Huub van de Wetering

Visual Traffic Jam Analysis Based on Trajectory Data

In this work, we present an interactive system for visual analysis of urban traffic congestion based on GPS trajectories. For these trajectories we develop strategies to extract and derive traffic jam information. After cleaning the trajectories, they are matched to a road network. Subsequently, traffic speed on each road segment is computed and traffic jam events are automatically detected. Spatially and temporally related events are concatenated in, so-called, traffic jam propagation graphs. These graphs form a high-level description of a traffic jam and its propagation in time and space. Our system provides multiple views for visually exploring and analyzing the traffic condition of a large city as a whole, on the level of propagation graphs, and on road segment level. Case studies with 24 days of taxi GPS trajectories collected in Beijing demonstrate the effectiveness of our system.

Visualization of vessel movements

We propose a geographical visualization to support operators of coastal surveillance systems and decision making analysts to get insights in vessel movements. For a possibly unknown area, they want to know where significant maritime areas, like highways and anchoring zones, are located. We show these features as an overlay on a map. As source data we use AIS data: Many vessels are currently equipped with advanced GPS devices that frequently sample the state of the vessels and broadcast them. Our visualization is based on density fields that are derived from convolution of the dynamic vessel positions with a kernel. The density fields are shown as illuminated height maps. Combination of two fields, with a large and small kernel provides overview and detail. A large kernel provides an overview of area usage revealing vessel highways. Details of speed variations of individual vessels are shown with a small kernel, highlighting anchoring zones where multiple vessels stop. Besides for maritime applications we expect that this approach is useful for the visualization of moving object data in general.

Visualization, Selection, and Analysis of Traffic Flows

Visualization of the trajectories of moving objects leads to dense and cluttered images, which hinders exploration and understanding. It also hinders adding additional visual information, such as direction, and makes it difficult to interactively extract traffic flows, i.e., subsets of trajectories. In this paper we present our approach to visualize traffic flows and provide interaction tools to support their exploration. We show an overview of the traffic using a density map. The directions of traffic flows are visualized using a particle system on top of the density map. The user can extract traffic flows using a novel selection widget that allows for the intuitive selection of an area, and filtering on a range of directions and any additional attributes. Using simple, visual set expressions, the user can construct more complicated selections. The dynamic behaviors of selected flows may then be shown in annotation windows in which they can be interactively explored and compared. We validate our approach through use cases where we explore and analyze the temporal behavior of aircraft and vessel trajectories, e.g., landing and takeoff sequences, or the evolution of flight route density. The aircraft use cases have been developed and validated in collaboration with domain experts.

Evaluation of the visibility of vessel movement features in trajectory visualizations

There are many visualizations that show the trajectory of a moving object to obtain insights in its behavior. In this user study, we test the performance of three of these visualizations with respect to three movement features that occur in vessel behavior. Our goal is to compare the recently presented vessel density by Willems et al. [ WvdWvW09 ] with well‐known trajectory visualizations such as an animation of moving dots and the space‐time cube. We test these visualizations with common maritime analysis tasks by investigating the ability of users to find stopping objects, fast moving objects, and estimate the busiest routes in vessel trajectories. We test the robustness of the visualizations towards scalability and the influence of complex trajectories using small‐scale synthetic data sets. The performance is measured in terms of correctness and response time. The user test shows that each visualization type excels for correctness for a specific movement feature. Vessel density performs best for finding stopping objects, but does not perform significantly less than the remaining visualizations for the other features. Therefore, vessel density is a nice extension in the toolkit for analyzing trajectories of moving objects, in particular for vessel movements, since stops can be visualized better, and the performance for comparing lanes and finding fast movers is at a similar level as established trajectory visualizations.

Visualization of Vessel Traffic

We discuss methods to visualize large amounts of object movements described with so called multivariate trajectories, which are lists of records with multiple attribute values about the state of the object. In this chapter we focus on vessel traffic as one of the examples of this kind of data. The purpose of our visualizations is to reveal what has happened over a period of time. For vessel traffic, this is beneficial for surveillance operators and analysts, since current visualizations do not give an overview of normal behavior, which is needed to find abnormally behaving ships that can be a potential threat. Our approach is inspired by the technique of kernel density estimation and smooths trajectories to obtain an overview picture with a distribution of trajectories: a density map. Using knowledge about the attributes in the data, the user can adapt these pictures by setting parameters, filters, and expressions as means for rapid prototyping, required for quickly finding other types of behavior with our visualization approach. Furthermore, density maps are computationally expensive, which we address by implementing our tools on graphics hardware. We describe different variations of our techniques and illustrate them with real-world vessel traffic data.

Vanishing point and gabor feature based multi-resolution on-road vehicle detection

Robust and reliable vehicle detection is a challenging task under the conditions of variable size and distance, various weather and illumination, cluttered background, the relative motion between the host vehicle and background. In this paper we investigate real-time vehicle detection using machine vision for active safety in vehicle applications. The conventional search method of vehicle detection is a full search one using image pyramid,which processes the image patches in same way and costs same computing time, even for no vehicle region according to prior knowledge. Our vehicle detection approach includes two basic phases. In the hypothesis generation phase, we determine the Regions of Interest (ROI) in an image according to lane vanishing points; furthermore, near, middle, and far ROIs, each with a different resolution, are extracted from the image. From the analysis of horizontal and vertical edges in the image, vehicle hypothesis lists are generated for each ROI. Finally, a hypothesis list for the whole image is obtained by combining these three lists. In the hypothesis validation phase, we propose a vehicle validation approach using Support Vector Machine (SVM) and Gabor feature. The experimental results show that the average right detection rate reach 90% and the average execution time is 30ms using a Pentium(R)4 CPU 2.4GHz.

Rendering hierarchical data

Why is my hard disk full? A question no doubt familiar to many readers, and one that has inspired our research for several years. Our goal is to provide more insight into large, hierarchical data sets, commonly known as trees. Hierarchical data sets can be found everywhere. A large number of items, such as files, products, employees, and stocks, can be handled and managed much more efficiently when they are grouped into larger entities. Recursive application of this approach results in a tree structure. A hierarchical file system is a prime example: The user can organize his disk, and only has to deal with a limited set of files while fulfilling a task. But the PC disk of an average user often contains dozens of gigabytes of data, distributed over hundreds of thousands of files. In this case it becomes difficult to maintain an overview, and to determine what is cluttering the disk. Often no single, simple answer exists. Perhaps another user of the PC has installed some large programs, or has failed to cleanup after finishing a task in his or her relief at meeting a deadline. Perhaps multiple copies of the same multimedia file are stored on the disk. How can we find large files and directories and identify patterns and structures easily in such large hierarchical data structures? Automatic methods, such as searching for the largest files, fall short, and standard file browsers, using indented lists, have not been developed with this problem in mind. We believe the best way to answer our question is to exploit the unique capabilities of the human visual system, tuned and optimized in the course of millions of years of evolution to extract information from images [9]. In other words, let us try to make synthetic images, using a wide variety of visual cues to transfer information as efficiently and effectively as possible.

Illustrative white matter fiber bundles

Diffusion Tensor Imaging (DTI) has made feasible the visualization of the fibrous structure of the brain white matter. In the last decades, several fiber‐tracking methods have been developed to reconstruct the fiber tracts from DTI data. Usually these fiber tracts are shown individually based on some selection criteria like region of interest. However, if the white matter as a whole is being visualized clutter is generated by directly rendering the individual fiber tracts. Often users are actually interested in fiber bundles, anatomically meaningful entities that abstract from the fibers they contain. Several clustering techniques have been developed that try to group the fiber tracts in fiber bundles. However, even if clustering succeeds, the complex nature of white matter still makes it difficult to investigate. In this paper, we propose the use of illustration techniques to ease the exploration of white matter clusters. We create a technique to visualize an individual cluster as a whole. The amount of fibers visualized for the cluster is reduced to just a few hint lines, and silhouette and contours are used to improve the definition of the cluster borders. Multiple clusters can be easily visualized by a combination of the single cluster visualizations. Focus+context concepts are used to extend the multiple‐cluster renderings. Exploded views ease the exploration of the focus cluster while keeping the context clusters in an abstract form. Real‐time results are achieved by the GPU implementation of the presented techniques.

Contour based visualization of vessel movement predictions

We present a visualization method for the interactive exploration of predicted positions of moving objects, in particular, ocean-faring vessels. Two simple prediction models, one based on similarity to historical trajectories and one on Monte Carlo simulation, are presented. The prediction models generate temporal probability density fields starting from a known situation. We use contours to visualize spatio-temporal zones of these density fields. Predictions are split into a configurable number of segments for which we render one or more contours. Users, investigating and exploring the possible development of a situation, can see where a vessel will be in the near future according to a given prediction model. Through a number of real-world use cases and a discussion with users, we show our methods can be used in monitoring traffic for collision avoidance, and detecting illegal activities, like piracy or smuggling. By applying our methods to pedestrian movements, we show that our methods can also be applied to a different domain.

Case study: visualization of annotated DNA sequences

DNA sequences and their annotations form ever expanding data sets. Proper explorations of such data sets require new tools for visualization and analysis. In this case study, we have defined the requirements for a visualization tool for annotated DNA sequences. We have implemented these requirements in a new and flexible tool for browsing and comparing annotated DNA sequences interactively and in real-time. The use of standard information visualization techniques, such as linked windows, perspective walls, and smooth interaction, enables genome researchers to obtain better insight in large DNA data sets in an effective, efficient, and attractive way.