Vehicle laser radar data city road shaft identification algorithm based on multi-frame joint
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A vehicle-mounted lidar, multi-frame combination technology, applied in scene recognition, character and pattern recognition, calculation and other directions, can solve the problems of large amount of calculation, low recognition rate, missed detection and other problems, achieve small amount of calculation, sufficient feature extraction, The effect of high recognition rate
Active Publication Date: 2018-11-06
STATE GRID LIAONING ELECTRIC POWER RES INST +1
View PDF3 Cites 11 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
Its purpose is to solve the problems of insufficient feature extraction, low recognition rate, large amount of calculation, and missed detection in the existing urban road pole recognition system.
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0027] like figure 1 As shown, the present invention is a kind of urban road rod recognition algorithm based on multi-frame joint vehicle laser radar data, comprising the following steps:
[0028] 1. LiDAR point cloud data acquisition.
[0029] Because the point cloud data of a single frame is relatively sparse, which is not conducive to object recognition, in order to better identify rods, the present invention uses multi-frame joint point cloud data. The multi-frame joint mainly uses the ICP (Iterative Closest Point) algorithm, and its key idea is to find corresponding point pairs to achieve the purpose of point cloud splicing, thereby forming dense point cloud data. Therefore, the amount of point cloud data after splicing is large, and preprocessing and screening are required.
[0030] The pretreatment screening includes three steps: intensity value screening, rod rough screening and hierarchical clustering screening.
[0031] 2. Intensity value screening.
[0032] Afte...
Embodiment 2
[0055] There are a total of 600 frames of experimental data in this experiment, and these experimental data are tested one by one, and the recognition results of all experimental data are collected for statistics.
[0056] For the 600 frames of 32-line radar data measured, 120 frames were extracted every 5 frames for statistics of the experimental results, and the recall rate (Recall) and recognition rate (Precision) were counted.
[0057] Recall = true rods / all rods
[0058] Accuracy (Precision) = Truly a rod / Algorithm detects a rod
[0059] After manually counting 2130 rod-shaped objects, the algorithm detected 2098 rod-shaped objects, of which 1970 were actually rod-shaped objects, so the recall rate was 92.49% and the accuracy rate was 93.90%.
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 invention belongs to the technical field of artificial intelligence, especially relates to a vehicle laser radar data city road shaft identification algorithm based on multi-frame joint. The algorithm comprises the following steps of: laser radar point cloud data obtaining; screening of an intensity value; coarse screening of a shaft; layered clustering screening; shaft area growth; and shaft combination output. Through adoption of the multi-frame joint technology, the point cloud features of the shaft is more obvious so as to better facilitate identification of the shaft. The vertical voxelization, layered clustering and area growth technologies are employed to allow the vehicle laser radar data city road shaft identification algorithm to have full feature extraction, high identification and few computing quantity. The vehicle laser radar data city road shaft identification algorithm provides rapid and effective shaft identification at the aspects of vehicle map construction, checking of electric rods or road lamps,, three-dimensional reconstruction and detection of buildings, road condition survey and analysis, road measurement and prospecting so as to achieve intelligent traffic and intelligent industry.
Description
technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to an urban road pole-shaped object recognition algorithm based on multi-frame combined vehicle-mounted laser radar data. Background technique [0002] LiDAR technology (Light Detection And Ranging- LiDAR) is a new technology for information acquisition and automatic processing of digital cities, digital industries, and transportation infrastructure construction. It provides a simple and efficient way to obtain urban infrastructure data. It is widely used in the construction of vehicle maps, inventory of poles or street lamps, three-dimensional reconstruction and detection of buildings, investigation and analysis of road status, road measurement and survey, etc. Lidar can effectively and quickly acquire high-precision three-dimensional space information on both sides of the road, providing a new means for realizing intelligent transportation and intellige...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more