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

Obstacle size prediction method fusing image information and improved LSSVM

A technology that integrates images and prediction methods. It is applied in image analysis, image data processing, biological models, etc. It can solve problems such as insufficient access to environmental information, reduce measurement costs, simplify measurement processes, and improve breadth and depth. Effect

Pending Publication Date: 2022-07-15
HUNAN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The above research mainly focuses on the obstacle avoidance method proposed by environmental perception, and has achieved relatively good research results, but the above research does not fully obtain environmental information, such as the actual size information of obstacles

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
  • Obstacle size prediction method fusing image information and improved LSSVM
  • Obstacle size prediction method fusing image information and improved LSSVM
  • Obstacle size prediction method fusing image information and improved LSSVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0069] like figure 1 As shown, an obstacle size prediction method that fuses image information and improves LSSVM includes the following steps:

[0070] Step 1: Build an obstacle image information acquisition platform, and use machine vision algorithms to obtain obstacle pixel size information.

[0071] like figure 1 As shown in (a), the obstacle image information acquisition platform includes a camera for collecting information about the surrounding environment, a ranging sensor for collecting the distance from the obstacle to the camera, and a computer for control. The camera and the ranging sensor are connected respectively. computer.

[0072] The specific process of using the machine vision algorithm to obtain the pixel size information of obstacles is as follows:

[0073] (1-1) Image preprocessing: Obtain the original image of the obstacle throug...

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 an image information and improved LSSVM (Least Square Support Vector Machine)-fused obstacle size prediction method, which comprises the following steps of: constructing an obstacle image information acquisition platform, and acquiring obstacle pixel size information by adopting a machine vision algorithm; the genetic algorithm is combined with the whale optimization algorithm to optimize regularization parameters and kernel function width of the least square support vector machine; building an obstacle size prediction model based on a genetic algorithm, a whale optimization algorithm and a least square support vector machine by taking the pixel size of the obstacle and the distance from the obstacle to a camera as input parameters and taking the actual size of the obstacle as an output parameter; and inputting the pixel size of the obstacle into the obstacle size prediction model to obtain the actual size of the obstacle. According to the method, regularization parameters and kernel function width of the LSSVM model are optimized through GA-WOA, and the problem that a whale optimization algorithm is prone to falling into a local optimal solution is solved.

Description

technical field [0001] The invention relates to the technical field of environmental perception of mobile working robots, in particular to a method for predicting the size of obstacles by fusing image information and improving LSSVM. Background technique [0002] With the rapid development of the world economy and science and technology, mobile robots are widely used in human scientific research, production and life. It can replace humans to complete tasks autonomously in complex and dangerous environments, and has a very broad application prospect. With the increasing task demands of mobile robots, their working environment has also changed from a simple structured environment to an outdoor unstructured environment. Therefore, this puts forward higher requirements for mobile robots to perform environment perception and obstacle avoidance navigation. [0003] Mobile robots perceive the environment through various types of sensors, and then use information fusion technology ...

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): G06V20/10G06V10/25G06V10/26G06V10/80G06V10/764G06K9/62G06N3/00G06N3/12G06T7/11G06T7/13G06T7/155
CPCG06N3/006G06N3/126G06T7/11G06T7/155G06T7/13G06F18/2411G06F18/25
Inventor 宁宇金永平彭佑多颜健
Owner HUNAN UNIV OF SCI & TECH