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

Quality grading and perceptual hash characteristic combination-based unmanned aerial vehicle image retrieval method

A quality classification and perceptual hashing technology, applied in the field of image processing, can solve problems such as complex retrieval algorithms, achieve fast and accurate retrieval, good algorithm time performance, and low data dimensionality

Active Publication Date: 2016-11-16
BEIHANG UNIV
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the different retrieval content, content-based image retrieval can be roughly divided into two levels: 1) Based on the underlying visual features, such as color, shape, texture and other features, this level of retrieval is concise and intuitive, relevant There are many studies, and many relatively mature image retrieval algorithms have appeared; 2) Based on semantic content, image retrieval is performed by using high-level semantic descriptions of images. Because it contains high-level concepts, it often requires human knowledge reasoning to perform image retrieval. recognition and interpretation, so this level of retrieval algorithm is relatively complex

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
  • Quality grading and perceptual hash characteristic combination-based unmanned aerial vehicle image retrieval method
  • Quality grading and perceptual hash characteristic combination-based unmanned aerial vehicle image retrieval method
  • Quality grading and perceptual hash characteristic combination-based unmanned aerial vehicle image retrieval method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0075] In this embodiment, the UAV image data set containing 500 images is tested, and the test process and results are as follows:

[0076] The first step is to perform automatic quality classification on the UAV training image set, extract the hash code, and establish a database application;

[0077] First, based on edge information statistics, the UAV image clarity is automatically graded and quality labels are assigned;

[0078] 1) Data preparation, constructing an image dataset with image quality classification;

[0079] The UAV image dataset contains a total of 500 real-shot images of UAVs at an altitude of 4km-5km, including 400 training set images and 100 test set images. According to the application requirements for image retrieval, based on the comparison between the subjective perception of the human eye and the images, the UAV reconnaissance images are divided into four levels 1-4, corresponding to very good definition, good definition, average definition, clear ...

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 quality grading and perceptual hash characteristic combination-based unmanned aerial vehicle image retrieval method, and belongs to the technical field of image processing. The method comprises the steps of firstly, performing automatic quality grading and quality label allocation on an unmanned aerial vehicle training image set, extracting perceptual hash codes, and establishing database applications corresponding to images and texts; secondly, setting quality label and perceptual hash code-based data attributes for to-be-retrieved images, like the sub-steps in the first step; thirdly, performing Hamming distance matching on the obtained data attributes of the to-be-retrieved images and images in a database; and finally, allocating a certain weight to a similar image set obtained by matching in combination with similarity and quality labels to establish a weight function, performing resorting according to a weight progressive increase sequence, and outputting an image result. According to the method, image characteristics can be quickly extracted and image quality grading can be effectively finished, so that quick and accurate retrieval of the unmanned aerial vehicle images is realized.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a UAV image retrieval method based on a combination of quality classification and perceptual hash features. Background technique [0002] In recent years, unmanned aerial vehicles (UAVs) have played an important role in military, civilian and scientific research fields due to their advantages of low cost, high flexibility and high efficiency. In the military, UAVs can perform tasks such as target detection, identification and tracking, battlefields, communication relays, and air strikes; in civilian use, UAVs occupy an important position in fields such as aerial photography of film and television materials, and emergency handling. ; In terms of scientific research, it can perform tasks such as resource surveying and meteorological observation. UAV images are the basic data obtained by UAV missions, which can provide effective scientific research data for gro...

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): G06F17/30
CPCG06F16/583
Inventor 丁文锐王玉峰李红光
Owner BEIHANG 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