The Combined Use of Remote Sensing and Social Sensing Data in Fine-Grained Urban Land Use Mapping: A Case Study in Beijing, China

Zhang, Yuan; Li, Qiangzi; Huang, Huaguo; Wu, Wei; Du, Xin; Wang, Hongyan

doi:10.3390/rs9090865

Cited by 102 publications

(90 citation statements)

References 48 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At last, the proposed concept can be further extent to different types of RS images and applications. RS image segmentation is indispensable to measure urban metrics [66,67], to monitor landscape changes [68] and to model the pattern and extent of urban sprawl [69]. It is also important to define urban typologies [5], to classify land use [4], to manage urban environment [2] and to support sustainable urban development [6,7].…”

Section: Discussionmentioning

confidence: 99%

One View Per City for Buildings Segmentation in Remote-Sensing Images via Fully Convolutional Networks: A Proof-of-Concept Study

Wen

Jin

et al. 2019

Sensors

View full text Add to dashboard Cite

The segmentation of buildings in remote-sensing (RS) images plays an important role in monitoring landscape changes. Quantification of these changes can be used to balance economic and environmental benefits and most importantly, to support the sustainable urban development. Deep learning has been upgrading the techniques for RS image analysis. However, it requires a large-scale data set for hyper-parameter optimization. To address this issue, the concept of “one view per city” is proposed and it explores the use of one RS image for parameter settings with the purpose of handling the rest images of the same city by the trained model. The proposal of this concept comes from the observation that buildings of a same city in single-source RS images demonstrate similar intensity distributions. To verify the feasibility, a proof-of-concept study is conducted and five fully convolutional networks are evaluated on five cities in the Inria Aerial Image Labeling database. Experimental results suggest that the concept can be explored to decrease the number of images for model training and it enables us to achieve competitive performance in buildings segmentation with decreased time consumption. Based on model optimization and universal image representation, it is full of potential to improve the segmentation performance, to enhance the generalization capacity, and to extend the application of the concept in RS image analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

One View Per City for Buildings Segmentation in Remote-Sensing Images via Fully Convolutional Networks: A Proof-of-Concept Study

Wen

Jin

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Pei et al [22] utilized the mobile phone dataset and a semi-supervised clustering method to classify different land-use types, and the detection rate of land-use reached 58.03%. Zhan, Ukkusuri, and Zhu [23] successfully explored the possibility and validity of using social media check-in dataset to classify land-use types.Meanwhile, many classification methods have also been widely developed to classify land use types and urban functional zones, such as K-Nearest Neighbors [24], Decision Tree [25], Support Vector Machine (SVM) [1,26], and Random Forest [19,27]. For instance, DeFries, Hansen, Townshend, and Sohlberg [28] used the Decision Tree algorithm to classify global land cover of 8 × 8 km resolution, which achieved an accuracy of over 80%.…”

mentioning

confidence: 99%

“…Although SVM is able to deal with high-dimensional and nonlinear problems, the uncertainty caused during the model training process due to its sensitivity to the initial parameters should also be noted. The Random Forest algorithm, a nonparametric classification model, is effective in obtaining accurate and stable predictions and reducing overfitting through building and merging multiple decision trees together [32], and was quite popular for land use and urban functional zones classification studies in past years [27,[33][34][35]. Yao et al [19] used the greedy algorithm, Random Forest algorithm and CBOW-based Word2Vec model to identify urban land use types based on POI data with an accuracy of 87.28%.…”

mentioning

confidence: 99%

“…Meanwhile, many classification methods have also been widely developed to classify land use types and urban functional zones, such as K-Nearest Neighbors [24], Decision Tree [25], Support Vector Machine (SVM) [1,26], and Random Forest [19,27]. For instance, DeFries, Hansen, Townshend, and Sohlberg [28] used the Decision Tree algorithm to classify global land cover of 8 × 8 km resolution, which achieved an accuracy of over 80%.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Approaches for Urban Functional Zones Classification Based on Multi-Source Geospatial Data: A Case Study in Yuzhong District, Chongqing, China

