Application of Object-Oriented Median Absolute Deviation Method to Building Extraction

被引：1
|
作者：
Gong Xunqiang [1 ,2 ]
Liu Xinglei [1 ,3 ]
Lu Tieding [1 ]
Chen Zhigao [1 ]
机构：
[1] East China Univ Technol, Fac Geomat, Nanchang 330013, Jiangxi, Peoples R China
[2] East China Univ Technol, Res Ctr Ecol Civilizat Construct Syst Jiangxi Pro, Nanchang 330013, Jiangxi, Peoples R China
[3] Xian Inst Geotech Invest & Surveying Mapping, Xian 710054, Shaanxi, Peoples R China
来源：
LASER & OPTOELECTRONICS PROGRESS | 2021年 / 58卷 / 12期
关键词：
measurement; remote sensing image; spectral information; morphological building index; median absolute deviation; training samples; CLASSIFICATION; INDEX;
D O I：
10.3788/LOP202158.1212005
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Buildings are extremely important artificial feature objects. Extracting buildings can provide technical support for urban planning, population estimation, and landscape analysis. Object-oriented classification is an effective method for extracting ground objects and has been widely used in the extraction of building information. The object-oriented morphological building index method has good practicability, but the effect of extracting sparse buildings still needs to be improved. To solve this problem, the median absolute deviation is applied to the object-oriented building extraction, and the two situations of dense and sparse buildings are analyzed. Precision, recall, and F-1 score are used to evaluate the extraction results. Experimental results show that the object-oriented median absolute deviation method extracts sparse buildings significantly better than the object-oriented classification and object-oriented morphological building index methods.
引用
收藏
页数：6
相关论文
共 22 条
  • [1] Extraction of Buildings in Urban Area for Surface Area Assessment from Satellite Imagery based on Morphological Building Index using SVM Classifier
    Avudaiammal, R.
    Elaveni, P.
    Selvan, Shirley
    Rajangam, Vijayarajan
    [J]. JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING, 2020, 48 (09) : 1325 - 1344
  • [2] Buschenfeld T, 2012, ISPRS ANN PHOTOGRAMM, VI-7, P117
  • [3] Chellasamy M., 2015, IEEE J SELECTED TOPI, V8, P10
  • [4] Shape Sparse Representation for Joint Object Classification and Segmentation
    Chen, Fei
    Yu, Huimin
    Hu, Roland
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (03) : 992 - 1004
  • [5] Chen H., 2019, BULLETIN SURVEYING M, V9, P34
  • [6] Status of land cover classification accuracy assessment
    Foody, GM
    [J]. REMOTE SENSING OF ENVIRONMENT, 2002, 80 (01) : 185 - 201
  • [7] Gong X Q, 2019, JOURNAL INDIANS SOC, V474, P647
  • [8] [龚循强 Gong Xunqiang], 2020, [激光与光电子学进展, Laser & Optoelectronics Progress], V57
  • [9] INFLUENCE CURVE AND ITS ROLE IN ROBUST ESTIMATION
    HAMPEL, FR
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1974, 69 (346) : 383 - 393
  • [10] A novel building change index for automatic building change detection from high-resolution remote sensing imagery
    Huang, Xin
    Zhu, Tingting
    Zhang, Liangpei
    Tang, Yuqi
    [J]. REMOTE SENSING LETTERS, 2014, 5 (08) : 713 - 722
123