A moving target extraction method and device for image sequences

A moving target, image sequence technology, applied in the field of computer vision, can solve the problem of low efficiency of classification and extraction scheme, and achieve the effect of improving efficiency, fast and accurate extraction

Active Publication Date: 2020-06-05
AEROSPACE INFORMATION
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method and device for extracting moving objects in image sequences, which is used to solve the problem of low efficiency of classification and extraction schemes for specific moving objects in existing image sequences

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 moving target extraction method and device for image sequences
  • A moving target extraction method and device for image sequences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026]Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0027] Aiming at the problem of low efficiency of classification and extraction schemes for specific moving objects in existing image sequences, the present invention proposes a scheme for object extraction using a hidden Markov model (hidden Markov model, HMM). The classic usage of HMM is to use it for recognition after modeling a series of motions of the framed target, such as shooting a basketball. When modeling, it is necessary to frame the position of the shooter in each frame of the training data in advance. The recognition also needs to know the test in advance. The position of the shooter in each frame of the data, and then the HMM can give the probabilit...

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 the technical field of computer vision, and discloses a moving target extraction method and apparatus for an image sequence. The moving target extraction method comprises the steps of building hidden Markov models of various moving targets; detecting the image sequence of to-be-extracted moving targets by adopting the hidden Markov models, and outputting an attribute information set of each enclosing box obtained by detection of the hidden Markov models corresponding to the various moving targets in each frame image; and searching out a set of the to-be-extracted moving targets from the attribute information set in combination with a forward probability propagation algorithm and a reverse backtracking algorithm. According to the method and the apparatus, the moving targets are modeled by adopting the hidden Markov models, so that representations of the targets under different poses are accurately characterized and the targets with complex changes can be processed; and in combination with forward probability propagation and reverse backtracking methods, an optimal subsequence is searched for in an enclosing box set obtained by detection in the image sequence, so that quick and accurate extraction of the moving targets is realized.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a method and device for extracting a moving target from an image sequence. Background technique [0002] In the field of computer vision, target extraction and target tracking for a specific moving target in an image sequence are two similar applications. The difference is that target extraction is to extract the position of the target in each frame from the existing image sequence. and size; and target tracking is to find the position and size of the known target in the newly arrived image according to the existing image sequence each time a new frame of image arrives, such as missile guidance. [0003] Technically, the target extraction process generally assumes that each frame of image is known and can be used for search and matching. The commonly used search method is the dynamic programming algorithm, but the algorithm is low in efficiency; Model the known 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): G06T7/277
CPCG06T2207/10016
Inventor 胡懋地
Owner AEROSPACE INFORMATION
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