A deep super-resolution image filtering processing method

A super-resolution and image filtering technology, applied in image data processing, image enhancement, graphics and image conversion, etc., can solve the problem of low efficiency of image smoothing filtering, achieve fast image smoothing filtering, improve image filtering accuracy, reduce effect of noise

Active Publication Date: 2020-11-17
深圳文远知行智能科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a deep super-resolution image filtering method to solve the low efficiency of image smoothing and filtering in the prior art

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 deep super-resolution image filtering processing method
  • A deep super-resolution image filtering processing method
  • A deep super-resolution image filtering processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Embodiment one: if figure 1 As shown, Embodiment 1 of the present invention discloses a depth super-resolution image filtering processing method, including the following steps:

[0028] S1. Input the image I to be processed;

[0029] S2. Bring the deep super-resolution image filtering framework into the image I to obtain the upsampled dense depth image D of the image I F ; Wherein, the depth super-resolution image filtering framework is specifically shown in formula 1:

[0030]

[0031] D. F is an upsampled dense depth image, F(D) is a filtered image with upsampled depth values, and F(M) is a filtered image without upsampled depth processing. The processing steps of the filtered image F(D) of the upsampled depth value are: S21, calculate the upsampled depth value D(P) of the image I at P; S22, bring the upsampled depth value D(P) into the filter The filtered image F(D) of the upsampled depth value is obtained in the device F(x). In step S21, the specific calcula...

Embodiment 2

[0038] Embodiment two: if figure 2 As shown, Embodiment 2 of the present invention also discloses a method for processing depth super-resolution image filtering, including the following steps:

[0039] S1. Input the image I to be processed;

[0040] S2. Replace the depth super-resolution image filtering framework in Embodiment 1 of the present invention with the depth super-resolution image filtering model, and bring the depth super-resolution image filtering model into image I to obtain an upsampled dense depth image of image I D. F , where the depth super-resolution image filtering model is specifically shown in formula 3:

[0041]

[0042] (a i ,b i ,c i ) represents the parameters of the i-th surface model, Denote the depth of pixel p by pixel coordinates [x, y], f is the spatial Gaussian filter kernel, g is the range filter kernel centered on the RGB image value at p, and Ω is the spatial support of kernel f.

[0043] The establishment of this deep super-resol...

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 relates to the technical field of automatic driving image processing, and relates to a depth super-resolution image filtering processing method, comprising the following steps: S1, inputting an image I to be processed; S2, the depth super-resolution image filtering frame is brought into the image I to obtain the up-sampled dense depth image DF of the image I; Alternatively, in step S2, the depth super-resolution image filtering model is substituted for the depth super-resolution image filtering framework, and the depth super-resolution image filtering model is brought into the image I to obtain the up-sampled dense depth image DF of the image I. The invention overcomes the defect of low image smoothing filtering processing efficiency in the prior art, improves the image filtering processing precision, and achieves the purpose of high efficiency and fast filtering processing of images.

Description

technical field [0001] The present invention relates to the technical field of automatic driving image processing, and more specifically, relates to a depth super-resolution image filtering processing method. Background technique [0002] Self-driving car, also known as unmanned car, computer-driven car, or wheeled mobile robot, is a kind of intelligent car that realizes unmanned driving through a computer system. It has a history of several decades in the 20th century, and it has shown a trend close to practicality in the early 21st century. Self-driving cars rely on artificial intelligence, visual computing, radar, monitoring devices, and global positioning systems to work together to allow computers to automatically and safely operate motor vehicles without any active human intervention. During the driving process of the self-driving car, it is necessary to use the camera to capture the road conditions and perform image smoothing and filtering on the road conditions imag...

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): G06T5/00G06T3/40
CPCG06T3/4053G06T5/002
Inventor 杨庆雄许金涛吴彝丹刘振陈学海
Owner 深圳文远知行智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap