Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder

Abstract

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.

arXiv commentCopyright 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

References in corpus (9)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Metric Learning for Novelty and Anomaly Detection
• A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories
• Clustering of Driving Encounter Scenarios Using Connected Vehicle Trajectories
• An Unsupervised Random Forest Clustering Technique for Automatic Traffic Scenario Categorization
• Unsupervised and Supervised Learning with the Random Forest Algorithm for Traffic Scenario Clustering and Classification
• Deep Representation Learning and Clustering of Traffic Scenarios

Cited by in corpus (2)

• Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios
• Conditioning Latent-Space Clusters for Real-World Anomaly Classification