SteerBug: an interactive framework for specifying and detecting steering behaviors.
ABSTRACT The size of crowds that modern computer games and urban simulations are capable of handling has given rise to the challenging problem of debugging and testing massive simulations of autonomous agents. In this paper, we propose SteerBug: an interactive framework for specifying and detecting steering behaviors. Our framework computes a set of time-varying metrics for agents and their environment, which characterize steering behaviors. We identify behaviors of interest by applying conditions (rules) or user defined sketches on the associated metrics. The behaviors we can specify and detect include unnatural steering, plainly incorrect results, or application-specific behaviors of interest. Our framework is extensible and independent of the specifics of any steering approach. To our knowledge, this is the first work that aims to provide a computational framework for specifying and detecting crowd behaviors in animation.
[Show abstract] [Hide abstract]
ABSTRACT: In this paper, we propose a new model to quantitatively compare global flow characteristics of two crowds. The proposed approach explores a 4-D histogram that contains information on the local velocity (speed and orientation) of each spatial position, and the comparison is made using histogram distances. The 4-D histogram also allows the comparison of specific characteristics, such as distribution of orientations only, speed only, relative spatial occupancy only, and combinations of such features. Experimental results indicate that the proposed quantitative metric correlates with visual inspection. Copyright © 2012 John Wiley & Sons, Ltd.Computer Animation and Virtual Worlds 02/2012; 23(1):49-57. DOI:10.1002/cav.1423 · 0.42 Impact Factor
Conference Paper: Hot-spot detection by group interaction extraction from trajectories[Show abstract] [Hide abstract]
ABSTRACT: We present a method for detecting hot-spots from surveillance videos via the extraction of group interactions (defined as stable and continuous spatial proximity of multiple objects). With a method that we propose for multi-object tracking in the multi-view scenario, we collect the trajectories of objects, from which we detect the group interactions. We assume that the movement of each object is driven by its interest of interaction, and model a group interaction by the mutual interests between objects. We solve detection of group interactions as a tracking problem, which first extracts unit-interactions by grouping objects at each individual frame, and then temporally associates them into continuous group interactions. We perform experiments on a publicly available dataset, and show that our tracking method achieves an accuracy around 95% and our detected group interactions could recall 80% of manually annotated hot-spots.RO-MAN, 2013 IEEE; 01/2013
Conference Paper: Cloning Crowd Motions[Show abstract] [Hide abstract]
ABSTRACT: This paper introduces a method to clone crowd motion data. Our goal is to efficiently animate large crowds from existing examples of motions of groups of characters by applying an enhanced copy and paste technique on them. Specifically, we address spatial and temporal continuity problems to enable animation of significantly larger crowds than our initial data. We animate many characters from the few examples with no limitation on duration. Moreover, our animation technique answers the needs of real-time applications through a technique of linear complexity. Therefore, it is significantly more efficient than any existing crowd simulation-based technique, and in addition, we ensure a predictable level of realism for animations. We provide virtual population designers and animators with a powerful framework which (i) enables them to clone crowd motion examples while preserving the complexity and the aspect of group motion and (ii) is able to animate large-scale crowds in real-time. Our contribution is the formulation of the cloning problem as a double search problem. Firstly, we search for almost periodic portions of crowd motion data through the available examples. Secondly, we search for almost symmetries between the conditions at the limits of these portions in order to interconnect them. The result of our searches is a set of crowd patches that contain portions of example data that can be used to compose large and endless animations. Through several examples prepared from real crowd motion data, we demonstrate the advantageous properties of our approach as well as identify its potential for future developments.Eurographics/ACM SIGGRAPH Symposium on Computer Animation; 07/2012