A target tracking method based on an LSTM neural network

A target tracking and neural network technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as difficulty in target tracking and difficulty in establishing tracking accuracy for target models, and achieve the effect of simplifying the nonlinear filtering process.

Pending Publication Date: 2019-05-10
HARBIN ENG UNIV
View PDF6 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is to provide a kind of target tracking method based on LSTM neural network, utilize long-short-term memory model (LSTM) to the target tracking of complex, non-linear motion, solve target tracking difficulty, target model is difficult to set up and the problem of low tracking accuracy

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 target tracking method based on an LSTM neural network
  • A target tracking method based on an LSTM neural network
  • A target tracking method based on an LSTM neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0074] For the LSTM-based target tracking method described in the above specific implementation, the following examples are given:

[0075] use as image 3 The sensor in (a) to obtain image 3 (b) Longitude and latitude information and speed information of the small and medium-sized vehicles. Assuming that the target is moving on the ground, the maneuvering of the robot is random during the test, and the measured data includes the process of uniform straight line, turning process, acceleration process and deceleration process. The data acquisition rate of the sensor is 1Hz, and a total of 1,200 sets of data are measured, and the data is filtered out to longitude, latitude and speed information. Put the processed data into the constructed LSTM neural network model as a training set, set the number of iterations and learning rate, so that it can adjust the internal parameters of the network by itself. Select 300 sets of data from 1200 sets of data as the test set to test the ...

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 target tracking method based on an LSTM neural network, and belongs to the technical field of target tracking. According to the method, the LSTM is used for tracking the complex and non-linear motion target, and the problems that target tracking is difficult, a target model is difficult to establish and the tracking precision is low are solved; the method comprises the following steps: firstly, acquiring latitude and longitude information and speed information of a target, and processing acquired data; designing an LSTM neural network structure for single target tracking; and finally, adjusting LSTM neural network parameters to realize target tracking. According to the method, the nonlinear filtering process is effectively simplified, and a complex nonlinear target can be effectively tracked; the establishment of a target motion model and the utilization of a traditional filtering algorithm are not needed; estimating the target motion state of the next momentby using historical target motion information; adjusting internal parameters of the neural network by using a back propagation algorithm; the learning rate attenuation method reduces the calculation amount and improves the precision.

Description

technical field [0001] The invention belongs to the technical field of target tracking, and in particular relates to a target tracking method based on an LSTM neural network. Background technique [0002] Maneuvering target tracking is a relatively active research topic at present. How to track targets quickly, accurately and reliably is the main purpose of target tracking system design. Target tracking, that is, real-time tracking and prediction of the target's position, velocity, attitude angle and other information. Target tracking can be divided into single target tracking and multi-target tracking according to the number of targets. Most single target tracking is based on Bayesian filter estimation, this form of target tracking is not ideal for complex moving targets, the motion model is difficult to select and the amount of calculation is large. However, in practical applications, the motion of the target is complex and changeable. It is very difficult to establish an...

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): G06N3/04G06N3/08
Inventor 王宏健阮力王莹高伟何姗姗
Owner HARBIN ENG UNIV
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