Computer vision is embracing a new research focus in which the aim is to develop visual skills for robots that allow them to interact with a dynamic, realistic environment. To achieve this aim, new kinds of vision algorithms need to be developed which run in real time and subserve the robot's goals. Two fundamental goals are determin-ing the location of a known object. Color can be successfully used for both tasks. This article demonstrates that color histograms of multicolored objects provide a robust, efficient cue for index-ing into a large database of models. It shows that color histograms are stable object representations in the presence of occlusion and over change in view, and that they can differentiate among a large number of objects. For solving the identification problem, it introduces a technique called Histogram Intersection, which matches model and im-age histograms and a fast incremental version of Histogram Intersection, which allows real-time indexing into a large database of stored models. For solving the location problem it introduces an algorithm called Histogram Backprojection, which performs this task efficiently in crowded scenes. 1

We present a real-time face tracker in this paper. The system has achieved a rate of 30+ frames/second using an HP-9000 workstation with a framegrabber and a Canon VC-C1 camera. It can track a person’s face while the person moves freely (e.g., walks, jumps, sits down and stands up) in a room. Three types of models have been employed in developing the system. First, we present a stochastic model to characterize skin-color distributions of human faces. The information provided by the model is sufficient for tracking a human face in various poses and views. This model is adaptable to different people and different lighting conditions in real-time. Second, a motion model is used to estimate image motion and to predict search window. Third, a camera model is used to predict and to compensate for camera motion. The system can be applied to tele-conferencing and many HCI applications including lip-reading and gaze tracking. The principle in developing this system can be extended to other tracking problems such as tracking the human hand. 1

Abstract. This paper studies a statistical skin-color model and its adaptation. It is revealed that (1) human skin colors cluster in a small region in a color space; (2) the variance of a skin color cluster can be reduced by intensity normalization, and (3) under a certain lighting condition, a skin-color distribution can be characterized by amultivariate normal distribution in the normalized color space. We then propose an adaptive model to characterize human skin-color distributions for tracking human faces under di erent lighting conditions. The parameters of the model are adapted based on the maximum likelihood criterion. The model has been successfully applied to a real-time face tracker and other applications. 1

This paper is organized as follows. In Section 2, the dichromatic reflectance under "white" reflection is introduced and new photometric invariant color features are proposed. The performance of object recognition by histogram matching differentiated for the various color models is evaluated and compared on an image database of 500 reference images in Section 3. 2 Photometric Color Invariance In this paper, we concentrate on the following standard, essentially different, color features derived from RGB: intensity I(R; G; B) = R + B + G, RGB, normalized colors r(R; G; B) = R R+G+B , g(R; G; B) = G R+G+B , b(R; G; B) = B R+G+B , hue H(R; G; B) = arctan \Gamma p 3(G\GammaB) (R\GammaG)+(R\GammaB) \Delta and saturation S(R; G; B) = 1 \Gamma min(R;G;B) R+G+B . 2.1 The Reflection Model Consider an image of an infinitesimal surface patch. Using the red, green and blue sensors with spectral sensitivities given by fR (), fG () and fB () respectively, to obtain an image of the surface patch illuminated by a SPD of the incident light denoted by e(), the measured sensor values will be given by Shafer [5]: C = m b (n; s) Z

in the area of digital color imaging. In order to establish the background and lay down terminology, fundamental concepts of color perception and measurement are first presented using vector-space notation and terminology. Present-day color recording and reproduction systems are reviewed along with the common mathematical models used for representing these devices. Algorithms for processing color images for display and communication are surveyed, and a forecast of research trends is attempted. An extensive bibliography is provided. I.

