移动机器人基于多传感器信息融合的室外场景理解

本文研究了移动机器人多传感器信息融合技术,提出一种融合激光测距与视觉信息的实时室外场景理解方法．基于三维激光测距数据构建了高程图描述场景地形特征,同时利用条件随机场模型从视觉信息中获取地貌特征,并以高程图中的栅格作为载体,应用投影变换和信息统计方法将激光信息与视觉信息进行有效融合．在此基础上,对融合后的环境模型分别在地形和地貌两个层面进行可通过性评估,从而实现自主移动机器人实时室外场景理解．实验结果和数据分析验证了所提方法的有效性和实用性．     

6D scan registration using depth-interpolated local image features

This paper describes a novel registration approach that is based on a combination of visual and 3D range information. To identify correspondences, local visual features obtained from images of a standard color camera are compared and the depth of matching features (and their position covariance) is determined from the range measurements of a 3D laser scanner. The matched depth-interpolated image features allow one to apply registration with known correspondences. We compare several ICP variants in this paper and suggest an extension that considers the spatial distance between matching features to eliminate false correspondences. Experimental results are presented in both outdoor and indoor environments. In addition to pair-wise registration, we also propose a global registration method that registers all scan poses simultaneously.     

Three-dimensional iterative closest point-based outdoor SLAM using terrain classification

To navigate in an unknown environment, a robot should build a model for the environment. For outdoor environments, an elevation map is used as the main world model. We considered the outdoor simultaneous localization and mapping (SLAM) method to build a global elevation map by matching local elevation maps. In this research, the iterative closest point (ICP) algorithm was used to match local elevation maps and estimate a robot pose. However, an alignment error is generated by the ICP algorithm due to false selection of corresponding points. Therefore, we propose a new method to classify environmental data into several groups, and to find the corresponding points correctly and improve the performance of the ICP algorithm. Different weights are assigned according to the classified groups because certain groups are very sensitive to the viewpoint of the robot. Three-dimensional (3-D) environmental data acquired by tilting a 2-D laser scanner are used to build local elevation maps and to classify each grid of the map. Experimental results in real environments show the increased accuracy of the proposed ICP-based matching and a reduction in matching time.     

基于激光雷达的环境特征提取方法研究

环境特征提取是移动机器人导航中的研究难点,以2D激光雷达为环境感知传感器,针对室内环境中的应用提出一种环境特征提取方法;通过激光雷达的测距精度评估,基于近邻方法对环境中障碍进行空间分类特征提取;对该方法不足进行分析的基础之上,为了能够提取更为精确的特征信息,将SOM方法应用于激光雷达的环境特征提取中;结合装备2D激光雷达LMS291的自行研制的移动机器人采集的数据进行实验,实验结果验证了所提方法的有效性.     

真实感3D重建中的纹理映射技术

精确的纹理映射是体现模型视觉真实感的关键因素。本文在阐述纹理映射技术原理的基础上,探讨了基于3维激光扫描设备进行3D重建过程中,实现具有高度真实感的纹理映射所遇到的实际问题,提出了基于纹理的模型重构和纹理光照连续性重建算法,解决了纹理图像空间不连续、光照不连续等因素对模型真实感的影响,并通过真实数据的实验对算法有效性进行了验证,为大型户外实体的真实感3D重建奠定了技术基础。     

Registration and integration of multiple object views for 3D modelconstruction

Automatic 3D object model construction is important in applications ranging from manufacturing to entertainment, since CAD models of existing objects may be either unavailable or unusable. We describe a prototype system for automatically registering and integrating multiple views of objects from range data. The results can then be used to construct geometric models of the objects. New techniques for handling key problems such as robust estimation of transformations relating multiple views and seamless integration of registered data to form an unbroken surface have been proposed and implemented in the system. Experimental results on real surface data acquired using a digital interferometric sensor as well as a laser range scanner demonstrate the good performance of our system     

Graph cut based panoramic 3D modeling and ground truth comparison with a mobile platform – The Wägele

Efficient and comfortable acquisition of large 3D scenes is an important topic for many current and future applications in the field of robotics, factory and office visualization, 3DTV and cultural heritage.In this paper we present both an omnidirectional stereo vision approach for 3D modeling based on graph cut techniques and also a new mobile 3D model acquisition platform where it is employed. The platform comprises a panoramic camera and a 2D laser range scanner for self localization by scan matching. 3D models are acquired just by moving the platform around and recording images in regular intervals. Additionally, we concurrently build 3D models using two supplementary laser range scanners. This enables the investigation of the stereo algorithm’s quality by comparing it with the laser scanner based 3D model as ground truth. This offers a more objective point of view on the achieved 3D model quality.     

