Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification

被引:1
|
作者
Tang, Jiechen [1 ]
Tong, Hengjian [1 ]
Tong, Fei [2 ]
Zhang, Yun [2 ]
Chen, Weitao [1 ]
机构
[1] China Univ Geosci, Sch Comp Sci, 68 Jincheng St, East Lake New Technol Dev Zone, Wuhan 430078, Peoples R China
[2] Univ New Brunswick, Dept Geodesy & Geomatics Engn, 15 Dineen Dr, Fredericton, NB E3B 5A3, Canada
基金
中国国家自然科学基金;
关键词
high spatial resolution image; superpixel-based image classification; active learning; supervised learning; label spread; SEGMENTATION;
D O I
10.3390/rs15030715
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Superpixel-based classification using Active Learning (AL) has shown great potential in high spatial resolution remote sensing image classification tasks. However, in existing superpixel-based classification models using AL, the expert labeling information is only used on the selected informative superpixel while its neighboring superpixels are ignored. Actually, as most superpixels are over-segmented, a ground object always contains multiple superpixels. Thus, the center superpixel tends to have the same label as its neighboring superpixels. In this paper, to make full use of the expert labeling information, a Similar Neighboring Superpixels Search and Labeling (SNSSL) method was proposed and used in the AL process. Firstly, we identify superpixels with certain categories and uncertain superpixels by supervised learning. Secondly, we use the active learning method to process those uncertain superpixels. In each round of AL, the expert labeling information is not only used to enrich the training set but also used to label the similar neighboring superpixels. Similar neighboring superpixels are determined by computing the similarity of two superpixels according to CIELAB Dominant Colors distance, Correlation distance, Angular Second Moment distance and Contrast distance. The final classification map is composed of the supervised learning classification map and the active learning with SNSSL classification map. To demonstrate the performance of the proposed SNSSL method, the experiments were conducted on images from two benchmark high spatial resolution remote sensing datasets. The experiment shows that overall accuracy, average accuracy and kappa coefficients of the classification using the SNSSL have been improved obviously compared with the classification without the SNSSL.
引用
收藏
页数:17
相关论文
共 50 条
  • [21] Spatial contextual Gaussian process learning for remote-sensing image classification
    Hassouna, Houda
    Melgani, Farid
    Mokhtari, Zouhir
    REMOTE SENSING LETTERS, 2015, 6 (07) : 519 - 528
  • [22] WIDE CONTEXTUAL RESIDUAL NETWORK WITH ACTIVE LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION
    Liu, Shengjie
    Luo, Haowen
    Tu, Ying
    He, Zhi
    Li, Jun
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 7145 - 7148
  • [23] Active learning for training sample selection in remote sensing image classification using spatial information
    Lu, Qikai
    Ma, Yong
    Xia, Gui-Song
    REMOTE SENSING LETTERS, 2017, 8 (12) : 1210 - 1219
  • [24] A Hybrid Classification Method for High Spatial Resolution Remote Sensing Image
    Wang, Ke
    2019 IEEE 2ND INTERNATIONAL CONFERENCE ON ELECTRONICS AND COMMUNICATION ENGINEERING (ICECE 2019), 2019, : 62 - 65
  • [25] Brain MR Image Classification Using Superpixel-Based Deep Transfer Learning
    Behera, Tanmay Kumar
    Khan, Muhammad Attique
    Bakshi, Sambit
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (03) : 1218 - 1227
  • [26] Superpixel-Based Difference Representation Learning for Change Detection in Multispectral Remote Sensing Images
    Gong, Maoguo
    Zhan, Tao
    Zhang, Puzhao
    Miao, Qiguang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017, 55 (05): : 2658 - 2673
  • [27] Spectral-Spatial Hyperspectral Image Classification Using Superpixel-based Spatial Pyramid Representation
    Fan, Jiayuan
    Tan, Hui Li
    Toomik, Maria
    Lu, Shijian
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII, 2016, 10004
  • [28] HIGH RESOLUTION REMOTE SENSING IMAGE CLASSIFICATION OF ANCIENT VILLAGES BASED ON DEEP LEARNING
    Chen, Fei
    Fang, Jun
    Hu, Jun
    FRESENIUS ENVIRONMENTAL BULLETIN, 2021, 30 (04): : 3310 - 3324
  • [29] Superpixel-Based Active Learning and Online Feature Importance Learning for Hyperspectral Image Analysis
    Guo, Jielian
    Zhou, Xiong
    Li, Jun
    Plaza, Antonio
    Prasad, Saurabh
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2017, 10 (01) : 347 - 359
  • [30] Land cover classification based on the PSPNet and superpixel segmentation methods with high spatial resolution multispectral remote sensing imagery
    Yuan, Xiaolei
    Chen, Zeqiang
    Chen, Nengcheng
    Gong, Jianya
    JOURNAL OF APPLIED REMOTE SENSING, 2021, 15 (03)