Effective extraction of road boundaries plays a significant role in intelligent transportation applications, including autonomous driving, vehicle navigation, and mapping. This paper presents a new method to automatically extract 3-D road boundaries from mobile laser scanning (MLS) data. The proposed method includes two main stages: supervoxel generation and 3-D road boundary extraction. Supervoxels are generated by selecting smooth points as seeds and assigning points into facets centered on these seeds using several attributes (e.g., geometric, intensity, and spatial distance). 3-D road boundaries are then extracted using the α-shape algorithm and the graph cuts-based energy minimization algorithm. The proposed method was tested on two data sets acquired by a RIEGL VMX-450 MLS system. Experimental results show that road boundaries can be robustly extracted with an average completeness over 95%, an average correctness over 98%, and an average quality over 94% on two data sets. The effectiveness and superiority of the proposed method over the state-of-the-art methods is demonstrated.

Using mobile Light Detection and Ranging point clouds to accomplish road scene labeling tasks shows promise for a variety of applications. Most existing methods for semantic labeling of point clouds require a huge number of fully supervised point cloud scenes, where each point needs to be manually annotated with a specific category. Manually annotating each point in point cloud scenes is labor intensive and hinders practical usage of those methods. To alleviate such a huge burden of manual annotation, in this paper, we introduce an active learning method that avoids annotating the whole point cloud scenes by iteratively annotating a small portion of unlabeled supervoxels and creating a minimal manually annotated training set. In order to avoid the biased sampling existing in traditional active learning methods, a neighbor-consistency prior is exploited to select the potentially misclassified samples into the training set to improve the accuracy of the statistical model. Furthermore, lots of methods only consider short-range contextual information to conduct semantic labeling tasks, but ignore the long-range contexts among local variables. In this paper, we use a higher order Markov random field model to take into account more contexts for refining the labeling results, despite of lacking fully supervised scenes. Evaluations on three data sets show that our proposed framework achieves a high accuracy in labeling point clouds although only a small portion of labels is provided. Moreover, comparative experiments demonstrate that our proposed framework is superior to traditional sampling methods and exhibits comparable performance to those fully supervised models.

A terrestrial laser scanning (TLS) point cloud acquired from a given ground view is incomplete because of severe occlusion and self-occlusion. The models reconstructed by aligning the cross-source point clouds [TLS and structure-from-motion (SFM) point clouds] provide a more complete large-scale outdoor scene. However, because of differences in nonrigid deformation, stratified redundancy of alignment is inevitable and ubiquitous. Therefore, this paper presents a volumetric fusing method for cross-source three-dimensional reconstructions. To eliminate the stratification of aligned cross-source point clouds, we propose a graph-cuts method with boundary constraints for blending the two cross-source point clouds. Then, to reduce the gaps that exist in the blending results, we develop a progressive migration method combined with the local average direction of normal vectors to smooth the unconnected boundary. Finally, experimental results demonstrate the effectiveness of eliminating stratification with the proposed blending algorithm, and the progressive migration method achieves a smooth connection in the boundary of the blended point clouds.