Identifying vegetation from laser data in structured outdoor environments

The ability to reliably detect vegetation is an important requirement for outdoor navigation with mobile robots as it enables the robot to navigate more efficiently and safely. In this paper, we present an approach to detect flat vegetation, such as grass, which cannot be identified using range measurements. This type of vegetation is typically found in structured outdoor environments such as parks or campus sites. Our approach classifies the terrain in the vicinity of the robot based on laser scans and makes use of the fact that plants exhibit specific reflection properties. It uses a support vector machine to learn a classifier for distinguishing vegetation from streets based on laser reflectivity, measured distance, and the incidence angle. In addition, it employs a vibration-based classifier to acquire training data in a self-supervised way and thus reduces manual work. Our approach has been evaluated extensively in real world experiments using several mobile robots. We furthermore evaluated it with different types of sensors and in the context of mapping, autonomous navigation, and exploration experiments. In addition, we compared it to an approach based on linear discriminant analysis. In our real world experiments, our approach yields a classification accuracy close to 100%.     

Localization of an unmanned ground vehicle based on hybrid 3D registration of 360 degree range data and DSM

A computer vision technique to identify the location of an outdoor unmanned ground vehicle (UGV) is presented. The proposed technique is based on hybrid 3D registration of 360 degree laser range data to a digital surface model (DSM). Range frames obtained from 48 laser detectors are aligned with the reference coordinate system of the DSM. Three novel approaches are proposed for accurate and fast 3D registration of range data and the DSM. First, a two-step hybrid 3D registration technique is proposed. A pair-wise registration step of two consecutive range frames is followed by a refinement step using a layered DSM. Second, a fast projection-based pair-wise registration is proposed by employing rasterized 360 degree range frames. Third, a high elevation DSM is divided into several elevation layers and correspondence search is done near the vehicle’s current elevation. This reduces the number of matching outliers and facilitates fast localization. Experimental results show that the proposed approaches yield better performance in 3D localization compared to conventional 3D registration techniques. Error analysis on five outdoor paths is presented with respect to ground truth.     

3D reconstruction and classification of natural environments by an autonomous vehicle using multi-baseline stereo

In natural outdoor settings, advanced perception systems and learning strategies are major requirement for an autonomous vehicle to sense and understand the surrounding environment, recognizing artificial and natural structures, topology, vegetation and drivable paths. Stereo vision has been used extensively for this purpose. However, conventional single-baseline stereo does not scale well to different depths of perception. In this paper, a multi-baseline stereo frame is introduced to perform accurate 3D scene reconstruction from near range up to several meters away from the vehicle. A classifier that segments the scene into navigable and non-navigable areas based on 3D data is also described. It incorporates geometric features within an online self-learning framework to model and identify traversable ground, without any a priori assumption on the terrain characteristics. The ground model is automatically retrained during the robot motion, thus ensuring adaptation to environmental changes. The proposed strategy is of general applicability for robot’s perception and it can be implemented using any range sensor. Here, it is demonstrated for stereo-based data acquired by the multi-baseline device. Experimental tests, carried out in a rural environment with an off-road vehicle, are presented. It is shown that the use of a multi-baseline stereo frame allows for accurate reconstruction and scene segmentation at a wide range of visible distances, thus increasing the overall flexibility and reliability of the perception system.     

Range segmentation of large building exteriors: A hierarchical robust approach

There are three main challenging issues associated with processing range data of large-scale outdoor scene: (a) significant disparity in the size of features, (b) existence of complex and multiple structures; and (c) high uncertainty in data due to the construction error or moving objects. Existing range segmentation methods in computer vision literature have been generally developed for laboratory-sized objects or shapes with simple geometric features and do not address these issues. This paper studies the main problems involved in segmenting the range data of large building exteriors and presents a robust hierarchical segmentation strategy to extract fine as well as large details from such data. The proposed method employs a high breakdown robust estimator in a coarse-to-fine approach to deal with the existing discrepancies in size and sampling rates of various features of large outdoor objects. The segmentation algorithm is tested on several outdoor range datasets obtained by different laser rangescanners. The results show that the proposed method is an accurate and computationally cost-effective tool that facilitates automatic generation of 3D models of large-scale objects in general and building exteriors in particular.     

Land cover classification using multi‐temporal MERIS vegetation indices

The spectral, spatial, and temporal resolutions of Envisat's Medium Resolution Imaging Spectrometer (MERIS) data are attractive for regional‐ to global‐scale land cover mapping. Moreover, two novel and operational vegetation indices derived from MERIS data have considerable potential as discriminating variables in land cover classification. Here, the potential of these two vegetation indices (the MERIS global vegetation index (MGVI), MERIS terrestrial chlorophyll index (MTCI)) was evaluated for mapping eleven broad land cover classes in Wisconsin. Data acquired in the high and low chlorophyll seasons were used to increase inter‐class separability. The two vegetation indices provided a higher degree of inter‐class separability than data acquired in many of the individual MERIS spectral wavebands. The most accurate landcover map (73.2%) was derived from a classification of vegetation index‐derived data with a support vector machine (SVM), and was more accurate than the corresponding map derived from a classification using the data acquired in the original spectral wavebands.     

Modelling and animating faces using scanned data

This paper extends a physically-based approach to the realistic modelling and animation of human heads using scanned data. A three-step procedure is proposed which begins with geometry and colour data acquired from a subject's head using a radial laser scanner, continues with the construction of a 3D model of the head with complete colour texture mapping, and culminates in real-time, interactive facial animation. First, an adaptive meshing technique is described that creates non-uniform facial meshes from the densely sampled data. These geometrically accurate facial meshes adapt to features of interest in the data, increasing polygon density over articulate face regions and areas of high curvature. Secondly, the mesh is transformed into a physically-based head model of the subject. This incorporates a physical approximation to facial tissue and a set of anatomically-motivated facial muscle actuators. Finally, these components are integrated in a facial modelling and animation system.     

Directional reflectance properties determined by analysis of airborne multispectral scanner data and atmospheric correction

Directional reflectance properties of natural surfaces are very important in the interpretation of remotely sensed data. The analysis of multispectral scanner data shows a distinct dependence on scan angle, wavelength (0.4–1.1 μm), and classes (e.g., bare soil, vegetation). This relationship can be described by polynomials determined by regression methods. Atmospheric effects are computed with a simple model by parametrization of the multiple scattered skylight. The model permits a quick and sufficient estimation of the airlight, depending on the data collection conditions. Comparisons of the scanner data with the corresponding model yield the following results: The differences between airborne and ground measurements are due to atmospheric effects. The directional variation in brightness is mainly caused by the object itself with the exception of short wavelengths and/or a very low albedo. The hue shift of vegetation is essentially produced by the object and modified by the atmosphere. Taking into account the directional reflectance properties in a direction-dependent classification procedure results in an improvement of up to 20% in comparison with algorithms used so far. Quantitative relationships between ground measurements and radiation measurements by airborne sensors including atmospheric effects can be determined with the proposed methods.     

Mobile robot motion estimation by 2D scan matching with genetic and iterative closest point algorithms

The paper reports on mobile robot motion estimation based on matching points from successive two‐dimensional (2D) laser scans. This ego‐motion approach is well suited to unstructured and dynamic environments because it directly uses raw laser points rather than extracted features. We have analyzed the application of two methods that are very different in essence: (i) A 2D version of iterative closest point (ICP), which is widely used for surface registration; (ii) a genetic algorithm (GA), which is a novel approach for this kind of problem. Their performance in terms of real‐time applicability and accuracy has been compared in outdoor experiments with nonstop motion under diverse realistic navigation conditions. Based on this analysis, we propose a hybrid GA‐ICP algorithm that combines the best characteristics of these pure methods. The experiments have been carried out with the tracked mobile robot Auriga‐α and an on‐board 2D laser scanner. © 2006 Wiley Periodicals, Inc.     

Noise analysis and synthesis for 3D laser depth scanners

This paper analyses the noise present in range data measured by a Konica Minolta Vivid 910 scanner, in order to better characterise real scanner noise. Methods for denoising 3D mesh data have often assumed the noise to be Gaussian, and independently distributed at each mesh point. We show via measurements of an accurately machined almost planar test surface that real scanner data does not have such properties: the errors are not quite Gaussian, and more importantly, exhibit significant short range correlation. We use this to give a simple model for generating noise with similar characteristics. We also consider how noise varies with such factors as laser intensity, orientation of the surface, and distance from the scanner. Finally, we evaluate the performance of three typical mesh denoising algorithms using real and synthetic test data, and suggest that new denoising algorithms are required for effective removal of real noise.     

Range image smoothing and completion utilizing laser intensity

In this paper, we propose new denoising techniques for a deteriorated range image taken by a laser scanner. Laser scanner acquires a range value from the scanner to the target by measuring the round-trip time of the emitted laser pulse. At the same time, they can obtain the strength of the reflected light as a side product of the range value. Focusing on the laser intensity, we propose two denoising techniques for a deteriorated range image utilizing the intensity image: smoothing by extended bilateral filter, and completion by belief propagation. The extended bilateral filter makes use of laser intensity in addition to the spatial and range information in order that we can smooth a range image corrupted by noises while the geometric features such as jump and roof edges are preserved. The range image completion technique with belief propagation restores a deteriorated range image using the adjacent range values and the corresponding intensity values simultaneously. We conduct simulations and experiments using synthesized images and actual range images taken by a laser scanner and verify that the proposed techniques suppress noise while preserving jump and roof edges and repair deteriorated range images.     

Development of deep learning architecture for automatic classification of outdoor mobile LiDAR data

This paper proposes a deep convolutional neural network (CNN) architecture for automatic classification of mobile laser scanning (MLS) data obtained for outdoor environment, which are characterized by noise, clutter, large size and larger quantum of information. The developed architecture introduces a look up table (LUT) based approach, which retains the geometry of the input MLS point cloud while rescaling. Further, with the voxelisation of the input MLS sample, the ambiguity of selecting one out of multiple point values within a voxel is resolved. The performance of the architecture is evaluated on MLS data of outdoor environment in two instances, first using tree and non-tree classes (non-tree class has objects like electric pole, wire, low vegetation, wall, house and ground) and then with tree and electric pole classes. Additional testing is carried out by mixing the outdoor MLS data of tree and electric pole classes with three classes of indoor objects, taken from Modelnet dataset, thereby assessing the architecture efficacy over an ensemble of three-dimensional (3D) datasets. Classification of tree and non-tree classes, followed by tree and electric pole classes from MLS samples result in total accuracies of 86.0%, 90.0% respectively and kappa values of 72.0%, 78.7% respectively. Moreover, for the combinations of MLS and Modelnet classes, the classification results are promising, reaching a total accuracy of 95.2% and kappa of 92.5%. The LUT based approach has shown better classification over the traditional rescaling approach for the MLS dataset, resulting in an enhancement up to 9.0% and 18.0% in total accuracy and kappa, respectively. With different varieties of tree, non-tree and electric pole samples, the proposed architecture has shown its potential for automatic classification of MLS data with high accuracy. This study further reveals that the accuracy of classification is improved by introducing more spatial features in the input layer. The accuracies produced in this work can be further improved with the availability of better hardware resources.     

基于足底扫描仪扫描数据的处理研究

由于环境及设备因素的影响,利用三维激光扫描仪获得的STL格式的足底数据,含有大量冗余数据、噪声点和对模型重构作用不大的点数据。这严重影响了数据读取与显示的效率,不利于后续的曲面重构。针对三维足底扫描系统FS-200 Pro所获得的足底数据,本文提出采用在读取时进行冗余点判断,不重复读取顶点;对读取数据用孤立点去除法和弦高法对扫描线数据进行去噪;通过计算距离与弦高,设定阈值遍历比较每个数据点判断其是否为去除点。经实例检测验证,上述方法能有效去除噪声点,提高简化效率,在保持数据原型的基础上达到了预期效果。