Investigation on the Relationship between Population Density and Satellite Image Features—a Deep Learning Based Approach

doi:10.11947/j.JGGS.2022.0405

Abstract

Abstract:

Timely and accurate population statistic data plays an important role in many fields. To illustrate the demographic characteristics, population density is a crucial factor in evaluating population data. With a dynamic regional migration in population, it is a challenging job to evaluate population density without a census-based survey. We present the approach to classify satellite images in different magnitudes in population density and execute the comparative experiment to discuss the factors that influence the identification to the images with the deep learning approach. In this paper, we use satellite imagery and community population density data. With convolutional neural networks, we evaluated the performance of CNN on population estimation with satellite images, found the features that are important in population estimation, and then perform the sensitive analysis.

Key words: population estimation; satellite imagery; convolutional neural network

Junxiang ZHANG, Peiran LI, Haoran ZHANG, Xuan SONG. Investigation on the Relationship between Population Density and Satellite Image Features—a Deep Learning Based Approach[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(4): 50-58.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Fig.5

Tab.2

Tab.3

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

References 29

[1]	ROBINSON C, HOHMAN F, DILKINA B. A deep learning approach for population estimation from satellite imagery[C]// Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities. Redondo Beach: ACM, 2017: 47-54.
[2]	HU Wenjie, PATEL J H, ROBERT Z A, et al. Mapping missing population in rural india: a deep learning approach with satellite imagery[C]// Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society. Honolulu: ACM, 2019: 353-359.
[3]	MENG Yao, LI Rui, JIANG Jie, et al. Urban street scale population estimation based on building information[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8): 1194-1200. DOI: 10.13203/j.whugis20190343. doi: 10.13203/j.whugis20190343
[4]	HEAD A, MANGUIN M, TRAN N, et al. Can human development be measured with satellite imagery?[C]// Proceedings of the Ninth International Conference on Information and Communication Technologies and Development. Lahore: ACM, 2017: 8. DOI: 10.1145/3136560.3136576. doi: 10.1145/3136560.3136576
[5]	HAN S, AHN D, PARK S, et al. Learning to score economic development from satellite imagery[C]// Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. Virtual Event: ACM, 2020: 2970-2979. DOI: 10.1145/3394486.3403347. doi: 10.1145/3394486.3403347
[6]	ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]// Proceedings of the 13th European Conference on Computer Vision. Zurich: Springer, 2014: 818-833.
[7]	FAN Dazhao, DONG Yang, ZHANG Yongsheng. Satellite image matching method based on deep convolutional neural network[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(2): 90-100. DOI: 10.11947/j.JGGS.2019.0210. doi: 10.11947/j.JGGS.2019.0210
[8]	GONG Jianya, JI Shunping. Photogrammetry and deep learning[J]. Journal of Geodesy and Geoinformation Science, 2018, 1(1): 1-15. DOI: 10.11947/j.JGGS.2018.0101. doi: 10.11947/j.JGGS.2018.0101
[9]	SOWMYA D R, SHENOY P D, VENUGOPAL K R. Remote sensing satellite image processing techniques for image classification: a comprehensive survey[J]. International Journal of Computer Applications, 2017, 161(11): 24-37.
[10]	JEAN N, BURKE M, XIE M, et al. Combining satellite imagery and machine learning to predict poverty[J]. Science, 2016: 353(6301), 790-794. doi: 10.1126/science.aaf7894 pmid: 27540167
[11]	WANG L, WANG S, ZHOU Y, et al. Mapping population density in China between 1990 and 2010 using remote sensing[J]. Remote sensing of environment, 2018, 210: 269-281. doi: 10.1016/j.rse.2018.03.007
[12]	ABBURU S, GOLLA S B. Satellite image classification methods and techniques: a review[J]. International journal of computer applications, 2015, 119(8).
[13]	JIN T, LI Z, LI T, et al. System design and analysis for improving geometric accuracy of high-resolution optical remote sensing satellite image[J]. Journal of Astronautics, 2013, 34(8): 1159-1165.
[14]	PELLETIER C, WEBB G I, PETITJEAN F. Temporal convolutional neural network for the classification of satellite image time series[J]. Remote Sensing, 2019, 11(5): 523. doi: 10.3390/rs11050523
[15]	CARLEER A P, DEBEIR O, WOLFF E. Assessment of very high spatial resolution satellite image segmentations[J]. Photogrammetric Engineering & Remote Sensing, 2005, 71(11): 1285-1294.
[16]	LU D, WENG Q. A survey of image classification methods and techniques for improving classification performance[J]. International Journal of Remote Sensing, 2007, 28(5): 823-870. doi: 10.1080/01431160600746456
[17]	NATH S S, MISHRA G, KAR J, et al. A survey of image classification methods and techniques[C]// Proceedings of 2014 International Conference on Control, Instrumentation,Communication and Computational Technologies. Kanyakumari: IEEE, 2014: 554-557.
[18]	PIRES DE LIMA R, MARFURT K. Convolutional neural network for remote-sensing scene classification: transfer learning analysis[J]. Remote Sensing, 2020, 12(1): 86. doi: 10.3390/rs12010086
[19]	LI P, ZHANG H, GUO Z, et al. Understanding rooftop PV panel semantic segmentation of satellite and aerial images for better using machine learning[J]. Advances in applied energy, 2021:4, 100057.
[20]	NILSSON M. Estimation of forest variables using satellite image data and airborne LiDAR[D]. Umea: Swedish University of Agricultural Sciences, 1997.
[21]	CHEN C, GONG W, HU Y, et al. Learning oriented region-based convolutional neural networks for building detection in satellite remote sensing images[J]. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, 42: 461.
[22]	HELMER E H, RUEFENACHT B. Cloud-free satellite image mosaics with regression trees and histogram matching[J]. Photogrammetric Engineering & Remote Sensing, 2005, 71(9): 1079-1089.
[23]	FU Gang, LIU Changjun, ZHOU Rong, et al. Classification for high resolution remote sensing imagery using a fully convolutional network[J]. Remote Sensing, 2017, 9(5): 498. doi: 10.3390/rs9050498
[24]	VAILAYA A, JAIN A, ZHANG H J. On image classification: city images vs. landscapes[J]. Pattern Recognition, 1998, 31(12): 1921-1935. doi: 10.1016/S0031-3203(98)00079-X
[25]	ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]// Proceedings of Computer Vision-ECCV 2014: 13th European Conference. Zurich, Switzerland: Springer International Publishing, 2014:818-833.
[26]	DOLLÁR P, TU Zhuowen, TAO Hai, et al. Feature mining for image classification[C]// Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007: 1-8.
[27]	HA I, KIM H, PARK S, et al. Image retrieval using BIM and features from pretrained VGG network for indoor localization[J]. Building and Environment, 2018, 140: 23-31. doi: 10.1016/j.buildenv.2018.05.026
[28]	CHAIB S, YAO Hongxun, GU Yanfeng, et al. Deep feature extraction and combination for remote sensing image classification based on pre-trained CNN models[C]// Proceedings of SPIE Ninth International Conference on Digital Image Processing (ICDIP 2017). Hong Kong, China: SPIE, 2017: 104203D.
[29]	SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. Computer Science, 2014.

