基于DeepLabV3+的遥感影像道路中心线提取北大核心CSCD

针对目前已有基于遥感影像道路中心线提取算法易受道路旁树木遮挡、建筑物及其阴影覆盖和道路上车辆等因素影响,造成提取出来的道路中心线存在断裂、不完整现象,提出了一种基于深度学习语义分割的道路掩膜,引用细化算法提取道路中心线矢量数据,对矢量道路中心线进行优化的道路中心线提取方法。首先,通过对深度学习语义分割提取出来的道路掩膜进行形态学膨胀处理,减少道路掩膜出现部分断裂、空洞、不完整现象;然后,利用细化算法,对膨胀处理后的道路掩膜提取道路中心线并进行矢量化;最后,结合出现断裂处的道路中心线间几何、空间等约束关系,进行优化处理。实验结果表明:该方法相对于其他道路中心线提取方法,具有较高的精确度、完整度,在不考虑前期深度学习样本制作、模型训练所使用时间的情况下,提取效率也优于其他方法;生成了标准格式的矢量道路中心线数据,可直接用于实际生产。     

高分辨率遥感影像上道路中心线的半自动提取

提出一种半自动的基于活动窗口线段特征匹配来提取高分辨率遥感影像上道路中心线的方法.通过用户在道路中心线上输入起始点,采用定义活动模板窗、阈值分割、线段特征匹配和改进的SSDA,实现了道路中心线的自动跟踪.另外,该方法还允许在跟踪过程中加入少量人工干预来处理某些匹配失败的情况,提高了实用性.对0.61m分辨率QuickBird影像和1m分辨率IKONOS影像进行道路提取的实验表明:该方法能够快速、准确地提取出主要道路的中心线,对噪声的干扰具有良好的鲁棒性.     

分割道路影像并形成道路网的新方法

根据卫星影像提取道路信息过程,提出了一种从高分辨率卫星影像中提取道路网的新方法.先找到一点处纹理和灰度一致性最优方向,以此方向上的纹理描述值构成分割用特征矢量,将MRF模型应用于特征空间分割出道路目标.接着用改进的直线段匹配法去除以错分点组成的斑块,并借助仿真实验手段取得道路段中心线.连接中心线形成道路网.仿真结果验证了新方法的正确性.     

利用邻域质心投票从分类后影像提取道路中心线

目的 利用分类算法对高分辨率影像中的道路进行分割时,得到的二值图像往往混杂了许多非道路区域,且道路区域呈面状,无法直接应用于生产与研究。针对该问题,提出一种利用邻域质心投票提取道路中心线的算法。方法 首先检测像素在各方向上的连通距离以构建邻域多边形,随后进行质心投票来提取道路的中心线,与此同时估算道路宽度并判断出连通距离较长的方向数目,以排除非道路区域的干扰,最后经形态学处理得到细化的中心线。结果 选取测试图像及具有不同道路分布特征的高分辨率航空影像的分类结果进行实验,并将该算法与Zhang和Couloigner提出的算法进行了对比分析。结果显示,该算法的提取质量为80.6%和79.0%,且计算效率较高,处理实际影像的用时小于参考算法的20%,此外在稳定性及对不同路宽的适应性等多个方面均具有优势。结论 提出一种邻域质心投票算法,该算法能够同时实现传统方法中提纯与中心线提取两个步骤所对应的功能,从分类影像直接提取道路中心线。实验结果表明,该算法能够根据形状特征有效检测道路,且具备一定抗干扰能力,适用于对混杂了非道路区域的高分辨率影像的分类结果进行处理。     

基于数学形态学的高分辨率遥感影像道路提取

利用数学形态学的方法对高分辨率遥感影像道路提取进行了研究,通过对影像进行预处理增强道路信息,依据影像灰度直方图信息,对预处理后的影像进行阈值分割,得到一个包含道路信息的二值影像;进一步使用形态开运算去除细小噪声,同时将一部分粘连在道路上的噪声与道路信息进一步分割;接着结合形态腐蚀和形态重建运算获取影像中主要道路网络信息,并用形态闭运算完善道路网络信息;最后对道路网络信息进行形态细化和一定次数的形态修剪处理,得到单像素宽的道路中心线信息.利用数学计算软件MATLAB在高分辨率遥感影像上作了实验,并进行了总结和分析.     

基于Hough变换的高分辨率遥感影像城市直线道路提取

根据高分辨率遥感影像城市直线道路特性,提出在图像分割获得道路网轮廓的基础上,使用Hough变换检测道路所在直线,对直线进行道路判断,再将所得道路段进行修剪、连接形成道路网,实现道路提取。实验结果表明,该方法能有效的从高分辨遥感影像中提取城市直线道路。     

高分辨率多光谱遥感影像中城区道路信息的自动提取

提出一种从高分辨率遥感影像提取城市区域道路网络的方法。该方法采用改进的数学形态学运算方法对影像进行分割,进而得到粗略道路信息网,然后利用道路网的几何特征实现道路与建筑物的有效区分,最后通过抽骨架的方法获得最终道路网中心线。试验数据为某一城区高分辨率卫星影像,并对最终提取的结果进行了评价,结果表明,所提出的方法能够从高分辨率多波段卫星遥感影像上精确、有效、自动提取城区道路网络。     

基于VB/Matlab的果园移动机器人路径识别系统

为实现果园移动机器人导航信息的获取与实时显示,提出一种道路中心线类型的判别方法,并设计一种果园路径识别系统。通过对十六色相环在HSV颜色空间下H分量的分析,确定图像二值化阈值。针对处理完成的二值图,采用行扫描点检测算法获得道路中心离散点并用直线进行拟合,以直线和弯曲道路图为样本,分析离散点至拟合直线距离的均值方差分布,确定果园道路中心线类型判别条件,根据判别结果拟合果园道路中心线。为实现系统可视化,采用Matlab与VB混合编程技术将导航信息实时显示在VB设计的系统界面中。实验结果表明,与采用垂直投影法的Matlab-GUI视觉导航系统相比,该系统导航信息更新速度较快,道路识别成功率较高。     

全卷积神经网络遥感影像道路提取方法

针对人工选取简单特征提取道路效果不理想以及深度神经网络隐藏层信息应用较少的现状,提出一种基于全卷积神经网络的遥感影像道路提取方法。采用初始区域获取、中心线提取、中心线校正的工作流程对资源三号影像进行道路提取。首先自动标注训练样本,完成全卷积神经网络训练,借助卷积层等隐藏层提取的复杂特征获取道路区域;然后依据道路长宽比、形态学运算和格拉斯-普克(Douglas-Peucker,DP)算法完成干扰图斑滤除和断裂区域连接等工作;最后使用Zhang-Suen算法提取中心线,并利用网络首层卷积结果进行中心线校正。实验结果表明,该方法能借助自主学习的特征和网络隐藏层信息实现道路较好提取,不同实验区域中平均准确度在90%以上。     

园林景观设计中融合SVM的高分辨率遥感影像道路提取研究

为提高园林景观设计中高分辨率遥感影像道路提取的精度及效果,提出一种融合SVM的高分辨率遥感影像道路提取方法。该方法首先结合Mean Shift算法与数学形态学运算(简称MS-MMO)进行影像阴影提取;再根据阴影提取结果对原始影像阴影区域进行亮度补偿后输入SVM,得到初步提取的道路图像;然后利用高斯滤波算法进行图像平滑处理,利用边缘滤波、纹理滤波等算法去除图像中的非道路区域,得到道路区域提取图;最后基于张量投票提取道路中心线,基于“交点”搜索方法去除道路中心线上的毛刺,完成道路提取。实验结果表明,MS-MMO的具有较好的阴影提取精度及效果;根据MS-MMO输出的阴影提取结果对原始影像阴影区域进行亮度补偿后,道路提取的整体性能更高;融合SVM的高分辨率遥感影像道路提取方法提取的道路完整性、正确性、质量分别达到92.4%、92.7%、89.0%,道路提取性能较好,且道路具有连通属性,在该方法提取的道路图像上进行园林景观设计,可有效提升道路植物配置效果。     

A two-stage framework for road extraction from high-resolution satellite images by using prominent features of impervious surfaces

The segmentation and classification of high-resolution satellite images (HRSI) are useful approaches to extract information. In recent times, roads and buildings have been classified for analysis of urban areas in a better manner. Apart from these, healthy trees are also an important factor in HRSI, i.e. adjacent to roads, and vegetation. They reflect the area in an image as land cover. Other important information, shadow, is extracted from satellite images, which indicates the presence of trees and built-up areas such as buildings, flyovers, etc. In this article, a weighted membership-function-based fuzzy c-means with spatial constraints (WMFCSC) approach for automated satellite image classification is proposed. Initially, spatially fuzzy clustering is used to classify the satellite images in healthy trees with vegetation, roads, and shadows, which includes the information of spatial constraints. The road results of the classified image are still having non-road segments. Therefore, the proposed four intermediate stages (IS) are used to extract the road information, followed by the results of road areas of the WMFCSC approach. The framework of IS helps to remove the false road segments which are adjacent to roads and renovates the segmented roads due to the shadow effect. A final step of a hybrid WMFCSC-IS approach is used to extract the road network. The results of classified images confirm the effectiveness of the WMFCSC-IS approach for satellite image classification.     

