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

Movement estimation method and movement estimation device

A technology of motion estimation and preliminary estimation, applied in the field of image processing, can solve problems such as slow convergence speed and errors, and achieve fast convergence speed and high precision

Inactive Publication Date: 2017-03-01
RICOH KK
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there are currently some methods for removing the influence of outliers, these methods, due to the influence of noise, have slow convergence speed and may lead to large errors

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
  • Movement estimation method and movement estimation device
  • Movement estimation method and movement estimation device
  • Movement estimation method and movement estimation device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0013] First, refer to figure 1 A motion estimation method according to an embodiment of the present invention is described.

[0014] like figure 1 As shown, first, in step S110, an image sequence including multiple frames of images is acquired. Specifically, for example, when the motion estimation method of the embodiment of the present invention is applied to fields such as visual ranging, the image sequence including multiple frames of images may be collected by a camera installed on a moving object such as a vehicle.

[0015] Next, in step S120, feature points in each frame of the image sequence are detected. Specifically, those skilled in the art may use various methods known in the field of image processing and developed in the future to detect feature points in each frame of image, which will not be described in detail here.

[0016] After det...

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 provides a movement estimation method and a movement estimation device. The movement estimation method comprises steps of acquiring an image sequence including multiple frames of images; detecting feature points of each frame of image in the image sequence; determining a matching feature point pair between adjacent frames of images, and taking the matching feature point pairs as a sampling point set; and carrying out weight-based iteration estimation on the sampling point set so as to obtain a movement estimation parameter and take the movement estimation parameter as a movement estimation result.

Description

technical field [0001] The present invention relates to the field of image processing, and more specifically, the present invention relates to a motion estimation method and a motion estimation device. Background technique [0002] In the field of image processing, so-called motion estimation methods are usually used in order to determine the changes of objects between multiple image frames. In motion estimation methods, due to various reasons such as image noise, occlusion, blur, viewing angle, illumination change, etc., outliers often appear among the matched feature points, that is, feature points that are incorrectly associated together. The existence of outliers affects the accuracy of motion estimation, especially when the number of image frames is large. Although there are currently some methods for removing the influence of outliers, these methods, due to the influence of noise, have a slow convergence speed and may cause large errors. Contents of the invention ...

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): G06T7/246G06T7/207
CPCG06T2207/10016
Inventor 刘童师忠超任杰李静雯陈超
Owner RICOH KK