Spatiotemporal representation of driving scenarios and classification using neural networks
Authors:
- 1 June 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1782-1788
Abstract
Large scale fleet tests of autonomous vehicles lead to the availability of massive recorded datasets, offering significant potential for the generation of realistic virtual test drives, for the development and training of machine learning based functions, and facilitated performance analysis. Automated scenario classification and data labeling is necessary to maximize the utility of these massive datasets and make them fully accessible and searchable for developers. In this paper we present and compare several spatiotemporal representations of recorded driving scenarios and analyze the impact of the representation type on the results of the subsequent automated scenario classification with deep neural networks. Built on a fused list of objects that combines data from several sensor types, we create and annotate datasets for each of the representations and train the classification algorithm. The best classification results were achieved with the presented Stacked Velocity Grid, which includes temporal information.Keywords
This publication has 9 references indexed in Scilit:
- Defining and Substantiating the Terms Scene, Situation, and Scenario for Automated Driving2015
- Classification for Safety-Critical Car-Cyclist Scenarios Using Machine Learning2015
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Towards a Global Optimal Multi-Layer Stixel Representation of Dense 3D Data2011
- Ontology-Based Hierarchical Conceptual Model for Semantic Representation of Events in Dynamic Scenes2006
- Long Short-Term MemoryNeural Computation, 1997
- The use of the area under the ROC curve in the evaluation of machine learning algorithmsPattern Recognition, 1997
- Using occupancy grids for mobile robot perception and navigationComputer, 1989
- Nearest neighbor pattern classificationIEEE Transactions on Information Theory, 1967