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

Method for evaluating quality of image shot by unmanned aerial vehicle

A technology for capturing images and evaluating quality. Applied in the field of image processing, it can solve the problems of background texture interference, image sharpness evaluation disturbance, and inability to predict the absolute sharpness of the image, and achieve the effect of prominent image and significant substantive features.

Active Publication Date: 2017-06-16
SHANGHAI UNIV
View PDF4 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This technology uses both the entire region around each pixel within images or areas inside them to analyze it separately from other parts like surrounding pixels. It then ranks these regions based on their importance towards overall visual performance such as brightness contrast ratio and color balance. By analyzing this data over time, we aimed at finding specific areas where there are no important details about what they're doing well without any complicated texture patterns or lights affecting how good things look when taken by robots flying through airspace.

Problems solved by technology

This patented technical problem addressed in this patents relates to accurately identifying objects within moving imagery without causing confusion due to complicated background patterns. Existing algorithms used for object recognition involve binary pixel values alone, making them difficult to interpret even if the surrounding areas contain significant detail. Additionally, existing approaches require multiple steps and take longer periods of time compared to automated systems like cameras.

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
  • Method for evaluating quality of image shot by unmanned aerial vehicle
  • Method for evaluating quality of image shot by unmanned aerial vehicle
  • Method for evaluating quality of image shot by unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0038] like figure 1 As shown, a method for evaluating the quality of images taken by UAVs. For an image captured by a UAV during inspection, the quality of the image is analyzed from the overall and local details of the image; the specific steps are as follows:

[0039] 1) Give an overall evaluation of the image taken by the UAV, which is mainly divided into two parts: one is to manage the edge line segment through Blob analysis, and count the orientation and distribution of the line segment; the other is to analyze the overall clarity of the image in the transform domain degree, DFT transforms the image, and counts the average sharpness index on the spectrum as an evaluation index for the overall sharpness of the image; the overall evaluation divides the image quality of the UAV into five levels: very good, good, acceptable, poor, very poor;

...

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 method for evaluating the quality of an image shot by an unmanned aerial vehicle, which is characterized in that for an image shot by the unmanned aerial vehicle in patrol inspection, the quality of the image is analyzed from the whole image and local details; for blurring generated by focusing misalignment caused by motions or shakes of the unmanned aerial vehicle, a frequency domain sharpness index and the distribution density and orientation features of edge segments in a space domain are firstly fused so as to judge whether an image captured by the unmanned aerial vehicle image is blur or not on the whole; under the condition that the image quality is acceptable on the whole, salient edge regions in the image are further searched, and the local detail blur degree of image edges is judged through analyzing the average width of difference salient edges. The method is applied to images shot by the unmanned aerial vehicle under outdoor conditions, the image quality can be effectively evaluated under various complex backgrounds without being influenced by the image content, and the evaluation is consistent with subjective evaluation of people in grade.

Description

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

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
Owner SHANGHAI 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