TY - GEN
T1 - Novelty detection and analysis of traffic scenario infrastructures in the latent space of a vision transformer-based triplet autoencoder
AU - Wurst, Jonas
AU - Balasubramanian, Lakshman
AU - Betsch, Michael
AU - Utschick, Wolfgang
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/11
Y1 - 2021/7/11
N2 - Detecting unknown and untested scenarios is crucial for scenario-based testing. Scenario-based testing is considered to be a possible approach to validate autonomous vehicles. A traffic scenario consists of multiple components, with infrastructure being one of it. In this work, a method to detect novel traffic scenarios based on their infrastructure images is presented. An autoencoder triplet network provides latent representations for infrastructure images which are used for outlier detection. The triplet training of the network is based on the connectivity graphs of the infrastructure. By using the proposed architecture, expert-knowledge is used to shape the latent space such that it incorporates a pre-defined similarity in the neighborhood relationships of an autoencoder. An ablation study on the architecture is highlighting the importance of the triplet autoencoder combination. The best performing architecture is based on vision transformers, a convolution-free attention-based network. The presented method outperforms other state-of-the-art outlier detection approaches.
AB - Detecting unknown and untested scenarios is crucial for scenario-based testing. Scenario-based testing is considered to be a possible approach to validate autonomous vehicles. A traffic scenario consists of multiple components, with infrastructure being one of it. In this work, a method to detect novel traffic scenarios based on their infrastructure images is presented. An autoencoder triplet network provides latent representations for infrastructure images which are used for outlier detection. The triplet training of the network is based on the connectivity graphs of the infrastructure. By using the proposed architecture, expert-knowledge is used to shape the latent space such that it incorporates a pre-defined similarity in the neighborhood relationships of an autoencoder. An ablation study on the architecture is highlighting the importance of the triplet autoencoder combination. The best performing architecture is based on vision transformers, a convolution-free attention-based network. The presented method outperforms other state-of-the-art outlier detection approaches.
UR - http://www.scopus.com/inward/record.url?scp=85118849752&partnerID=8YFLogxK
U2 - 10.1109/IV48863.2021.9575730
DO - 10.1109/IV48863.2021.9575730
M3 - Conference contribution
AN - SCOPUS:85118849752
T3 - IEEE Intelligent Vehicles Symposium, Proceedings
SP - 1304
EP - 1311
BT - 32nd IEEE Intelligent Vehicles Symposium, IV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 32nd IEEE Intelligent Vehicles Symposium, IV 2021
Y2 - 11 July 2021 through 17 July 2021
ER -