Heuristic sample learning for complex urban scenes: Application to urban functional-zone mapping with VHR images and POI data

Abstract Urban functional zones are basic units of urban planning and resource allocation, and contribute to a wide range of urban studies and investigations. Existing studies on functional-zone mapping with very-high-resolution (VHR) satellite images focused much on feature representations and classification techniques, but ignored zone sampling which however was fundamental to automatic zone classifications. Functional-zone sampling is much complicated and can hardly be resolved by classical sampling methods, as functional zones are complex urban scenes which consist of heterogeneous land covers and have highly abstract categories. To resolve the issue, this study presents a novel sampling paradigm, i.e., heuristic sample learning (HSL). It first proposes a sparse topic model to select representative functional zones, then uses deep forest to select confusing zones, and finally embraces Chinese restaurant process to label these selected zones. The presented method collects both representative and confusing zone samples and identifies their categories accurately, which makes the functional-zone classification process robust and the classification results accurate. Experiments conducted in Beijing indicate that HSL is effective and efficient for functional-zone sampling and classifications. Compared to traditional manual sampling, HSL reduces the time cost by 55% and improves the classification accuracy by 11.3% on average; furthermore, HSL can reduce the variation in sampling and classification results caused by different proficiency of operators. Accordingly, HSL significantly contributes to functional-zone mapping and plays an important role in urban studies.

[1]  Xiaoping Liu,et al.  Sensing spatial distribution of urban land use by integrating points-of-interest and Google Word2Vec model , 2017, Int. J. Geogr. Inf. Sci..

[2]  Bo Du,et al.  Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Shihong Du,et al.  Integrating bottom-up classification and top-down feedback for improving urban land-cover and functional-zone mapping , 2018, Remote Sensing of Environment.

[4]  Shihong Du,et al.  Learning selfhood scales for urban land cover mapping with very-high-resolution satellite images , 2016 .

[5]  Shihong Du,et al.  A Linear Dirichlet Mixture Model for decomposing scenes: Application to analyzing urban functional zonings , 2015 .

[6]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[7]  Peter I. Frazier,et al.  Distance dependent Chinese restaurant processes , 2009, ICML.

[8]  T. Oke,et al.  Local Climate Zones for Urban Temperature Studies , 2012 .

[9]  Hyun Bang Shin,et al.  Residential Redevelopment and the Entrepreneurial Local State: The Implications of Beijing’s Shifting Emphasis on Urban Redevelopment Policies , 2009 .

[10]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[11]  Sean J V Lafontaine,et al.  A direct observation method for auditing large urban centers using stratified sampling, mobile GIS technology and virtual environments , 2017, International Journal of Health Geographics.

[12]  Shihong Du,et al.  Do Urban Functional Zones Affect Land Surface Temperature Differently? A Case Study of Beijing, China , 2019, Remote. Sens..

[13]  Shihong Du,et al.  Semantic and Spatial Co-Occurrence Analysis on Object Pairs for Urban Scene Classification , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[15]  T. Esch,et al.  Urban structure type characterization using hyperspectral remote sensing and height information , 2012 .

[16]  Yi Wu,et al.  Sampling Strategies for Active Learning in Personal Photo Retrieval , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[17]  Wanqing Li,et al.  Semantic and Spatial Content Fusion for Scene Recognition , 2015 .

[18]  Mihai Datcu,et al.  Semantic Annotation of Satellite Images Using Latent Dirichlet Allocation , 2010, IEEE Geoscience and Remote Sensing Letters.

[19]  D. Angluin Queries and Concept Learning , 1988 .

[20]  Lei Ma,et al.  Active learning for object-based image classification using predefined training objects , 2018 .

[21]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[22]  Z. Pengjun,et al.  Transportation implications of the metropolitan spatial planning in megacity Beijing , 2009 .

[23]  M. Huber,et al.  Testing exclusion restrictions and additive separability in sample selection models , 2014 .

[24]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[25]  Brian P. Salmon,et al.  Multiview Deep Learning for Land-Use Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[26]  William J. Emery,et al.  Active Learning Methods for Remote Sensing Image Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[28]  Edward R. Dougherty,et al.  Effect of separate sampling on classification accuracy , 2014, Bioinform..

[29]  David M. Mount,et al.  A Fast Implementation of the Isodata Clustering Algorithm , 2007, Int. J. Comput. Geom. Appl..

[30]  Shihong Du,et al.  Multiscale Geoscene Segmentation for Extracting Urban Functional Zones from VHR Satellite Images , 2018, Remote. Sens..

[31]  T. Moon The expectation-maximization algorithm , 1996, IEEE Signal Process. Mag..

[32]  Liangpei Zhang,et al.  Automatic Labelling and Selection of Training Samples for High-Resolution Remote Sensing Image Classification over Urban Areas , 2015, Remote. Sens..

[33]  Shihong Du,et al.  Hierarchical semantic cognition for urban functional zones with VHR satellite images and POI data , 2017 .

[34]  Yang Yu,et al.  Spectrum of Variable-Random Trees , 2008, J. Artif. Intell. Res..

[35]  Bo Du,et al.  Unsupervised Scene Change Detection via Latent Dirichlet Allocation and Multivariate Alteration Detection , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  Shihong Du,et al.  Semantic classification of urban buildings combining VHR image and GIS data: An improved random forest approach , 2015 .

[37]  Ruimao Zhang,et al.  Cost-Effective Active Learning for Deep Image Classification , 2017, IEEE Transactions on Circuits and Systems for Video Technology.