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

Recent studies of eye movements in reading and other information processing tasks, such as music reading, typing, visual search, and scene perception, are reviewed. The major emphasis of the review is on reading as a specific example of cognitive processing. Basic topics discussed with respect to reading are (a) the characteristics of eye movements, (b) the perceptual span, (c) integration of information across saccades, (d) eye movement control, and (e) individual differences (including dyslexia). Similar topics are discussed with respect to the other tasks examined. The basic theme of the review is that eye movement data reflect moment-to-moment cognitive processes in the various tasks examined. Theoretical and practical considerations concerning the use of eye movement data are also discussed. Many studies using eye movements to investigate cognitive processes have appeared over the past 20 years. In an earlier review, I (Rayner, 1978b) argued that since the mid-1970s we have been in a third era of eye movement research and that the success of research in the current era would depend on the ingenuity of researchers in designing interesting and informative

Motion perception and interpretation plays an important role in the human visual system. It helps us recognize different objects and their motion in a scene, infer their relative depth, their rigidity, etc. In psychology, this process has been studied extensively by Johansson using moving light displays (MLDs). MLDs consist of bright spots attached to the joints of an actor dressed in black, and moving in front of a dark background. The collection of spots carry only 2D information and no structural information, since they are not connected. A set of static spots remained meaningless to observers, while their relative movement created a vivid impression of a person walking, running, dancing, etc. The gender of a person, and even the gait of a friend can be recognized based solely on the motion of those spots. There are two theories about the interpretation of MLD type stimuli, from a psychology point of view. In the first, people use motion information in the MLD to recover t...

Introduction Marr (1982) may have been one of the first vision researchers to insist that in modeling vision it is important to separate the location of visual features from their type. He argued that in early stages of visual processing there must be "place tokens" that enable subsequent stages of the visual system to treat locations independent of what specific feature type was at that location. Thus, in certain respects a collinear array of diverse features could still be perceived as a line, and under certain conditions could function as such in perceptual phenomena like the Poggendorf illusion. The idea that locations and feature-types are encoded independently is not a new one. A closely related distinction was widely acknowledged in the literature on list-learning and letterrecognition, where it has long been known that item information could be encoded or retained independent of order information (e.g., Estes, Allmeyer & Reder, 1976; Co

Many researchers interested in connectionist models accept that such models are "neurally inspired " but do not worry too much about whether their models are biologically realistic. While such a position may be perfectly justifiable, the present paper attempts to illustrate how biological information can be used to constrain connectionist models. Two particular areas are discussed. The first section deals with visual information processing in the primate and human visual system. It is argued that speed with which visual information is processed imposes major constraints on the architecture and operation of the visual system. In particular, it seems that a great deal of processing must depend on a single bottum-up pass. The second section deals with biological aspects of learning algorithms. It is argued that although there is good evidence for certain coactivation related synaptic modification schemes, other learning mechanisms, including back-propagation, are not currently supported by experimental data.

Researchers have long argued that an attentional mechanism is required to perform many vision tasks. This thesis includes an implementation and evaluation of an attentional prototype as it applies to early and intermediate levels of visual computation. The model is composed of a processing hierarchy and an attention beam that traverses the hierarchy, passing through the regions of greatest interest and inhibiting the regions that are not relevant. The amount of computation required is crucial to the derivation of this model. As a result, this scheme "scales up" extremely well with the size of the problem and in fact scales to human-size problems. In addition, the domain of input to the prototype is not limited to visual stimuli, making this system applicable to many different sensory modalities. Dimensions of attention such as localizing spatial regions of interset and ordering their importance are addressed, whereas other aspects of attention such as the role of task guidance are not....

