Method, device and storage medium for augmenting laser point cloud data
A technology of laser point cloud data and laser point cloud, which is applied in the computer field, can solve problems such as the inability to increase the number of point clouds, the inability to supplement point clouds, and unfavorable target detection.
Active Publication Date: 2021-04-27
知行汽车科技(苏州)股份有限公司
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] This application provides a method, device, and storage medium for laser point cloud data augmentation, which can solve the problem that the current supplementary method of point cloud data cannot increase the number of point clouds in each frame. Without the edge information, it is impossible to supplement the point cloud, which is not conducive to the problem of subsequent target detection.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0025] The specific implementation manners of the present application will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present application, but not to limit the scope of the present application.
[0026] figure 1 It is a schematic diagram of the framework provided by an embodiment of the application that can realize the method and device of the application, such as figure 1 As shown, the framework includes a data processing module 101 and a perception module 102, and the data processing module and the perception module establish a communication connection. In this embodiment, the driverless car is equipped with a laser radar with non-repetitive scanning. The laser radar is installed on the driverless car to form a rigid body structure. The laser radar has a built-in inertial measurement unit (Inertial measurement unit, IMU), and the IMU is a measurement object The three-axis attitude...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present application relates to a method, device and storage medium for augmenting laser point cloud data, including: sequentially acquiring laser point cloud data of a preset number of consecutive frames at predetermined time intervals, the laser point cloud data adopting a non-repetitive method Obtained by scanning; motion compensation is performed on the coordinates of each laser point in each frame of laser point cloud data acquired, and the position coordinates of each laser point in each frame of point cloud data at the next moment are obtained; each frame after motion compensation The frame laser point cloud is sequentially superimposed on the laser point cloud acquired at the next moment to obtain the current frame laser point cloud after augmentation. It can solve the current supplementary method of point cloud data. Because the number of point clouds in each frame cannot be increased, if the target in front is not scanned, the edge information cannot be extracted, and the point cloud cannot be supplemented, which is not conducive to the subsequent target detection. .
Description
technical field [0001] The application relates to a method, device and storage medium for augmenting laser point cloud data, and belongs to the field of computers. Background technique [0002] Driverless cars usually use lidar to collect point cloud data for target detection to identify the target in front of the vehicle. For target detection, it is usually necessary to use a training sample set to train a deep learning network. In general, for training The point cloud data in the sample set needs data augmentation to supplement the point cloud data. [0003] Data augmentation is one of the commonly used techniques in deep learning. It is mainly used to increase the training data set and make the data set as diverse as possible, so that the trained model has stronger generalization ability. The current point cloud supplement method is mainly based on software algorithms, which detect edge points on a frame of data that has been collected, and then match and interpolate to ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01S7/48G01S17/931G05D1/02G06K9/00G06T17/00
CPCG01S7/4802G01S17/931G05D1/0257G06T17/00G06V20/56
Inventor 陈伟
Owner 知行汽车科技(苏州)股份有限公司