Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A complementary trajectory prediction benchmark

: Hug, Ronny; Becker, Stefan; Hübner, Wolfgang; Arens, Michael

Fulltext urn:nbn:de:0011-n-6219464 (5.2 MByte PDF)
MD5 Fingerprint: 69d0a5226eae9a193956c3172d83366a
Created on: 4.2.2021

Workshop on Benchmarking Trajectory Forecasting Models, BTFM 2020. Online resource : Online, 23-28 August 2020, in conjunction with the 16th European Conference on Computer Vision, ECCV 2020
Online im WWW, 2020
5 pp.
Workshop on Benchmarking Trajectory Forecasting Models (BTFM) <2020, Online>
European Conference on Computer Vision (ECCV) <16, 2020, Online>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Existing benchmarks targeting the overall performance of trajectory prediction models lack the possibility of gaining insight into a model’s behavior under specific conditions. Towards this end, a new benchmark aiming to take on a complementary role compared to existing benchmarks is proposed. It consists of synthetically generated and modified real-world trajectories from established datasets with scenario-dependent test and training splits. The benchmark provides a hierarchy of three inference tasks, representation learning, de-noising, and prediction, comprised of several test cases targeting specific aspects of a given machine learning model. This allows a differentiated evaluation of the model’s behavior and generalization capabilities. As a result, a sanity check for single trajectory models is provided aiming to prevent failure cases and highlighting requirements for improving modeling capabilities.