Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-sensor target data partitioning method and system of Spark distributed computing engine and target object data fusion method and system

A distributed computing and multi-sensor technology, applied in the field of vehicle multi-sensor target data, can solve problems such as low efficiency and long running time, and achieve the effect of improving accuracy, increasing computing speed, and quickly and accurately extracting fusion

Pending Publication Date: 2022-07-08
CHINA FIRST AUTOMOBILE
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The present invention solves the problem that the existing fusion method of target object data can only be output in real time during the operation of the vehicle, and when processing hundreds of millions of lines or even more data at one time, the problem of long operation time and extremely low efficiency

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
  • Multi-sensor target data partitioning method and system of Spark distributed computing engine and target object data fusion method and system
  • Multi-sensor target data partitioning method and system of Spark distributed computing engine and target object data fusion method and system
  • Multi-sensor target data partitioning method and system of Spark distributed computing engine and target object data fusion method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0060] Embodiment 1. The multi-sensor target data partitioning method of the Spark distributed computing engine described in this embodiment is characterized in that it includes the following steps:

[0061] Step S1, select the historical data of the vehicle speed greater than 0 detected by the multi-sensor, take the historical data in consecutive time points as a partition, and the difference between the end time of each partition and the starting time of the next partition is less than 1s. to merge;

[0062] Step S2, set the partition end threshold i to 10, calculate the difference between the number of rows in each partition and the maximum number of partition rows, until the difference between the number of rows in each partition and the maximum number of partition rows is less than i%, then end each partition. partitioning;

[0063] Step S3, if the final partition end i value exceeds 30, the historical data needs to be re-partitioned to ensure that the difference between...

Embodiment approach 2

[0067] Embodiment 2. This embodiment further defines the multi-sensor target data partitioning method of the Spark distributed computing engine described in Embodiment 1. In this embodiment, in step S2, the calculation of each partition is performed. The difference between the number of rows and the maximum number of partition rows is:

[0068] If it is greater than i%, according to the condition that the historical data volume of the target object in each partition is less than 1, the historical data volume of the target object in each partition is divided to obtain a new partition;

[0069] If it is less than i% and the i value does not exceed 30, the partition ends.

[0070] In this embodiment, according to the condition that the historical data amount of surrounding objects in each partition is less than 1, the first partition is performed, that is, the segmentation is performed again in the interval where each vehicle speed is not 0, because it is necessary to ensure that...

Embodiment approach 3

[0071] Embodiment 3. This embodiment further defines the multi-sensor target data discrimination method of the Spark distributed computing engine described in Embodiment 2. In this embodiment, the historical data volume of the target in each partition is further limited. After dividing to obtain new partitions, calculate the difference between the number of rows in each partition and the maximum number of branches as:

[0072] If it is still greater than i%, then divide and obtain a new partition according to the condition that the historical data amount of the target object is greater than 1 and the relative distance and relative speed are stable within 2s;

[0073] If it is less than i% and the i value does not exceed 30, the partition ends.

[0074] In this embodiment, segmentation is performed according to the condition that the historical data amount of the target object is greater than 1 and the relative distance and relative speed are stable within 2s, in order to ensur...

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 multi-sensor target data partitioning method and system of a Spark distributed computing engine and a target object data fusion method and system, and belongs to the technical field of vehicle multi-sensor target data. The problems that an existing fusion mode is long in operation time consumption and extremely low in efficiency are solved. Comprising the following steps of S1, selecting historical data, detected by multiple sensors, of which the vehicle speed is greater than 0, taking the historical data in continuous time points as a subarea, and combining the subareas of which the difference between the termination time of each subarea and the starting time of the next subarea is less than 1s; s2, setting a partition ending threshold value i to be 10, calculating the difference between the line number of each partition and the line number of the maximum partition, and ending segmentation of each partition until the difference between the line number of each partition and the line number of the maximum partition is smaller than i%; and S3, if the final partitioning end i value exceeds 30, the historical data needs to be partitioned again so as to ensure that the difference between the data row number of each partition and the maximum partition row number is smaller than 30%.

Description

technical field [0001] The invention relates to the technical field of vehicle multi-sensor target data, in particular to a multi-sensor target data partition method and system of a Spark distributed computing engine, and a target object data fusion method and system. Background technique [0002] With the rise of intelligent driving vehicles, the verification of the reliability and accuracy of the automatic driving function control software is becoming more and more important. Therefore, it is necessary to build an intelligent network-connected vehicle intelligent driving scene library for various scenes such as highway scenes and urban expressway congestion scenes. During the construction process, the vehicle needs to be intelligently modified, and various target detection sensors such as smart cameras, lidar, millimeter-wave radar and other traditional sensors, such as acceleration sensors, GPS positioning, vehicle CAN bus acquisition, etc., need to be installed. In the p...

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 Applications(China)
IPC IPC(8): G06F3/06G06K9/62
CPCG06F3/0644G06F18/25Y02T10/40
Inventor 张宇飞郑建明覃斌张建军刘迪
Owner CHINA FIRST AUTOMOBILE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com