Image processing method in underwater visual slam system

An image processing and vision technology, applied in image data processing, image analysis, instruments, etc., can solve problems such as difficult real-time performance, time-consuming, affecting real-time performance of algorithms, etc., to achieve rapid and accurate extraction, overcome poor real-time performance, and overcome features The effect of point redundancy

Active Publication Date: 2017-11-21
JIANGSU UNIV OF SCI & TECH IND TECH RES INST OF ZHANGJIAGANG
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the SIFT algorithm has many advantages, but real-time performance is a major problem it faces, mainly because the SIFT algorithm only needs to successfully match 3 or more feature points for a target due to the large number of feature descriptors. to confirm the existence of the target
However, the SIFT algorithm can often provide thousands of feature points in an image, and 50% to 80% of these feature points are not used and need to be filtered out. They will consume a lot of time in the process of extraction and matching. time, which seriously affects the real-time performance of the algorithm

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
  • Image processing method in underwater visual slam system
  • Image processing method in underwater visual slam system
  • Image processing method in underwater visual slam system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043] like figure 1 As shown, an image processing method in an underwater vision SLAM system includes the following steps:

[0044] Step 1: Build a visual SLAM system model

[0045] Step 1.1: Build the carrier motion model

[0046] The carrier motion model is to model the motion of the robot under the condition of effective external force and noise. Its main function is to calculate the state of the robot at the next moment according to the motion state of the carrier at the previous moment.

[0047] x v (k+1)=F v [x v (k),u v (k+1),k+1]+V v (k+1)

[0048] In the formula, x v (k) is the carrier state vector at time k, the equation Fv[ ] is the carrier dynamics equation, u v (k+1) is the effective inner and outer input at time k+1, V v Indicates some uncertain factors.

[0049] For these unpredictable factors, the measure we take is to introduce a random variable to simulate these uncertain factors, with V v means that it satisfies the following conditions:

[005...

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 processing method in an underwater vision SLAM system, which includes establishing an underwater imaging model, processing the influence of underwater environmental factors on camera imaging, and image feature extraction and matching. This method enhances the extraction of feature points of underwater environment images in the later stage. The newly proposed data association method based on the improved SLAM system matches and extracts feature points, which can extract feature points more quickly and accurately, and improve the real-time performance of SIFT algorithm. The method of correlating the relative position factors of the binocular camera and the landmark point position factors as auxiliary conditions can effectively solve the problem of mismatching and matching efficiency in the data association.

Description

technical field [0001] The invention relates to an underwater visual SLAM system, in particular to an image processing method in the underwater visual SLAM system. Background technique [0002] As an important development direction of autonomous navigation of mobile robots, vision-based SLAM systems have gradually received attention in recent years. SLAM (real-time localization and map construction) technology is the key technology for the intelligentization of mobile robots. The current visual SLAM mainly relies on the method of road signs, that is, obtaining the environmental information of the robot through the visual sensor, and positioning and composing itself through this information. The implementation method is the EKF (Extended Kalman Filter) commonly used in SLAM. ) and PF (Particle filter, particle filter) and other methods. [0003] Montiel et al. mainly studied the SLAM problem based on monocular vision, and they mainly used the method of inverse depth paramet...

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): G06T7/33G06T7/13
CPCG06V10/462G06V10/757G06V20/05
Inventor 杨平乐潘志宏张仕杰陈文博程海洋
Owner JIANGSU UNIV OF SCI & TECH IND TECH RES INST OF ZHANGJIAGANG
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