Name
Title | ||
|---|---|---|
How Good Is My Prediction? Finding A Similarity Measure For Trajectory Prediction Evaluation |
Abstract | ||
|---|---|---|
The reliable prediction of traffic participants' trajectories is an important challenge for automated driving. Prediction methods that try to deal with this challenge need similarity measures for trajectories in order to evaluate the quality of their prediction. Currently there exists no commonly accepted similarity measure suitable for this task. In this paper we review common trajectory similarity measures and analyze them with regard to prediction evaluation. Further we introduce a new approach for synthesizing a hybrid measure that combines a set of similarity measures and provide a heuristic to determine the parameters for this approach. |
Year | Venue | Field |
|---|---|---|
2017 | 2017 IEEE 20TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC) | Computer vision,Heuristic,Existential quantification,Similarity measure,Artificial intelligence,Engineering,Trajectory,Machine learning |
DocType | ISSN | Citations |
Conference | 2153-0009 | 2 |
PageRank | References | Authors |
0.38 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jannik Quehl | 1 | 2 | 0.72 |
| Haohao Hu | 2 | 2 | 1.05 |
| Ömer Sahin Tas | 3 | 10 | 3.39 |
| Rehder, E. | 4 | 23 | 2.85 |
| Martin Lauer | 5 | 21 | 8.98 |