From On-Road to Off: Transfer Learning within a Deep Convolutional Neural Network for Segmentation and Classification of Off-Road Scenes

Holder, C.J.; Breckon, T.P.; Wei, X.

doi:10.1007/978-3-319-46604-0_11

From On-Road to Off: Transfer Learning within a Deep Convolutional Neural Network for Segmentation and Classification of Off-Road Scenes

Holder, C.J.; Breckon, T.P.; Wei, X.

Authors

C.J. Holder

Professor Toby Breckon toby.breckon@durham.ac.uk
Professor

X. Wei

Contributors

Gang Hua
Editor

Hervé Jégou
Editor

Abstract

Real-time road-scene understanding is a challenging computer vision task with recent advances in convolutional neural networks (CNN) achieving results that notably surpass prior traditional feature driven approaches. Here, we take an existing CNN architecture, pre-trained for urban road-scene understanding, and retrain it towards the task of classifying off-road scenes, assessing the network performance within the training cycle. Within the paradigm of transfer learning we analyse the effects on CNN classification, by training and assessing varying levels of prior training on varying sub-sets of our off-road training data. For each of these configurations, we evaluate the network at multiple points during its training cycle, allowing us to analyse in depth exactly how the training process is affected by these variations. Finally, we compare this CNN to a more traditional approach using a feature-driven Support Vector Machine (SVM) classifier and demonstrate state-of-the-art results in this particularly challenging problem of off-road scene understanding.

Citation

Holder, C., Breckon, T., & Wei, X. (2016). From On-Road to Off: Transfer Learning within a Deep Convolutional Neural Network for Segmentation and Classification of Off-Road Scenes. In G. Hua, & H. Jégou (Eds.), Computer Vision – ECCV 2016 workshops : Amsterdam, The Netherlands, October 8-10 and 15-16, 2016. Proceedings. Part I (149-162). https://doi.org/10.1007/978-3-319-46604-0_11

Conference Name	European Conference on Computer Vision Workshops.
Conference Location	Amsterdam, The Netherlands
Acceptance Date	Jul 21, 2016
Online Publication Date	Sep 18, 2016
Publication Date	Sep 18, 2016
Deposit Date	Oct 3, 2016
Publicly Available Date	Sep 18, 2017
Publisher	Springer Verlag
Pages	149-162
Series Title	Lecture notes in computer science
Series Number	9913
Series ISSN	0302-9743,1611-3349
Book Title	Computer Vision – ECCV 2016 workshops : Amsterdam, The Netherlands, October 8-10 and 15-16, 2016. Proceedings. Part I.
ISBN	9783319466033
DOI	https://doi.org/10.1007/978-3-319-46604-0_11
Keywords	automotive vision, off-road semantic understanding, off-road computer vision, off-road scene labelling, terrain segmentation, terrain segments, transfer learning, convolutional neural networks, bag of visual words, deep learning
Public URL	https://durham-repository.worktribe.com/output/1150276
Related Public URLs	https://breckon.org/toby/publications/papers/holder16offroad.pdf