Scene map point and image frame matching method in environment modeling

A matching method and image frame technology, which can be applied in graphics and image conversion, image enhancement, image analysis, etc., can solve the problems of incompatibility between reconstruction range and reconstruction accuracy, limited video memory size, etc., achieve excellent reconstruction effect and improve depth estimation Effect

Inactive Publication Date: 2021-06-25
GUIZHOU UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to build a better map, Lzadi et al. built a KinectFusion dense reconstruction system, using the 3D reconstruction of small-scale scenes and individual objects, and using the truncation

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
  • Scene map point and image frame matching method in environment modeling
  • Scene map point and image frame matching method in environment modeling
  • Scene map point and image frame matching method in environment modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the associated drawings. Preferred embodiments of the invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in this application. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0086] In addition, an element in the present invention is said to be "fixed" or "disposed on" another element, and it may be directly on another element or an intervening element may also exist. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical", "horizontal", "left", "right" and similar expressions used in ...

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 scene map point and image frame matching method in environment modeling. The method mainly adopts a monocular camera to research inverse depth estimation of map points, the inverse depth of the map points is expressed as a depth filter under Gaussian distribution assumption, and inverse depth observation information is utilized to update the map points; meanwhile, a key frame selection strategy and an observation-updating mechanism based on the depth filter are utilized, extraction and inverse depth observation of the map points are researched emphatically, map point matching is improved by adopting a rough-accurate matching mode, and in terms of setting of the real world and robustness, the semi-dense reconstruction scene after inverse depth optimization is more detailed, and the depth estimation is more accurate.

Description

technical field [0001] The invention relates to the technical field of distribution network operation state estimation, in particular to a method for matching scene map points and image frames in environment modeling. Background technique [0002] Map creation is an important part of SLAM. It is a basic building block for many existing industries. From UAV, UGV to the current virtual reality, SLAM gradually shifts from the original medium and large equipment to lightweight level, such as Sweeping robots, service robots, etc. In the absence of prior environmental information, they will estimate their own poses based on the collected information and build a spatial model of their environment at the same time. At present, visual SLAM mainly includes feature-based and pixel-based methods. Although feature-based methods have occupied the field and industry for a long time, many direct methods, dense methods, and semi-dense methods have become popular in recent years. [0003] 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
IPC IPC(8): G06T7/73G06T7/246G06T3/00G06T3/40G06F16/29
CPCG06T7/74G06T7/248G06T3/0006G06T3/4007G06F16/29G06T2207/20201G06T2207/30241
Inventor 赵津刘畅
Owner GUIZHOU 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