Search

Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological properties of multiscale regions comprising instances of the 2D category; (2) learning a region-based structural model of the category in terms of these properties; and (3) detection, recognition and segmentation of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to extract the maximally matching subtrees across the set, which are taken as instances of the target category. The extracted subtrees are then fused into a tree-union that represents the canonical category model. Detection, recognition, and segmentation of objects from the learned category are achieved simultaneously by finding matches of the category model with the segmentation tree of a new image. Experimental validation on benchmark datasets demonstrates the robustness and high accuracy of the learned category models, when only a few training examples are used for learning without any human supervision.

The analysis of periodic or repetitive motions is useful in many applications, such as the recognition and classification of human and animal activities. Existing methods for the analysis of periodic motions first extract motion trajectories using spatial information and then determine if they are periodic. These approaches are mostly based on feature matching or spatial correlation, which are often infeasible, unreliable, or computationally demanding. In this paper, we present a new approach, based on the time-frequency analysis of the video sequence as a whole. Multiple periodic trajectories are extracted and their periods are estimated simultaneously. The objects that are moving in a periodic manner are extracted using the spatial domain information. Experiments with synthetic and real sequences display the capabilities of this approach.

A mirror pyramid consists of a set of planar mirror faces arranged around an axis of symmetry and inclined to form a pyramid. By strategically positioning a number of conventional cameras around a mirror pyramid, the viewpoints of the cameras' mirror images can be located at a single point within the pyramid and their optical axes pointed in different directions to effectively form a virtual camera with a panoramic field of view. Mirror pyramid-based panoramic cameras have a number of attractive properties, including single-viewpoint imaging, high resolution, and video rate capture. It is also possible to place multiple viewpoints within a single mirror pyramid, yielding compact designs for simultaneous multiview panoramic video rate imaging. Nalwa [4] first described some of the basic ideas behind mirror pyramid cameras. In this paper, we analyze the general class of multiview panoramic cameras, provide a method for designing these cameras, and present experimental results using a prototype we have developed to validate single-pyramid multiview designs. We first give a description of mirror pyramid cameras, including the imaging geometry, and investigate the relationship between the placement of viewpoints within the pyramid and the cameras' field of view (FOV), using simulations to illustrate the concepts. A method for maximizing sensor utilization in a mirror pyramid-based multiview panoramic camera is also presented. Images acquired using the experimental prototype for two viewpoints are shown.

A learning account for the problem of object recognition is developed within the probably approximately correct (PAC) model of learnability. The key assumption underlying this work is that objects can be recognized (or discriminated) using simple representations in terms of syntactically simple relations over the raw image. Although the potential number of these simple relations could be huge, only a few of them are actually present in each observed image, and a fairly small number of those observed are relevant to discriminating an object. We show that these properties can be exploited to yield an efficient learning approach in terms of sample and computational complexity within the PAC model. No assumptions are needed on the distribution of the observed objects, and the learning performance is quantified relative to its experience. Most important, the success of learning an object representation is naturally tied to the ability to represent it as a function of some intermediate representations extracted from the image. We evaluate this approach in a large-scale experimental study in which the SNoW learning architecture is used to learn representations for the 100 objects in the Columbia Object Image Library. Experimental results exhibit good generalization and robustness properties of the SNoW-based method relative to other approaches. SNoW's recognition rate degrades more gracefully when the training data contains fewer views, and it shows similar behavior in some preliminary experiments with partially occluded objects.

We consider the problem of estimating the 3D shape and reflectance properties of an object made of a single material from a set of calibrated views. To model the reflectance, we propose to use the View Independent Reflectance Map (VIRM), which is a representation of the joint effect of the diffuse+specular Bidirectional Reflectance Distribution Function (BRDF) and the environment illumination. The object shape is parameterized using a triangular mesh. We pose the estimation problem as minimizing the cost of matching input images, and the images synthesized using the shape and VIRM estimates. We show that by enforcing a constant value of VIRM as a global constraint, we can minimize the cost function by iterating between the VIRM and shape estimation. Experimental results on both synthetic and real objects show that our algorithm can recover both the 3D shape and the diffuse/specular reflectance information. Our algorithm does not require the light sources to be known or calibrated. The estimated VIRM can be used to predict the appearances of objects with the same material from novel viewpoints and under transformed illumination. [ABSTRACT FROM AUTHOR]

Presents a approach to hierarchical clustering of point patterns. Description of two algorithms for hierarchical location and density based clustering; Performance of the clustering methods.

Computer vision, as a means to interpret visual images, promises to play explicitly in the artificial intelligence domain. Images are significantly larger and more complex than speech signals, and data reduction in this case is more critical. The scientific significance of a solution to the problem of multiscale-structure deduction of visual images might range from the design of human-friendly medical aids to weather data interpretation to automatic video access and retrieval. Low-level image structures serve intensifying image abstractions and help initiate hierarchical, closed-loop image interpretation. Major issues in successful multi-scale low-level image segmentation include shape and topology invariance, photometric scaling, spatial scaling, and stability and automatic scale selection. The ultimate objective in the process of data reduction is to derive a multi-scale segmentation of the image and represent it through a hierarchical structure. To achieve such segmentation performance, it is necessary that minimal restrictions be placed on the detection process.