Kai-Uwe Doerr

CGLX: A Scalable, High-Performance Visualization Framework for Networked Display Environments

The Cross Platform Cluster Graphics Library (CGLX) is a flexible and transparent OpenGL-based graphics framework for distributed, high-performance visualization systems. CGLX allows OpenGL based applications to utilize massively scalable visualization clusters such as multiprojector or high-resolution tiled display environments and to maximize the achievable performance and resolution. The framework features a programming interface for hardware-accelerated rendering of OpenGL applications on visualization clusters, mimicking a GLUT-like (OpenGL-Utility-Toolkit) interface to enable smooth translation of single-node applications to distributed parallel rendering applications. CGLX provides a unified, scalable, distributed OpenGL context to the user by intercepting and manipulating certain OpenGL directives. CGLXs interception mechanism, in combination with the core functionality for users to register callbacks, enables this framework to manage a visualization grid without additional implementation requirements to the user. Although CGLX grants access to its core engine, allowing users to change its default behavior, general development can occur in the context of a standalone desktop. The framework provides an easy-to-use graphical user interface (GUI) and tools to test, setup, and configure a visualization cluster. This paper describes CGLXs architecture, tools, and systems components. We present performance and scalability tests with different types of applications, and we compare the results with a Chromium-based approach.

Optimal hardware and software design of an image-based system for capturing dynamic movements

In contrast to conventional image-capture systems, which attempt to minimize the amount of data collected during capture, typically by using hardware filters, the more general condition of using all information captured on a camera sensor is much more challenging and requires rigorous consideration of the hardware and software pipelines to obtain accurate tracking results. In this paper, this issue is specifically addressed by describing a unique hardware and software design implemented for use as a fully image-based capture system. An attempt is made to minimize the cost of this system by maximizing hardware control through software implementation. The hardware and software requirements are described in the context of the desired high-speed capture suitable for earthquake motions or other dynamic movements in a scene. Experiments are conducted and presented illustrating the good performance and stability of the system. This system is deemed suitable for the general condition of a building interior.

Visualization of high-resolution image collections on large tiled display walls

This paper introduces an approach to interactively visualize a large collection of high-resolution images in large-scale tiled display environments. Our approach fully utilizes the distributed computing and rendering capabilities of visualization clusters that are driving tiled display walls. A seamless and unified workspace spanning across the entire wall is provided, while view dependent resource management strategies support smooth and fully interactive data analysis of a collection of images. Interactive image filtering and graphing techniques are presented, allowing features in individual images and patterns in image sets to be visualized on the fly. The provided case studies show that the presented approach can scale well beyond terapixel-scale visualization while providing highly responsive interactive environments.

A METHODOLOGY FOR IMAGE-BASED TRACKING OF SEISMIC-INDUCED MOTIONS

Previous experiences during earthquake events emphasize the need for new technologies for real-time monitoring and assessment of facilities with high value nonstructural elements such as equipment or other contents. Moreover, there are substantial limitations to our ability to rapidly evaluate and identify potential hazard zones within a structure, exposing rescue workers, society and the environment to unnecessary risks. A real-time monitoring system, integrated with critical warning systems, would allow for improved channeling of resources. Ideally such a system would acquire all relevant data non-intrusively, at high rates and resolution and disseminate it with low latency over a trusted network to a central repository. This repository can then be used by the building owner and rescue workers to make informed decisions. In recognition of these issues, in this paper, we describe a methodology for image-based tracking of seismically induced motions. The methodology includes calibration, acquisition, processing, and analysis tools geared towards seismic assessment. We present sample waveforms extracted considering pixel-based algorithms applied to images collected from an array of high speed, high-resolution charged-couple-device (CCD) cameras. This work includes use of a unique hardware and software design involving a multi-threaded process, which bypasses conventional hardware frame grabbers and uses a software-based approach to acquire, synchronize and time stamp image data.

Development and Evaluation of a Seismic Monitoring System for Building Interiors—Part II: Image Data Analysis and Results

Previous experiences during earthquake events emphasize the need for new technologies for real-time monitoring and assessment of facilities with high-value nonstructural contents. Moreover, there is a substantial limitation in our ability to rapidly evaluate and identify potential hazard zones within a structure, exposing rescue workers, society, and the environment to unnecessary risks. A real-time image-based monitoring system, which is integrated with warning systems, would allow for improved channeling of resources and informed decision making for rescue workers and building owners. In recognition of these issues, in this paper, we describe a methodology for image-based tracking of seismically induced motions. The methodology includes the acquisition, calibration, and processing of image sequences to detect and track object features under seismic-event conditions. We address the issue of providing a reliable feature/object-detection and object-tracking methodology for an image sequence from a single camera view. In addition, we introduce an extension to the 2-D tracking approach by providing a 3-D feature tracking methodology when the camera array itself is affected by the seismic event. The methods presented are demonstrated using the data collected during the full-scale field vibration tests conducted on a vacant building that was damaged during the 1994 Northridge earthquake (presented in a companion paper). We present experimental tracking results of the implemented algorithms for a variety of objects and discuss additional challenges that emerge when image-based systems are used under these extreme conditions.

Development and Evaluation of a Seismic Monitoring System for Building Interiors—Part I: Experiment Design and Results

The advent of high-speed, lightweight, and durable sensor technologies opens new possibilities for field monitoring applications. In particular, under natural or man-made loading conditions, applying these new technologies to the monitoring of building interiors may substantially help rescue and reconnaissance crews during postevent evaluations. To test such a methodology, in this paper, we develop a specialized network of conventional analog and digital (camera) sensors and use them in monitoring nonstructural components subjected to vibration loading within a demonstration building structure. A full-scale vibration experiment is conducted with a research team from the University of California, Los Angeles, on a vacant structure damaged during the 1994 Northridge Earthquake. The building of interest is a four-story office building located in Sherman Oaks, CA. The investigation has two primary objectives: (1) to characterize the seismic response of an important class of equipment and building contents and (2) to study the applicability of tracking the response of these equipment and contents using arrays of image-based monitoring systems. In this paper, we describe the experimental field setup, including the analog and camera sensor systems and the networking hardware used to collect data, present the testing matrix, and sample the processed analog data results. We summarize the difficulties encountered in the field implementation of these types of monitoring systems while highlighting their potential benefits. In a companion paper, we present the analysis methodology applied to the image sequences collected and summarize needs for future work if such systems are to be robustly employed in the field.

Interactive image fusion in distributed visualization environments

This paper presents an immediate-mode, integrated approach to image fusion and visualization of multi-band satellite data, drawing from the computational resources of networked, high-resolution, tiled display environments. The presented workflow enables researchers to intuitively and interactively experiment with all tunable parameters, exposed through external devices such as MIDI controllers, to rapidly modify the image processing pipeline and resulting visuals. This presented approach demonstrates significant savings across a set of case studies, with respect to overall data footprint, processing and analysis time complexity.

Monitoring earthquake-induced loading with camera networks: case study in Sherman Oaks, California

The advent of high speed, CCD-based camera technologies opens new possibilities for field monitoring applications. In particular, under natural or man-made loading conditions, applying these new technologies towards the monitoring of building interiors may substantially help rescue and reconnaissance crews during post-event evaluations. To test such a methodology, we have developed a specialized network of high-speed cameras and supporting hardware for monitoring and tracking nonstructural elements subjected to vibration loading, within building structures. Teamed with the University of California, Los Angeles, a full-scale vibration experiment is conducted on a vacant structure damaged during the 1994 Northridge Earthquake. The building of interest is a four-story office building located in Sherman Oaks, California. The investigation has two primary objectives: (1) to characterize the seismic response of an important class of equipment and building contents and (2) to study the applicability of tracking the response of these equipment and contents using arrays of image-based monitoring systems. In this paper, we describe the image acquisition (hardware and software) system and the experimental field set-up are described. In addition, the underlying communication, networking and synchronization of the camera sensor system are discussed.