Year-end Sale % OFF 
Abstract
The identification of overpass structures in road networks has great significance for multi-scale modeling of roads, congestion analysis, and vehicle navigation. The traditional vector-based methods identify overpasses by the methodologies coming from computational geometry and graph theory, and they overly rely on the artificially designed features and have poor adaptability to complex scenes. This paper presents a novel method of identifying overpasses based on a target detection model (Faster-RCNN). This method utilizes raster representation of vector data and convolutional neural networks (CNNs) to learn task adaptive features from raster data, then identifies the location of an overpass by a Region Proposal network (RPN). The contribution of this paper is: (1) An overpass labelling geodatabase (OLGDB) for the OpenStreetMap (OSM) road network data of six typical cities in China is established; (2) Three different CNNs (ZF-net, VGG-16, Inception-ResNet V2) are integrated into Faster-RCNN and evaluated by accuracy performance; (3) The optimal combination of learning rate and batchsize is determined by fine-tuning; and (4) Five geometric metrics (perimeter, area, squareness, circularity, and W/L) are synthetized into image bands to enhance the training data, and their contribution to the overpass identification task is determined. The experimental results have shown that the proposed method has good accuracy performance (around 90%), and could be improved with the expansion of OLGDB and switching to more sophisticated target detection models. The deep learning target detection model has great application potential in large-scale road network pattern recognition, it can task-adaptively learn road structure features and easily extend to other road network patterns.
Highlights
As the framework of a city, road networks have attracted the concern of scholars in all aspects of urban research and are regarded as one of the five major elements in city construction by Lynch (1960) [1]
In order to handle the location problem mentioned above, this paper aims to identify overpasses in road networks using a target detection model of deep learning (Faster-Region Convolutional neural network, Faster-RCNN)
The Region Proposal network (RPN) network shares the same group of convolutional layers with Fast-RCNN
Summary
As the framework of a city, road networks have attracted the concern of scholars in all aspects of urban research and are regarded as one of the five major elements in city construction by Lynch (1960) [1]. In order to identify overpasses in actual data more accurately, Qian and He proposed to solve the overpass classification problem by a machine learning method in 2018 [12] In their method, a convolutional neural network (CNN) was trained with images containing overpasses to classify them into different types. Designed feature items were not needed, instead, road data was converted into raster data as the training data for the CNN model Their method combines vector data and raster images, and uses the neural network learn the fuzzy characteristics of overpasses, and classifies the complex overpass structures in OSM. Feature items are not needed to be given manually, and the uncertainty of the result is reduced by the self-learning mechanism His method can only be used to classified the types of overpasses and cannot be used to identify the location of overpasses in a large range of road networks.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
