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

A 3D multi-target tracking method based on fusion of image and laser point cloud

A multi-target tracking and laser point cloud technology, applied in the field of three-dimensional multi-target tracking, can solve the problems of tracking loss and difficulty in identifying disappearing targets.

Active Publication Date: 2020-09-11
NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the technical problems of tracking loss caused by target occlusion and difficult recognition of disappearing targets during long-term tracking

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 3D multi-target tracking method based on fusion of image and laser point cloud
  • A 3D multi-target tracking method based on fusion of image and laser point cloud
  • A 3D multi-target tracking method based on fusion of image and laser point cloud

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described in detail below with reference to the accompanying drawings of the specification and specific preferred examples, but the protection scope of the present invention is not limited thereby.

[0048] Such as figure 1 As shown in this example, the three-dimensional multi-target tracking method of fusion image and laser point cloud, the steps include:

[0049] S1. Obtain point cloud data from lidar, detect the three-dimensional space position information of the target and extract point cloud features;

[0050] S2. Obtain image data from the camera, project the three-dimensional boundary of the target onto the image plane, and extract the image features of the projection area;

[0051] S3. Calculate the similarity matrix of the detected target and tracking trajectory in the point cloud three-dimensional space position information, point cloud features, and image features, and merge the three similarity matrices;

[0052] S4. The merged si...

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 present invention is a three-dimensional multi-target tracking method for fusion of image and laser point cloud, which integrates the point cloud of laser radar and the image data of the camera, fully utilizes the complementary advantages between point cloud data and image data, and extracts the three-dimensional space position of the target Information, point cloud features, and image features are used to match the detection target and the tracking trajectory, and combine the Kalman filter to estimate the state of the tracking trajectory to obtain accurate and stable three-dimensional multi-target tracking. The invention can be used for tracking and prediction of moving targets such as pedestrians and vehicles in various types of unmanned vehicles, and can also be used in fields such as security monitoring and ground target reconnaissance by unmanned aerial vehicles.

Description

Technical field [0001] The invention belongs to the field of information and communication technology, and specifically relates to a three-dimensional multi-target tracking method. Background technique [0002] Most current multi-target tracking methods are based on a single sensor, such as relying only on lidar or cameras. The point cloud data of lidar can provide three-dimensional information of the target. Although it can better overcome the problem of mutual occlusion of targets, the point cloud data only has geometric information, and it is difficult to identify target attributes, so it is difficult to identify targets that reappear during tracking. Identify it. [0003] Since image data has richer information than point cloud data, multi-target tracking based on image and video data is a method that has been studied more at present, but the image is greatly affected by light and shadow, making the tracking reliability greatly reduce. In addition, since the image only has t...

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): G06T7/246G06T7/277G06T7/73G06T7/80G06K9/62G06N3/04G01S17/66
CPCG06T7/246G06T7/277G06T7/73G06T7/80G01S17/66G06T2207/10044G06T2207/10028G06T2207/20081G06T2207/20084G06T2207/30241G06T2207/20221G06V2201/07G06N3/045G06F18/22
Inventor 许娇龙聂一鸣肖良赵大伟
Owner NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI
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