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

High-precision image registration method under the condition of scene and illumination changes

A lighting change, high-precision technology, used in image enhancement, image analysis, graphics and image conversion, etc., can solve problems such as change detection that cannot be directly applied to low-cost and fine texture, achieve reliable saliency detection results, improve processing capabilities, Effects that resolve scale selection difficulties

Active Publication Date: 2019-10-25
TIANJIN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these recent developments either require complex optimization functions or capture multiple images under dense lighting conditions, making them not directly applicable for low-cost, end-to-end, fine-grained change detection.

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
  • High-precision image registration method under the condition of scene and illumination changes
  • High-precision image registration method under the condition of scene and illumination changes
  • High-precision image registration method under the condition of scene and illumination changes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be further described in detail below in conjunction with the accompanying drawings and through specific embodiments. The following embodiments are only descriptive, not restrictive, and cannot limit the protection scope of the present invention.

[0052] A high-precision image registration method under the conditions of scene and illumination changes, the steps are as follows:

[0053] 1. Camera repositioning:

[0054]Collect scene observation samples at different times. Capture 7 images in a scene: 1 ambient lighting and 6 directional side lighting. The pictures are stored as column vectors.

[0055] Given X as the matrix composed of the above 7 lights is as follows:

[0056]

[0057] Wherein, 1≤k≤K, K is the number of side lighting orientations (here K=6).

[0058] Relocate the current camera to an angle and position similar to the last observation, and roughly adjust it after comparing with the last observation of multiple DSLs to ob...

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 relates to a method for high-precision registration of images under scene and illumination variation conditions. The method comprises the following steps of camera relocation, initialization of L and F, illumination correction and correction of a geometric position of a camera. The invention provides a multiscale low-rank significance testing method and applies GMM-based synergetic significance prior to popularize multiscale low-rank significance testing to synergetic significance testing of multiple images, so that the same or similar regions in multiple images are tested. Compared with the conventional significance testing method, a low-rank multiscale super-pixel fusion algorithm provided by the invention solves a problem of difficulty in scale selection and obtains a more reliable significance testing result.

Description

technical field [0001] The invention belongs to the field of image registration, and relates to a high-precision registration method for high-value images under scene and illumination changes. This method applies the camera's fast relocation technology to the problem of high-precision image registration when the scene and illumination change, and uses 1 main direction image and 6 auxiliary direction images that appeared during the camera relocation process and the last observed image High-precision registration of the current image is the goal. Background technique [0002] The background technology involved in the present invention has: [0003] (1) Change Detection: Change detection is an important preprocessing step for high-level vision applications. In terms of detection steps and decision rules in change detection, CDNet provides a realistic large-scale benchmark video dataset and maintains a good ranking among change detection algorithms. Based on many newly propos...

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): G06T3/00G06T5/00G06T7/00
CPCG06T3/0068G06T5/006
Inventor 冯伟孙济洲田飞鹏张乾周策
Owner TIANJIN UNIV
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