Abstract | ||
---|---|---|
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
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">traffic pattern dictionary</italic>
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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/TVCG.2018.2873695 | IEEE transactions on visualization and computer graphics |
Keywords | Field | DocType |
Computational modeling,Measurement,Solid modeling,Trajectory,Dictionaries,Data models,Benchmark testing | Data mining,Computer vision,Fidelity,Traffic flow,Airfield traffic pattern,Computer science,Traffic simulation,Robustness (computer science),Reconstruction error,Ground truth,Artificial intelligence,Trajectory | Journal |
Volume | Issue | ISSN |
26 | 3 | 1077-2626 |
Citations | PageRank | References |
0 | 0.34 | 21 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qianwen Chao | 1 | 4 | 1.43 |
Zhigang Deng | 2 | 1366 | 91.38 |
Yangxi Xiao | 3 | 0 | 0.34 |
Dunbang He | 4 | 0 | 0.34 |
Qiguang Miao | 5 | 355 | 49.69 |
Xiaogang Jin | 6 | 1075 | 117.02 |