Superresolution mapping using a Hopfield neural network with lidar data
Superresolution mapping using a Hopfield neural network with lidar data
复制标题
DOI：
10.1109/lgrs.2005.851551
复制
发表时间：
2005-07
影响因子：
4.8
通讯作者：
M. Q. Nguyen;P. Atkinson;H. Lewis
中科院分区：
文献类型：
--
作者：
M. Q. Nguyen;P. Atkinson;H. Lewis
超分辨率映射是一组从软分类生成的土地覆盖比例图像中获取子像素图的技术。与土地覆盖比例图像中的信息一起，子像素级别的补充信息可用于生成更详细和准确的土地覆盖图。本研究旨在利用光探测和测距（激光雷达）的高程数据作为使用 Hopfield 神经网络 (HNN) 进行超分辨率测绘的附加信息源。 HNN 的能量函数中添加了一个新的高度函数，用于超分辨率映射。根据高斯分布计算某一类的每个子像素的高度函数值。使用一组模拟数据来测试新技术。结果表明，0.8 米空间分辨率的数字表面模型可以与 4 米空间分辨率的光学数据相结合，用于超分辨率绘图。
Superresolution mapping is a set of techniques to obtain a subpixel map from land cover proportion images produced by soft classification. Together with the information from the land cover proportion images, supplementary information at the subpixel level can be used to produce more detailed and accurate land cover maps. This research aims to use the elevation data from light detection and ranging (lidar) as an additional source of information for superresolution mapping using the Hopfield neural network (HNN). A new height function was added to the energy function of the HNN for superresolution mapping. The value of the height function was calculated for each subpixel of a certain class based on the Gaussian distribution. A set of simulated data was used to test the new technique. The results suggest that 0.8-m spatial resolution digital surface models can be combined with optical data at 4-m spatial resolution for superresolution mapping.