A low-altitude moving target detection method based on visible light sequence images

A technology of sequential images and moving objects, which is applied in the field of image processing, can solve the problems of high complexity of object feature extraction and high dependence on moving objects, and achieve the effect of shortening search time, optimizing search strategy, and shortening time

Active Publication Date: 2020-02-14
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to avoid the deficiencies of the prior art, the present invention proposes a low-altitude moving target detection method based on visible light sequence images, aiming at the existing visible light sequence image moving target detection and recognition methods, the complexity of target feature extraction is high, and the moving target Highly dependent problems

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 low-altitude moving target detection method based on visible light sequence images
  • A low-altitude moving target detection method based on visible light sequence images
  • A low-altitude moving target detection method based on visible light sequence images

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0071] Specific embodiment: the specific implementation mode of the present invention is described in conjunction with the low-altitude moving target detection example of visible light sequence image:

[0072] It includes the following steps: Step 1: Block processing the target frame image and calculate the dimensionality reduction Haar feature vector; Step 2: Compare the target frame with the corresponding block of the comparison frame to find the moving target; Step 3: For each moving target in the target Find the position of the target after moving in the frame.

[0073] Step 1. Obtain a sequence of images F of length n with the same background, where each frame of image is denoted as f i (1,2,...,n), since each frame image uses the same feature template is fixed, so first generate the feature template of each frame image. Specifically divided into two processes:

[0074] (1) According to the image pixel size and the volume of the low-altitude moving target, each frame of...

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 a low-altitude moving target detection method based on visible light sequence images, which uses a Haar feature optimized by applying a particle filter sampling strategy to reduce the dimensionality of the local features of the image, shortens the time for processing image data, and reduces the target features. of complexity. On the basis of obtaining the eigenvector of the moving target feature, combined with the adjacent frame difference to divide the search area, the image block processing technology and the search strategy of the undirected graph topological relationship, the position difference of the target between adjacent frames in the sequence image is realized Detect the moving state of the target and estimate the possible position of the target to shorten the time of searching for the moving target, so as to realize the accurate and fast detection of the moving target in the sequence image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a low-altitude moving target detection method based on visible light sequence images. Background technique [0002] Moving object detection is an important research topic in the field of image processing and machine vision. At present, moving object detection technology has been widely used in the fields of security monitoring, remote sensing images and intelligent robots. Objects are distinguished and extracted from the background. In recent years, with the development of UAVs, the demand for safety monitoring of UAVs has gradually increased. Therefore, moving object detection in low-altitude airspace is one of the research hotspots in current image sequence moving object detection. [0003] In Wang Xiaoxia ("Detection of Moving Objects in Complex Scenes", Computer Application and Software, 2015, 32-2, 203-206), based on the background subtraction method, the improved ba...

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): G06T7/11G06T7/181G06T7/73G06K9/46
CPCG06T7/11G06T7/181G06T7/73G06V10/44G06V2201/07
Inventor 王靖宇姜海旭张科王霰禹王佩吕梅柏徐有新
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

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