This tutorial paper gives an introduction and overview of various topics related to airborne laser scanning (ALS) as used to measure range to and reflectance of objects on the earth surface. After a short introduction, the basic principles of laser, the two main classes, i.e., pulse and continuous-wave lasers, and relations with respect to time-of-flight, range, resolution, and precision are presented. The main laser components and the role of the laser wavelength, including eye safety considerations, are explained. Different scanning mechanisms and the integration of laser with GPS and INS for position and orientation determination are presented. The data processing chain for producing digital terrain and surface models is outlined. Finally, a short overview of applications is given.

Meanwhile, we compared the performances of five classifiers. The rule-based method provides the highest overall accuracy at 97.0%. The rule-based method provides over 99.0% accuracy for the ground and roof classes, and a minimum accuracy of 90.0% for the water, vegetation, wall and undefined object classes. Notably, the accuracy of the roof element class is only 70% with the rule-based method, or even lower with other classifiers. Most roof elements have been assigned to the roof class, as shown in the confusion matrix. These erroneous assignments are not fatal errors because both a roof and a roof element are part of a building. In addition, a new feature which indicates the average point space within the planar segment is generalised to distinguish vegetation from other classes. Its performance is compared to the percentage of points with multiple pulse count in planar segments. Using the feature computed with only average point space, the detection rate of vegetation in a rule-based classifier is 85.5%, which is 6% lower than that with pulse count information.

Results for the ISPRS benchmark test data show that to rely on color information to separate vegetation from non-vegetation areas does mostly lead to good results, but in particular in shadow areas a confusion between classes might occur. The unsupervised classification strategy is especially sensitive in this respect. As far as the point cloud densification is concerned, we observe similar sensitivity with respect to color which makes some planes to be missed out, or false detections still remain. For planes where the densification is successful we see the expected enhancement of the outline.

Using high-spatial-resolution multispectral imagery alone is insufficient for achieving highly accurate and reliable thematic mapping of urban areas. Integration of lidar-derived elevation information into image classification can considerably improve classification results. Additionally, traditional pixel-based classifiers have some limitations in regard to certain landscape and data types. In this study, we take advantage of current advances in object-based image analysis and machine learning algorithms to reduce manual image interpretation and automate feature selection in a classification process. A sequence of image segmentation, feature selection, and object classification is developed and tested by the data sets in two study areas (Mannheim, Germany and Niagara Falls, Canada). First, to improve the quality of segmentation, a range image of lidar data is incorporated in an image segmentation process. Among features derived from lidar data and aerial imagery, the random forest, a robust ensemble classifier, is then used to identify the best features using iterative feature elimination. On the condition that the number of samples is at least two or three times the number of features, a segmentation scale factor has no particular effect on the selected features or classification accuracies. The results of the two study areas demonstrate that the presented object-based classification method, compared with the pixel-based classification, improves by 0.02 and 0.05 in kappa statistics, and by 3.9% and 4.5% in overall accuracy, respectively.

在分析LiDAR点云数据分类现状的基础上,针对植被与建筑物重叠区域分类困难的问题,提出了一种基于面向对象的点云分类方法。首先采用三角网渐进内插的滤波方法将点云分为地面点和非地面点,并得到DTM; 然后对高出DTM一定高度的非地面点建立三角网,删除较长的三角网的边(地物间的边),从而将非地面点云分割成多个对象; 再利用各个对象内的三角网坡度信息熵大小判断该对象属于植被或建筑物; 最后对于难以区分的对象(植被与建筑物重叠区)根据建筑物几何规则形状延伸扩充,从而提高植被和建筑物重叠区的点云分类准确率。实验结果表明,该方法能够很好地区分建筑物和植被点,分类准确率达到87%。

A large number of applications and research fields rely on up-to-date and accurate representation of existing buildings, for example in GIS or 3D city models. Besides verification of existing building datasets, the detection of new objects from remote sensing data is a major task in digital photogrammetry. This paper presents a new approach on building detection and simple reconstruction using airborne oblique images only. Fa ades are detected in oblique images using edge and height information. The latter is extracted from the same images using a dense image matching technique, implying the need for stereo overlap at the particular fa ade. The fa ades are represented as vertical planes in object space and are used to define building hypotheses. These initial buildings are then verified and refined employing the point cloud as derived from multiple image dense matching. The method has been tested on almost 400 buildings in two areas which include different building structures. The results show that the detection rate depends on the number of viewing directions available at a particular building. A building is considered to be detected as soon as any portion of it is detected by our algorithm. Accordingly the correctness is constant above 90%, demonstrating the robustness of the approach. The completeness varies from 67% to 95%, while the geometric accuracy is limited because only box models are fitted to fa ades. Thus, the next step in the research will be to adapt the outline delineation to irregular buildings.

In addition to aerial imagery, point clouds are important remote sensing data in urban environment studies. It is essential to extract semantic information from both images and point clouds for such purposes; thus, this study aims to automatically classify 3-D point clouds generated using oblique aerial imagery (OAI)/vertical aerial imagery (VAI) into various urban object classes, such as roof, facade, road, tree, and grass. A multicamera airborne imaging system that can simultaneously acquire VAI and OAI is suggested. The acquired small-format images contain only three RGB spectral bands and are used to generate photogrammetric point clouds through a multiview-stereo dense matching technique. To assign each 3-D point cloud to a corresponding urban object class, we first analyzed the original OAI through object-based image analyses. A rule-based hierarchical semantic classification scheme that utilizes spectral information and geometry- and topology-related features was developed, in which the object height and gradient features were derived from the photogrammetric point clouds to assist in the detection of elevated objects, particularly for the roof and facade. Finally, the photogrammetric point clouds were classified into the aforementioned five classes. The classification accuracy was assessed on the image space, and four experimental results showed that the overall accuracy is between 82.47% and 91.8%. In addition, visual and consistency analyses were performed to demonstrate the proposed classification scheme's feasibility, transferability, and reliability, particularly for distinguishing elevated objects from OAI, which has a severe occlusion effect, image-scale variation, and ambiguous spectral characteristics.

针对机载LiDAR系统数据分类中多源特征与城区分类目标相关性不明确的问题，在面向对象的数据特征挖掘基础上，提出了一种基于随机森林的机载LiDAR系统特征选择与分类方法，利用不同地区数据实验证明:本文方法能对机载LiDAR系统数据多源特征的重要性进行正确评估，通过特征选择，在减少特征的情况下仍能够达到较高的分类精度。

The filtering of point clouds is a ubiquitous task in the processing of airborne laser scanning (ALS) data; however, such filtering processes are difficult because of the complex configuration of the terrain features. The classical filtering algorithms rely on the cautious tuning of parameters to handle various landforms. To address the challenge posed by the bundling of different terrain features into a single dataset and to surmount the sensitivity of the parameters, in this study, we propose an adaptive surface filter (ASF) for the classification of ALS point clouds. Based on the principle that the threshold should vary in accordance to the terrain smoothness, the ASF embeds bending energy, which quantitatively depicts the local terrain structure to self-adapt the filter threshold automatically. The ASF employs a step factor to control the data pyramid scheme in which the processing window sizes are reduced progressively, and the ASF gradually interpolates thin plate spline surfaces toward the ground with regularization to handle noise. Using the progressive densification strategy, regularization and self-adaption, both performance improvement and resilience to parameter tuning are achieved. When tested against the benchmark datasets provided by ISPRS, the ASF performs the best in comparison with all other filtering methods, yielding an average total error of 2.85% when optimized and 3.67% when using the same parameter set.

Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.

Airborne lidar systems have become a source for the acquisition of elevation data. They provide georeferenced, irregularly distributed 3D point clouds of high altimetric accuracy. Moreover, these systems can provide for a single laser pulse, multiple returns or echoes, which correspond to different illuminated objects. In addition to multi-echo laser scanners, full-waveform systems are able to record 1D signals representing a train of echoes caused by reflections at different targets. These systems provide more information about the structure and the physical characteristics of the targets. Many approaches have been developed, for urban mapping, based on aerial lidar solely or combined with multispectral image data. However, they have not assessed the importance of input features. In this paper, we focus on a multi-source framework using aerial lidar (multi-echo and full waveform) and aerial multispectral image data. We aim to study the feature relevance for dense urban scenes. The Random Forests algorithm is chosen as a classifier: it runs efficiently on large datasets, and provides measures of feature importance for each class. The margin theory is used as a confidence measure of the classifier, and to confirm the relevance of input features for urban classification. The quantitative results confirm the importance of the joint use of optical multispectral and lidar data. Moreover, the relevance of full-waveform lidar features is demonstrated for building and vegetation area discrimination.