Method and device for distinguishing pedestrians and vehicles on the basis of 2D laser radar
A technology of laser radar and pedestrians, which is applied in the direction of character and pattern recognition, instruments, computer parts, etc., to achieve the effect of improving recognition and accuracy
Pending Publication Date: 2018-10-30
浙江梧斯源通信科技股份有限公司
View PDF9 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention aims to solve the problem of traffic safety supervision at crossroads, and provides an intelligent method and device for distinguishing pedestrians and vehicles based on 2D laser radar that can improve recognition and accuracy through training
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
[0018] The present invention will be further described below in conjunction with the accompanying drawings.
[0019] Such as figure 1 As shown, based on the method of distinguishing pedestrians and vehicles based on 2D lidar, several 2D lidars are set on the road, including the following steps: 1) generating a laser point cloud by irradiating obstacles with 2D lidar to construct a real-time dynamic two-dimensional scene; 2 ) divide the laser point cloud in the scene into clusters, remove point cloud clusters with fewer points, and thin out the remaining point cloud clusters to reduce the density of points in the laser point cloud while ensuring that the shape of the laser point cloud remains unchanged, and then Filter and remove point cloud clusters with high dispersion; 3) Calculate various geometric features according to the pre-acquired samples of pedestrians and vehicles, obtain the feature vectors of the samples, and train these samples to obtain a classification model. A...
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 invention discloses a method for distinguishing pedestrians and vehicles on the basis of a 2D laser radar, and is provided with a plurality of 2D laser radars on a road. The method comprises the following steps that: 1) through the 2D laser radars, irradiating an obstacle to generate laser point cloud to construct a real-time dynamic 2D scene; 2) segmenting the laser point cloud in the scene into clusters, and filtering to remove point cloud clusters with high dispersion; 3) calculating a probability value that a target cluster is a pedestrian or a vehicle; and 4) carrying out probabilityjudgment on the target cluster in the selected area, preliminarily judging that the target cluster is the pedestrian or the vehicle, calculating the motion speed and direction of the target cluster inshort time, filtering the cluster which conforms to the motion characteristics of the pedestrian or the vehicle, and finishing distinguishing pedestrians and vehicles. By use of the method, pedestrians and vehicles can be intelligently distinguished, and a differentiation degree and accuracy for distinguishing the pedestrians and vehicles can be improved through training.
Description
technical field [0001] The invention relates to the technical field of automatic traffic management, in particular to a method and device for distinguishing pedestrians and vehicles based on 2D laser radar. Background technique [0002] In the field of traffic safety, whether for traffic management departments or for motor vehicle drivers, detecting pedestrians has always been of great significance. Especially with the rise of intelligent transportation, the extraction and analysis of pedestrians, vehicles, and other road environment information has been extensively studied. [0003] At present, the mainstream method of distinguishing pedestrians and vehicles at home and abroad is to use cameras as sensors and identify them through certain image processing algorithms. Its advantages are simple and convenient installation and use, and low cost. However, its disadvantage is that it is easily affected by light and shadow, and ordinary cameras cannot obtain depth information. ...
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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/10G06V20/584G06F18/214
Inventor 王海军陈铁英沈汪晴
Owner 浙江梧斯源通信科技股份有限公司