Moving object capturing method fused with optical flow and neural network

A moving target and neural network technology, applied in the field of image target detection, can solve problems such as limited scope of application, and achieve the effect of reasonable and reliable target, elimination of influence, and complete and accurate target detection results.

Inactive Publication Date: 2017-08-11
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Yang Wei from Harbin Institute of Technology and others proposed a new method for detection in complex environments, but its scope of application is limited
Restricted by existing technical conditions, the overall research is basically in its infancy. Compared with foreign research, my country has a certain gap in the conceptual research, theoretical methods, and practical applications of UAV optical flow positioning, navigation and control. Therefore, further in-depth research in this area is urgently needed

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
  • Moving object capturing method fused with optical flow and neural network
  • Moving object capturing method fused with optical flow and neural network
  • Moving object capturing method fused with optical flow and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0059] A moving target capture method that combines optical flow method and neural network, such as figure 1 As shown, the specific steps are as follows.

[0060] Step 1: Firstly, the motion vector of the target contour pixel is detected by the optical flow sensor and the corresponding algorithm, and then the position of each pixel is obtained.

[0061] The invention adopts an algorithm combining the Snake greedy algorithm and the classical LK algorithm for improved optical flow target detection. Among them, the Snake greedy algorithm is based on boundary information, is sensitive to the position of the contour curve, and has high convergence accuracy. After the initial outline of the target is accurately selected by the Snake algorithm, the position information of the target can be detected quickly and stably by using the classic LK algo...

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 moving object capturing method fused with optical flow and neural network. The moving object capturing method fused with optical flow and neural network includes the steps: utilizing the improved optical flow to detect the position of a moving object from an image; utilizing a pulse coupling neural network model to detect the position of the moving object from the image; and finally, performing fusion filtering on the object detection result based on the optical flow and the neural network to obtain the accurate moving object position. The moving object capturing method fused with optical flow and neural network integrates the advantages of the optical flow and the neural network, and can accurately, quickly and completely determine the position of the moving object.

Description

technical field [0001] The invention belongs to the technical field of image target detection, and in particular relates to a moving target capture method combining an optical flow method and a neural network. Background technique [0002] In recent years, with the development of multimedia technology, electronic technology and communication technology, computer vision and digital image processing have attracted more and more attention from scholars and researchers at home and abroad. Moving object detection technology is an important branch of computer vision and digital image processing technology. It is widely used in robot navigation, intelligent video monitoring, industrial inspection, aerospace and many other fields. It has important significance in theoretical research and practical application. . Moving object detection is to separate the moving object from the image containing the background. At present, there are many researches in this area at home and abroad. Op...

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
IPC IPC(8): G06T7/269G06T7/246
CPCG06T2207/20084G06T2207/30241
Inventor 朱平甄子洋覃海群
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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