Dictionary-based Fidelity Measure for Virtual Traffic


IEEE Transactions on Visualization and Computer Graphics, 2018 (accepted)

Qianwen Chao, Zhigang Deng, Yangxi Xiao, Dunbang He, Qiguang Miao, and Xiaogang Jin

Fidelity measure comparisons among three virtual traffic flows generated by a microscopic IDM model with three different parameter sets ((b)-(d)). The initial traffic states of the simulator were set as the same as the real-world traffic flow in the same scenario (a). Differences between the simulated traffic and real-world ground truth are highlighted with white circles. For the dictionary-based fidelity evaluation, a smaller value of the metric indicates a higher fidelity of virtual traffic.


Aiming at objectively measuring the realism of virtual traffic flows and evaluating the effectiveness of different traffic simulation techniques, this paper introduces a general, dictionary-based learning method to evaluate the fidelity of any traffic trajectory data. First, a traffic pattern dictionary that characterizes common patterns of real-world traffic behavior is built offline from pre-collected ground truth traffic data. The corresponding learning error is set as the benchmark of the dictionary-based traffic representation. With the aid of the constructed dictionary, the realism of input simulated traffic flow data can be evaluated by comparing its dictionary-based reconstruction error with the dictionary error benchmark. This evaluation metric can be robustly applied to any simulated traffic flow data; in other words, it is independent of how the traffic data are generated. We demonstrated the effectiveness and robustness of this metric through many experiments on real-world traffic data and various simulated traffic data, comparisons with the state-of-the-art entropy-based similarity metric for aggregate crowd motions, and perceptual evaluation studies.