Mixed measurement-based video data panoramic imaging method

A technology for video data and wide-view imaging, applied in the field of image processing, can solve the problems of low execution efficiency and low-precision wide-view imaging, and achieve the effect of satisfying real-time performance, increasing robustness, and ensuring accuracy

Active Publication Date: 2011-10-19
哈尔滨工业大学高新技术开发总公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problems of low execution efficiency and low precision of wide-view imaging in the existing wide-view imaging algorithm proposed for the registration and stitching of two images when processing video data, and to provide a video based on mixed measures. Data Panoramic Imaging Method

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
  • Mixed measurement-based video data panoramic imaging method
  • Mixed measurement-based video data panoramic imaging method
  • Mixed measurement-based video data panoramic imaging method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0036] Specific implementation mode 1: the following combination Figure 1 to Figure 4 Describe this embodiment,

[0037] The present invention is realized through the following technical solutions:

[0038] First set the initial sampling step size, collect two frames of images from the video image data, and judge the validity of frame scanning and frame splicing respectively to identify whether the performance of the sampling frame meets the requirements of wide-view imaging, and verify After meeting the requirements, the two sampled feature frames are registered. Here, the two-step registration method from coarse to fine is adopted. The mutual information measure is used for coarse registration, and then the background of the image is removed to reduce noise interference. Using the obtained registration displacement as the initial value, the gradient correlation method is used for accurate registration in its neighborhood. Finally, the gap gradient weighted fusion method is used ...

specific Embodiment approach 2

[0116] Specific embodiment two, this embodiment combines Figure 1 to Figure 11 Give a specific example,

[0117] In order to evaluate the proposed hybrid measurement-based wide-view imaging method for video data, we take a piece of human tissue ultrasound scan video collected in real time from clinical equipment as an example. The video has a total of 293 frames of images, and the size of each frame is 461*421 pixels. , The pixel value is an 8-bit unsigned integer value.

[0118] Perform step 1: Set the initial sampling step , To extract the first and second frame image data from the video data, such as Figure 5 Shown.

[0119] Perform step 2: Perform sampling frame performance evaluation on two frames of images. First evaluate its scanning effectiveness and set the "pixel threshold" , Set the "statistical threshold" , According to statistics, both images satisfy The conditions can be used for wide-view imaging processing. Then the stitching effectiveness of the two frames o...

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 present invention discloses a mixed measurement-based video data panoramic imaging method, belongs to the field of image processing, solves the problems of low execution efficiency, low panoramic imaging precision and the like of the conventional panoramic imaging algorithm aiming at registering and splicing two images during processing the video data, and provides a mixed measurement-based panoramic imaging method. The method comprises the following steps of: 1, sampling to acquire a registration frame image; 2, sampling again to acquire the frame image to be registered; 3, performing effectiveness evaluation; 4, acquiring a registration parameter; 5, judging whether a transverse registration displacement and a longitudinal registration displacement exceed a threshold range respectively; 6, splicing the registration frame image of which the registration parameter is acquired and the frame image to be registered by using a tapered slot weighted fusion method, taking the spliced image as a next registration frame image, returning to the step 2 and performing the next image sampling, splicing until the video data sampling process is over and exiting the circulation to finish the splicing process of a panoramic image.

Description

Technical field [0001] The invention relates to a video data wide-view imaging method based on a hybrid measurement, which belongs to the field of image processing. Background technique [0002] Wide-view imaging refers to the continuous video image obtained by the real-time acquisition device in the process of moving, using image processing technologies such as image noise suppression, image registration, and image fusion to synthesize a complete large format, low noise and high definition Wide view image. Because of the large amount of data processing, this technology generally uses a high-speed processor or computer to reconstruct the single image, and is more and more widely used in fields such as robotics, computer vision, virtual reality, and medicine. For example, in robot vision, the processing of complex environments requires wide-view imaging technology. By synthesizing sub-images obtained by the robot's binoculars, wide-view environmental information is obtained. For...

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): H04N5/262G03B37/00
Inventor 金晶沈毅王艳李雪萌
Owner 哈尔滨工业大学高新技术开发总公司
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