Abstract

Abstract. Semi-global matching is a well-known stereo matching algorithm in photogrammetric and computer vision society. Epipolar images are supposed as input of this algorithm. Epipolar geometry of linear array scanners is not a straight line as in case of frame camera. Traditional epipolar resampling algorithms demands for rational polynomial coefficients (RPCs), physical sensor model or ground control points. In this paper we propose a new solution for epipolar resampling method which works without the need for these information. In proposed method, automatic feature extraction algorithms are employed to generate corresponding features for registering stereo pairs. Also original images are divided into small tiles. In this way by omitting the need for extra information, the speed of matching algorithm increased and the need for high temporal memory decreased. Our experiments on GeoEye-1 stereo pair captured over Qom city in Iran demonstrates that the epipolar images are generated with sub-pixel accuracy.

Highlights

  • Rectified images, resampled along the epipolar line to omit yparallax, which are called epipolar images are considered as input to SGM algorithm (Hirschmüller, 2008)

  • Our proposed algorithm omits the need for rational polynomial coefficients (RPCs) and improve the SGM performance by reducing the memory required by this algorithm

  • In this paper we propose and analyse new epipolar resampling methods for high resolution stereo images

Read more

Summary

INTRODUCTION

Rectified images, resampled along the epipolar line to omit yparallax, which are called epipolar images are considered as input to SGM algorithm (Hirschmüller, 2008). As we consider on image point in left scene, its conjugate location in right scene is determined as c, b, d and e, which are obtained by changing the correspondence object point on the ray of “a” These points creates the epipolar curve of point “ a' ” in right scene. Epipolar images could be generated in object space on a reference plan with constant height value equals to mean height of area In this method the relation between the original image and generated epipolar image is established by RPCs (Wang et al, 2011). Studies on orbital parameters of sensors demonstrates that the epipolar line appears as quasi-hyperbola (Kim, 2000) To determine this curve one needs to access accurate orbital parameters of sensor. Terrain-independent rational polynomial coefficients (RPCs) are proposed to overcome the

SEMI-GLOBAL MATCHING ALGORITHM
PROPOSED METHOD
F8 1 1
Pre-processing
Epipolar resampling and computing disparity map
Findings
CONCLUDING REMARKS
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call