This study's main result is to show that under the conditions imposed by the Maloney-Wandell color constancy algorithm, whereby illuminants are three dimensional and reflectances two dimensional (the 3-2 world), color constancy can be expressed in terms of a simple independent adjustment of the sensor responses (in other words, as a von Kries adaptation type of coefficient rule algorithm) as long as the sensor space is first transformed to a new basis. A consequence of this result is that any color constancy algorithm that makes 3-2 assumptions, such as the Maloney-Wandell subspace algorithm, Forsyth's MWEXT, and the Funt-Drew lightness algorithm, must effectively calculate a simple von Kries-type scaling of sensor responses, i.e., a diagonal matrix. Our results are strong in the sense that no constraint is placed on the initial spectral sensitivities of the sensors. In addition to purely theoretical arguments, we present results from simulations of von Kriestype color constancy in which the spectra of real illuminants and reflectances along with the human-conesensitivity functions are used. The simulations demonstrate that when the cone sensor space is transformed to its new basis in the appropriate manner a diagonal matrix supports nearly optimal color constancy. Key words: color constancy, von Kries, chromatic adaptation, color balancing. 1.

We introduce a context for testing computational color constancy, specify our approach to the implementation of a number of the leading algorithms, and report the results of three experiments using synthesized data. Experiments using synthesized data are important because the ground truth is known, possible confounds due to camera characterization and pre-processing are absent, and various factors affecting color constancy can be efficiently investigated because they can be manipulated individually and precisely.

Techniques for color-based tracking of faces or hands often assume a static skin color model. However, skin color perceived by a camera can change when lighting changes. In common real environment multiple light sources impinge on the skin. Therefore, for robust skin pixel detection, a dynamic skin color model that can cope with the changes must be employed. We show that skin detection in video can be enhanced by exploiting the knowledge of the range of possible skin colors for the camera used. In normalized color coordinates this range has a distinct shape we call the skin locus. We developed an adaptive histogram backprojection technique where the skin color model is updated by pixels in the search region which fall in the skin locus. We demonstrate increased detection capability with webcam videos of faces taken successively under daylight, incandescent lamp, fluorescent light and a combination of these light sources.

Abstract — Computer vision is a broad and significant ongoing research challenge, even when performed on an individual image or on streaming video from a high-quality stationary camera with abundant computational resources. When faced with streaming video from a lower-quality, rapidly moving camera and limited computational resources, the challenge increases. We present our implementation of a vision system on a mobile robot platform that uses a camera image as the primary sensory input. Having to perform all processing, including segmentation and object detection, in real-time on-board the robot, eliminates the possibility of using some state-of-the-art methods that otherwise might apply. We describe the methods that we developed to achieve a practical vision system within these constraints. Our approach is fully implemented and tested on a team of Sony AIBO robots. Index Terms — Vision and Recognition, Legged Robots. I.

This paper’s main result is to show that under the conditions imposed by the Maloney- Wandell color con-stancy algorithm, color constancy can in fact he ex-pressed in terms of a simple independent adjustment of the sensor responses-in other words as a uon Kries adaptation type of coeficient rule algorithm-so long as the sensor space is first transformed to a new ha-sis. Our overall goal is to present a theoretical analy-sis connecting many established theories of color con-stancy. For the case where surface refiectances are 2-dimensional and illuminants are $dimensional, we prove that perfect color constancy can always be solved for by an independent adjustment of sensor responses, which means that the color constancy transform can he expressed as a diagonal matrix. This result re-quires a prior transformation of the sensor basis and to support it we show in particular that there exists n transformation of the original sensor basis under which the non-diagonal meth,ods of Maloney- Wandell, Forsyth’s MWEXT and Funt and Drew’s lightness al-gorithm all reduce to simpler, diagonal-matrix theones of color constancy. Our results are strong in the sense that no constraint is placed on the initial sensor spec-tral sensitzuities. In addition to purely theoretical ar-guments, the paper contains results from simulations of diagonal-matrix-based color constancy in which the spectra of real illuminants and refiectances along with the human cone sensitivity functions are used. The simulations demonstrate that when the cone sensor space is transformed to its new basis in the appropriate manner, a diagonal matrix supports close to optimal color constancy. 1