Search

We introduce a software framework called the Java Vision Toolkit (JVT) for teaching image processing and computer vision. The toolkit provides over 50 image operations and presents them to the user in a GUI that can render grayscale, color and 3D range images. The software is written in Java, enabling it to be integrated into HTML documents and interactive course materials. The framework is designed for extensibility using a source code template that supports the implementation of any new operation with a minimal amount of supporting code. For students, this framework encapsulates the GUI, file I/O and other trivial programming details and allows them the maximum amount of time to spend on understanding computer vision. We compare the JVT with other computer vision software frameworks that are used for teaching and research. We also discuss the use of the JVT in an undergraduate image processing course at the University of South Florida.

This paper addresses position estimation of a micro-rover mobile robot (called the “daughter”) as a larger robot (the “mother”) tracks it through large spaces with unstructured lighting. Position estimation is necessary for localization, where the mother extracts the relative position of the daughter for mapping purposes, and for cooperative navigation, where the mother controls the daughter in real-time. The approach taken is to employ the Spherical Coordinate Transform color segmenter developed for medical applications as a low computational and hardware cost solution. Data was collected from 50 images taken in five types of lighting: fluorescent, tungsten, daylight lamp, natural daylight indoors and outdoors. The results show that average pixel error was 1.5, with an average error in distance estimation of 6.3 cm. The size of the error did not vary greatly with the type of lighting. The segmentation and distance tracking have also been implemented as a real-time tracking system. Using this system, the mother robot is able to autonomously control the micro-rover and display a map of the daughter's path in real-time using only a Pentium class processor and no specialized hardware.

In this work we discuss how the quality of localization knowledge impacts the remote operation of rovers on the surface of Mars. We look at the techniques of localization estimation used in the Mars Pathfinder and Mars Exploration Rover missions. We discuss the virtues and shortcomings of existing approaches and new improvements in the latest operations tools used to support the Mars Exploration Rover missions and rover technology development tasks at the Jet Propulsion Laboratory. We conclude with future directions we plan to explore in improving the localization knowledge available for operations and more effective targeting of rovers and their instrument payloads.

This paper describes the target designation, tracking, approach, and camera handoff technologies required to achieve accurate, single-command autonomous instrument placement for a planetary rover. It focuses on robust tracking integrated with obstacle avoidance during the approach phase, and image-based camera handoff to allow vision-based instrument placement. It also provides initial results from a complete system combining these technologies with rover base placement to maximize arm manipulability and image-based instrument placement.

The unprecedented endurance of both the Spirit and Opportunity rovers during the Mars Exploration Rover Mission (MER) brought with it many unexpected challenges. Scientists, many of whom had planned on staying at the Jet Propulsion Laboratory (JPL) in Pasadena, CA for 90 days, were eager to return to their families and home institutions. This created a need for the rapid conversion of a mission-planning tool, the science activity planner (SAP), from a centralized application usable only within JPL, to a distributed system capable of allowing scientists to continue collaborating from locations around the world. Rather than changing SAP itself, the rapid conversion was facilitated by a collection of software utilities that emulated the internal JPL software environment and provided efficient, automated information propagation. During this process many lessons were learned about scientific collaboration in a concurrent environment, use of existing server-client software in rapid systems development, and the effect of system latency on end-user usage patterns. Switching to a distributed mode of operations also saved a considerable amount of money, and increased the number of specialists able to actively contribute to mission research. Long-term planetary exploration missions of the future will build upon the distributed operations model used by MER

Previous performance evaluation of range image segmentation algorithms has depended on manual tuning of algorithm parameters, and has lacked a basis for a test of the significance of differences between algorithms. We present an automated framework for evaluating the performance of range image segmentation algorithms. Automated tuning of algorithm parameters in this framework results in performance as good as that previously obtained with careful manual tuning by the algorithm developers. Use of multiple training and test sets of images provides the basis for a test of the significance of performance differences between algorithms. The framework implementation includes range images, ground truth overlays, program source code, and shell scripts. This framework should a) make it possible to objectively and reliably compare the performance of range image segmentation algorithms; b) allow informed experimental feedback for the design of improved segmentation algorithms. The framework is demonstrated using range images, but in principle it could be used to evaluate region segmentation algorithms for any type of image.

This paper addresses position estimation of a micro-rover mobile robot (called the "daughter") as a larger robot (the "mother") tracks it through large spaces with unstructured lighting. Position estimation is necessary for localization, where the mother extracts the relative position of the daughter for mapping purposes, and for cooperative navigation, where the mother controls the daughter in real-time. The approach taken is to employ the spherical coordinate transform color segmenter developed for medical applications as a low computational and hardware cost solution. Data was collected from 50 images taken in five types of lighting: fluorescent, tungsten, daylight lamp, natural daylight indoors and outdoors. The results show that average pixel error was 1.5, with an average error in distance estimation of 6.3 cm. The size of the error did not vary greatly with the type of lighting. The segmentation and distance tracking have also been implemented as a real-time tracking system. Using this system, the mother robot is able to autonomously control the micro-rover and display a map of the daughter's path.

