The appearance of a particular object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then- in theory- the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, ive consider only the set of images of an object under variable allumination (including multiple, extended light sources and attached shadows). We prove that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IR " and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, we show that the cone for a particular object can be constructed from three properly chosen images. Finally, we prove that the set of n-pixel images of an object of any shape and with an arbitrary reflectance function, seen under all possi-ble illumination conditions, still forms a convex cone in Rn. Th.ese results immediately suggest certain approaches to object recognition. Throughout this paper, we ofler results demonstrating the empirical validity of the illumination cone representation. 1

Abstract — In this paper, we propose an original approach to control camera position and/or lighting conditions in an environment using image gradient information. Our goal is to ensure a good viewing condition and good illumination of an object to perform vision-based task (recognition, tracking, etc.). Within the visual servoing framework, we propose solutions to two different issues: maximizing the brightness of the scene and maximizing the contrast in the image. Solutions are proposed to consider either a static light and a moving camera, eitheror a moving light and a static/moving camera. The proposed method is independent of the structure, color and aspect of the objects. Experimental results on both synthetic and real images are finally presented. I. OVERVIEW In this paper we investigate the problem of relative placement

This report is on the Lehigh/Columbia MURI contract. While the original focus was on sensors for manufacturing, the natural evolution of our basic research has led us to more general problems in more generic settings. As a multifaculty multi-disciplinary project much of the work is naturally done in smaller subgroup. The major results over the past year were on 3D modeling /sensor planning, omni-directional imaging, and reflectance/image/noise modeling. There were more focused results in deformable models, feature detection, appearance matching, and video segmentation. Note that some projects (e.g., the outdoor 3D model building) bring together many of the above topics. This report provides short summaries of our significant contributions with citations to related papers. Length of presentation herein does not reflect level of effort nor our view of its significance -- many of the most important areas have papers elsewhere in these proceedings.

A framework for color image segmentation is presented, which combines color histogram analysis and region merging approach. Its main goal is to segment an image at material boundaries (i.e., discontinuities of reflectance properties) while ignoring spatial color inhomogeneities of uniformly pigmented (colored) objects, caused by accidents of illumination and viewing geometry. Theoretical examination of light spectrum transformations upon light reflection from material surfaces and upon interaction with a sensor system shows that in a wide variety of viewed scenes (even containing interreflections and highlight areas) uniformly pigmented objects are projected to the color space of the sensor as planar, linear, or point-like clusters, depending on lighting and viewing conditions and object geometry. To detect such clusters in the color space, three methods are suggested: Generalized Hough Transform method, gradient descent method, and eigenvectors method. A framework algorithm of color segmentation based on region merging approach is developed, which can use any of these methods. Testing this algorithm with both artificially generated and real images shows quite reliable results.