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

被引:4
|
作者
Huang, Wenjun [1 ]
Sun, Qun [1 ]
Yu, Anzhu [1 ]
Guo, Wenyue [1 ]
Xu, Qing [1 ]
Wen, Bowei [1 ]
Xu, Li [1 ]
机构
[1] Informat Engn Univ, Inst Geospatial Informat, Zhengzhou 450001, Peoples R China
基金
中国国家自然科学基金;
关键词
point symbol recognition; scanned topographic map; deep learning; generalization ability; data augmentation; IMAGES;
D O I
10.3390/ijgi12030128
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页数:23
相关论文
共 50 条
  • [1] The Recognition of the Point Symbols in the Scanned Topographic Maps
    Miao, Qiguang
    Xu, Pengfei
    Li, Xuelong
    Song, Jianfeng
    Li, Weisheng
    Yang, Yun
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (06) : 2751 - 2766
  • [2] Toponym recognition in scanned color topographic maps
    Pouderoux, Joachim
    Gonzato, Jean-Christophe
    Pereira, Aurlien
    Guitton, Pascal
    ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2007, : 531 - 535
  • [3] Convolutional Neural Network Classification of Topographic Electroencephalographic Maps on Alcoholism
    Gimenez, Victor Borghi
    Dos Reis, Suelen Lorenzato
    de Souza, Fabio M. Simoes
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2023, 33 (05)
  • [4] Automatic vectorization of point symbols on archive maps using deep convolutional neural network
    Vassanyi, Gergely
    Gede, Matyas
    30TH INTERNATIONAL CARTOGRAPHIC CONFERENCE (ICC 2021), VOL 4, 2021,
  • [5] Recognition of Contour Line from Scanned Military Topographic Maps
    Chen, Hong
    Tang, Xiao'an
    Yang, Yaoming
    2008 INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION, VOLS 1-4, 2008, : 873 - 878
  • [6] Superpixel-Based Shallow Convolutional Neural Network (SSCNN) for Scanned Topographic Map Segmentation
    Liu, Tiange
    Miao, Qiguang
    Xu, Pengfei
    Zhang, Shihui
    REMOTE SENSING, 2020, 12 (20) : 1 - 21
  • [7] Deep convolutional neural network-based Leveraging Lion Swarm Optimizer for gesture recognition and classification
    Maashi, Mashael
    Al-Hagery, Mohammed Abdullah
    Rizwanullah, Mohammed
    Osman, Azza Elneil
    AIMS MATHEMATICS, 2024, 9 (04): : 9380 - 9393
  • [8] Emergence of topographic organization in a non-convolutional deep neural network
    Doerig, Adrien
    Krahmer, Bas
    Bosch, Victoria
    Kietzmann, Tim C.
    PERCEPTION, 2022, 51 : 74 - 75
  • [9] A Review of Image Recognition with Deep Convolutional Neural Network
    Liu, Qing
    Zhang, Ningyu
    Yang, Wenzhu
    Wang, Sile
    Cui, Zhenchao
    Chen, Xiangyang
    Chen, Liping
    INTELLIGENT COMPUTING THEORIES AND APPLICATION, ICIC 2017, PT I, 2017, 10361 : 69 - 80
  • [10] Deep Convolutional Neural Network for Arabic Speech Recognition
    Amari, Rafik
    Noubigh, Zouhaira
    Zrigui, Salah
    Berchech, Dhaou
    Nicolas, Henri
    Zrigui, Mounir
    COMPUTATIONAL COLLECTIVE INTELLIGENCE, ICCCI 2022, 2022, 13501 : 120 - 134