Rethinking labelling in road segmentation
Authors:
- 26 April 2019
- journal article
- research article
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 40 (22) , 8359-8378
Abstract
Deep models are extremely data hungry. Their success is being driven by the availability of large amounts of data for training. For semantic segmentation tasks on aerial and satellite imagery, a major dilemma at present is that it still relies heavily on manual labelling of data. Among these tasks, the semantic segmentation of road is special since it is possible to use auxiliary data, such as GPS track data, to automatically label data. For a better understanding of this possibility, this paper proposes to rethink some basic issues of labelling approaches for roads. We experimentally investigated the unavoidable class imbalance problem in road segmentation tasks through simulated and real datasets and quantitatively show that class imbalance has a serious detrimental impact on deep model’s generalization performance. We also observed that the detrimental impact even outweighs the benefits of strictly annotating roads – expanding road labels can give deep networks better segmentation accuracy, even though the segmentation location is no longer the edge of the road. We think this is because the impact of class imbalance is much overwhelming than the sensitivity of DNN on the edges of real roads. This finding is valuable for supporting the use of centreline-based approaches in place of edge-based approaches in some applications for better cost-effective solutions. We proposed a guided Random Sample Consensus (RANSAC) algorithm to determine the optimal expansion ratio of road label. On these bases, we further proposed a general framework to combine two networks to achieve better performance than the state-of-the-art performance of using alone. We attribute this to the alleviation of the class imbalance problem because simply cascading the two networks does not achieve the purpose of improving accuracy in our experiments. We believe that this work is enlightening for studies of road segmentation.Keywords
This publication has 28 references indexed in Scilit:
- Explaining nonlinear classification decisions with deep Taylor decompositionPattern Recognition, 2017
- Towards better exploiting convolutional neural networks for remote sensing scene classificationPattern Recognition, 2017
- Convolutional Neural Networks for Large-Scale Remote-Sensing Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2016
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- Building and road detection from large aerial imagery2015
- Learning to Detect Roads in High-Resolution Aerial Images2010
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- OpenStreetMap: User-Generated Street MapsIEEE Pervasive Computing, 2008