Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine

Abstract

Extracting road networks from very-high-resolution (VHR) aerial and satellite imagery has been a long-standing problem. In this article, a neural-dynamic tracking framework is proposed to extract road networks based on deep convolutional neural networks (DNN) and a finite state machine (FSM). Inspired by autonomous mobile systems, the authors train a DNN to recognize the pattern of input data, which is an image patch extracted in a detection window centred at the current location of the tracker. The pattern is predefined according to the environment and associated with the states in the FSM. A vector-guided sampling method is proposed to generate the training data set for the DNN, which extracts massive image-direction pairs from the imagery and existing vector road maps. In the tracking procedure, the size of the detection window is determined by a fusion strategy and the extracted image patches represent the orientation features of the road (local environment) that can be recognized by the trained DNN. The reactive unit in FSM associates states with behaviours of the tracker while continually modifying the orientation to follow the road and generating a sequence of states and locations. In this way, our framework combines the DNN and FSM. DNN acts as a key component to recognize patterns from a complex and changing environment; FSM translates the recognized patterns to states and controls the behaviour of the tracker. The results illustrate that our approach is more accurate and efficient than the traditional ones.

View correction statement:

Corrigendum

Acknowledgements

The authors would like to acknowledge the provision of the Downtown Toronto data set by Optech Inc., First Base Solutions Inc., GeoICT Lab at York University, and ISPRS WG III/4. The Vaihingen data set was provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) (Jacobsen et al. 2010).

Additional information

Funding

This work was supported by the High Resolution Earth Observation System of Major National Science and Technology projects [grant numbers 06-Y30B04-9002-13/15] and the National High Technology Research and Development Program of China [grant numbers 2012AA12A401, 2013AA12A403].