Imagers based on focal plane arrays (FPA) risk introducing in-band and out-of-band spurious response, or aliasing, due to undersampling. This can make high-level discrimination tasks such as recognition and identification much more difficult. To overcome this problem, three-chip color charge coupled device (CCD) cameras typically offset one CCD by 1/2 pixel with respect to the other two. Analogously, monochrome imagers including infrared can use microscan (or dither) to reduce aliasing. This...
I joined the EVASION team in september 2006 in order to work on real time rendering of natural landscapes as a whole. I'm interested in the animation and realistic rendering of terrain, atmosphere, ocean, vegetation, rivers, clouds, etc. I'm looking for real-time and scalable algorithms allowing users to navigate freely anywhere in very large landscapes (up to whole planets), from ground to space, without visible transitions.
Mat estimateRigidTransform(const Mat& srcpt, const Mat& dstpt, bool fullAffine)¶ Computes optimal affine transformation between two 2D point sets Parameters: * srcpt – The first input 2D point set * dst – The second input 2D point set of the same size and the same type as A * fullAffine – If true, the function finds the optimal affine transformation with no any additional resrictions (i.e. there are 6 degrees of freedom); otherwise, the class of transformations to choose from is limited to combinations of translation, rotation and uniform scaling (i.e. there are 5 degrees of freedom) The function finds the optimal affine transform [A|b] (a 2 \times 3 floating-point matrix) that approximates best the transformation from \texttt{srcpt}_i to \texttt{dstpt}_i : [A^*|b^*] = arg \min _{[A|b]} \sum _i \| \texttt{dstpt} _i - A { \texttt{srcpt} _i}^T - b \| ^2 where [A|b] can be either arbitrary (when fullAffine=true ) or have form
Synopsis: Homography transform in Fourier spectrum with application to object recognition. Ideally, recognition of objects should be projection, scale, translation and rotation invariant, just as they are in human vision. This, however, is a very complex problem, since numerous times an object is occluded and many objects rarely appear the same twice, due to different camera/observer positions, variable lighting or object motion. Our goal in this regard is to investigate autonomous object recognition in unconstrained environments by means of outlines of the objects, which we will refer to as the contours. One of the reasons for the popularity of contour-based analysis techniques is that edge detection constitutes an important aspect of shape recognition by the human visual system. The main motivation behind this work is that 2-D homography may overcome the problem of noise sensitivity and boundary variations.
Image alignment is the process of matching one image called template (let's denote it as T) with another image, I (see the above figure). There are many applications for image alignment, such as tracking objects on video, motion analysis, and many other tasks of computer vision. In 1981, Bruse D. Lucas and Takeo Kanade proposed a new technique that used image intensity gradient information to search for the best match between a template T and another image I. The proposed algorithm has been widely used in the field of computer vision for the last 20 years, and has had many modifications and extensions. One of such modifications is an algorithm proposed by Simon Baker, Frank Dellaert, and Iain Matthews. Their algorithm is much more computationally effective than the original Lucas-Kanade algorithm.
The NASA Vision Workbench (VW) is a general purpose image processing and computer vision library developed by the Autonomous Systems and Robotics (ASR) Area in the Intelligent Systems Division at the NASA Ames Research Center. VW has been publicly released under the terms of the NASA Open Source Software Agreement.
ClusterViz is a software to visualize the clustering process using the family of k-means algorithms. The program is free software under the GNU General Public License (GPL). ClusterViz allows to cluster data while visualizing an up to three dimensional projection. The clustering process is visualized using OpenGL. As clustering algorithms the family of k-means algorithms is implemented, including mixture models.
This is a release of a Camera Calibration Toolbox for Matlab® with a complete documentation. This document may also be used as a tutorial on camera calibration since it includes general information about calibration, references and related links.