Showing papers by "Paul A. Viola published in 1999"

Roxels: responsibility weighted 3D volume reconstruction

Abstract: This paper examines the problem of reconstructing a voxelized representation of 3D space from a series of images. An iterative algorithm is used to find the scene model which jointly explains all the observed images by determining which region of space is responsible for each of the observations. The current approach formulates the problem as one of optimization over estimates of these responsibilities. The process converges to a distribution of responsibility which accurately reflects the constraints provided by the observations, the positions and shape of both solid and transparent objects, and the uncertainty which remains. Reconstruction is robust, and gracefully represents regions of space in which there is little certainty about the exact structure due to limited, non-existent, or contradicting data. Rendered images of voxel spaces recovered from synthetic and real observation images are shown.

A cluster-based statistical model for object detection

Abstract: This paper presents an approach to object detection which is based on recent work in statistical models for texture synthesis and recognition. Our method follows the texture recognition work of De Bonet and Viola (1998). We use feature vectors which capture the joint occurrence of local features at multiple resolutions. The distribution of feature vectors for a set of training images of an object class is estimated by clustering the data and then forming a mixture of Gaussian models. The mixture model is further refined by determining which clusters are the most discriminative for the class and retaining only those clusters. After the model is learned, test images are classified by computing the likelihood of their feature vectors with respect to the model. We present promising results in applying our technique to face detection and car detection.

Learning Informative Statistics: A Nonparametnic Approach

Abstract: We discuss an information theoretic approach for categorizing and modeling dynamic processes. The approach can learn a compact and informative statistic which summarizes past states to predict future observations. Furthermore, the uncertainty of the prediction is characterized nonparametrically by a joint density over the learned statistic and present observation. We discuss the application of the technique to both noise driven dynamical systems and random processes sampled from a density which is conditioned on the past. In the first case we show results in which both the dynamics of random walk and the statistics of the driving noise are captured. In the second case we present results in which a summarizing statistic is learned on noisy random telegraph waves with differing dependencies on past states. In both cases the algorithm yields a principled approach for discriminating processes with differing dynamics and/or dependencies. The method is grounded in ideas from information theory and nonparametric statistics.

Nonparametric estimation of aspect dependence for ATR

Abstract: In conventional SAR image formation, idealizations are made about the underlying scattering phenomena in the target field. In particular, the reflected signal is modeled as a pure delay and scaling of the transmitted signal where the delay is determined by the distance to the scatterer. Inherent in this assumption is that the scatterers are isotropic, i.e. their reflectivity appears the same from all orientations, and frequency independent, i.e. the magnitude and phase of the reflectivity are constant with respect to the frequency of the transmitted signal. Frequently, these assumptions are relatively poor resulting in an image which is highly variable with respect to imaging aspect. This variability often poses a difficulty for subsequent processing such as ATR. However, this need not be the case if the nonideal scattering is taken into account. In fact, we believe that if utilized properly, these nonideal characteristics may actually be used to aid in the processing as they convey distinguishing information about the content of the scene under investigation. In this paper, we describe a feature set which is specifically motivated by scattering aspect dependencies present in SAR. These dependencies are learned with a nonparametric density estimator allowing the full richness of the data to reveal itself. These densities are then used to determine the classification of the image content.

Boosting Image Database Retrieval

Abstract: We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is generated by a sparse set of visual “causes” and that images which are visually similar share causes. We propose a mechanism for generating a large number of complex features which capture some aspects of this causal structure. Boosting is used to learn simple and efficient classifiers in this complex feature space. Finally we will describe a practical implementation of our retrieval system on a database of 3000 images.