Intersection automatic identification method and system, and model storage method and system thereof
A technology of intersection and identification method, applied in the field of intersection map production, can solve problems such as low efficiency and complicated work, and achieve the effect of high identification efficiency and high segmentation efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] At present, there is no method for automatic identification of intersections based on unmanned vehicles. However, there are existing methods for identifying the types of fork road intersections based on unmanned vehicles. The method used to identify the types of fork road intersections is: to obtain the traversable distances of unmanned vehicles at various angles in the horizontal direction, and generate the angle- The histogram defined by the passable distance is used to obtain the beam model, and then the real-time identification and classification of fork road intersections are performed based on the beam model. However, most of the fork road intersection type identification methods use the fixed origin of the vehicle body coordinate system as the reference point for constructing the beam model when constructing the beam model. The point of the distance is used as the reference point for the construction of the beam model. Since the reference points for the construct...
Embodiment 2
[0070] This embodiment is used to provide an automatic identification system for intersections, such as Figure 7 As shown, the identification system includes:
[0071] The first acquisition module M1 is used to acquire the three-dimensional point cloud data of the surrounding environment of the unmanned vehicle; the unmanned vehicle is located in the intersection;
[0072] The first construction module M2 is configured to construct a two-dimensional grid map according to the three-dimensional point cloud data;
[0073] The construction reference point determination module M3 is used to obtain the construction reference point by using a straight line detection algorithm according to the two-dimensional grid map;
[0074] Building module M4, used for building beam model according to said building reference point;
[0075] The identification module M5 is configured to automatically identify the intersection according to the light beam model.
Embodiment 3
[0077] This embodiment is used to provide a method for saving an intersection model, such as Figure 8 As shown, the preservation method includes:
[0078] T1: Obtain 3D point cloud data of the surrounding environment of the unmanned vehicle; construct a 2D grid map according to the 3D point cloud data; use a straight line detection algorithm to obtain construction reference points according to the 2D grid map; People and vehicles are in the intersection;
[0079] Specifically, the specific method of this step is the same as the methods of S1, S2, and S3 in Embodiment 1, and will not be repeated here.
[0080] T2: According to the 3D point cloud data, use the LeGO-LOAM algorithm to construct a global map model;
[0081] The Lego-Loam algorithm is an open source SLAM (Synchronous Mapping and Localization) algorithm. Of course, in this embodiment, other SLAM algorithms may also be used when constructing the global map model, and there is no limitation on this.
[0082] T3: U...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More