No feature-based vision system can work unless good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can be tracked well and correspond to physical points in the world is still hard. We propose a feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world. These methods are based on a new tracking algorithm that extends previous Newton-Raphson style search methods to work under affine image transformations. We test performance with several simulations and experiments.

Abstract. Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods. Our taxonomy is designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. We have also produced several new multi-frame stereo data sets with ground truth and are making both the code and data sets available on the Web. Finally, we include a comparative evaluation of a large set of today’s best-performing stereo algorithms.

This paper formulates and solves a new variant of the stereo correspondence problem: simultaneously recovering the disparities, true colors, and opacities of visible surface elements. This problem arises in newer applications of stereo reconstruction, such as view interpolation and the layering of real imagery with synthetic graphics for special effects and virtual studio applications. While this problem is intrinsically more difficult than traditional stereo correspondence, where only the disparities are being recovered, it provides a principled way of dealing with commonly occurring problems such as occlusions and the handling of mixed (foreground/background) pixels near depth discontinuities. It also provides a novel means for separating foreground and background objects (matting), without the use of a special blue screen. We formulate the problem as the recovery of colors and opacities in a generalized 3-D (x, y, d) disparity space, and solve the problem using a combination of initial evidence aggregation followed by iterative energy minimization.

Abstract. This paper presents a complete system for constructing panoramic image mosaics from sequences of images. Our mosaic representationassociates a transformationmatrix with each input image, rather thanexplicitly projecting all of the images onto a common surface (e.g., a cylinder). In particular, to construct a full view panorama, we introduce a rotational mosaic representation that associates a rotation matrix (and optionally a focal length) with each input image. A patch-based alignment algorithm is developed to quickly aligntwo images givenmotionmodels. Techniques for estimating and refining camera focal lengths are also presented. Inorder to reduce accumulated registrationerrors, we apply global alignment (block adjustment) to the whole sequence of images, which results inanoptimally registered image mosaic. To compensate for small amounts of motion parallax introduced by translations of the camera and other unmodeled distortions, we use a local alignment (deghosting) technique which warps each image based on the results of pairwise local image registrations. By combining both global and local alignment, we significantly improve the quality of our image mosaics, thereby enabling the creation of full view panoramic mosaics with hand-held cameras. We also present an inverse texture mapping algorithm for efficiently extracting environment maps from our panoramic image mosaics. By mapping the mosaic onto an arbitrary texture-mapped polyhedron surrounding the origin, we can explore the virtual environment using standard 3D graphics viewers and hardware without requiring special-purpose players.

Although it is well known that cross correlation can be efficiently implemented in the transform domain, the normalized form of cross correlation preferred for feature matching applications does not have a simple frequency domain expression. Normalized cross correlation has been computed in the spatial domain for this reason. This short paper shows that unnormalized cross correlation can be efficiently normalized using precomputing integrals of the image and image 2 over the search window. 1

This paper presents some techniques for constructing panoramic image mosaics from sequences of images. Our mosaic representation associates a transformation matrix with each input image, rather than explicitly projecting all of the images onto a common surface (e.g., a cylinder). In particular, to construct a full view panorama, we introduce a rotational mosaic representation that associates a rotation matrix (and optionally a focal length) with each input image. A patch-based alignment algorithm is developed to quickly align two images given motion models. Techniques for estimating and refining camera focal lengths are also presented. In order to reduce accumulated registration errors, we apply global alignment (block adjustment) to the whole sequence of images, which results in an optimally registered image mosaic. To compensate for small amounts of motion parallax introduced by translations of the camera and other unmodeled distortions, we develop a local alignment (deghosting) tec...

This tutorial reviews image alignment and image stitching algorithms. Image alignment algorithms can discover the correspondence relationships among images with varying degrees of overlap. They are ideally suited for applications such as video stabilization, summarization, and the creation of panoramic mosaics. Image stitching algorithms take the alignment estimates produced by such registration algorithms and blend the images in a seamless manner, taking care to deal with potential problems such as blurring or ghosting caused by parallax and scene movement as well as varying image exposures. This tutorial reviews the basic motion models underlying alignment and stitching algorithms, describes effective direct (pixel-based) and feature-based alignment algorithms, and describes blending algorithms used to produce seamless mosaics. It ends with a discussion of open research problems in the area. 1

The task of image registration is fundamental in image processing. It often is a critical preprocessing step to many modern image processing and computer vision tasks, and many algorithms and techniques have been proposed to address the registration problem. Often, the performances of these techniques have been presented using a variety of relative measures comparing different estimators, leaving open the critical question of overall optimality. In this paper, we present the fundamental performance limits for the problem of image registration as derived from the Cramer-Rao inequality. We compare experimental performance of several popular methods with respect to this performance bound, and explain the fundamental tradeoff between variance and bias inherent to the problem of image registration. In particular, we derive and explore the bias of the popular gradient-based estimator showing how widely used multiscale methods for improving performance can be explained with this bias expression. Finally, we present experimental simulations showing general rule-of-thumb performance limits for gradient-based image registration techniques.

We present ordinal measures of association for establishing visual correspondence in images. Linear correspondence measures like correlation and the sum of squared differences are known to be fragile. Ordinal measures, which are based on relative ordering of intensity values in windows, have demonstrable robustness to depth discontinuities, occlusion, and noise. The relative ordering of intensity values in each window is represented by a rank permutation which is obtained by sorting the corresponding intensity data. By using distance metrics between the rank permutations of windows, ordinal correlation coefficients can be arrived at. These coefficients are independent of absolute intensity scale, i.e they are normalized measures. Further, since rank permutations are invariant to monotone transformations of the intensity values, the coefficients are unaffected by nonlinear effects like gamma variation between images. We discuss two crucial properties of ordinal measures for stereo appli...

When a terrain elevation map is computed from widely separated images the perspective distortion may result in a large number of false matches and poor reconstruction accuracy. This paper describes three image matching algorithms designed specifically to process images taken with large base-to-height ratios. They include a new match score, a subpixel interpolation scheme, and a multi-resolution unwarping technique. The algorithms are incorporated into a stereo analysis package and the system is tested by processing a single pair of high altitude images with a base-to-height ratio of 0.63 and a sequence of simulated images with base-to-height ratios that varied between 0.25 and 2.25. Analysis of the simulated data show that when these techniques are implemented the reconstruction accuracy remains independent of the base-to-height ratio. Keywords: stereo, stereo vision, three-dimensional reconstruction, terrain reconstruction, photogrammetry 1 Introduction For applications such as aut...