This paper presents a novel platform for image retrieval based on a two-level architecture inspired from human cognitive mechanisms. These two levels provide both generic similarity and semantic information related to special characteristics. Although the proposed architecture can be customized for any content-based image retrieval application, our work is focused on medical images and more specifically on brain MRI data. Our main motivation is that in medical applications, it is crucial to be able to combine in an efficient way, image similarity with specific, semantics related to pathology in order to provide the user with relevant cases and aid diagnosis. A description of the architecture and function of the proposed CBIR platform is presented, as well as specific details for the application to brain MRI retrieval

In vivo fluorescence molecular imaging and tomography has facilitated monitoring of genomics and proteomics over time and on the same animal. A highly important issue, however, has been the robust registration of animals imaged at different time points to obtain accurate description of activity and location. This paper presents a method for aligning temporal data of small animals based on surface anatomical features and improving the accuracy of monitoring fluorophore distribution. The method can account for differences in the positioning and compression of small animals and can be extended to three-dimensional as well as to other imaging modalities.

Many vision tasks rely upon the identification of sets of corresponding features among different images. This paper presents a method that, given some corresponding features in two stereo images, matches them with features extracted from a second stereo pair captured from a distant viewpoint. The proposed method is based on the assumption that the viewed scene contains two planar surfaces and exploits geometric constraints that are imposed by the existence of these planes to first transfer and then match image features between the two stereo pairs. The resulting scheme handles point and line features in a unified manner and is capable of successfully matching features extracted from stereo pairs that are acquired from considerably different viewpoints. Experimental results are presented, which demonstrate that the performance of the proposed method compares favorably to that of epipolar and tensor-based approaches.

Plane detection is a prerequisite to a wide variety of vision tasks. This paper proposes a novel method that exploits results from projective geometry to automatically detect planes using two images. Using a set of point and line features that have been matched between images, the method exploits the fact that every pair of a 3D line and a 3D point defines a plane and utilizes an iterative voting scheme for identifying coplanar subsets of the employed feature set. The method does not require camera calibration, circumvents the 3D reconstruction problem, is robust to the existence of mismatched features and is applicable either to stereo or motion sequence images. Sample results from the application of the proposed method to real imagery are also provided. 1

In robotics, homing can be defined as that behavior which enables a robot to return to its initial (home) position, after traveling a certain distance along an arbitrary path. Odometry has traditionally been used for the implementation of such a behavior, but it has been shown to be an unreliable source of information. In this work, a novel method for visual homing is proposed, based on a panoramic camera. As the robot departs from its initial position, it tracks characteristic features of the environment (corners). As soon as homing is activated, the robot selects intermediate target positions on the original path. These intermediate positions (IPs) are then visited sequentially, until the home position is reached. For the robot to move between two consecutive IPs, it is only required to establish correspondence among at least three corners. This correspondence is obtained through a feature tracking mechanism. The proposed homing scheme is based on the extraction of very low-level sensory information, namely the bearing angles of corners, and has been implemented on a robotic platform. Experimental results show that the proposed scheme achieves homing with a remarkable accuracy, which is not affected by the distance traveled by the robot.

Several vision tasks rely upon the availability of sets of corresponding features among images. This paper presents a method which, given some corresponding features in two stereo images, addresses the problem of matching them with features extracted from a second stereo pair captured from a distant viewpoint. The proposed method is based on the assumption that the viewed scene contains two planar surfaces and exploits geometric constraints that are imposed by the existence of these planes to predict the location of image features in the second stereo pair. The resulting scheme handles point and line features in a unified manner and is capable of successfully matching features extracted from stereo pairs acquired from considerably different viewpoints. Experimental results from a prototype implementation demonstrate the effectiveness of the approach.

To avoid collisions, mobile robots need a measure for assessing the proximity of obstacles. A measure that is well suited to this purpose is provided by the time-to-contact. In this paper, a novel method for estimating the time-to-contact is presented. The method is based on the assumption that the robot is moving on a locally planar ground, parts of which are visible in the acquired images. Using the optical flow field induced by the robot's motion, the time-to-contact with points on the ground is first estimated and then the concept of planar parallax is exploited to recover the time-to-contact with obstacle points. The computation of high order derivatives of the image flow, which are known to be very difficult to estimate accurately, is completely avoided. Moreover, no knowledge of the egomotion is necessary. Experimental results from the application of the method on real and simulated flow fields are also reported.

Feature matching is a prerequisite to a wide variety of vision tasks. This paper presents a method that addresses the problem of matching disparate views of coplanar points and lines in a unified manner. The proposed method employs a randomized search strategy combined with the two-line two-point projective invariant to derive small sets of possibly matching points and lines. These candidate matches are then verified by recovering the associated plane homography, which is further used to predict more matches. The resulting scheme is capable of successfully matching features extracted from views that differ considerably, even in the presence of large numbers of outlying features. Experimental results from the application of the method to indoor and aerial images indicate its effectiveness and robustness. 1 Introduction A fundamental problem in computer vision, that appears in different forms in tasks such as discrete motion estimation, feature-based stereo, object recognition, image r...

This paper considers a specific problem of visual perception of motion, tamely the problem of visual detection of independent 3D motion. Most of the existing techniques for solving this problem rely on restrictive assumptions about the environment, the observer's motion, or both. Moreover, they are based on the computation of a dense optical flow field, which amounts to solving the ill-posed correspondence problem. In this work independent motion detection is formulated as a problem of robust parameter estimation applied to the visual input acquired by a rigidly moving observer. The proposed method automatically selects a planar surface in the scene and the residual planar parallax normal flow field with respect to the motion of this surface is computed at two successive time! instants. The two resulting normal flow fields are then combined in a linear model. The parameters of this model are related to the parameters of self-motion (ego-motion) and their robust estimation leads to a segmentation of the scene based on 3D motion. The method avoids a complete solution to the correspondence problem by selectively matching subsets of image points and by employing normal flow fields. Experimental results demonstrate the effectiveness of the proposed method in detecting independent motion in scenes with large depth variations and unrestricted observer motion.

This paper considers a specific problem of visual perception of motion, namely the problem of visual detection of independent 3D motion. Most of the existing techniques for solving this problem rely on restrictive assumptions about the environment, the observer's motion, or both. Moreover they are based on the computation of optical flow, which amounts to solving the ill-posed correspondence problem. In this work, independent motion detection is formulated as robust parameter estimation applied to the visual input acquired by a binocular rigidly moving observer. Depth and motion measurements are combined in a linear model. The parameters of this model are related to the parameters of self-motion (egomotion) and the parameters of the stereoscopic configuration of the observer. The robust estimation of this model leads to a segmentation of the scene based on 3D motion. The method avoids the correspondence problem by employing only normal flow fields. Experimental results demonstrate the effectiveness of this method in detecting independent motion in scenes with large depth variations, without any constraints imposed on observer motion.

An approach towards providing advanced navigational support to robotic wheelchair platforms is presented. In order to avoid any modifications to the environment, we propose an approach that employs computer vision techniques which facilitate space perception and navigation. Computer vision has not been introduced to date in rehabilitation robotics, since the former is not mature enough to meet the needs of this sensitive application. However, in the proposed approach, stable techniques are exploited that facilitate reliable, automatic navigation to any point in the visible environment. Preliminary results obtained from its implementation on a laboratory robotic platform indicate its usefulness and flexibility.

This paper presents WebOnCOLL, a web-based medical collaboration environment, which has been designed in the context of the regional healthcare network of Crete. WebOnCOLL employs the infrastructure of regional healthcare networks to provide integrated services for virtual workspaces, annotations, e-mail, and on-line collaboration. Virtual workspaces support collaborative concepts like personal web pages, bulletin boards, discussion lists, shared workspaces, and medical case folders. Annotations provide a natural way for people to interact with multimedia content, while e-mail is one of the most popular forms of communication today. On-line collaboration satisfies the need for a more direct form of communication.

