开成 82 个子类。而且 NDVI differencing 方法被用来开发变化面具。当鉴别参考区域能为 ANN 那个生产更精确的变化察觉结果时，结果显示出那把 NDVI differencing 方法与视觉解释相结合通行证变化分类。而且，和 PCA 部件把举起和斜坡用作额外的隧道是有效的，在多山的学习区域执行基于 ANN 的变化察觉。把植被转变类分开成子类基于也是重要的光谱反应模式，特别为多山的地面。这个处理能减少地志的效果并且改进变化察觉精确性。展开更多
In order to minimise the bushfires negative impacts on society, an efficient andreliable bushfire detection system was proposed to assess the devastated effects of the2009 Victorian bushfires.It is possible to utilise...In order to minimise the bushfires negative impacts on society, an efficient andreliable bushfire detection system was proposed to assess the devastated effects of the2009 Victorian bushfires.It is possible to utilise the repetitive capability of satellite remotesensing imagery to identify the location of change to the Earth's surface and integrate thedifferent remotely sensed indices.The results confirm that the procedure can offer essentialspatial information for bushfire assessment.展开更多
矿区土地覆盖变化信息的高精度提取,是区域资源环境保护和地质灾害防治领域的关键问题。以SPOT-5高分辨率卫星影像为数据源,以分类后比较法为变化信息提取方法,利用分类性能良好的支持向量机(SVM)为分类算法,分别设置不同SVM核函数及参...矿区土地覆盖变化信息的高精度提取,是区域资源环境保护和地质灾害防治领域的关键问题。以SPOT-5高分辨率卫星影像为数据源,以分类后比较法为变化信息提取方法,利用分类性能良好的支持向量机(SVM)为分类算法,分别设置不同SVM核函数及参数对实验样区进行分类,并评价分析不同核函数及参数对分类效果的影响。实验发现在4种核函数中高斯核函数分类精度最高,为87.1%;Sigmoid和多项式核函数分类精度适中,线性核函数分类精度最低,为78.7%。因此,利用高斯核函数分别对3个时相的大屯矿区影像进行分类,提取出变化信息空间分布并定量统计分析其变化特征。结果表明:矿区植被覆盖面积在近十年内持续减少18.539 km 2,塌陷面积共扩大4.379 km 2,而矿区厂矿增加、煤矿开采规模扩大、采煤塌陷区面积扩大以及耕地占用面积增大等人为因素,是威胁大屯矿区生态环境的主要因素。展开更多
文摘This paper examines the utility of high-resolution airborne RGB orthophotos and LiDAR data for mapping residential land uses within the spatial limits of suburb of Athens, Greece. Modem remote sensors deliver ample information from the AOI （area of interest） for the estimation of 2D indicators or with the inclusion of elevation data 3D indicators for the classification of urban land. In this research, two of these indicators, BCR （building coverage ratio） and FAR （floor area ratio） are automatically evaluated. In the pre-processing step, the low resolution elevation data are fused with the high resolution optical data through a mean-shift based discontinuity preserving smoothing algorithm. The outcome is an nDSM （normalized digital surface model） comprised of upsampled elevation data with considerable improvement regarding region filling and ＂straightness＂ of elevation discontinuities. Following this step, a MFNN （multilayer feedforward neural network） is used to classify all pixels of the AOI into building or non-building categories. The information derived from the BCR and FAR building indicators, adapted to landscape characteristics of the test area is used to propose two new indices and an automatic post-classification based on the density of buildings.
基金Supported by the National Key Project for Basic Research on Ecosystem Changes in Longitudinal Range-Gorge Region and Transboundary Eco-security of Southwest China(Grant No.2003CB415102)Vlanmse Interuniversitaire Raad(VLIR ZEIN2002PR264-886)Belgium and Foundation of Provincial Education,Yunnan Province(Grant No.04Y220B)
文摘地球的及时、精确的变化察觉“ s 表面特征为更好计划，管理和环境研究提供基础。在这个学习 ANN 变化，察觉被用来执行植被变化察觉，并且与分类以后的方法相比。以前分类以后被执行 ANN 分类被用来产出多时间的植被地图。ANN 也被用来在 2003 和 2004 为图象执行一个一个通行证分类。DEM 和斜坡被用作二条额外的隧道。在训练阶段期间，训练数据包括 36 个变化子类和 46 个没有变化子类被分开成 82 个子类。而且 NDVI differencing 方法被用来开发变化面具。当鉴别参考区域能为 ANN 那个生产更精确的变化察觉结果时，结果显示出那把 NDVI differencing 方法与视觉解释相结合通行证变化分类。而且，和 PCA 部件把举起和斜坡用作额外的隧道是有效的，在多山的学习区域执行基于 ANN 的变化察觉。把植被转变类分开成子类基于也是重要的光谱反应模式，特别为多山的地面。这个处理能减少地志的效果并且改进变化察觉精确性。
文摘In order to minimise the bushfires negative impacts on society, an efficient andreliable bushfire detection system was proposed to assess the devastated effects of the2009 Victorian bushfires.It is possible to utilise the repetitive capability of satellite remotesensing imagery to identify the location of change to the Earth's surface and integrate thedifferent remotely sensed indices.The results confirm that the procedure can offer essentialspatial information for bushfire assessment.
文摘矿区土地覆盖变化信息的高精度提取,是区域资源环境保护和地质灾害防治领域的关键问题。以SPOT-5高分辨率卫星影像为数据源,以分类后比较法为变化信息提取方法,利用分类性能良好的支持向量机(SVM)为分类算法,分别设置不同SVM核函数及参数对实验样区进行分类,并评价分析不同核函数及参数对分类效果的影响。实验发现在4种核函数中高斯核函数分类精度最高,为87.1%;Sigmoid和多项式核函数分类精度适中,线性核函数分类精度最低,为78.7%。因此,利用高斯核函数分别对3个时相的大屯矿区影像进行分类,提取出变化信息空间分布并定量统计分析其变化特征。结果表明:矿区植被覆盖面积在近十年内持续减少18.539 km 2,塌陷面积共扩大4.379 km 2,而矿区厂矿增加、煤矿开采规模扩大、采煤塌陷区面积扩大以及耕地占用面积增大等人为因素,是威胁大屯矿区生态环境的主要因素。
