Michael Oren

A general framework for object detection

This paper presents a general trainable framework for object detection in static images of cluttered scenes. The detection technique we develop is based on a wavelet representation of an object class derived from a statistical analysis of the class instances. By learning an object class in terms of a subset of an overcomplete dictionary of wavelet basis functions, we derive a compact representation of an object class which is used as an input to a support vector machine classifier. This representation overcomes both the problem of in-class variability and provides a low false detection rate in unconstrained environments. We demonstrate the capabilities of the technique in two domains whose inherent information content differs significantly. The first system is face detection and the second is the domain of people which, in contrast to faces, vary greatly in color, texture, and patterns. Unlike previous approaches, this system learns from examples and does not rely on any a priori (hand-crafted) models or motion-based segmentation. The paper also presents a motion-based extension to enhance the performance of the detection algorithm over video sequences. The results presented here suggest that this architecture may well be quite general.

Pedestrian detection using wavelet templates

This paper presents a trainable object detection architecture that is applied to detecting people in static images of cluttered scenes. This problem poses several challenges. People are highly non-rigid objects with a high degree of variability in size, shape, color, and texture. Unlike previous approaches, this system learns from examples and does not rely on any a priori (hand-crafted) models or on motion. The detection technique is based on the novel idea of the wavelet template that defines the shape of an object in terms of a subset of the wavelet coefficients of the image. It is invariant to changes in color and texture and can be used to robustly define a rich and complex class of objects such as people. We show how the invariant properties and computational efficiency of the wavelet template make it an effective tool for object detection.

Generalization of the Lambertian model and implications for machine vision

Lamberts model for diffuse reflection is extensively used in computational vision. It is used explicitly by methods such as shape from shading and photometric stereo, and implicitly by methods such as binocular stereo and motion detection. For several real-world objects, the Lambertian model can prove to be a very inaccurate approximation to the diffuse component. While the brightness of a Lambertian surface is independent of viewing direction, the brightness of a rough diffuse surface increases as the viewer approaches the source direction. A comprehensive model is developed that predicts reflectance from rough diffuse surfaces. The model accounts for complex geometric and radiometric phenomena such as masking, shadowing, and interreflections between points on the surface. Experiments have been conducted on real samples, such as, plaster, clay, sand, and cloth. All these surfaces demonstrate significant deviation from Lambertian behavior. The reflectance measurements obtained are in strong agreement with the reflectance predicted by the proposed model. The paper is concluded with a discussion on the implications of these results for machine vision.

Generalization of Lambert's reflectance model

Lamberts model for body reflection is widely used in computer graphics. It is used extensively by rendering techniques such as radiosity and ray tracing. For several real-world objects, however, Lamberts model can prove to be a very inaccurate approximation to the body reflectance. While the brightness of a Lambertian surface is independent of viewing direction, that of a rough surface increases as the viewing direction approaches the light source direction. In this paper, a comprehensive model is developed that predicts body reflectance from rough surfaces. The surface is modeled as a collection of Lambertian facets. It is shown that such a surface is inherently non-Lambertian due to the foreshortening of the surface facets. Further, the model accounts for complex geometric and radiometric phenomena such as masking, shadowing, and interreflections between facets. Several experiments have been conducted on samples of rough diffuse surfaces, such as, plaster, sand, clay, and cloth. All these surface demonstrate significant deviation from Lambertian behavior. The reflectance measurements obtained are in strong agreement with the reflectance predicted by the model.

A theory of specular surface geometry

A theoretical framework is introduced for the perception of specular surface geometry. When an observer moves in three-dimensional space, real scene features such as surface markings remain stationary with respect to the surfaces they belong to. In contrast, a virtual feature which is the specular reflection of a real feature, travels on the surface. Based on the notion of caustics, a feature classification algorithm is developed that distinguishes real and virtual features from their image trajectories that result from observer motion. Next, using support functions of curves, a closed-form relation is derived between the image trajectory of a virtual feature and the geometry of the specular surface it travels on. It is shown that, in the 2D case, where camera motion and the surface profile are coplanar, the profile is uniquely recovered by tracking just two unknown virtual features. Finally, these results are generalized to the case of arbitrary 3D surface profiles that are traveled by virtual features when camera motion is not confined to a plane. This generalization includes a number of mathematical results that substantially enhance the present understanding of specular surface geometry. An algorithm is developed that uniquely recovers 3D surface profiles using a single virtual feature tracked from the occluding boundary of the object. All theoretical derivations and proposed algorithms are substantiated by experiments.

Improved Diffuse Reflection Models for Computer Vision

There are many computational vision techniques that fundamentally rely upon assumptions about the nature of diffuse reflection from object surfaces consisting of commonly occurring nonmetallic materials. Probably the most prevalent assumption made about diffuse reflection by computer vision researchers is that its reflected radiance distribution is described by the Lambertian model, whether the surface is rough or smooth. While computationally and mathematically a relatively simple model, in physical reality the Lambertian model is deficient in accurately describing the reflected radiance distribution for both rough and smooth nonmetallic surfaces. Recently, in computer vision diffuse reflectance models have been proposed separately for rough, and, smooth nonconducting dielectric surfaces each of these models accurately predicting salient non-Lambertian phenomena that have important bearing on computer vision methods relying upon assumptions about diffuse reflection. Together these reflectance models are complementary in their respective applicability to rough and smooth surfaces. A unified treatment is presented here detailing important deviations from Lambertian behavior for both rough and smooth surfaces. Some speculation is given as to how these separate diffuse reflectance models may be combined.

Visual appearance of matte surfaces

All visual sensors, biological and artificial, are finite in resolution by necessity. As a result, the effective reflectance of surfaces in a scene varies with magnification. A reflectance model for matte surfaces is described that incorporates the effect of macroscopic surface undulations on image brightness. The model takes into account complex physical phenomena such as masking, shadowing, and interreflections between points on the surface, and it predicts the appearance of a wide range of natural surfaces. The implications of these results for human vision, machine vision, and computer graphics are demonstrated with both real and rendered images of three-dimensional objects. In particular, objects with extremely rough surfaces produce silhouette images devoid of shading, precluding visual perception of the objects shape.

Seeing Beyond Lambert's Law

Lamberts model for diffuse reflection is extensively used in computational vision. For several real-world objects, the Lambertian model can prove to be a very inaccurate approximation to the diffuse component. While the brightness of a Lambertian surface is independent of viewing direction, the brightness of a rough diffuse surface increases as the viewer approaches the source direction. A comprehensive model is developed that predicts reflectance from rough diffuse surfaces. Experiments have been conducted on real samples, such as, plaster, clay, and sand. The reflectance measurements obtained are in strong agreement with the reflectance predicted by the proposed model.

Diffuse reflectance from rough surfaces

A comprehensive model that predicts reflectance from rough diffuse surfaces is presented. It is shown that diffuse reflectance from rough surfaces increases as the viewing direction approaches the source direction. This is in contrast to Lambertian surfaces, where radiance is independent of the viewing direction. The new model is a generalization of the Lambertian model, and has significant implications for machine vision, graphics, and remote sensing.<<ETX>>