Obtain the depth of field based on two-view

Authors:
Zhao Liang;Liu Jian-hui
Affiliations:
Institute of Graduate, Liaoning Technical University, Huludao, China;School of Electronic and Information Engineering, Liaoning Technical University, Huludao, China
Venue:
CAR'10 Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 1
Year:
2010

Citing 3
Cited 0

A Flexible New Technique for Camera Calibration

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Machine Vision Algorithms and Applications

Machine Vision Algorithms and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

this paper attempts to propose a method that uses images taken in different locations by a single camera or from a video stream interception to restore depth information of the scene. At first, the SIFT algorithm is used to process two images, to find the feature points and match them into pairs, then these pairs are used to calculate the corresponding fundamental matrix. From the fundamental matrix the epipolar can be got. The feature points are matched with the epipolar constraint to improve accuracy. With these matched points, the binocular stereo vision method is used to find the depth information. For a visual representation, the coordinates of the points are input to Matlab to show the result. Experiments show that the method can get information of depth of the field without a known position relationship between images.