Detection method of weak and small moving targets on the ground based on target saliency

A moving target and satellite image technology, applied in the field of satellite image detection of weak and small moving targets on the ground, can solve the problems of low detection rate of weak and small moving targets and high false alarm rate, and achieve the effect of increasing the detection rate and reducing the false alarm rate.

Active Publication Date: 2019-03-26
NORTHWESTERN POLYTECHNICAL UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the detection result of this method depends on the characteristics of the geometric direction of the moving target. For weak and small moving targets, the geometric direction of the moving target cannot be obtained. The detection rate of weak and small moving targets is extremely low, and the false alarm rate is high.

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
  • Detection method of weak and small moving targets on the ground based on target saliency
  • Detection method of weak and small moving targets on the ground based on target saliency
  • Detection method of weak and small moving targets on the ground based on target saliency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific steps of the method for detecting weak and small moving targets on the ground based on the satellite image of the target salience of the present invention are as follows:

[0030] (a) Salient image calculation: Calculate the saliency image for the current input image. Note that a pixel value in the image is I k , where k represents the kth pixel in the image. Denote w as pixel I k centered sliding window. ||·|| represents the gray distance matrix between pixels, d i Indicates the distance from pixel k to pixel i. Then image pixel I k The local significance value of is expressed as

[0031]

[0032] where f( ) is about d i A linearly decreasing function of .

[0033] Input an image sequence captured by a satellite, first use the local saliency to calculate the local saliency of each pixel for the current frame image. In order to ensure computational efficiency and detection performance, the size of the sliding window w is set to 3 in this example...

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 method for detecting a small moving object on the ground on the basis of a satellite image with target significance. The method is used for solving the technical problem of low detection efficiency for the small moving object according to the existing method. According to the technical scheme, the method comprises the following steps: firstly, performing background modeling on a significance image; performing significance analysis on a gray level image; strengthening the moving object in the image. The gauss mixing background modeling is performed on the significance image, so that the difficulty in detecting the small moving object is solved; the grading is utilized to generate track; the track information is utilized to filter false alarm; compared with the background technical method, the method has the advantages that the detection efficiency is increased by 10% and the false alarm is reduced by 5%.

Description

technical field [0001] The invention relates to a method for detecting weak and small moving targets on the ground by satellite images, in particular to a method for detecting weak and small moving targets on the ground by satellite images based on the saliency of the target. Background technique [0002] Earth-moving target detection in satellite images is an important research topic in the field of computer vision. The detection rate of the existing detection algorithms for weak and small moving targets on the ground in satellite images is low. The document "Vehicle Detection and Roadside TreeShadow Removal in High Resolution Satellite Images, 2010" discloses a method for detecting weak and small moving targets on the ground from satellite images. This method utilizes the geometric features of vehicles in satellite images and uses an improved scale circle spot matching algorithm to detect elliptical moving vehicles in satellite images. For vehicles running on the road, t...

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): G06T7/20
CPCG06T7/20G06T2207/10032G06T2207/20012
Inventor 杨涛张艳宁姚博伟贺战男
Owner NORTHWESTERN POLYTECHNICAL UNIV
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