A complex junction recognition method based on GoogLeNet model. Issue 6 (7th September 2020)

• Record Type: Journal Article
• Authors: Li, Chengming; Zhang, Honggang; Wu, Pengda; Yin, Yong; Liu, Sichao
• Is Part Of: Transactions in GIS. Volume 24:Issue 6(2020)
• Page Start: 1756
• Page End: 1778
• Publication Date: 2020-09-07
• Subjects: Geographic information systems -- Periodicals; 910.285
• DOI: 10.1111/tgis.12681
• Languages: English
• ISSNs: 1361-1682

Abstract

Abstract: Complex junctions are typical microstructures in large‐scale road networks with intricate structures and varied morphologies. It is a challenge to identify junctions in map generalization and car navigation tasks accurately. Generally, traditional recognition methods rely on low‐level characteristics of manual design, such as parallelism and symmetry. In recent years, preliminary studies using deep learning‐based recognition methods were conducted. However, only a few junction types can be recognized by existing methods, and these methods cannot effectively identify junctions with irregular shapes and numerous interference sections. Hence, this article proposes a complex junction recognition method based on the GoogLeNet model. First, the Delaunay triangulation clustering algorithm was used to automatically identify the center point and spatial range of training samples for complex junctions. Second, vector training samples were selected from OpenStreetMap (OSM) data of 39 cities across China, and the samples were then augmented through simplification, rotation, and mirroring. Finally, the vector sample data were transformed into raster images, and the GoogLeNet model was trained to learn the high‐level fuzzy characteristics. Experiments based on OSM data from Tianjin city, China, revealed that compared with state‐of‐the‐art methods, the proposed method effectively identified more types of complex junctions and achieved a significantly higher identification accuracy. Furthermore, the proposed method has strong generalizability and anti‐interference capability.