Education, Science, Technology, Innovation and Life
Open Access
Sign In

Recognition and Extraction of High-Resolution Satellite Remote Sensing Image Buildings Based on Deep Learning

Download as PDF

DOI: 10.23977/jipta.2023.060104 | Downloads: 9 | Views: 213


Xuebo Yan 1, Shiwei Chen 1, Gang Lei 2


1 Fujian University of Technology, Fuzhou, Fujian, China
2 Fujian Guotai Construction Co., Ltd, Sanming, Fujian, China

Corresponding Author

Xuebo Yan


As the technology applications continue to emerge and create innovations, building identification and extraction by high-resolution satellite remote sensing image technology has been a challenge for scholars to overcome. And many scholars have achieved some success in this field. Space information is clear, shadows are disorderly and details are not obvious in satellite remote sensing image technology. The current remote sensing processing technology usually can not meet the requirements of high-resolution remote sensing image detail processing. This paper uses an object-oriented analysis technology based on deep learning to solve this problem. It can make full use of some characteristics of the image. Compared with the current remote sensing image processing technology, its most important feature is that it can process the smallest unit, which is composed of some similar attributes, rather than a single pixel. Finally, the identification and extraction of buildings are detected. In this paper, we compare the multi-scale segmentation algorithm and mean shift segmentation algorithm. These two methods can obtain more accurate object outlines derived at high resolution from the remote sensing satellite pictures. Results of experiments show this paper that the proposed method has better effect on the recognition as well as detection and extraction of buildings. The accuracy of recognizing as well as selecting buildings from the high definition remote sensing satellite pictures is 89.7%.


Deep Learning, Image Recognition, High-Resolution Satellite Remote Sensing Images, Target Detection


Xuebo Yan, Shiwei Chen, Gang Lei, Recognition and Extraction of High-Resolution Satellite Remote Sensing Image Buildings Based on Deep Learning. Journal of Image Processing Theory and Applications (2023) Vol. 6: 41-53. DOI:


