Leveraging Deep Convolutional Neural Network for Point Symbol Recognition in Scanned Topographic Maps

Bibliographic Data

ID22032480
AuthorsWenjun Huang (0000-0003-3614-106X, PLA Information Engineering University), Qun Sun (0000-0002-4372-8865, Institute of Geospatial Information, Information Engineering University, Zhengzhou 450001, China), Sun Qun (PLA Information Engineering University), Anzhu Yu (0000-0002-3332-9668, PLA Information Engineering University), Wenyue Guo (0000-0002-5538-7535, PLA Information Engineering University), Qing Xu (0000-0002-8243-6670, PLA Information Engineering University, corresponding author), Bowei Wen (PLA Information Engineering University), Li Xu (0000-0001-5665-4861, PLA Information Engineering University)
Year2023
Volume12
Issue3
Pages128
Publication date2023-03-16
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueISPRS International Journal of Geo-Information (JOURNAL)
Journal identifiersISSN: 2220-9964 • E-ISSN: 2220-9964
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/ijgi12030128
OpenAlexW4327699115
LanguageEN
Citations received2
References cited36

Point symbols on a scanned topographic map (STM) provide crucial geographic information. However, point symbol recognition entails high complexity and uncertainty owing to the stickiness of map elements and singularity of symbol structures. Therefore, extracting point symbols from STMs is challenging. Currently, point symbol recognition is performed primarily through pattern recognition methods that have low accuracy and efficiency. To address this problem, we investigated the potential of a deep learning-based method for point symbol recognition and proposed a deep convolutional neural network (DCNN)-based model for this task. We created point symbol datasets from different sources for training and prediction models. Within this framework, atrous spatial pyramid pooling (ASPP) was adopted to handle the recognition difficulty owing to the differences between point symbols and natural objects. To increase the positioning accuracy, the k-means++ clustering method was used to generate anchor boxes that were more suitable for our point symbol datasets. Additionally, to improve the generalization ability of the model, we designed two data augmentation methods to adapt to symbol recognition. Experiments demonstrated that the deep learning method considerably improved the recognition accuracy and efficiency compared with classical algorithms. The introduction of ASPP in the object detection algorithm resulted in higher mean average precision and intersection over union values, indicating a higher recognition accuracy. It is also demonstrated that data augmentation methods can alleviate the cross-domain problem and improve the rotation robustness. This study contributes to the development of algorithms and the evaluation of geographic elements extracted from STMs

Convolutional neural network · Deep learning · Pooling · 3D Surveying and Cultural Heritage · Computer Science · Mathematics · Remote Sensing and LiDAR Applications · Robotics and Sensor-Based Localization · Artificial Intelligence

Tools

Open DOIOpen Access