Surface target detection method based on high-resolution image

A high-resolution image and detection method technology, applied in the field of high-resolution image target detection, can solve the problems of inability to adapt to various complex scenes, low detection efficiency, low detection accuracy, etc., to improve description performance and good robustness , The effect of high detection accuracy

Pending Publication Date: 2022-07-29
丹阳钒曦光电科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the problems existing in the existing technology are: surface target detection based on high-resolution images generally has low detection accuracy, low detection efficiency, inability to adapt to various complex scenes, and poor robustness

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
  • Surface target detection method based on high-resolution image
  • Surface target detection method based on high-resolution image
  • Surface target detection method based on high-resolution image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] combine figure 1 , the surface target detection method based on high-resolution images of the present invention includes the following steps:

[0027] (10) Image preprocessing: preprocessing the high-resolution image containing the target, and the preprocessing includes image grayscale and image filtering;

[0028] First, the image is preprocessed to improve image contrast, achieve image enhancement, and achieve image denoising and other effects.

[0029] High-resolution images as raw input such as figure 2 shown.

[0030] The (10) image preprocessing step includes:

[0031] (11) Image grayscale:

[0032] A grayscale image is obtained by blending an image with multiple channels into one channel using the formula shown below:

[0033] f=l×r+m×g+n×b (1)

[0034] In the formula, f represents the grayscale value of the grayscale image, r, g, and b represent the grayscale values ​​of the red channel, green channel, and blue channel in the original image, and l, m, and...

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 a surface target detection method based on a high-resolution image, and the method is high in detection precision and robustness. The surface target detection method comprises the following steps: (10) image preprocessing: preprocessing a high-resolution image containing a target; (20) histogram multi-threshold segmentation: carrying out multi-threshold segmentation on the preprocessed image through a gray histogram of the image to obtain a plurality of interested surface regions; (30) Hough transform detection: carrying out edge detection on the region of interest, and detecting to obtain an interested straight line or circular line in combination with Hough transform; and (40) shape area judgment: combining detection results of the previous two steps, matching with existing surface target model features, and judging the type of a surface target.

Description

technical field [0001] The invention belongs to the technical field of high-resolution image target detection, in particular to a high-resolution image-based surface target detection method with high detection accuracy and strong robustness. Background technique [0002] With the development of science and technology, the spatial resolution of various images obtained by ground-based and space-based equipment equipped with cameras is getting higher and higher, which has generally reached the meter level or even sub-meter level. The target to be detected has become a surface target with clear details. However, the surface target detection technology based on high-resolution images is not yet mature. [0003] Generally speaking, automatic surface object detection consists of two parts, the candidate region determination (Hypothesis Generation, HG) and the target confirmation (Hypothesis Verification, HV), namely the HG stage and the HV stage. In the HG stage, the area where 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 Applications(China)
IPC IPC(8): G06T7/11G06T7/13G06T7/136G06T7/187G06T5/00G06T5/40
CPCG06T7/11G06T7/13G06T7/136G06T7/187G06T5/002G06T5/40
Inventor 郭海峰钱惟贤
Owner 丹阳钒曦光电科技有限公司
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