[1] Tskhay K O, Rule N O. People Automatically Extract Infants' Sex from Faces[J]. Journal of Nonverbal Behavior, 2016, 40(4):1-8.
[2] Pavol Marák, Alexander Hambalík. Fingerprint Recognition System Using Artificial Neural Network as Feature Extractor: Design and Performance Evaluation[J]. Nephron Clinical Practice, 2016, 67(1):117-134.
[3] Ji S, Wei S, Meng L. Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57(1):574-586.
[4] Li C, Zhang B, Hu H, et al. Enhanced Bird Detection from Low-Resolution Aerial Image Using Deep Neural Networks[J]. Neural Processing Letters, 2019, 49(3):1021-1039.
[5] Gudius P, Kurasova O, Darulis V, et al. Deep learning-based object recognition in multispectral satellite imagery for real-time applications[J]. Machine Vision and Applications, 2021, 32(4):1-14.
[6] Hao X, Zhang G, Ma S. Deep Learning[J]. International Journal of Semantic Computing, 2016, 10(03):417-439.
[7] Litjens, Geert, Kooi, Thijs, Bejnordi, Babak Ehteshami. A Survey on Deep Learning in Medical Image Analysis[J]. Medical Image Analysis, 2017, 42(9):60-88.
[8] Chen Y, Lin Z, Zhao X, et al. Deep Learning-Based Classification of Hyperspectral Data[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2017, 7(6):2094-2107.
[9] FH Wagner, Ferreira M P, Sanchez A, et al. Individual tree crown delineation in a highly diverse tropical forest using very high resolution satellite images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 145PB(NOV.):362-377.
[10] Moeskops P, Viergever M A, Adriënne M. Mendrik, et al. Automatic Segmentation of MR Brain Images With a Convolutional Neural Network[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1252-1261.
[11] Kang E, Min J, Ye J C. A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction[J]. Medical Physics, 2017, 44(10):e360.
[12] Poria S, Cambria E, Gelbukh A. Aspect extraction for opinion mining with a deep convolutional neural network[J]. Knowledge-Based Systems, 2016, 108(sep.15):42-49.
[13] Ma L. Research on distance education image correction based on digital image processing technology[J]. EURASIP Journal on Image and Video Processing, 2019, 2019(1):1-9.
[14] Corr D, Accardi M, Graham-Brady L, et al. Digital image correlation analysis of interfacial debonding properties and fracture behavior in concrete[J]. Engineering Fracture Mechanics, 2016, 74(1-2):109-121.
[15] Anton, Kuzmin, Lauri, et al. Automatic Segment-Level Tree Species Recognition Using High Resolution Aerial Winter Imagery[J]. European Journal of Remote Sensing, 2017, 49(1):239-259.
[16] Bhuiyan M Z A, Wang G, Vasilakos A V. Local Area Prediction-Based Mobile Target Tracking in Wireless Sensor Networks[J]. Computers IEEE Transactions on, 2015, 64(7):1968-1982.
[17] She J, Wang F, Zhou J. A Novel Sensor Selection and Power Allocation Algorithm for Multiple-Target Tracking in an LPI Radar Network[J]. Sensors, 2016, 16(12):2193.
[18] Nayak V, Karaya R R. Target Tracking by a Quadrotor Using Proximity Sensor Fusion Based on a Sigmoid Function[J]. IFAC-PapersOnLine, 2018, 51( 1):154-159.
[19] Parodi M, Storace M, Regazzoni C. Circuit realization of Markov random fields for analog image processing[J]. International Journal of Circuit Theory and Applications, 2015, 26(5):477-498.
[20] Segl K, Kaufmann H. Detection of small objects from high-resolution panchromatic satellite imagery based on supervised image segmentation[J]. Geoence & Remote Sensing IEEE Transactions on, 2017, 39(9):2080-2083.
[21] Liu Q, Hang R, Song H, et al. Learning Multiscale Deep Features for High-Resolution Satellite Image Scene Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(1):117-126.
[22] Rich R L, Frelich L, Reich P B, et al. Detecting wind disturbance severity and canopy heterogeneity in boreal forest by coupling high-spatial resolution satellite imagery and field data[J]. Remote Sensing of Environment, 2016, 114(2):299-308.
[23] Zhang L, Shi Z, Wu J. A Hierarchical Oil Tank Detector With Deep Surrounding Features for High-Resolution Optical Satellite Imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 8(10):1-15.
[24] Zeng D, Zhang T, Fang R, et al. Neighborhood Geometry Based Feature Matching for Geostationary Satellite Remote Sensing Image[J]. Neurocomputing, 2016, 236(MAY2):65-72.
[25] Kaynar K, Sivrikaya F. Distributed Attack Graph Generation[J]. IEEE Transactions on Dependable & Secure Computing, 2016, 13(5):519-532.
[26] Kim, Miae, Lee, et al. Deep learning-based monitoring of overshooting cloud tops from geostationary satellite data[J]. GIScience & Remote Sensing, 2018, 55(5):763-792.
[27] Feng Y, Wang L, Zhang M. A multi-scale target detection method for optical remote sensing images[J]. Multimedia Tools and Applications, 2019, 78(7):8751-8766.
[28] Liu Y, Yang L, Chen F S. Multispectral registration method based on stellar trajectory fitting[J]. Optical and quantum electronics, 2018, 50(4):189.1-189.10.
[29] Jasiewicz J, Stepinski T, Niesterowicz J. Multi-scale segmentation algorithm for pattern-based partitioning of large categorical rasters[J]. Computers & geoences, 2018, 118(SEP.):122-130.
[30] Sun S, Song H, He D, et al. An adaptive segmentation method combining MSRCR and mean shift algorithm with K-means correction of green apples in natural environment[J]. Information Processing in Agriculture, 2019, 6(2):200-215.

Downloads: 966
Visits: 85804

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.