Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems

Georg Waltner, Michael Maurer, Thomas Holzmann, Patrick Ruprecht, Michael Opitz, Horst Possegger, Friedrich Fraundorfer, Horst Bischof

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung


Automated toll systems rely on proper classification of the passing vehicles. This is especially difficult when the images used for classification only cover parts of the vehicle. To obtain information about the whole vehicle. we reconstruct the vehicle as 3D object and exploit this additional information within a Convolutional Neural Network (CNN). However, when using deep networks for 3D object classification, large amounts of dense 3D models are required for good accuracy, which are often neither available nor feasible to process due to memory requirements. Therefore, in our method we reproject the 3D object onto the image plane using the reconstructed points, lines or both. We utilize this sparse depth prior within an auxiliary network branch that acts as a regularizer during training. We show that this auxiliary regularizer helps to improve accuracy compared to 2D classification on a real-world dataset. Furthermore due to the design of the network, at test time only the 2D camera images are required for classification which enables the usage in portable computer vision systems.
Titel2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers
ISBN (elektronisch)9781728103235
PublikationsstatusVeröffentlicht - 7 Dez. 2018
Veranstaltung21st IEEE International Conference on Intelligent Transportation Systems - Maui, Maui, USA / Vereinigte Staaten
Dauer: 4 Nov. 20187 Nov. 2018


Konferenz21st IEEE International Conference on Intelligent Transportation Systems
KurztitelITSC 2018
Land/GebietUSA / Vereinigte Staaten


Untersuchen Sie die Forschungsthemen von „Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren