The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform

Jingyuan Zhang - One of the best experts on this subject based on the ideXlab platform.

  • fast Computer Vision Algorithms for reconfigurable meshes
    Image and Vision Computing, 1992
    Co-Authors: Stephan Olariu, James L Schwing, Jingyuan Zhang
    Abstract:

    Abstract A bus system that can change dynamically to suit computational needs is referred to as reconfigurable. The purpose of this work is to show that a number of seemingly unrelated low-level Computer Vision tasks are in the same class, in the sense that they can be solved using the same technique. We show that a novel technique for computing integer prefix sums on meshes, augmented with a reconfigurable bus system (reconfigurable meshes), affords us fast Algorithms to compute low-level descriptors including perimeter, area, histogram, and median row. Specifically, for an N × N digitized image stored one pixel per processor, all our Algorithms run in O(loglog N) time, which is a vast improvement over the state of the art .

  • fast Computer Vision Algorithms for reconfigurable meshes
    International Parallel Processing Symposium, 1992
    Co-Authors: Stephan Olariu, James L Schwing, Jingyuan Zhang
    Abstract:

    A bus system that can change dynamically to suit computational needs is referred to as reconfigurable. The authors are interested in obtaining fast Algorithms for a number of low-level Vision tasks on a two-dimensional mesh augmented with a reconfigurable bus system (reconfigurable mesh). Specifically, for an n*n digitized image stored one pixel per processor they present O(loglogn) Algorithms to compute low-level descriptors including perimeter, area, histogram, median row, center as well as several moments. >

Charles V Stewart - One of the best experts on this subject based on the ideXlab platform.

  • Computer Vision Algorithms for retinal image analysis current results and future directions
    International Conference on Computer Vision, 2005
    Co-Authors: Charles V Stewart
    Abstract:

    Automated image analysis tools have the potential to play an important role in assisting in the diagnosis and treatment of retinal diseases. Problems that must be addressed in developing these tools include extraction of vascular and non-vascular features, segmentation of pathologies, unimodal and multimodal image registration, mosaic construction, and real-time systems. Research at Rensselaer Polytechnic Institute since the late 1990’s has focused on several of these problems. Most significantly, we have developed a series of registration and mosaic formation Algorithms which have been validated on thousands of retinal images and have been extended beyond the retina application. While the core fundus image registration problem is essentially solved, important problems remain in many aspects of retinal image analysis.

  • Computer Vision Algorithms for retinal vessel detection and width change detection
    2004
    Co-Authors: Charles V Stewart, Badrinath Roysam, Kenneth Fritzsche
    Abstract:

    Detection of width changes in blood vessels of the retina may be indicative of eye or systemic disease. However, fundus images taken at different times have different scales and are difficult to compare side by side. This research presents automated techniques for detection of vessel width change from two images acquired at different points in time. In order to detect vessel width change; vessels must first be identified in available images. This research starts by making numerous improvements to an existing vessel tracing algorithm. However, even the improved results exhibit too much variance, primarily attributable to the discrete nature of the tracing algorithm. Thus new methods for estimating vessels are explored to address the limitations of the vessel tracing algorithm. These methods are designed to provide smooth, continuous boundaries. Five ribbon-like objects are put into an active contour framework, all initialized using the results from tracing. These ribbons are shown to provide more repeatable vessel boundaries than tracing with an innovative technique named in this research as cross section snakes selected as best. In addition to estimating vessels from a single image, a technique is explored that uses information from multiple images acquired in a single sitting to estimate vessel boundaries in a single image with greater accuracy. This technique was subjectively evaluated by five people and was preferred at a rate that is double the sum of two other single image estimation techniques. In detecting change, two approaches are tried. One that alternately tests vessel boundaries in the other image before determining change, and one that uses a statistical hypothesis test as the basis for the determination of change. The first method is the better of the two based on three criteria. First, method 1 achieves a positive predictive power of 78% and method 2, 57%. Second, method 1 correctly identifies 15 out of 20 vessel segments as changed compared with only 7 in method 2. Finally, method 1 is shown to be superior at correctly identifying no change (i.e. less false positives) over method 2.

