利用Faster R-CNN进行立交桥自动识别与定位

立交桥结构的自动识别对道路网多尺度建模、空间分析和车辆导航具有重要意义.传统基于矢量数据的立交桥识别方法过分依赖人工设计的特征,对复杂场景的适应性较差.本文提出了一种基于目标检测Faster R-CNN神经网络模型的立交桥识别方法,该方法利用卷积神经网络学习立交桥样本的深层次结构特征,进而实现立交桥的自动识别与准确定位...     

基于卷积神经网络的无人机影像违章建筑检测应用

无人机航拍影像具有分辨率高、回访周期短等特点,利用无人机遥感技术手段对城市范围的建设进行动态监测,可及时、有效地发现涉嫌违法的建设活动.本文结合实际项目需求,研究通过卷积神经网络方法进行违章建筑的自动检测,替代过去靠大量人力检查的模式,目前测试区域无人机影像试验取得了较好的效果,在样本数据不足5000份的情况下,准确率...     

激光雷达点云电力线自动提取算法

针对当前电力线提取方法自动化程度和精度不高的问题,本文从点云数据的空间分布特征出发,提出了一种高效的电力线自动提取方法.首先基于自然裂点法,将点云数据按高程分类后去除地面点;然后对数据进行空间划分,基于子空间的点密度及空间结构特征的差异化,利用地物分割算法去除电塔点和残留的植被点;最后利用基于欧氏距离分割的电力线自动检...     

轨道扣件病害自动化检测研究及应用

传统扣件检查基本采用人工检查方式,不仅工作效率低、劳动强度大,而且人为干扰因素多、检查采样率低.针对以上问题,本文提出了一种基于线结构光传感器的轨道扣件损伤和松动检测方法,并开发了轨道扣件智能监测系统以实现扣件病害自动检测.最终将研究成果应用于徐州市某地铁区间轨道扣件检测,验证了该方法的可行性和准确率,为地铁轨道扣件检...     

基于点云投影线探测的高墩位姿自动检测方法

针对目前超高桥墩垂直度检测方法存在危险系数较高、精度难以保证或自动化程度与工作效率较低的情况,本文提出一种基于三维激光扫描技术的点云数据超高桥墩位姿自动检测方法.该方法首先将海量墩面点云双向分层;然后依条件选择分层文件探测点云投影线并划分桥墩面缓冲区;最后根据缓冲区自动提取墩面点云并进行位姿检测.本文以某山区高速桥梁高...     

基于显著性图像与纹理特征的遥感影像云检测

遥感影像云检测是遥感影像处理中非常关键的环节,准确识别影像含云区域能够提升影像的利用价值.根据遥感影像的成像特点,将阈值法和纹理特征结合实现云和下垫面的分割.首先将影像从RGB(red-green-blue)空间转化为HSI(hue-saturation-intensity)空间,进而构建影像的显著性图像,利用Otsu...     

激光雷达点云树木建模研究进展与展望

三维树木几何模型是数字城市与数字林业工程的重要组成部分.针对点云树木建模,深入分析了基于广义(泛在)激光雷达点云的树木模型重建方法,提出了聚类思想建模、图论方法建模、先验假设建模、拉普拉斯算子建模与轻量化表达建模5类建模体系,归纳总结了不同建模体系在树冠枝干的细节表达、建模算法性能、树木模型的多层次细节表达、建模体系综...     

多时相遥感影像的变化监测方法研究

多时相遥感影像图变化监测已经在国民经济及国防建设领域得到了广泛应用。通过分析同一地域不同时相的遥感图像变化监测提供地物发生变化的信息,对资源环境数据进行更新及利用。论文围绕变化监测中的一些关键理论方法进行了研究。     

A multi-index learning approach for classification of high-resolution remotely sensed images over urban areas

In recent years, it has been widely agreed that spatial features derived from textural, structural, and object-based methods are important information sources to complement spectral properties for accurate urban classification of high-resolution imagery. However, the spatial features always refer to a series of parameters, such as scales, directions, and statistical measures, leading to high-dimensional feature space. The high-dimensional space is almost impractical to deal with considering the huge storage and computational cost while processing high-resolution images. To this aim, we propose a novel multi-index learning (MIL) method, where a set of low-dimensional information indices is used to represent the complex geospatial scenes in high-resolution images. Specifically, two categories of indices are proposed in the study: (1) Primitive indices (PI): High-resolution urban scenes are represented using a group of primitives (e.g., building/shadow/vegetation) that are calculated automatically and rapidly; (2) Variation indices (VI): A couple of spectral and spatial variation indices are proposed based on the 3D wavelet transformation in order to describe the local variation in the joint spectral-spatial domains. In this way, urban landscapes can be decomposed into a set of low-dimensional and semantic indices replacing the high-dimensional but low-level features (e.g., textures). The information indices are then learned via the multi-kernel support vector machines. The proposed MIL method is evaluated using various high-resolution images including GeoEye-1, QuickBird, WorldView-2, and ZY-3, as well as an elaborate comparison to the state-of-the-art image classification algorithms such as object-based analysis, and spectral-spatial approaches based on textural and morphological features. It is revealed that the MIL method is able to achieve promising results with a low-dimensional feature space, and, provide a practical strategy for processing large-scale high-resolution images.     

Spectral monitoring of moorland plant phenology to identify a temporal window for hyperspectral remote sensing of peatland

Recognising the importance of the timing of image acquisition on the spectral response in remote sensing of vegetated ecosystems is essential. This study used full wavelength, 350–2500 nm, field spectroscopy to establish a spectral library of phenological change for key moorland species, and to investigate suitable temporal windows for monitoring upland peatland systems. Spectral responses over two consecutive growing seasons were recorded at single species plots for key moorland species and species sown to restore eroding peat. This was related to phenological change using narrowband vegetation indices (Red Edge Position, Photochemical Reflectance Index, Plant Senescence Reflection Index and Cellulose Absorption Index); that capture green-up and senescence related changes in absorption features in the visible to near infrared and the shortwave infrared. The selection of indices was confirmed by identifying the regions of maximum variation in the captured reflectance across the full spectrum. The indices show change in the degree of variation between species occurring from April to September, measured for plant functional types. A discriminant function analysis between indices and plant functional types determines how well each index was able to differentiate between the plant functional groups for each month. It identifies April and July as the two months where the species are most separable. What is presented here is not one single recommendation for the optimal temporal window for operational monitoring, but a fuller understanding of how the spectral response changes with the phenological cycle, including recommendations for what indices are important throughout the year.