Multi-Class Pixel Certainty Active Learning Model for Classification of Land Cover Classes Using Hyperspectral Imagery

被引:17
|
作者
Pradhan, Monoj Kumar [2 ]
Gangadharan, Syam Machinathu Parambil [3 ]
Chaudhary, Jitendra Kumar [4 ]
Singh, Jagendra [5 ]
Khan, Arfat Ahmad [6 ]
Haq, Mohd Anul [7 ]
Alhussen, Ahmed [8 ]
Wechtaisong, Chitapong [9 ]
Imran, Hazra [10 ]
Alzamil, Zamil S. [7 ]
Pattanayak, Himansu Sekhar [5 ]
Yadav, Chandra Shekhar [1 ]
机构
[1] Jawaharlal Nehru Univ, Sch Comp & Syst Sci, New Delhi 110062, India
[2] Indira Gandhi Krishi Vishwavidyalaya, Dept Agril Stat, Raipur 492012, Madhya Pradesh, India
[3] Gen Mills, Minneapolis, MN 55305 USA
[4] Graph Era Hill Univ, Sch Comp, Bhimtal 263156, India
[5] Bennett Univ, Sch Comp Sci Engn & Technol, Greater Noida 203206, India
[6] Khon Kaen Univ, Coll Comp, Khon Kaen 40000, Thailand
[7] Majmaah Univ, Coll Comp & Informat Sci, Dept Comp Sci, Al Majmaah 11952, Saudi Arabia
[8] Majmaah Univ, Coll Comp & Informat Sci, Dept Comp Engn, Al Majmaah 11952, Saudi Arabia
[9] Suranaree Univ Technol, Sch Telecommun Engn, Nakhon Ratchasima 30000, Thailand
[10] Simon Fraser Univ, Sch Comp Sci, Burnaby, BC V5A 1S6, Canada
关键词
active learning; heuristics; hyperspectral images; multi-class classification; relevance vector machine; remote sensing; spectral-spatial classification; SPECTRAL-SPATIAL CLASSIFICATION; SUPPORT VECTOR MACHINES; FEATURE-EXTRACTION; FRAMEWORK;
D O I
10.3390/electronics11172799
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
An accurate identification of objects from the acquisition system depends on the clear segmentation and classification of remote sensing images. With the limited financial resources and the high intra-class variations, the earlier proposed algorithms failed to handle the sub-optimal dataset. The building of an efficient training set iteratively in active learning (AL) approaches improves classification performance. The heuristics-based AL provides better results with the inheritance of contextual information and the robustness to noise variations. The uncertainty exists pixel variations make the heuristics-based AL fail to handle the remote sensing image classification. Previously, we focused on the extraction of clear textural pattern information by using the extended differential pattern-based relevance vector machine (EDP-AL). This paper extends that work into the novel pixel-certainty activity learning (PCAL) based on the information about textural patterns obtained from the extended differential pattern (EDP). Initially, distributed intensity filtering (DIF) is used to eliminate noise from the image, and then histogram equalization (HE) is used to improve the image quality. The EDP is used to merge and classify different labels for each image sample, and this algorithm expresses the textural information. The PCAL technique is used to classify the HSI patterns that are important in remote sensing applications using this pattern collection. Pavia University and Indian Pines (IP) are the datasets used to validate the performance of the proposed PCAL (PU). The ability of PCAL to accurately categorize land cover types is demonstrated by a comparison of the proposed PCAL with existing algorithms in terms of classification accuracy and the Kappa coefficient.
引用
收藏
页数:19
相关论文
共 50 条
  • [1] A novel multi-class land use/land cover classification using deep kernel attention transformer for hyperspectral images
    Ganji Tejasree
    Agilandeeswari L
    [J]. Earth Science Informatics, 2024, 17 : 593 - 616
  • [2] A novel multi-class land use/land cover classification using deep kernel attention transformer for hyperspectral images
    Tejasree, Ganji
    Agilandeeswari, L.
    [J]. EARTH SCIENCE INFORMATICS, 2024, 17 (01) : 593 - 616
  • [3] Hyperspectral Image Classification Using Multi-class SLEX Model
    Huang, Hsiao-Yun
    Liu, Hsiang-Chuan
    Kuo, Bor-Chen
    Hsieh, Tier-Yu
    [J]. 2006 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-8, 2006, : 553 - +
  • [4] Research on the Optimization of Multi-Class Land Cover Classification Using Deep Learning with Multispectral Images
    Li, Yichuan
    Yu, Junchuan
    Wang, Ming
    Xie, Minying
    Xi, Laidian
    Pang, Yunxuan
    Hou, Changhong
    [J]. LAND, 2024, 13 (05)
  • [5] An active learning algorithm for multi-class classification
    Liu, Dongjiang
    Liu, Yanbi
    [J]. PATTERN ANALYSIS AND APPLICATIONS, 2019, 22 (03) : 1051 - 1063
  • [6] Multi-class classification in nonparametric active learning
    Njike, Boris Ndjia
    Siebert, Xavier
    [J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [7] Optimized extreme learning machine for urban land cover classification using hyperspectral imagery
    Hongjun Su
    Shufang Tian
    Yue Cai
    Yehua Sheng
    Chen Chen
    Maryam Najafian
    [J]. Frontiers of Earth Science, 2017, 11 : 765 - 773
  • [8] Optimized extreme learning machine for urban land cover classification using hyperspectral imagery
    Su, Hongjun
    Tian, Shufang
    Cai, Yue
    Sheng, Yehua
    Chen, Chen
    Najafian, Maryam
    [J]. FRONTIERS OF EARTH SCIENCE, 2017, 11 (04) : 765 - 773
  • [9] Multi-Class Active Learning for Image Classification
    Joshi, Ajay J.
    Porikli, Fatih
    Papanikolopoulos, Nikolaos
    [J]. CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4, 2009, : 2364 - +
  • [10] An active learning algorithm for multi-class classification
    Dongjiang Liu
    Yanbi Liu
    [J]. Pattern Analysis and Applications, 2019, 22 : 1051 - 1063