Anna Helena Reali Costa - One of the best experts on this subject based on the ideXlab platform.

  • implementing Computer Vision Algorithms in hardware an fpga vhdl based Vision system for a mobile robot
    Robot Soccer World Cup, 2002
    Co-Authors: Reinaldo A C Ianchi, Anna Helena Reali Costa
    Abstract:

    A time critical process in a real-time mobile robot application such as RoboCup is the determination of the robot position in the game field. Aiming at low-cost and efficiency, this paper proposes the use of field-programmable gate array device (FPGA) in the Vision system of a robotic team. We describe the translation of well-known Computer Vision Algorithms to VHDL and detail the design of a working prototype that includes image acquisition and processing. The CV Algorithms used in the system includes thresholding, edge detection and chain-code segmentation. Finally, we present results showing that an FPGA device provides hardware speed to user applications, delivering real-time speeds for image segmentation at an affordable cost. An efficiency comparison is made among the hardware-implemented and a software-implemented (C language) system using the same Algorithms.

Nikolaos Papanikolopoulos - One of the best experts on this subject based on the ideXlab platform.

  • tracking all traffic Computer Vision Algorithms for monitoring vehicles individuals and crowds
    IEEE Robotics & Automation Magazine, 2005
    Co-Authors: Benjamin Maurin, O Masoud, Nikolaos Papanikolopoulos
    Abstract:

    This article presents a Vision-based system for monitoring crowded urban scenes. The approach combines an effective detection scheme based on optical flow and background removal that can locate vehicles, individual pedestrians, and crowds. The detection phase is followed by the tracking phase that tracks all the detected entities. Traffic objects are not simply tracked but a wealth of information (position, velocity, acceleration/deceleration, bounding rectangle, and shape features) is gathered about them also. Potential applications of the methods include intersection control, traffic data collection, and even crowd control after athletic events. Extensive experimental results for a variety of weather conditions are presented. Future work would focus on methods to deal with shadows and occlusions.

  • Computer Vision Algorithms for intersection monitoring
    International Conference on Intelligent Transportation Systems, 2003
    Co-Authors: Harini Veeraraghavan, O Masoud, Nikolaos Papanikolopoulos
    Abstract:

    The goal of this project is to monitor activities at traffic intersections for detecting/predicting situations that may lead to accidents. Some of the key elements for robust intersection monitoring are camera calibration, motion tracking, incident detection, etc. In this paper, we consider the motion-tracking problem. A multilevel tracking approach using Kalman filter is presented for tracking vehicles and pedestrians at intersections. The approach combines low-level image-based blob tracking with high-level Kalman filtering for position and shape estimation. An intermediate occlusion-reasoning module serves the purpose of detecting occlusions and filtering relevant measurements. Motion segmentation is performed by using a mixture of Gaussian models which helps us achieve fairly reliable tracking in a variety of complex outdoor scenes. A visualization module is also presented. This module is very useful for visualizing the results of the tracker and serves as a platform for the incident detection module.

Toon Goedeme - One of the best experts on this subject based on the ideXlab platform.

  • real time embedded Computer Vision on uavs
    European Conference on Computer Vision, 2018
    Co-Authors: Kristof Van Beeck, Tinne Tuytelaars, Davide Scarramuza, Toon Goedeme
    Abstract:

    In this paper we present an overview of the contributed work presented at the UAVision2018 ECCV workshop. This workshop focused on real-time image processing on-board of Unmanned Aerial Vehicles (UAVs). For such applications the computational complexity of state-of-the-art Computer Vision Algorithms often conflicts with the need for real-time operation and the extreme resource limitations of the hardware. Apart from a summary of the accepted workshop papers, this work also aims to identify common challenges and concerns which were addressed by multiple authors during the workshop, and their proposed solutions.