In this paper, we propose a novel shape representation we call Directional Histogram Model (DHM). It captures the shape variation of an object and is invariant to scaling and rigid transforms. The DHM is computed by first extracting a directional distribution of thickness histogram signatures, which are translation invariant. We show how the extraction of the thickness histogram distribution can be accelerated using conventional graphics hardware. Orientation invariance is achieved by computing the spherical harmonic transform of this distribution. Extensive experiments show that the DHM is capable of high discrimination power and is robust to noise.
This paper proposes a novel stratified selfcalibration method of camera based on rotation movement. The proposed method firstly captures more than three images of the same scene in the case of constant internal parameters by panning and rotating the camera with small relative rotation angles among the captured images. After feature extraction and matching of captured images, the pixel coordinates of feature point are normalized. Then the stratified self-calibration is performed, following projective, affine and metric calibration. Projective calibration determines the camera projective matrix of every image in the projective reconstruct space. Affine calibration calculates the parameters of infinity reference plane in this space and the homography according to approximately equal relationship among the main diagonal elements of homography, which is inferred by virtue of small relative rotation angles among the captured images and the property of internal reference matrix corresponding to normalized pixel coordinates. Lastly metric calibration acquires internal reference matrix from the calculated homography. The proposed method can be online applied to simply, fast, accurately obtain internal parameters of camera without using the calibration reference with known 3D information. Real data has been used to test the proposed approach, and very good results have been achieved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.