A Window Fusion Method Based on Thermal Diffusion Theory

A fusion method and thermal diffusion technology, applied in the field of window fusion, can solve problems such as inaccurate target scale information, and achieve the effect of preventing adjacent target interference and eliminating false detection

Active Publication Date: 2015-11-18
HOPE CLEAN ENERGY (GRP) CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the obtained target scale information is not accurate.

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 Window Fusion Method Based on Thermal Diffusion Theory
  • A Window Fusion Method Based on Thermal Diffusion Theory
  • A Window Fusion Method Based on Thermal Diffusion Theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to describe the content of the present invention conveniently, some terms are explained first.

[0024] Thermodynamic system: In thermodynamics, a specific spatial range selected as a research object. The present invention assumes that all initial detection windows form a thermodynamic system, and there is heat transfer between each window and between the windows and the environment.

[0025] Thermal conductivity: A measure of how quickly an object conducts energy.

[0026] The present invention provides a window fusion method based on thermal diffusion theory, comprising the following steps:

[0027] Step 1. Define that each initial detection window corresponds to a position in the thermodynamic system, and the set of all positions is V.

[0028] Step 2. Define the thermal conductivity b between any two positions x, y in the system xy :

[0029] b xy =ol(x,y)×mean(sc(x),sc(y))

[0030] ol ( x , ...

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 provides a window fusion method based on the heat diffusion theory. The method includes the steps that each initial detection window corresponds to one position in a thermodynamic system; a heat conduction coefficient between positions, corresponding to any two initial detection windows, in the thermodynamic system is calculated; a linear anisotropy heat diffusion equation which is in a discrete version under a steady state is established by using of the heat conduction coefficient between any two positions; K positions are selected in the system as heat sources to enable the temperature sum of the whole system to reach the maximum under the condition of heat diffusion; the repeated initial detection windows are eliminated through a non-maxima suppression method because duplicate detection of the corresponding K detection windows still possibly exists after the K positions of the heat resources are determined. According to the window fusion method based on the heat diffusion theory, the method of maximizing the temperature sum of the system under the condition of linear anisotropy heat diffusion is utilized for simulating an objective law of the initial detection windows, and therefore precision of target detection can be greatly improved.

Description

technical field [0001] The invention belongs to the field of image processing and computer vision, and mainly relates to window fusion technology in sliding window target detection. Background technique [0002] Object detection is a core issue in the field of computer vision research. It judges whether a certain type of object of interest appears in a digital picture or video, and the specific location and scale of the appearance. There are various target detection methods, among which the sliding window method has attracted much attention because of its better detection performance. The general sliding window method mainly includes three steps: (1) training the target classifier; (2) selecting windows of different sizes and scales to traverse the entire image, and using the target detector of the target classifier to judge whether each window belongs to the target or the background , the greater the response score output by a target detector in a window, the greater the p...

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): G06T1/00G06T7/00
Inventor 解梅张抒陈路毛河何磊
Owner HOPE CLEAN ENERGY (GRP) CO LTD
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