The field of view (FOV) in most head-mounted displays (HMDs) is no more than 60 degrees wide -- far narrower than our normal FOV of about 200 wide. This mismatch arises mostly from the difficulty and expense of building wide-FOV HMDs. Restricting a person's FOV, however, has been shown in real environments to affect people's behavior and degrade task performance. Previous work in virtual reality too has shown that restricting FOV to 50 or less in an HMD can degrade performance. I conducted experiments with a custom, wide-FOV HMD and found that performance is degraded even at the relatively high FOV of 112, and further at 48. The experiments used a prototype tiled wide-FOV HMD to measure performance in VR at up to 176 total horizontal FOV, and a custom large-area tracking system to establish new findings on performance while walking about a large virtua...

In the literature dealing with the reanalysis of garden path sentences such as While the man hunted the deer ran into the woods, it is generally assumed that people either completely repair their initial incorrect syntactic representations yielding a final interpretation whose syntactic structure is fully consistent with the input string, or that the parse fails. In a series of five experiments, we explored the possibility that partial reanalyses take place. Specifically, we examined the conditions under which part of the initial incorrect analysis persists at the same time that part of the correct final analysis is constructed. In Experiments 1a and 1b, we found that both the length of the ambiguous region and the plausibility of the ultimate interpretation affected the likelihood that such sentences would be fully reanalyzed. In Experiment 2, we compared garden path sentences with non-garden path sentences and compared performance on two different types of comprehension questions. In...

A variety of cell types exist in the temporal cortex providing high-level visual descriptions of bodies and their movements. We have investigated the sensitivity of such cells to different viewing conditions to determine the frame(s) of reference utilized in processing. The responses of the majority of cells in the upper bank of the superior temporal sulcus (areas TPO and PGa) found to be sensitive to static and dynamic information about the body were selective for one perspective view (e.g. right profile, reaching right or walking left). These cells can be considered to provide viewer-centred descriptions because they depend on the observer's vantage point. Viewer-centred descriptions could be used in guiding behaviour. They could also be used as an intermediate step for establishing view-independent responses of other cell types which responded to many or all perspective views selectively of the same object (e.g. head) or movement. These cells have the properties of object-centred descriptions, where the object viewed provides the frame of reference for describing the disposition of object parts and movements (e.g. head on top of shoulders, reaching across the body, walking forward 'following the nose'). For some cells in the lower bank of the superior temporal sulcus (area TEa) the responses to body movements were related to the object or goal of the movements (e.g. reaching for or walking towards a specific place). This goal-centred sensitivity to interaction allowed the cells to be selectively activated in situations where human subjects would attribute causal and intentional relationships.

Recent physiological experiments have shown that the responses of many neurons in V1 and V3a are modulated by the direction of gaze. We have developed a neural network model of the hierarchy of maps in visual cortex to explore the hypothesis that visual features are encoded in egocentric (spatiotopic) coordinates at early stages of visual processing. Most psychophysical studies that have attempted to examine this question have concluded that features are represented in reti-nal coordinates, but the interpretation of these experiments does not preclude the type of retinospatiotopic representation that is embodied in our model. The model also explains why electrical stimulation experiments in visual cortex cannot distinguish between retinal and retinospatiotopic coordinates in the early stages of visual processing. Psychophysical predictions are made for testing the existence of retinospatiotopic representations. The three most common types of coordinates used for representing visual objects in biological and computer vision systems are eye-centered (retinal), object-centered, and viewer-centered (egocentric). Eye-centered representations are consistent with many physiological and psychophysical studies of early vision. Neurons in primary visual cortex and most extrastriate areas are organized into retinotopic maps (Felleman & Van Essen, 1991). Most psychophysical experiments designed to determine the nature of spatial representation at early visual stages have reached the same conclusion, as we review in the discussion. Other types of representation are believed to be used at the highest stages of visual processing. Mishkin, Ungerleider, and Macko (1983) proposed a functional distinction between two main streams of processing, the "what " and "where " pathways leading, respectively, in the temporal and parietal cortex. Object-centered reference frames have been suggested for the representation of objects in the inferior temporal cortex and egocentric reference frames have been proposed for the representation of spatial location in the parietal cortex (Andersen,