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

Real-time video camera tracking method based on key frames

A key frame, camera technology, applied in the field of camera tracking, can solve problems such as instability and time-consuming, and achieve the effect of stable solution results and high calculation efficiency

Inactive Publication Date: 2010-06-30
ZHEJIANG UNIV
View PDF0 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Their key frames are manually selected by the user, which is relatively an unstable and time-consuming process

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
  • Real-time video camera tracking method based on key frames
  • Real-time video camera tracking method based on key frames
  • Real-time video camera tracking method based on key frames

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0086]The present invention proposes a real-time camera tracking method based on key frames, which mainly includes four steps: 1. recovering the sparse three-dimensional feature point structure of the scene from the index image sequence; 2. automatically selecting key frames from the index image; 3. real-time During camera tracking, quickly select candidate key frames; 4. Perform feature matching on real-time input images and candidate key frames to obtain matching points containing two-dimensional and three-dimensional information, and finally solve the camera orientation. The specific implementation process is divided into the preprocessing part and the real-time camera tracking part. The process is as follows: figure 2 As shown, the following describes the steps to process a real-time example of a campus scene.

[0087] 1. Preprocessing part:

[0088] 1) Using the technique of inferring structure from motion, from indexed image sequences Recover the sparse SIFT 3D featu...

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 real-time video camera tracking method based on key frames, which comprises the following steps: (1) capturing an index image sequence, and restoring a sparse three-dimensional characteristic point structure of a scene by a method of inferring a structure from movement; (2) giving the index image sequence and the sparse three-dimensional characteristic point structure, and automatically selecting the key frames by optimizing an energy function related to the key frames; (3) in the real-time video camera tracking process, for each frame of real-time input image, firstly, quickly positioning a candidate key frame similar to the real-time input image from the key frame set by a characteristic word tree method of image recognition; and (4) matching the characteristic points abstracted on the real-time input image with the characteristic points on the candidate key frame, obtaining the corresponding three dimensional coordinates of the characteristic points on the image, and calculating the directionality parameters of the video camera. The invention has high calculating efficiency and stable solving result, and the video camera tracking result obtained by the method can be directly used for the applications of reality enhancement, virtual interaction and the like.

Description

technical field [0001] The invention relates to a camera tracking method, in particular to a key frame-based real-time camera tracking method. Background technique [0002] Real-time camera tracking technology refers to recovering the orientation of the camera in real time according to the video image input of the camera in natural scenes. The technology can be classified as hardware-based or vision-based camera tracking, which is the most critical component in augmented reality, video editing, and machine navigation. Hardware devices include gyroscopes, GPS navigation devices, depth scanners, etc. The advantage of hardware equipment is that the error range is stable and the versatility is strong; however, the error is relatively large and the economic cost is relatively high. Vision-based methods mainly use computer vision algorithms to extract features from image sensors, analyze the features, and recover the orientation of the camera in space. [0003] The existing cam...

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
IPC IPC(8): G06T7/20
Inventor 章国锋鲍虎军董子龙
Owner ZHEJIANG 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