In this project, we worked on a network based cooperative surveillance system. It can be used to track either humans or monitor still objects for anti-theft purpose. We designed multiple ways for user to select the tracking target. The tracking algorithm is based on a Tracking-Learning-Detection pipeline. Experiment results show fast and accurate tracking performance of the system. The potentia...

• This project aims to simplify the modeling process with a machine learning pipeline that generates a non-linear vehicle model for simulation, control design, and analysis with minimal reliance on domain knowledge. • A locally weighted linear regression [3] approach was investigated to provide full flight envelope modeling of an unconventional Vertical Takeoff and Landing (VTOL) aircraft with ...

In this paper we discuss an application of our MVE-2 project in a research experiment. The MVE-2 stands for “Modular Visualization Environment version 2”. It is our grass root effort to create a general and easy to use pipeline based environment. These days we are in the stage of first real-world research experiments. Following text contains an introduction to the system and its possibilities. ...

We introduce our publicly available Wide-Field-Imaging reduction pipeline THELI. The procedures applied for the efficient pre-reduction and astrometric calibration are presented. A special emphasis is put on the methods applied to the photometric calibration. As a test case the reduction of optical data from the ESO Deep Public Survey including the WFI-GOODS data is described. The end-products ...

In this paper we describe a project that integrates a non-photorealistic rendering pipeline into an existing CAD system. The pipeline enables the customers of the CAD company to create aesthetically appealing renderings in addition to the classical CAD output. Since these customers are operating in the high-quality segment of furniture and interior design, the visual style of the sales brochure...

In this paper, we describe a robust algorithm for 2-Manifold generation of various kinds of ShapeNet Models. The input of our pipeline is a triangle mesh, with a set of vertices and triangular faces. The output of our pipeline is a 2-Manifold with vertices roughly uniformly distributed on the geometry surface. Our algorithm uses an octree [Meagher 1982] to represent the original mesh, and const...

The article describes a pipeline, based on image-data, for the 3D reconstruction of building façades or architectural elements and the successive modeling using geometric primitives. The approach overcome some existing problems in modeling architectural elements and deliver efficient-in-size reality-based textured 3D models useful for metric applications. For the 3D reconstruction, an opensourc...

In this design case, the design of visualization tools to support the Laser Interferometer Gravitational Wave Observatory (LIGO) is described. A participatory approach to visualizing a complex computational pipeline was adopted, with the goal of exploring what benefits might be derived when groups of people visualize complex information for themselves. Direct participation in LIGO activities he...

CLONEPICKER is a software pipeline that integrates sequence data with BAC clone fingerprints to dynamically select a minimal overlapping clone set covering the whole genome. In the Rat Genome Sequencing Project (RGSP), a hybrid strategy of "clone by clone" and "whole genome shotgun" approaches was used to maximize the merits of both approaches. Like the "clone by clone" method, one key challeng...

This paper presents UNRET (unrolling and retiming), a new approach for resource-constrained loop pipelining. UNRET aims at nding a loop schedule with maximum throughput and minimum register pressure. UNRET is composed of two main phases. In the rst phase, a schedule with maximum throughput is found for a given set of resource constraints. To do so, diierent unrolling degrees are explored in dec...