A Novel Road Segmentation Technique from Orthophotos Using Deep Convolutional Autoencoders

Publication Type:
Journal Article
Korean Journal of Remote Sensing, 2017, 33, (4), pp. 423-436
Issue Date:
Full metadata record
This paper presents a deep learning-based road segmentation framework from very high resolution orthophotos.The proposed method usesDeep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model’s parameters is explained whichwas conducted via grid search method.The modelwas trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show thatthe proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition,the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size 106 × 106 pixels, and segment road objects from similar size and resolution images in around 14 minutes.The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.
Please use this identifier to cite or link to this item: