Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-source aerial photo-based abnormal scene identification method

A technology of scene recognition and aerial photographs, which is applied in the field of abnormal scene recognition of multi-source aerial photographs, can solve the problem of undiscovered scene recognition of three-source aerial photographs, and achieve the effect of speeding up the calculation speed

Active Publication Date: 2017-02-15
SHANGHAI JIAO TONG UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So far, no research on scene recognition of the three-source aerial film has been found at home and abroad.

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
  • Multi-source aerial photo-based abnormal scene identification method
  • Multi-source aerial photo-based abnormal scene identification method
  • Multi-source aerial photo-based abnormal scene identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Below in conjunction with accompanying drawing and embodiment, the present invention is described in detail: the example that this embodiment is carried out under the premise of the technical solution of the present invention, has verified the present invention for contraband drug processing field, these two kinds of scenes of terrorism-related training camp Identify the effect, and give the detailed implementation and process, but the protection scope of the present invention should not be limited to the following examples.

[0051] ①First of all, it is an embodiment of using the present invention to identify illegal drug processing plants, please refer to figure 1 and image 3 , figure 1 is a flowchart of the present invention, image 3 It is the input, intermediate process diagram and result diagram of this example. As shown in the figure, the specific implementation of the present invention is divided into two parts, and the steps of the first part are as follows...

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

A multi-source aerial photo-based abnormal scene identification method is disclosed. A temperature anomaly area set and a strong dielectricity area set are detected in far-infrared and SAR images, and the temperature anomaly area set and the strong dielectricity area set are combined into a suspected anomaly area set. Three source (visible light, far-infrared and SAR) features of the suspected anomaly area set are extracted one by one, and the three source features are fused on a feature level. At last, a fused feature is input into a classifier for classification identification. According to the multi-source aerial photo-based abnormal scene identification method, temperature anomaly and presence of artificial metal products are taken as common attributes of abnormal scenes, a feasible and practical identification framework is provided, and a research gap of abnormal scene identification based on three source images is filled.

Description

technical field [0001] The invention relates to image processing technology, in particular to an abnormal scene recognition method for multi-source aerial photographs by combining DOG (Difference of Gaussians) speckle detection algorithm and CFAR (Constant False-Alarm Rate) detection algorithm. Background technique [0002] The abnormal scene involved in the present invention is different from the definition of traditional research. It refers to the inaccessible area and the scene with traces of abnormal human activities. The basic attributes are abnormal temperature or artificial metal products. These places are often hidden deep in the mountains and deserts, and the manpower census is huge, and they have serious social hazards, such as illegal drug processing plants, terrorist training camps, and illegal casinos. [0003] According to the characteristics of the above scenes, the research and design of UAVs equipped with visible light, far-infrared and SAR cameras are carri...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/13G06F18/2411
Inventor 李元祥彭希帅徐俊陆永帅
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com