A method and system for image correction of jelly effect based on artificial intelligence

A technology of image correction and artificial intelligence, applied in the field of drone surveying and mapping, can solve problems such as point cloud incompatibility, and achieve the effect of ensuring accuracy

Active Publication Date: 2022-02-22
南通透灵信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Through the technical means proposed by the present invention, the regional features at the window can be obtained according to the gradient features of the depth image, which can well solve the problem that the point cloud of the original RGB image and the TOF image cannot be matched

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 image correction of jelly effect based on artificial intelligence
  • A method and system for image correction of jelly effect based on artificial intelligence
  • A method and system for image correction of jelly effect based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as figure 1 As shown, the present embodiment provides a method for correcting jelly effect images based on artificial intelligence, including:

[0051] Collecting the first image and the first depth image of the building respectively; performing edge detection on the window frame area in the first image to obtain the first edge image.

[0052] The RGB camera deployed by the UAV collects images of the building to be tested to obtain the first image.

[0053] Perform image processing on the collected first image, process the three-channel average grayscale, histogram equalization and denoising processing of the first image, use the edge detection algorithm to extract the edge information in the first image, and pass Edge screening removes the noise edge in the image, only retains the edge contour of the building, and completes the contour drawing of the edge points of the building, and uses the obtained edge contour of the building as the ROI area to analyze the fir...

Embodiment 2

[0113] Such as figure 2 As shown, a kind of artificial intelligence-based jelly effect image correction system in an embodiment of the present invention is provided, including: image acquisition module 21, image matching module 22, image correction judgment module 23, offset acquisition module 24, Offset correction module 25 and image correction module 26;

[0114] Image acquisition module 21: collect the first image and the first depth image of the building respectively; perform edge detection on the window frame area in the first image to obtain the first edge image;

[0115] Image matching module 22: match the point cloud in the first edge image with the point cloud in the first depth image, and use the confidence weight to compensate the unmatched point cloud in the first depth image , the compensated point cloud is matched again; the image composed of all the matched point cloud regions is used as the second edge image;

[0116] Image correction judgment module 23: Obt...

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 an artificial intelligence-based jelly effect image correction method, comprising: separately collecting a first image and a first depth image of a building; performing edge detection on a column of window frame regions in the first image to obtain a first edge image; Match the point cloud in the first edge image with the point cloud in the first depth image to obtain a second edge image; obtain the estimated offset value of each window frame in the first edge image, and calculate according to the estimated offset value The offset of all pixels in the first edge image, judge whether the overall offset obtained is accurate; if not, use the adjustment coefficient to obtain the adjusted confidence weight, repeat the above steps until the accurate pixel offset is obtained, according to The accurate pixel offset corrects the first edge image. Through the technical means proposed by the invention, the offset of the frame area of ​​the window is analyzed to correct the jelly effect image, so as to ensure the authenticity of the finally obtained image.

Description

technical field [0001] The invention relates to the field of unmanned aerial vehicle surveying and mapping, in particular to an artificial intelligence-based jelly effect image correction method. Background technique [0002] UAV surveying and mapping is a powerful supplement to traditional aerial photogrammetry methods. It has the characteristics of flexibility, high efficiency and speed, precision and accuracy, wide application range, and short production cycle. UAV surveying and mapping usually has a low flying altitude and is less affected by climatic conditions, but UAVs are easily affected by their own resonance during operations, resulting in a jelly effect in the image. Since the existence of the jelly effect will affect the quality of the image and the accuracy of surveying and mapping, it is necessary to perform image correction on the jelly effect image to avoid surveying and mapping errors. Image correction refers to the restorative processing of distorted image...

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): G06T5/00G06T7/13G06V10/75G06K9/62
CPCG06T5/006G06T7/13G06T2207/10028
Inventor 余伟玲詹碧玉
Owner 南通透灵信息科技有限公司
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