Self-driving vehicles use a variety of sensors to understand the environment they are in. In order to do so, they must accurately measure the distances and positions of the objects around them. A common representation of the environment around the vehicle is a 3D point cloud, or a set of 3D data points which represent the positions of objects in the real world relative to the car. However, while accurate and useful, these point clouds require large amounts of memory compared to other representations such as lightweight polygonal meshes. In addition, 3D point clouds can be difficult for a human to visually understand as the data points do not always form a naturally coherent object. This paper introduces a system to lower the memory consumption needed for the graphical representation of a virtual street environment. At this time, the proposed system takes in as input a single front-facing video. The system uses the video to retrieve still images of a scene which are then segmented to distinguish the different relevant objects, such as cars and stop signs. The system generates a corresponding virtual street scene and these key objects are visualized in the virtual world as low poly, or low resolution, models of the respective objects. This virtual 3D street environment is created to allow a remote operator to visualize the world that the car is traveling through. At this time, the virtual street includes geometric proxies for parallel parked cars in the form of lightweight polygonal meshes. These meshes are predefined, taking up less memory than a point cloud, which can be costly to transmit from the remote vehicle and potentially difficult for a remote human operator to understand. This paper contributes a design and analysis of an initial system for generating and placing these geometric proxies of parked cars in a virtual street environment from one input video. We discuss the limitations and measure the error for this system as well as reflect on future improvements.

No description available.

No description available.

No description available.

The motivation for this work arose from the recognised inability of relational databases to store and manipulate data that is outside normal commercial applications (e.g. graphical data). The published work in this area is described with respect to the major problems of representation and manipulation of complex data. A general purpose data model, called GDB, that sucessfully tackles these major problems is developed from a formal specification in ML and is implemented using the PRECI/C database system. This model uses three basic graphical primitives (line segments, plane surfaces - facets, and volume elements tetrons) to construct graphical objects and it is shown how user designed primitives can be included. It is argued that graphical database query languages should be designed to be application specific and the user should be protected from the relational algebra which is the basis of the database operations. Such a base language (an extended version of DEAL) is presented which is capable of performing the necessary graphical manipulation by the use of recursive functions and views. The need for object hierarchies is established and the power of the DEAL language is shown to be necessary to handle such complex structures. The importance of integrity constraints is discussed and some ideas for the provision of user defined constraints are put forward.

In this paper, we present an approach to discretizing multivariate continuous data while learning the structure of a graphical model. We derive the joint scoring function from the principle of predictive accuracy, which inherently ensures the optimal trade-off between goodness of fit and model complexity (including the number of discretization levels). Using the so-called finest grid implied by the data, our scoring function depends only on the number of data points in the various discretization levels. Not only can it be computed efficiently, but it is also independent of the metric used in the continuous space. Our experiments with gene expression data show that discretization plays a crucial role regarding the resulting network structure.

No description available.

No description available.

Thesis (Ph. D.)--University of Washington, 2002. / Vita. Includes bibliographical references (p. 121-123).

No