This paper presents a methodology for the detection of objects that move independently of the observer in a 3D dynamic environment. Independent 3D motion detection is formulated as a problem of robust regression applied to visual input acquired by a binocular, rigidly moving observer. The qualitative analysis of images acquired by a parallel stereo configuration yields a segmentation of a scene into depth layers. A depth layer consists of points of the 3D space with almost constant depth from the observer. Robust regression in the form of Least Median of Squares estimation is applied within each depth layer in order to segment the latter into coherently moving regions. Finally, a combination stage is applied across all layers in order to come up with an integrated view of independent motion in the whole 3D scene. In contrast to other existing approaches for independent motion detection which are based on the ill-posed problem of optical flow computation, the proposed methodology relies...

This paper presents a method for the detection of objects that move independently of the observer in a 3D dynamic scene, Independent motion detection is achieved through processing of stereoscopic image sequences acquired by a binocular, rigidly moving observer. A weak assumption is made about the observer's motion (egomotion), namely that the direction of the translational and rotational components of egomotion are constant in small image patches. This assumption facilitates the extraction of qualitative information about depth from motion, while additional qualitative depth information is independently computed from image stereo pairs acquired by the binocular vision system. Robust regression in the form of least median of squares estimation is applied within each image patch to test for consistency between the depth functions computed from motion and stereo. Possible inconsistencies signal the presence of independently moving objects. In contrast to other existing approaches for independent motion detection, which are based on the ill-posed problem of optical flow computation, the proposed method relies on normal flow fields for both stereo and motion processing. By exploiting local constraints of qualitative nature, the problem of independent motion detection is approached directly, without relying on a solution to the general structure from motion problem. Experimental results indicate that the proposed method is both effective and robust.

Load balancing requirements in parallel image analysis are considered and results on the performance of parallel implementations of two image feature extraction tasks on the Connection Machine and the iPSC/2 hypercube are reported and discussed. A load redistribution algorithm, which makes use of parallel prefix operations and one-to-one permutations among the processors, is described and has been used. The expected improvement in performance resulting from load balancing has been determined analytically and is compared to actual performance results obtained from the above implementations. The analytical results demonstrate the specific dependence of the expected improvement in performance on the computational and communication requirements of each task, characteristic machine parameters, a characterization of prior load distribution in terms of parameters which can be computed dynamically at the start of task execution, and the overhead incurred by load redistribution.>

The primary task of intermediate level vision (ILV) is to take the output of low level vision, which is typically a subset of pixels from the original image array, and to generate a representation of image content which is appropriate for symbolic manipulations at a higher level. These tasks, e.g. boundary detection, various types of segmentation or the computation of attributes of image components, involve operations on individual pixels, sets of pixels with a common label or on entities extracted from the raw pixel data, such as orientation of lines or distance between pairs of parallel lines. A class of tasks which operate on individual pixels or sets of pixels is described, problems which are raised in parallel implementations of this class of tasks are considered, and solutions are suggested.>

Issues related to the efficient embedding of interprocessor communications required by parallel implementations of intermediate-level vision tasks are discussed. The performance of alternative embeddings of the interprocessor communications required by specific tasks at the intermediate level of vision has been analyzed, and quantitative results have been obtained and compared to the results of corresponding implementations on the Connection Machine. In the quantitative analysis, the cost of communication primitives supported by this machine, characteristics of the task, and parameters which are characteristic of image content are taken into account. Based on the result of this analysis, a methodology is suggested for selecting the most efficient implementation of interprocessor communications among different alternatives.>

Abstract One data‐independent and one data‐dependent algorithm for the computation of image histograms on parallel computers are presented, analysed and implemented on the Connection Machine system CM‐2. The data‐dependent algorithm has a lower requirement on communication bandwidth by only transferring bins with a non‐zero count. Both algorithms perform all‐to‐all reduction, which is implemented through a sequence of exchanges as defined by a butterfly network. The two algorithms are compared based on predicted and actual performance on the Connection Machine CM‐2. With few pixels per processor the data‐dependent algorithm requires in the order of √B data transfers for B bins compared to B data transfers for the data‐independent algorithm. As the number of pixels per processor grows the advantage of the data‐dependent algorithm decreases. The advantage of the data‐dependent algorithm increases with the number of bins of the histogram.