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

Moving target detecting method for optical flow field segmentation based on partitioned homodromous speed accumulation

A moving target, detection method technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as the inability to determine the optical flow value

Inactive Publication Date: 2015-04-22
NAT UNIV OF DEFENSE TECH
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the optical flow value cannot be determined only by the basic equation of optical flow, which is called the aperture problem in optical flow calculation

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
  • Moving target detecting method for optical flow field segmentation based on partitioned homodromous speed accumulation
  • Moving target detecting method for optical flow field segmentation based on partitioned homodromous speed accumulation
  • Moving target detecting method for optical flow field segmentation based on partitioned homodromous speed accumulation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] A local method to calculate optical flow

[0044] Assuming that the optical flow remains constant on a small local image area Ω, an overdetermined system of equations is obtained from the fundamental equation

[0045] I x (x i )u+I y (x i )v+I t (x i )=0(x i ∈Ω(i=0,...,n-1))

[0046] Then the least squares method (LS, Least Squares) is used to solve the equations to obtain the optical flow value, and the process is as follows.

[0047] On Ω, the optical flow estimation error is defined as:

[0048] E LK = Σ x i ∈ Ω ( I x ( x i ) u + I y ...

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

Provided is an optical flow field segmentation method based on partitioned homodromous speed accumulation The method comprises the following steps: firstly, calculating optical flow through a local method by the moving target detecting method for the optical flow field segmentation based on the partitioned homodromous speed accumulation, assuming the optical flow field remains constant in a relatively small local image region to obtain an overdetermined equation, and solving the overdetermined equation by using a data fitting method to obtain a optical flow solution; secondly dividing an image into n*n small squares based on the size of a moving target after the optical flow field of the image is obtained, and selecting n according to the need, n is generally picked ranging from 8 to 12; thirdly, dividing the 0-360 degree direction into m grades, in another word, each grade contains 360 / m degrees; dividing the speed direction into m grades, m is picked ranging from 80 to 100; counting the cumulative sum of velocity amplitude of all speed directions of all squares. By means of the moving target detecting method, the moving target can be precisely segmented despite an object being motionless or moving.

Description

technical field [0001] The invention relates to a moving target detection method based on optical flow field segmentation. Background technique [0002] The calculation of the optical flow field is based on the Lucas-Kanade local optical flow algorithm. It can accurately segment the moving target from the calculated optical flow field, solve the technical problem of vector segmentation of the two-dimensional optical flow field, and lay the foundation for a series of subsequent processing. The theoretical basis of the traditional basic equation is the assumption of constant gray level, that is, in two consecutive adjacent frames of images, the gray level of the pixel corresponding to the same panel on the surface of the object remains unchanged. Based on this assumption, Horn et al. derived the fundamental equation of optical flow. [0003] Let I(x, y, t) be the imaging grayscale of the surface element (x, y) at time t, and the surface element moves to (x+δx, y+δy) at time ...

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): G06T7/20G06T7/00
CPCG06T2207/30221
Inventor 王鲁平李飚高颖慧王平赵明张路平梁楹范明喆
Owner NAT UNIV OF DEFENSE TECH
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