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

Characteristic selection method based on tracking time prediction

A feature selection method, a technology for tracking time, applied in image data processing, instrument, character and pattern recognition, etc., can solve the problem of no further consideration of influence, and achieve the effect of reducing uncertainty

Active Publication Date: 2012-10-03
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main starting point of the random feature selection algorithm is to improve the computational efficiency of the simultaneous positioning and map reconstruction algorithm, so the influence of feature selection on the positioning estimation of mobile robots is not further considered

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
  • Characteristic selection method based on tracking time prediction
  • Characteristic selection method based on tracking time prediction
  • Characteristic selection method based on tracking time prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be described in detail below in conjunction with the embodiments and accompanying drawings, but the present invention is not limited thereto.

[0028] figure 1 As shown, a feature selection method based on tracking time prediction includes the following steps:

[0029] (1) Randomly select n features of a frame of image for feature tracking, obtain the result of feature matching, and use the result of the feature matching to estimate the motion information of the two-dimensional image:

[0030] The motion of the two-dimensional image is represented by a six-parameter affine model as shown in formula (I):

[0031] u 2 =a 1 × u 1 +a 2 × v 1 +a 3

[0032] (I)

[0033] v 2 =a 4 × u 1 +a 5 × v 1 +a 6

[0034] Formula (I), [a 1 , a 2 , a 3 , a 4 , a 5 , a 6 ] is the parameter of the six-parameter affine model, a 1 , a 2 , a 4 , a 5 Indicates the scaling and rotation of the image, a 3 and a 6 Corresponding to up and down an...

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 characteristic selection algorithm based on tracking time prediction, comprising the following steps: randomly selecting n-numbered characteristics of one-frame two-dimensional images to be tracked, obtaining the characteristic matching result and estimating the motion information of the two-dimensional images by utilizing the result; segmenting the two-dimensional images to obtain a group of image subregions which do not overlap each other, taking the central pixel of each subregion as the characteristic point, predicting the tracking time of the characteristic point by the forward iterative algorithm according to the motion information of the two-dimensional images and the current location of the characteristic point and taking the tracking time of the characteristic point as the predicted tracking time of any characteristic in the subregion of the characteristic point, namely the predicted tracking time of each subregion; and comparing the predicted tracking time of all the subregions and carrying out characteristic extraction in the subregion with the maximum predicted tracking time. The characteristic selection method provided by the invention can effectively reduce the uncertainty of self location estimation when being used for selecting characteristics from the environment by robots.

Description

technical field [0001] The invention relates to the field of simultaneous positioning and map reconstruction of a robot, in particular to a method for how a robot selects features from an environment. Background technique [0002] When a mobile robot works in an unknown environment, it needs to create a map of the environment and use this map to determine its own position. In feature-based simultaneous localization and map reconstruction algorithms, the map is usually represented by features in the environment, so the selection of features in the environment is a problem that needs to be solved first. Feature selection in a broad sense includes two processes: extracting features in the image and selecting from the extracted features. However, in vision-based simultaneous localization and map reconstruction algorithms, feature selection is usually only considered as a feature extraction process. [0003] At present, there are many studies on the application of various featu...

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): G06K9/46G06T7/20
Inventor 陈耀武孟旭炯史勇强欧进利
Owner ZHEJIANG UNIV