A Real-time Incremental and Adaptive Clustering Method Based on Automotive Radar Data

A technology of automotive radar and data, which is applied in the field of real-time clustering processing of automotive radar data, can solve the problems of low clustering efficiency, unevenness, and inability to cope with data density clusters of automotive radar data, and solve the problem of uneven density of automotive radar data clusters. Uniform, time-saving, and clustering efficiency-enhancing effects

Active Publication Date: 2021-07-13
GUILIN UNIV OF ELECTRONIC TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the shortcomings of low clustering efficiency of automotive radar data working in a multi-target complex environment, and the inability to deal with the problem of uneven data density clusters

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
  • A Real-time Incremental and Adaptive Clustering Method Based on Automotive Radar Data
  • A Real-time Incremental and Adaptive Clustering Method Based on Automotive Radar Data
  • A Real-time Incremental and Adaptive Clustering Method Based on Automotive Radar Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] Refer to attached figure 1 , a real-time incremental and self-adaptive clustering method based on automotive radar data in the present invention, the innovation point is: improving the DBSCAN algorithm, combining EKF and DBSCAN to realize real-time clustering of automotive radar data.

[0029] attached figure 1 Among them, the improved DBSCAN algorithm of S3, the clustering standard is distance-angle two-dimensional data. In this embodiment, the pseudocode of the improved DBSCAN algorithm is as follows:

[0030] Algorithm 1 Improved Pseudocode of DBSCAN Algorithm

[0031]

[0032] Algorithm 2 Expand_cluster function

[0033]

[0034] Algorithm 1 gives the pseudocode of the improved DBSCAN algorithm, and Algorithm 2 gives the pseudocode of the subfunction Expand_cluster. The input data set is D, the initial distance radius is ε, the point threshold is MinPts, the Kalman prediction set is K, and the real-time data of the automobile 77Ghz millimeter-wave radar ...

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

No PUM Login to view more

Abstract

The invention discloses a real-time incremental and self-adaptive clustering method based on automotive radar data, and proposes to combine EKF and DBSCAN algorithm to realize real-time clustering of automotive radar data. The shortcomings of radar data clustering are low efficiency, and the problem of uneven data density clusters cannot be dealt with. The method of the present invention takes into account the characteristics of the EKF that the automotive radar often uses when tracking and predicting the target, and improves the DBSCAN algorithm. The improved DBSCAN algorithm can ensure that the clustering results are not affected by the overlap of the tracks to a large extent; it can also make Carl Mann filter parameters can be continuously iterated in the same target, which saves the time needed to iterate from the initial parameters and improves the clustering efficiency. The method of the invention realizes incremental and self-adaptive DBSCAN clustering at the same time, can keep low time memory overhead, and can be used to solve the situation of uneven density of automotive radar data clusters.

Description

technical field [0001] The present invention relates to the real-time cluster processing method of automobile radar data, specifically a kind of extended Kalman filter algorithm (EKF) based on automobile radar data, combined with density-based clustering algorithm (DBSCAN) to improve the real-time incremental and self-adaptive clustering method. Background technique [0002] Automotive Advanced Driver Assistance System (ADAS) uses various sensors installed on the car to sense the surrounding environment at any time during the driving process, collect data, identify, detect and track static and dynamic objects, and Combined with the map data of the navigator, the system is calculated and analyzed, so that the driver can be aware of possible dangers in advance, and the comfort and safety of driving can be effectively increased. [0003] In recent years, automotive advanced driver assistance systems (ADAS) have become a field of research that major automakers and technology co...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/23
Inventor 蒋留兵温和鑫车俐盘敏容
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap