Unlock instant, AI-driven research and patent intelligence for your innovation.

Sensor data association method, device and equipment and storage medium

A data association and sensor technology, applied in the field of vehicles, can solve the problems of missing association, high time complexity, and difficult algorithm implementation, and achieve the effect of improving efficiency and reducing missed association and false association.

Active Publication Date: 2021-03-09
CHINA FIRST AUTOMOBILE
View PDF24 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The GNN method needs to set a maximum matching distance in advance to verify the validity of the Hungarian matching results. When the maximum matching distance is too large, it is easy to cause mis-association. When the maximum matching distance is too small, it is easy to cause missing correlation. Therefore, it is easy to set a single maximum matching distance. Lead to missing association or false association; and when the number of targets is large or the number of sensors is large, due to the need to associate targets from any two sources, the time complexity of calculation is high, and the implementation of the algorithm is difficult

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
  • Sensor data association method, device and equipment and storage medium
  • Sensor data association method, device and equipment and storage medium
  • Sensor data association method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] figure 1 It is a flow chart of a sensor data association method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of sensor data association. The method can be executed by the sensor data association device in the embodiment of the present invention. The device can adopt implemented in software and / or hardware, such as figure 1 As shown, the method specifically includes the following steps:

[0075] S110, acquiring a target to be fused.

[0076] Wherein, the target to be fused may be data collected by multiple sensors, or may be a fused target in a previous period, which is not limited in this embodiment of the present invention.

[0077] S120. Cluster the target to be fused based on a clustering algorithm to obtain at least two cluster structures.

[0078] Wherein, the cluster structure includes two attributes: core distance and minimum reachable distance.

[0079] Wherein, the clustering algorithm may be an OPTICS cl...

Embodiment 2

[0138] figure 2 It is a schematic structural diagram of a device for associating sensor data provided by Embodiment 2 of the present invention. This embodiment can be applied to the situation of sensor data association, the device can be implemented in the form of software and / or hardware, and the device can be integrated in any device that provides sensor data association functions, such as figure 2 As shown, the sensor data association device specifically includes: an acquisition module 210 , a clustering module 220 , a generation module 230 and an association module 240 .

[0139] Wherein, the obtaining module 210 is used to obtain the target to be fused;

[0140] A clustering module 220, configured to cluster the target to be fused based on a clustering algorithm to obtain at least two cluster structures;

[0141] The generating module 230 is configured to select a target point from the target to be fused based on the core distance, the minimum reachable distance and the...

Embodiment 3

[0170] image 3 It is a schematic structural diagram of a computer device in Embodiment 3 of the present invention. image 3 A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the invention is shown. image 3 The computer device 12 shown is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0171] Such as image 3 As shown, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16 , system memory 28 , bus 18 connecting various system components including system memory 28 and processing unit 16 .

[0172] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus struc...

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 sensor data association method, device and equipment and a storage medium. The method comprises the steps of obtaining a to-be-fused target; clustering the to-be-fused targetbased on a clustering algorithm to obtain at least two cluster structures; based on the core distance, the minimum reachable distance and a preset distance set of the cluster structure, selecting a target point from the to-be-fused target, and generating a cluster set according to the target point, wherein the cluster densities in the cluster set are arranged from large to small; for each clusterin the cluster set, performing target association by using the maximum matching distance corresponding to the cluster density. According to the technical scheme of the invention, different maximum matching distances can be selected according to the density level to perform target association respectively, thereby reducing missing association and error association; and each cluster is associated in parallel, so that the efficiency of the algorithm can be further improved.

Description

technical field [0001] Embodiments of the present invention relate to vehicle technology, and in particular to a sensor data association method, device, equipment and storage medium. Background technique [0002] For autonomous driving, perception, decision-making and control constitute three functional modules. As the basis and premise of the three major functional modules, the perception module needs to realize accurate perception of the surrounding environment. Limited by the principle of sensor technology, different types of sensors perceive different target attributes and sensing ranges. Different sensors of the same type have different sensing areas due to different installation locations. Therefore, it is necessary to fuse the sensing results of each sensor. [0003] In practical applications, the existing perceptual fusion technology mainly adopts the target-level post-fusion method, which generally includes two steps of target association and target fusion. ,GNN) ...

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
IPC IPC(8): G06K9/62
CPCG06F18/23G06F18/25
Inventor 鹿强衣春雷吴健宇
Owner CHINA FIRST AUTOMOBILE