Showing papers by "Avinash C. Kak published in 2002"
TL;DR: The developments of the last 20 years in the area of vision for mobile robot navigation are surveyed and the cases of navigation using optical flows, using methods from the appearance-based paradigm, and by recognition of specific objects in the environment are discussed.
Abstract: Surveys the developments of the last 20 years in the area of vision for mobile robot navigation. Two major components of the paper deal with indoor navigation and outdoor navigation. For each component, we have further subdivided our treatment of the subject on the basis of structured and unstructured environments. For indoor robots in structured environments, we have dealt separately with the cases of geometrical and topological models of space. For unstructured environments, we have discussed the cases of navigation using optical flows, using methods from the appearance-based paradigm, and by recognition of specific objects in the environment.
1,386 citations
14 Oct 2002
TL;DR: An extensive database of American Sign Language motions, handshapes, words and sentences is reported on-the Purdue RVL-SLLL ASL database, which removes deficiencies in the existing databases.
Abstract: This article reports on an extensive database of American Sign Language (ASL) motions, handshapes, words and sentences. Research on automatic recognition of ASL requires a suitable database for the training and the testing of algorithms. The databases that are currently available do not allow, for algorithmic development that requires a step-by-step approach to ASL recognition -from the recognition of individual hand-shapes, to the recognition of motion primitives, and, finally, to the recognition of full sentences. We have sought to remove these deficiencies in a new database - Purdue RVL-SLLL ASL database.
92 citations
TL;DR: This paper presents a relevance feedback technique that uses decision trees to learn a common thread among instances marked relevant in a preexisting content-based image retrieval (CBIR) system that is used to access high resolution computed tomographic images of the human lung.
68 citations
TL;DR: The empirical evaluation shows that feature extraction based on physicians' perceptual categories achieves significantly higher retrieval precision than the traditional scattershot approach, and the use of perceptually based features gives the system the ability to provide an explanation for its retrieval decisions, thereby instilling more confidence in its users.
49 citations
07 Nov 2002
TL;DR: This paper focuses on content based image retrieval from large medical databases, and outlines the problems specific to this area, and presents some of the more significant results obtained with ASSERT (Automatic Search and Selection Engine with Retrieval Tools), the contentbased image retrieval system developed in the laboratory.
Abstract: The main goal of content based image retrieval is to efficiently retrieve images that are visually similar to a query image. In this paper we focus on content based image retrieval from large medical databases, outline the problems specific to this area, and describe the recent advances in the field. We also present some of the more significant results obtained with ASSERT (Automatic Search and Selection Engine with Retrieval Tools), the content based image retrieval system developed in our laboratory.
41 citations
10 Dec 2002
TL;DR: The hopes and dreams of a decade ago are examined, and the progress that has been made in the areas of visual servoing, bin-picking, mobile-robot navigation, etc.
Abstract: We will examine the hopes and dreams of a decade ago when there was a lot of excitement hi the community about what could be accomplished with model-based vision in robotics. Many of those dreams have not yet materialized because of a lack of availability of "vision" models (as opposed to CAD models), difficulty of constructing vision models, inadequate robustness of model-based recognition and pose-estimation schemes, excessive sensitivity of recognition and pose-estimation schemes to variations in ambient illumination and object surface condition, etc. Against a background of these difficulties, we chart out the progress that has been made in the areas of visual servoing, bin-picking, mobile-robot navigation, etc.
18 citations
07 Aug 2002
TL;DR: This paper validates the approach for calibrating active stereo heads for which no prior knowledge of the world coordinate system is required by presenting results as accurate as a few millimeters in the calculation of the XYZ coordinates of objects at 1.5m from the stereo head.
Abstract: This paper describes an approach for calibrating active stereo heads for which no prior knowledge of the world coordinate system is required. During an automated procedure derived from this approach, the mobile robot can be loosely positioned in front of a calibration pattern. Through our procedure, both the camera calibration and the neck-eye calibration are obtained. With this set of calibration matrices, the XYZ coordinates of a landmark can be determined with respect to the robot coordinate frame. The so calculated XYZ coordinates are accurate regardless of the orientation of the stereo head, even for orientations that were not used for calibration. This paper validates our approach by presenting results as accurate as a few millimeters in the calculation of the XYZ coordinates of objects at 1.5m from the stereo head.
12 citations
24 Jun 2002
TL;DR: A distinguishing aspect of this motion estimation scheme for solving the occlusion problem is that it cleanly handles the situation where the tracked features appear in different frames and, as features become unobservable, new features may need to be incorporated.
Abstract: Motion estimation in the presence of occlusion is a wide open research field As such, a critical component of the research is formulating a computational framework A distinguishing aspect of our motion estimation scheme for solving the occlusion problem is that it cleanly handles the situation where the tracked features appear in different frames and, as features become unobservable, new features may need to be incorporated As opposed to employing a 2D parametric motion model which restricts the object to a planar surface, we use a 3D motion model to capture the object motion and shape vectors The precise 3D contour of the tracked object is fine-tuned within a predicted potential field
3 citations
06 Aug 2002
TL;DR: The workings of a new planning system called SPAR, which uses a constraint posting approach for simultaneously fulfilling the operational, geometric and uncertainly reduction goals, and the PSEIKI system for evidential reasoning in a rangled hierarchy are described.
1 citations