A Video Dynamic Object Extraction Method Based on Feature Selection and Smooth Representation Clustering

A feature selection and dynamic target technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as poor real-time performance, poor anti-noise ability, complex calculation of high-dimensional data, etc., and achieve high accuracy, strong motion consistency, The effect of data adaptability

Active Publication Date: 2020-10-02
ZHEJIANG UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention solves the disadvantages of complex high-dimensional data calculation, poor real-time performance, and poor anti-noise ability in the traditional video dynamic target extraction technology, and provides a video dynamic target extraction method based on feature selection and smooth representation clustering, which can be used for target tracking and target detection

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 Video Dynamic Object Extraction Method Based on Feature Selection and Smooth Representation Clustering
  • A Video Dynamic Object Extraction Method Based on Feature Selection and Smooth Representation Clustering
  • A Video Dynamic Object Extraction Method Based on Feature Selection and Smooth Representation Clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0020] A video dynamic object extraction method based on feature selection and smooth representation clustering, comprising the following steps:

[0021] Step 1, video sequence data preprocessing. Suppose the video sequence is f=[1,2,...,F], a total of F frames, we select N pixels, and for each frame of N pixels Extract and track. In this way, N chains, also known as pixel trajectories, are obtained, and each chain is represented as a vector of length 2F N pixel tracks are combined into a 2F×N matrix Y=[y 1 ,y 2 ,...,y N ]∈R 2F×N . like figure 1 shown.

[0022] Step 2, take the video sequence matrix Y as input to establish the FSSR clustering model

[0023]

[0024] s.t.p T 1=1p i ≥0

[0025] Where Z is the coefficient matrix, p is the feature selection vector, L is the Laplacian matrix, L=D–W, D is the angle matrix, W=(w...

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 video dynamic target extraction method based on feature selection and smooth representation (FSSR) clustering. The method comprises the steps that (1) video data is preprocessed and encoded into a video sequence matrix Y; (2) the video sequence matrix Y is used as input to establish an FSSR clustering model; (3) an augmented Lagrangian function and an alternating direction method of multipliers are used to optimize the clustering model, and an optimal coefficient matrix Z<*> is obtained; (4) the formula (|Z<*>|+|Z<*T>|) / 2 is used to calculate an incidence matrix S; and (5) a normalized cut algorithm is used to cut the incidence matrix S, and a dynamic target image is acquired according to a clustering result. The method has the advantages of high operating efficiency, high data adaptability, high accuracy, high motion consistency and the like and is quite suitable for target extraction of high-dimensional feature video data.

Description

technical field [0001] The invention relates to a video dynamic target extraction method based on feature selection and smooth representation clustering, which can be used for target tracking and target detection. Background technique [0002] The analysis and understanding of video sequence scenes in computer vision is one of the important research contents, and its applications include: video coding, security monitoring, intelligent transportation, automatic navigation, machine vision, medical images, meteorological images, etc. The analysis and understanding of video sequence scenes include tracking, detection, segmentation, estimation and recognition of moving objects, and the extraction of dynamic objects is the premise of video sequence scene analysis and understanding. [0003] The key problem of video dynamic target extraction is to cluster and divide different moving objects in the video sequence according to the visual features extracted from the scene. Commonly u...

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): G06T7/246G06T7/10
CPCG06T7/10G06T7/246G06T2207/10016G06T2207/20081
Inventor 郑建炜路程杨平秦梦洁杨弘陈婉君
Owner ZHEJIANG UNIV OF TECH
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