Correspondence-Free Determination of the Affine Fundamental Matrix 2007. 2. 6 (Tue) Young Ki Baik, Computer Vision Lab. Correspondence-Free Determination of the Affine fundamental Matrix • References • Correspondence-Free Determination of the Affine Fundamental Matrix • Stefan Lehmann et. al. PAMI 2007 • Radon-based Structure from Motion Without Correspondences • Ameesh Makadia et. al. CVPR 2005 • Robust Fundamental Matrix Determination without Correspondences • Stefan Lehmann et. al. APRS 2005 2 Correspondence-Free Determination of the Affine fundamental Matrix • Contents • The conventional method of SfM • Features of the proposed method • Theory of the proposed algorithm • Experimental results • Discussion 3 Correspondence-Free Determination of the Affine fundamental Matrix • Conventional SfM Image Sequence Feature Extraction/ Matching Relating Image Projective Reconstruction AutoCalibration Dense Matching 3D Model Building 4 Correspondence-Free Determination of the Affine fundamental Matrix • The Problem of conventional SfM • The high sensitivity of fundamental matrix • Noise and outlier correspondences in feature data severely affect the precision of the fundamental matrix • Incomplete 3D reconstruction 5 Correspondence-Free Determination of the Affine fundamental Matrix • The Key Feature • Correspondence-free Finding Correspondence (X) • Illumination changes-free (?) • Intensity value (X) • Position of features (O) • • Limitation • Occlusion ? (X) • Affine camera only!! 6 Correspondence-Free Determination of the Affine fundamental Matrix • Parallel projection • Orthographic projection 7 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Assumption • • We have 3-dimensional N features. The 3D feature space is represented by, f 3 x, y, z N x x , y y , z z n n n n 1 xn , yn , zn : Individual feature locations : Dirac delta function 8 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Assumption • • • Parallel projection model determines the 2D feature projections along the lines that are running parallel to the view axis (z-axis) of the camera. The model considers a continuous projection plane with infinite extent. The corresponding 2D projection data is… f 2 x, y R f 3 x, y, z dz N x x , y y n n n 1 9 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Fourier spectra • The Fourier spectra of be denoted as F2 , e j xn yn f 3 x, y, z e j x y z dxdydz R3 N N f 2 x, y e j x y dxdy R2 F3 , , f 2 x, y and f 3 x, y, z can n 1 e j xn yn zn n 1 F2 , F3 , , 0 ,, : 3D frequency components The projection - slice theorem 10 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • 2-view case • The 3D correspondence feature point T P x, y, z , P x , y , z T • Relation between images P RP t R,t : nonhomogeneous 3D rotation and translation matrix • The 3D frequency vector Δ , , T 11 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • 2-view case • Relation between 3D spectrums F3Δ e F R T Δ j tT Δ F3Δ e 3 j PT Δ P RP t The equation shows that rotation R also establishes the transformation between corresponding frequency indices in the 3D Fourier spaces of the original and the transformed spectrum or scene. 12 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Matching line F2 , F3 , , 0 • The magnitudes of two spectra along these lines will be identical, while the phases will show a linear offset dependent upon the translational component of transformation. • The proposed method is to detect these matching lines. 13 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Matching line angle pair , • Angle pair of the matching lines with respect to the , axes of the frequency spectra F and F’, respectively. 14 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Analysis of the transformation parameters • , , , as the corresponding frequency locations along the matching lines of the spectrum F of the first and the spectrum F’ of the second set of 2D features, respectively. • It follows that, F2 , e j x0 y0 F2 , t x0 , y0 , z0 15 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Analysis of the transformation parameters F2 , e j x0 y0 F2 , t x0 , y0 , z0 cos , sin cos , sin F2 v cos , v sin e j v F2 v cos , v sin x0 cos y0 sin F1 v F2 v cos , v sin 16 Correspondence-Free Determination of the Affine fundamental Matrix • Mathematical Model • Derivation of a 3D rotation matrix R Rz Rx R z R z cos sin 0 sin cos 0 0 0 1 0 1 Rx 0 cos 0 sin R z : unknownangle cos sin 0 sin cos 0 sin cos 0 0 0 1 17 Correspondence-Free Determination of the Affine fundamental Matrix • Estimation of the fundamental matrix • By using 3D rotation matrix, we can obtain the relation between 2D projection point (x’,y’) of a 3D feature (x,y,z) with translation. x cos cos sin cos sin x cos sin sin cos cos y sin sin z x0 y sin cos cos cos sin x sin sin cos cos cos y cos sin z y0 18 Correspondence-Free Determination of the Affine fundamental Matrix • Estimation of the fundamental matrix • In the orthographic projection case, all epipolar lines are parallel. • Then we can denote the epipolar line of 2D feature point (x,y) as px qy c c depends on (x, v) c [ pcos cos sin cos sin qsin cos cos cos sin ]x [ pcos sin sin cos cos qsin sin cos cos cos ] y [ psin sin qcos sin ]z px0 qy0 19 Correspondence-Free Determination of the Affine fundamental Matrix • Estimation of the fundamental matrix px qy c p cos , q sin c [ pcos cos sin cos sin qsin cos cos cos sin ]x [ pcos sin sin cos cos qsin sin cos cos cos ] y [ psin sin qcos sin ]z px0 qy0 cos x sin y cos x sin y 20 Correspondence-Free Determination of the Affine fundamental Matrix • Estimation of the fundamental matrix cos x sin y cos x sin y 0 0 a F 0 0 b c d e ax by cx dy e 0 0 cos 0 F 0 0 sin cos sin , , ? 21 Correspondence-Free Determination of the Affine fundamental Matrix • Estimation of matching line angle • For the practical purpose, corresponding discrete spectra should be defined as follows. bk F1 2kf ck F12kf f : frequency resolution 2f : circular frequency resolution exp jk x N bk n cos y n sin n 1 N ck exp jk x cos y sin n n 1 n 22 Correspondence-Free Determination of the Affine fundamental Matrix • Estimation of matching line angle • The final object function d 2 arg max , , jk bk ck e k 1 N 2 b c 2 2 • Discrete Fourier-Mellin transformation method • To find out the matching line (According to the well known shift theorem of the FT, a shift in the space domain corresponds to a phase shift in the frequency domain.) 23 Correspondence-Free Determination of the Affine fundamental Matrix • Overall flow 24 Correspondence-Free Determination of the Affine fundamental Matrix • Experimental result • • • • test images : telephoto lens Feature points : Harris corner detection method Ideal epipolar lines are the horizontal lines. The proposed method shows us good result relative to conventional methods. 25 Camera Calibration Methods for Wide Angle view • Discussion • Key feature • Correspondence-free method for obtaining the fundamental matrix is presented. Matching line exists between the Fourier transformed data. • Limitation • Proposed method Considers only affine projection model Does not treat occlusion problem • Future work • Applying projective projection model 26
© Copyright 2026 Paperzz