基于改进的渐进纹理分析技术提取IKONOS影像中的城市主要道路

提出了一种从IKONOS多光谱影像提取城市主要道路的方法。首先对影像进行3个层次的纹理分析。第一层为检测集像元与训练集像元在波段空间中的闵氏距离;第二层为检测集像元及其3×3窗口内像元分布与训练集像元在波段空间中的巴氏距离;第三层为检测集像元及其3×3窗口内像元分布与训练集像元在彩色纹理特征空间中的巴氏距离。对上述获取的结果分别进行了阈值分割、细化,并结合道路的几何特征,采用模糊数学的方法对各个图层进行了融合。接着提出了一种基于道路知识的道路段连接算法。最后用多项式拟合方法对连接结果进行了优化,获得了较好的提取结果。     

Classified road detection from satellite images based on perceptual organization

Extracting roads from satellite images is an important task in both research and practice. This work presents an improved model for road detection based on the principles of perceptual organization and classification fusion in human vision system (HVS). The model consists of four levels: pixels, primitives, structures and objects, and two additional sub‐processes: automatic classification of road scenes and global integration of multiform roads. Based on the model, a novel algorithm for detecting roads from satellite images is also proposed, in which two types of road primitives, namely blob‐like primitive and line‐like primitive are defined, measured, extracted and linked using different methods for dissimilar road scenes. A hierarchical search strategy driven by saliency measurement is adopted in both linking processes. The blob primitives are linked using heuristic grouping and the line primitives are connected through genetic algorithm (GA) evolution. Finally, all of the linked road segments are normalized with centre‐main lines and integrated into global smooth road curves through tensor voting. Experimental results show that the algorithm is capable of detecting multiform roads from real satellite images with high adaptability and reliability.     

Road-edge delineation in rural areas: effects on driving behaviour

When driving on lower-category Dutch rural roads without any delineation, drivers are likely to drift off the road with their right-side wheels, thus incurring damage to the pavement edge or even leading to accidents. In two experiments, two types of road-edge delineation, with continuous or dashed edge lines, were compared with two control roads without lines or with only a dashed line on the road axis. The first experiment consisted of non-obtrusive video recordings of passing traffic. Vehicle position on the experimental roads was more to the road's centre than on the control roads. The second experiment was a driving test with an instrumented vehicle, during daytime lighting and during darkness. Again, vehicle lateral position was more central on the experimental roads, especially during darkness. Subjects could safely pass oncoming vehicles. Driving speed increased on the experimental roads compared with the unlined control road, but not beyond speeds found on the axis-lined control road. Driver's mental effort while driving over the experimental roads did not differ from the effort while driving over the control roads. Subjectively rated effort was higher for the unlined control road than for the three other roads. Subjects preferred the edge-lined roads to the unlined control road, but not more than the axis-lined control road. It was concluded that edge-lines may provide a simple and effective way of inducing a more favourable lateral position on rural roads without having negative effects on subjective appraisal, driving performance or mental workload.     

Road-edge delineation in rural areas: effects on driving behaviour

When driving on lower-category Dutch rural roads without any delineation, drivers are likely to drift off the road with their right-side wheels, thus incurring damage to the pavement edge or even leading to accidents. In two experiments, two types of road-edge delineation, with continuous or dashed edge lines, were compared with two control roads without lines or with only a dashed line on the road axis. The first experiment consisted of non-obtrusive video recordings of passing traffic. Vehicle position on the experimental roads was more to the road's centre than on the control roads. The second experiment was a driving test with an instrumented vehicle, during daytime lighting and during darkness. Again, vehicle lateral position was more central on the experimental roads, especially during darkness. Subjects could safely pass oncoming vehicles. Driving speed increased on the experimental roads compared with the unlined control road, but not beyond speeds found on the axis-lined control road. Driver's mental effort while driving over the experimental roads did not differ from the effort while driving over the control roads. Subjectively rated effort was higher for the unlined control road than for the three other roads. Subjects preferred the edge-lined roads to the unlined control road, but not more than the axis-lined control road. It was concluded that edge-lines may provide a simple and effective way of inducing a more favourable lateral position on rural roads without having negative effects on subjective appraisal, driving performance or mental workload.     

