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

Optical flow parallel acceleration method based on closet point search

A nearest-neighbor, optical flow technology, applied in the field of image processing, can solve the problem of time-consuming and achieve the effect of improving efficiency

Active Publication Date: 2017-10-24
BEIHANG UNIV
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical solution of the present invention: In order to overcome the time-consuming shortcoming of the current optical flow field calculation, a parallel accelerated optical flow method based on the nearest neighbor search is provided. Spend

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
  • Optical flow parallel acceleration method based on closet point search
  • Optical flow parallel acceleration method based on closet point search
  • Optical flow parallel acceleration method based on closet point search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In order to make the purpose and technical solution of the present invention clearer, the present invention will be further described in detail below in combination with the implementation modes and schematic diagrams.

[0027] like figure 1 Shown, the present invention is concretely realized as follows:

[0028] Step 1: Read in the two frames of images to be processed, convert them into grayscale images, and perform Gaussian filtering to reduce noise.

[0029] Step 2: Pyramid layering is performed on the two filtered images respectively. The size of each image layer is 0.9 times that of the previous layer, and it is divided into 20 to 30 layers depending on the size of the original image.

[0030] Step 3: Randomly initialize the optical flow field of the bottom image to make it a uniform distribution between (0,1).

[0031] Step 4: Calculate the gradient values ​​in the x-direction and y-direction of the layer image respectively, and perform Gaussian filtering on the...

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 optical flow parallel acceleration method based on closet point search. An optical flow correction algorithm of a Barnes closet point search is corrected, and an optical flow is corrected by adopting a gradient descent method, and then efficiency is improved. The transmission process of the optical flow is corrected, and then the parallel operation is easy to realize on a GPU, and then the acceleration is realized. The optical flow parallel acceleration method is used for optical flow calculation, and operation speed is obviously improved, and at the same time, certain accuracy is guaranteed.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an optical flow parallel acceleration method based on the nearest neighbor search. Background technique [0002] The concept of optical flow (Optical Flow) was first proposed by Gibson in 1950. It is generated by the relative motion of the camera and the scene, and represents the instantaneous relative motion speed of each pixel in the image. Optical flow field refers to the surface motion of the image grayscale pattern. Optical flow calculation is one of the hotspots in computer vision today. Optical flow algorithms are widely used in moving target detection and tracking, robot navigation, 3D reconstruction and other fields. In the early 1980s, Horn and Schunck proposed a dense optical flow algorithm based on the assumption of optical flow smoothness, which played a fundamental role in the development of optical flow calculations. After that, scholars succe...

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): G06T5/00G06T3/40
CPCG06T3/4007G06T2207/20024G06T5/70
Inventor 姜精萍杨昕欣刁为民郭正霖
Owner BEIHANG UNIV