Label	Number	Label	Number	Label	Number
0	2710	6	2613	12	188
1	1704	7	2189	13	71
2	1690	8	2036	14	30
3	1768	9	3387	15	10
4	2070	10	858	16	3
5	2580	11	323

Labels	Accuracy	Labels	Accuracy	Labels	Accuracy
0, 4, 8	0.7190	0, 6, 10	0.8333	1, 6, 11	0.8448
0, 4, 9	0.8138	0, 6, 11	0.8539	1, 7, 11	0.8078
0, 4, 10	0.7720	0, 7, 11	0.8726	2, 6, 10	0.7733
0, 4, 11	0.7725	1, 5, 9	0.8044	2, 6, 11	0.7589
0, 5, 9	0.8127	1, 5, 10	0.7714	2, 7, 11	0.8000
0, 5, 10	0.8153	1, 5, 11	0.8187	3, 7, 11	0.7687
0, 5, 11	0.8717	1, 6, 10	0.8097

Labels	Accuracy	Labels	Accuracy	Labels	Accuracy
0,3,6,9	0.6807	0,3,8,11	0.6869	1,4,7,10	0.5770
0,3,6,10	0.6646	0,4,7,10	0.6153	1,4,7,11	0.6142
0,3,6,11	0.6761	0,4,7,11	0.6907	1,4,8,11	0.3622
0,3,7,10	0.6312	0,4,8,11	0.6917	1,5,8,11	0.6920
0,3,7,11	0.6867	0,5,8,11	0.7083	2,5,8,11	0.6453