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

Multi-step neighborhood gray difference index image detection method for low-altitude targets

A technology of neighborhood grayscale difference and low-altitude target, which is applied in the field of low-altitude target detection and image detection, and can solve problems such as ground background interference.

Inactive Publication Date: 2016-11-30
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the defect that the existing technology is easily disturbed by the ground background when detecting low-altitude targets, the present invention provides a multi-step neighborhood gray-scale difference index image detection method for low-altitude targets. The projection characteristics segment the sky and the background area. After the ground background is removed, the target is detected in the sky area image according to the horizontal and vertical projection characteristics of the gray difference index of the mixed neighborhood, and the position coordinates of the target in the image are obtained.

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
  • Multi-step neighborhood gray difference index image detection method for low-altitude targets
  • Multi-step neighborhood gray difference index image detection method for low-altitude targets
  • Multi-step neighborhood gray difference index image detection method for low-altitude targets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] refer to figure 1 .

[0032] Step 1. Image preprocessing, converting the collected color image into a grayscale image, filtering and smoothing the grayscale image to remove noise interference, and obtaining image I with a resolution of 240×320.

[0033] Step 2. Segment the ground background and sky area

[0034] (a) After preprocessing, the gray value of the pixel point (i, j) in the image I is I(i, j), and the horizontal projection S of the inter-line neighborhood gray level difference index of the i-th row of the image is calculated x (i):

[0035] S x ( i ) = 1 320 exp { Σ ...

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 multi-step neighborhood gray scale difference index image detection method for a low-altitude target, which is used to solve the defect that the existing low-altitude target image detection technology is easily interfered by the ground background when detecting a low-altitude target, and belongs to the safety and detection of vehicles technology field. The technical solution is to segment the sky and background regions according to the horizontal projection characteristics of the inter-line grayscale difference index of the image. After removing the ground background, the target is detected in the sky region image according to the horizontal and vertical projection characteristics of the mixed grayscale difference index, and the target is obtained. The location coordinates in the image. The invention can solve the difficult problem that the low-altitude target detection is interfered by terrain and objects.

Description

technical field [0001] The invention relates to an image detection method, in particular to a low-altitude target detection method with a complex ground background, and belongs to the technical field of vehicle safety and detection. Background technique [0002] The detection of low-altitude flying targets is a key technology to ensure flight safety in low-altitude airspace. [0003] The document "Real-time detection algorithm for aerial targets based on image line correlation, Peng Chao, Mao Zheng, Zheng Liping, etc., "Ordnance Industry Automation", 2012, Vol.31(2), p40-42" discloses a background detection for weak and small targets method, this method first performs grayscale inversion on the image, performs background removal preprocessing according to the correlation between adjacent lines of the image, and calculates the pixel point with the largest grayscale value in the image to obtain the position coordinates of the target. However, in practical applications, there ...

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): G06T7/00
Inventor 张宇
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY