Accurate semantic analysis of LiDAR point clouds enables the interaction between intelligent vehicles and the real environment. This paper proposes a hybrid 2D and 3D Hough Net by combining 3D global Hough features and 2D local Hough features with a classification deep learning network. Firstly, the 3D object point clouds are mapped into the 3D Hough space to extract the global Hough features. The generated global Hough features are input into the 3D convolutional neural network for training global features. Furthermore, a multi-scale critical point sampling method is designed to extract critical points in the 2D views projected from the point clouds to reduce the computation of redundant points. To extract local features, a grid-based dynamic nearest neighbors algorithm is designed by searching the neighbors of the critical points. Finally, the two networks are connected to the full connection layer, which is input into fully connected layers for object classification.

Accurate observation and comprehension of the surroundings are made possible by 3D reconstruction technology. This study suggests a pyramid reference object for a 3D environment reconstruction system. First, LiDAR sensors are used to scan the indoor scene vertically in all directions. Then, the RANSAC(Random Sample Consensus) algorithm and the 3A-LSM( three-axis least square method) are used to precisely determine the plane equation of the calibration object in the LiDAR point clouds. The virtual feature corners are identified as the spots where the reference planes connect at a defined distance. The ICP (Iterative Closest Point) algorithm is used to predict the spatial transformation matrices of the LiDAR sensor between the successive frames based on the retrieved virtual corners. The loop closure optimization module, which optimizes the virtual corner extraction process to reduce the accumulated error in global mapping, is also added to the 3D reconstruction system. By using the loop closure optimization process, the LiDAR self-localization error is decreased by 29.4%, and the global environment reconstruction precision is increased by 12%.

The existing works have issues about the angular resolution limitations of the traditional mechanical LiDAR sensor. In such instance, it will fail to gain a complete depiction of the surroundings when gathering point cloud data. Therefore, we will employ a system to extracting feature points from intersecting planes in environment to achieve reconstruction in 3D environment. The system is combined with the RANSAC algorithm and 3A-LSM to better detect the intersecting planes in the scanned point cloud environment and fit the plane equations. The extracted intersection points are used as the feature points of the current frame. The virtual angle points are aligned between frames. The frames addresses the issues of the lack of an initial value in ICP alignment algorithm and poor efficiency of alignment perform in large- scale point clouds. Eventually, the outcomes of the experiments demonstrate that the system successfully completes the global three-dimensional reconstruction.