Vision-based autonomous land vehicle guidance in outdoor road environments using combined line and road following techniques

An intelligent approach to autonomous land vehicle (ALV) guidance in outdoor road environments using combined line and road following and color information clustering techniques is proposed. Path lines and road boundaries are selected as reference models, called the line-model and the road-model, respectively. They are used to perform line-model matching (LMM) and road-model matching (RMM) to locate the ALV for line and road following, respectively. If there are path lines in the road, the LMM process is used to locate the ALV because it is faster than the RMM process. On the other hand, if no line can be found in the road, the RMM process is used. To detect path lines in a road image, the Hough transform is employed, which does not take much computing time because bright pixels in the road are very few. Various color information on roads is used for extracting path lines and road surfaces. And the ISODATA clustering algorithm based on an initial-center-choosing technique is employed to solve the problem caused by great changes of intensity in navigations. The double model matching procedure combined with the color information clustering process enables the ALV to navigate smoothly in roads even if there are shadows, cars, people, or degraded regions on roadsides. Some intelligent methods to speed up the model matching processes and the Hough transform based on the feedback of the previous image information are also presented. Successful navigations show that the proposed approach is effective for ALV guidance in common roads. ©1997 John Wiley & Sons, Inc.     

基于激光点云的道路可通行区域检测方法

以车载激光雷达获取的点云数据为研究对象,针对无人车道路环境感知的关键技术展开研究。为解决无人驾驶中道路可通行区域检测存在的地面不平整、缓坡、障碍物单一等问题,提出基于激光点云数据的道路可通行区域检测方法。通过基于分段校准的RANSAC算法进行地面分割,解决地面不平整导致的欠分割问题。使用多特征复合判据,利用基于体素化的DBSCAN聚类算法和基于结构特征的障碍物识别方法完成障碍物的分割与识别。结合道路结构以及数据高程突变特征,提取道路边界候选点并拟合得到完整的道路边界线。将道路区域栅格化,根据道路边界悬空障碍物判断并更新可通行区域,实现可通行区域的准确检测。实验结果表明,该方法在复杂道路场景中的边界检测准确率高于95%,可有效检测出障碍物及道路的可通行区域,具有良好的实时性与鲁棒性。     

Road detection algorithm for Autonomous Navigation Systems based on dark channel prior and vanishing point in complex road scenes

Vision-based road extraction is essentially important in many fields, such as for intelligent traffic and robot navigation. However, the road detection in urban or ill-structured roads is still very challenging at current stage, and the existing methods often suffer from high computational complexity. This paper reports a novel and efficient method for road detection in challenging scenes. First, the dark channel based image segmentation is proposed to distinguish a rough road region from complex background noise, which is envisioned to reduce the workload of road detection. Furthermore, instead of using the conventional pixel-wise soft voting, a new voting strategy based on the vanishing point and the properties of the segmented regions is proposed to further reduce the computation time of road extraction stage. Finally, the segmented region which has the maximum voting value is selected as the road region. Experimental results demonstrated that the proposed algorithm shows superior performance in different kinds of road scenes. It can remove the interference from pedestrians, vehicles and other obstacles. Our method is about 40 times faster in detection speed, when compared to a recently well-known approach.     

DESIGNING ROAD NETWORKS FOR TRANSPORT PLANNING USING EVOLUTIONARY COMPUTATION

In this article, a new approach to designing optimum urban road networks using evolutionary methods is described. The model is capable of finding a road network that addresses the private transport assignment in a certain city area. Experiments using our model in real transport assignment tasks show the promise of the approach to improve existing roads and create new roads as projected in a near future.     

An unbiased algorithm for detection of curvilinear structures in urban remote sensing images

Based on the Gaussian scale‐space, a Gaussian comparison function is presented for extracting the linearly road features in aerial remote sensing image. Combining the geometric and radiometric features, the curvilinear structures of the roads are extracted based on locally oriented energy in continuous scale‐space. Curvilinear features of roads are verified, grouped and extracted by using both topologic and geometric methods. This algorithm is applicable to extracting the road features in different scale such as rural roads or urban highways, and significantly reduces the computation complexity of line tracing. Some discussions on the zero drift of the Gaussian comparison function are also presented.