1 December 2014 in Research in Astronomy and Astrophysics
3 July 2021 in Journal of Russian Laser Research
23 July 2021 in Journal of the Optical Society of America A
Collecting accurate outdoor point cloud data depends on complex algorithms and expensive experimental equipment. The requirement of data collecting and the characteristics of point clouds limit the development of semantic segmentation technology in point clouds. Therefore, this paper proposes a neural network model named PointCartesian-Net that uses only 3D coordinates of point cloud data for semantic segmentation. First, to increase the feature information and reduce the loss of geometric information, the 3D coordinates are encoded to establish a connection between neighboring points. Second, a dense connect and residual connect are employed to progressively increase the receptive field for each 3D point, and aggregated multi-level and multi-scale semantic features obtain rich contextual information. Third, inspired by the success of the SENet model in 2D images, a 3D SENet that learns the relation between the characteristic channels is proposed. It allows the PointCartesian-Net to weight the informative features while suppressing less useful ones. The experimental results produce 60.2% Mean Intersection-over-Union and 89.1% overall accuracy on the large-scale benchmark Semantic3D dataset, which shows the feasibility and applicability of the network.
23 November 2020 in Journal of the Optical Society of America A
Laser scanners can be employed for spatial measuring tasks, but measuring accuracy is restricted because of the time of flight working principle. Laser-scanner-based observations with measuring errors might lead to rough spatial reconstruction. In this paper, an image registration method applying a Markov random field (MRF) algorithm is proposed. First, point cloud images are projected to a particular plane in a specific way. Then, the characteristic points of the projected image and the color image are extracted by an improved Harris algorithm. Next, the rotation and translation matrices can be calculated from the two image planes through the registration method. Finally, the MRF model is established describing the relation between the pixels and corresponding point cloud, which improves the resolution of the point cloud image. Furthermore, the color information of the point cloud is also matched. This method improves the efficiency and accuracy of registration. The final experimental result shows that using the MRF model increases measuring accuracy by 15%.