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

A method and system for adaptive pyramid transformation

A transformation system and pyramid technology, applied in the field of image processing, can solve problems such as low flexibility and low image processing efficiency

Active Publication Date: 2018-05-15
ZEROTECH (SHENZHEN) INTELLIGENCE ROBOT CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides an adaptive pyramid transformation method and system, which solves the problems of low image processing efficiency and low flexibility caused by the fixed number of pyramid layers

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
  • A method and system for adaptive pyramid transformation
  • A method and system for adaptive pyramid transformation
  • A method and system for adaptive pyramid transformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] figure 1 The flow chart of the adaptive pyramid transformation method provided by Embodiment 1 of the present invention, this embodiment is applicable to the situation that the target object moves at a non-uniform speed in the image processing process, and the method can be executed by an embedded system such as on an ARM chip, specifically Including the following steps:

[0048] Step 110, obtaining continuous frame streams in real time, and calculating the relative moving speeds of the image pixels of the i-th frame to the i+n-th frame respectively;

[0049] Wherein, i is greater than 1, and n is greater than or equal to 1. In the process of image processing, there will be a dozen to dozens of frames of image changes per second, and the continuous frame stream is obtained in real time, that is, the continuous multi-frame images are read separately. For example, if i=10, n=3, the first continuous Frame 10, 11, 12 and 13 images. Among them, the tracked part, that is, ...

Embodiment 2

[0075] figure 2 Shown is a schematic structural diagram of the adaptive pyramid transformation system provided by Embodiment 2 of the present invention, the adaptive pyramid transformation system includes:

[0076] The relative speed calculation modulo 1 is used to obtain continuous frame streams in real time, and respectively calculate the relative moving speeds of the image pixels in the i-th frame to the i+n-th frame, wherein, i is greater than 1, and n is greater than or equal to 1;

[0077] The average value calculation module 2 is used to calculate the average value v of the absolute value of the relative moving speed;

[0078] The number of layers determination module 3 is configured to determine the number of layers of the pyramid according to the average value v and the number of layers threshold.

[0079] Wherein, the number of layers determination module 1 is specifically used to determine: when v is greater than 0 and less than 1, the number of pyramid layers is ...

Embodiment 3

[0089] image 3 It is a flow chart of the adaptive pyramid transformation method provided by Embodiment 3 of the present invention. This embodiment can provide a preferred example based on the foregoing embodiments. As shown in the figure, it specifically includes:

[0090] Step 310, the camera device acquires 5 consecutive frames of images;

[0091] Step 320, calculating the relative moving speed v1, v2, v3, v4, v5 of each frame image respectively;

[0092] Step 330, calculating the average value v of the absolute value of the relative moving speed;

[0093] Step 340: Determine the number of layers of the pyramid according to the average value v and the threshold value of the number of layers and establish a pyramid.

[0094] The present embodiment preferably obtains 5 consecutive frames of images as the original basis for determining the number of layers of the pyramid, and uses the optical flow method to calculate the relative motion speeds v1 to v5 between frames, such...

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 adaptive pyramid transformation method and system. The method comprises: obtaining a continuous frame stream in real time and calculating relative moving speeds of pixels of ith frame to (i+n)th frame of images, wherein i is greater than 1 and n is greater than or equal to 1; calculating a mean value v of absolute values of the relative moving speeds; and according to the mean value v and a layer number threshold, determining the number of layers of a pyramid. According to the adaptive pyramid transformation method and system, the problems of low image processing efficiency, high energy consumption and poor flexibility caused by the variable speed movement of a target object and the fixed number of layers of the pyramid in an image processing process are solved.

Description

technical field [0001] Embodiments of the present invention relate to image processing technologies, and in particular to an adaptive pyramid transformation method and system. Background technique [0002] When the optical flow method makes the objects and scenes in the three-dimensional space correspond to the movement of the two-dimensional image plane, their projections on the two-dimensional image plane form a movement, and the flow of this movement expressed in the brightness mode of the image plane is called optical flow. . The optical flow method is an important method for analyzing motion sequence images. Optical flow not only contains the motion information of the target in the image, but also contains rich information of the three-dimensional physical structure, so it can be used to determine the motion of the target and reflect other information such as the image. . [0003] Due to the defects of the optical flow method itself, it must meet the condition that th...

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): G06T7/207
CPCG06T2207/10016G06T2207/20016
Inventor 傅重阳郭双城杨霖杨建军
Owner ZEROTECH (SHENZHEN) INTELLIGENCE ROBOT CO LTD