This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different images of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substantial range of affine distortion, addition of noise, change in 3D viewpoint, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through leastsquares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest-neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low-residual least-squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially-occluded images with a computation time of under 2 seconds.

In many 3–D object-detection and pose-estimation problems, run-time performance is of critical importance. However, there usually is time to train the system, which we will show to be very useful. Assuming that several registered images of the target object are available, we developed a keypoint-based approach that is effective in this context by formulating wide-baseline matching of keypoints extracted from the input images to those found in the model images as a classification problem. This shifts much of the computational burden to a training phase, without sacrificing recognition performance. As a result, the resulting algorithm is robust, accurate, and fast-enough for frame-rate performance. This reduction in run-time computational complexity is our first contribution. Our second contribution is to show that, in this context, a simple and fast keypoint detector suffices to support detection and tracking even under large perspective and scale variations. While earlier methods require a detector that can be expected to produce very repeatable results in general, which usually is very time-consuming, we simply find the most repeatable object keypoints for the specific target object during the training phase. We have incorporated these ideas into a real-time system that detects planar, non-planar, and deformable objects. It then estimates the pose of the rigid ones and the deformations of the others.

While 2D and 3D vector fields are ubiquitous in computational sciences, their use in graphics is often limited to regular grids, where computations are easily handled through finite-difference methods. In this paper, we propose a set of simple and accurate tools for the analysis of 3D discrete vector fields on arbitrary tetrahedral grids. We introduce a variational, multiscale decomposition of vector fields into three intuitive components: a divergence-free part, a curl-free part, and a harmonic part. We show how our discrete approach matches its well-known smooth analog, called the HelmotzHodge decomposition, and that the resulting computational tools have very intuitive geometric interpretation. We demonstrate the versatility of these tools in a series of applications, ranging from data visualization to fluid and deformable object simulation.

We propose a new approach for automatic road extraction from aerial imagery with a model and a strategy mainly based on the multi-scale detection of roads in combination with geometry-constrained edge extraction using snakes. A main advantage of our approach is, that it allows for the first time a bridging of shadows and partially occluded areas using the heavily disturbed evidence in the image.

There is considerable evidence that object recognition in primates is based on the detection of local image features of intermediate complexity that are largely invariant to imaging transformations. A computer vision system has been developed that performs object recognition using features with similar properties. Invariance to image translation, scale and rotation is achieved by first selecting stable key points in scale space and performing feature detection only at these locations. The features measure local image gradients in a manner modeled on the response of complex cells in primary visual cortex, and thereby obtain partial invariance to illumination, affine change, and other local distortions. The features are used as input to a nearest-neighbor indexing method and Hough transform that identify candidate object matches. Final verification of each match is achieved by finding a best-fit solution for the unknown model parameters and integrating the features consistent with these parameter values. This verification procedure provides a model for the serial process of attention in human vision that integrates features belonging to a single object. Experimental results show that this approach can achieve rapid and robust object recognition in cluttered partially-occluded images.

this paper.

A novel, physically motivated deformable model for shape recovery and segmentation is presented. The model, referred to as the charged-particle model (CPM), is inspired by classical electrodynamics and is based on a simulation of charged particles moving in an electrostatic field. The charges are attracted towards the contours of the objects of interest by an electrostatic field, whose sources are computed based on the gradient-magnitude image. The electric field plays the same role as the potential forces in the snake model, while internal interactions are modeled by repulsive Coulomb forces. We demonstrate the flexibility and potential of the model in a wide variety of settings: shape recovery using manual initialization, automatic segmentation, and skeleton computation. We perform a comparative analysis of the proposed model with the active contour model and show that specific problems of the latter are surmounted by our model. The model is easily extendable to 3D and copes well with noisy images.

Abstract—In this paper, a continuous valued measure for local color symmetry is introduced. The new algorithm is an extension of the successful gray value-based symmetry map proposed by Reisfeld et al. The use of color facilitates the detection of focus points (FPs) on objects that are difficult to detect using gray-value contrast only. The detection of FPs is aimed at guiding the attention of an object recognition system; therefore, FPs have to fulfill three major requirements: stability, distinctiveness, and usability. The proposed algorithm is evaluated for these criteria and compared with the gray value-based symmetry measure and two other methods from the literature. Stability is tested against noise, object rotation, and variations of lighting. As a measure for the distinctiveness of FPs, the principal components of FP-centered windows are compared with those of windows at randomly chosen points on a large database of natural images. Finally, usability is evaluated in the context of an object recognition task. Index Terms—Focus-of-attention, color vision, symmetry, saliency maps, object recognition. æ 1

The subject of scale selection is essential to many aspects of multi-scale and multi-resolution processing of image data. This article shows how a general heuristic principle for scale selection can be appliedtotheproblem of detecting and localizing junctions. In a rst uncommitted processing step initial hypotheses about interesting scale levels (and regions of interest) are generated from scales where normalized di erential invariants assume maxima over scales (and space). Then, based on this scale (and region) information, a more re ned processing stage is invoked tuned to the task at hand. The resulting method is the rst junction detector with automatic scale selection. Whereas this article deals with the speci c problem of junction detection, the underlying ideas apply also to other types of di erential feature detectors, such as blob detectors, edge detectors, and ridge detectors. 1.