Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Hybrid Jitter Correction Method for UAV Video Acquisition

A machine video and image acquisition technology, applied in the field of hybrid shake correction, can solve problems such as distortion, vibration, image shaking, etc., achieve good shake correction, good real-time performance, and avoid over-processing effects

Active Publication Date: 2020-05-22
HANGZHOU DIANZI UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the problems of shake, vibration and distortion in the image taken by the existing UAV due to the shaking during image acquisition, the present invention provides a hybrid jitter correction method for UAV video acquisition

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
  • Hybrid Jitter Correction Method for UAV Video Acquisition
  • Hybrid Jitter Correction Method for UAV Video Acquisition
  • Hybrid Jitter Correction Method for UAV Video Acquisition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Such as figure 1 As shown, the hybrid shake correction method for UAV video acquisition provided by this embodiment begins with step S1, obtaining a pre-acquisition image from the UAV video image. In this embodiment, the video images collected by the drone are transmitted to the cloud storage, so the pre-collected images can be obtained in the cloud storage. However, the present invention does not impose any limitation on the storage or transmission methods of drone images.

[0035] After obtaining the pre-acquisition image, the Kalman filter is used to estimate the jitter parameters. The Kalman filter is a small and flexible algorithm. A large number of experiments have proved that the Kalman filter is used to process the pre-acquisition image of the UAV, which can well describe the inter-frame motion of the video image formed by the shake of the airborne camera. The small and flexible algorithm makes the hybrid jitter correction method for UAV video acquisition prov...

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 hybrid jitter correction method for UAV video collection. The method includes: obtaining a pre-collected image from the UAV video image; using the characteristic points of image rotation due to jitter in the pre-collected image to calculate the Kalman The system state transition matrix A of the filter; construct the Kalman filter system equation and process observation equation; calculate the estimate of the system state of the pre-acquired image at time k and the estimate of the state observation value based on the system noise variance Q and the observation noise variance R value; calculate the Kalman gain and combine it with the Kalman gain to calculate the characteristic parameters of the Kalman evaluation image; use a discretized Gaussian filter to perform low-pass filtering on the brightness matrix of the Kalman evaluation image to filter out system noise and observation noise, and obtain the corrected results jitter-free images.

Description

technical field [0001] The invention relates to the field of video image processing, and in particular to a hybrid shake correction method for video acquisition of drones. Background technique [0002] With the continuous development of UAV technology, the application of UAV in aerial photography or video surveillance is becoming more and more extensive, and it is gradually applied in high-precision detection fields such as surveying and mapping and reconnaissance. Affected by factors such as airflow and the vibration of the motor itself, the drone will shake during operation, which will cause shaking, vibration and distortion in the images captured by the onboard camera, which will cause instability between frames of the video captured by the drone , the angle of viewpoint change between frames is large, and the motion is blurred. Seriously affect task execution and bring difficulties to follow-up processing. [0003] In addition, small drones are more susceptible to inte...

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): G06T5/00G06T7/277
CPCG06T7/277G06T2207/10016G06T5/70
Inventor 吴占雄吴东南杨宇翔曾毓何志伟高明煜黄继业
Owner HANGZHOU DIANZI UNIV
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
Eureka Blog
Learn More
PatSnap group products