This work focuses on correcting color images illuminated by one or more light sources to improve the results of segmentation and feature extraction. First, we linearize the RGB data to make it conform to the assumptions made by many image processing algorithms. Then, we also eliminate intensity variation due to the illuminant with respect to distance and shading produced by surface orientation changes. We introduce a novel calibration procedure for estimating the finite distance and direction of the light source from points in the scene. We compare segmentations of original color images with that of their color-corrected images to evaluate the effectiveness of the methodology.

We have developed an automated framework for objectively evaluating the performance of region segmentation algorithms. This framework is demonstrated with range image data sets, but is applicable to any type of imagery. Parameters of the segmentation algorithm are tuned using training images. Images and source code for the training process care publicly available. The trained parameters are then used to evaluate the algorithm on a (sequestered) test set. The primary performance metric is the average number of correctly segmented regions. Statistical tests are used to determine the significance of performance improvement over a baseline algorithm.

We present a methodology for calibrating multiple light source locations in 3D from images. The procedure involves the use of a novel calibration object that consists of either 2 or 3 spheres at known relative positions. There are two variants of the process: one which uses range and intensity imaging to find the positions of the light sources, and one that uses only the intensity image to locate the illuminants. We conducted experiments using both variations of the technique to locate light sources in 51 different positions in a laboratory setting. Our data shows that the vector from a point in the scene to a light source can be measured to within 3/spl deg/(6%) of its tote direction and within 0.13 m (9%) of its true magnitude compared to empirically measured ground truth. Finally, we demonstrate how light source information can be applied to burn scar color correction and color segmentation.

An accurate one-dimensional model of the metal-silicon nitride-silicon dioxide-silicon (MNOS) capacitor is presented. The numerical solution technique uses space and time discretization to implicitly solve the carrier current equations in the insulators and the partial differential equations that describe the static and dynamic carrier distributions in the silicon. Avalanche carrier generation and avalanche carrier injection mechanisms are included. The improved understanding of the physical behavior that ensues is used to design a fast programming transient (

Stroboscopic electron beam blanking of a conventional SEM was employed to analyze high speed dynamic RAM operations. In the system described a time resolution of 20 nanoseconds was used to produce voltage contrast (V.C.) images of single events. Also the SEM was operated as a sampling oscilloscope to display timing waveforms from individual circuit nodes. Several types of 4K RAM (MCM6605) operations were analyzed to evaluate this technique in debugging MOS LSI circuits. The operations analyzed were memory cell timing waveforms, data-node storage, and node bootstrapping. The interaction of the SEM with the MCM6605 operation was also analyzed.

We have developed an automated framework for performance evaluation of curved-surface range image segmentation algorithms. Enhancements over our previous work include automated training of parameter values, correcting the artifact problem in K/sup 2/T scanner images, and acquisition of images of the same scenes from different range scanners. The image dataset includes planar, spherical, cylindrical, conical, and toroidal surfaces. We have evaluated the automated parameter tuning technique and found that it compares favorably with manual parameter tuning. We present initial results from comparing curved-surface segmenters by Besl and Jain (1988) and by Jiang and Bunke (1998).

This work focuses on creating a framework for objectively evaluating the performance of range image segmentation algorithms. The algorithms are evaluated in terms of correct segmentation, over- and under-segmentation, missed and noise regions. A set of images with ground truth was created for this work. The images were captured using a structured light scanner. Images used in the evaluation contain planar, spherical, cylindrical, toroidal and conical surface patches. The different surface patches in each image were manually identified to establish ground truth for performance evaluation. Two segmentation algorithms from the literature are compared.

We present a methodology for calibrating multiple light source locations in 3D from images. The procedure involves the use of a novel calibration object that consists of three spheres at known relative positions. The process uses intensity images to find the positions of the light sources. We conducted experiments to locate light sources in 51 different positions in a laboratory setting. Our data shows that the vector from a point in the scene to a light source can be measured to within 2.7/spl plusmn/4/spl deg/ at /spl alpha/=.05 (6 percent relative) of its true direction and within 0.13/spl plusmn/.02 m at /spl alpha/=.05 (9 percent relative) of its true magnitude compared to empirically measured ground truth. Finally, we demonstrate how light source information is used for color correction.

We present a methodology for correcting color images taken in practical indoor environments, such as laboratories, factories, and studios, that explicitly models illuminant location, surface reflectance and geometry, and camera responsivity. We explicitly model surfaces by taking our color images with corresponding registered three-dimensional (3-D) range images, which provide surface orientation and location information for every point in the scene. We automatically detect regions where color correction should not be applied, such as specularities, coarse texture regions, and jump edges. This correction results in objective color measures of the imaged surfaces. This kind of integrated, comprehensive system of color correction has not existed until now. i.e., it is the first of its kind in computer vision. We demonstrate results of applying this methodology to real images for applications in photorealistic rerendering, skin lesion detection, burn scar color measurement, and general color image enhancement. We also have tested the method under different lighting configurations and with three different range scanners.