2019

View full text Add to dashboard Cite

Accurate and timely classification and monitoring of urban functional zones prove to be significant in rapidly developing cities, to better understand the real and varying urban functions of cities to support urban planning and management. Many efforts have been undertaken to identify urban functional zones using various classification approaches and multi-source geospatial datasets. The complexity of this category of classification poses tremendous challenges to these studies especially in terms of classification accuracy, but on the opposite, the rapid development of machine learning technologies provides us with new opportunities. In this study, a set of commonly used urban functional zones classification approaches, including Multinomial Logistic Regression, K-Nearest Neighbors, Decision Tree, Support Vector Machine (SVM), and Random Forest, are examined and compared with the newly developed eXtreme Gradient Boosting (XGBoost) model, using the case study of Yuzhong District, Chongqing, China. The investigation is based on multi-variate geospatial data, including night-time imagery, geotagged Weibo data, points of interest (POI) from Gaode, and Baidu Heat Map. This study is the first endeavor of implementing the XGBoost model in the field of urban functional zones classification. The results suggest that the XGBoost classification model performed the best and was able to achieve an accuracy of 88.05%, which is significantly higher than the other commonly used approaches. In addition, the integration of night-time imagery, geotagged Weibo data, POI from Gaode, and Baidu Heat Map has also demonstrated their values for the classification of urban functional zones in this case study.In general, urban functional zones are categorized as commercial, recreational, industrial and residential zones. Numerous models have been developed to extract and analyze urban functional zones. Traditionally, urban functional areas are identified based on onsite survey and field observation [8]. With the improvement of high-resolution satellite images (Landsat, SPOT, QuickBird), many detailed urban land-use maps have also been produced with remote sensing technology, which mainly concentrates on feature representations, semantic cognition classification, and zonal segmentation [1,9,10]. The above-mentioned studies largely take advantage of the spectral features of a city, and satellite images can only describe the natural characteristics of ground elements, and largely ignore and cannot capture the real human activities.It is the activities of, and interactions between, urban inhabitants that give rise to the characteristic physical environment of the city, and which, in return, also conditions people's various behaviors in the urban setting. This also empowers social sensing studies in various disciplines. Liu et al. [11] proposed the concept of social sensing, an important complement to remote sensing that is able to capture social and economic activities in the city and explore the function of a city at a fine and temporal scale....

show abstract

“…Some POI categories are closely related to human activities and more attractive to population, while other categories of POIs are less attractive to the population and even have a reject effect. This allows POIs to analyze the social lifestyle of humans and estimate population distribution [29,[38][39][40][41][42][43][44][45]. In recent years, many studies have demonstrated the usefulness of POI data in generating fine-grained population maps.…”

mentioning

confidence: 99%

Improving the Accuracy of Fine-Grained Population Mapping Using Population-Sensitive POIs

Zhao

Zhang

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Many methods have been used to generate gridded population maps by downscaling demographic data. As one of these methods, the accuracy of the dasymetric model depends heavily on the covariates. Point-of-interest (POI) data, as important covariates, have been widely used for population estimation. However, POIs are often used indiscriminately in existing studies. A few studies further used selected categories of POIs identified based only on the nonspatial quantitative relationship between the POIs and population. In this paper, the spatial association between the POIs and population distribution was considered to identify the POIs with a strong spatial correlation with the population distribution, i.e., population-sensitive POIs. The ability of population-sensitive POIs to improve the fine-grained population mapping accuracy was explored by comparing the results of random forest dasymetric models driven by population-sensitive POIs, all POIs, and no POIs, along with the same sets of multisource remote sensing and social sensing data. The results showed that the model driven by population-sensitive POI had the highest accuracy. Population-sensitive POIs were also more effective in improving the population mapping accuracy than were POIs selected based only on their quantitative relationship with the population. The model built using population-sensitive POIs also performed better than the two popular gridded population datasets WorldPop and LandScan. The model we proposed in this study can be used to generate accurate spatial population distribution information and contributes to achieving more reliable analyses of population-related social problems.Dasymetric mapping, on the other hand, was used to generate the 1-km LandScan [5] and the 100-m WorldPop [18] annual population datasets.Dasymetric mapping is a well-known cartographic approach for generating high-resolution population maps [22][23][24]. The idea of dasymetric mapping is to generate a weighting layer using different kinds of covariates. This layer will then be used to redistribute the demographic data. Dasymetric mapping has been demonstrated to be more effective in generating more accurate population estimates than other approaches [25,26]. In the context of dasymetric mapping, the accuracy of the population estimates depends greatly on the covariates used [27]. Remote sensing products and geospatial big data are the most commonly used covariates in dasymetric mapping [1,3,18,[28][29][30][31][32][33][34][35]. Remotely sensed population-related products, such as land use/land cover (LULC) data and nighttime light (NTL) data, could show the actual surface conditions that reflect the physical factors that affect the population distribution. However, these data often lack semantic information. Semantic information can be used to describe the relationship between geographic attributes and geographic features, such as different human activities occurring at accurate geographic locations. With the development of location-aware devices and the emergence and p...

show abstract

The Combined Use of Remote Sensing and Social Sensing Data in Fine-Grained Urban Land Use Mapping: A Case Study in Beijing, China

Cited by 102 publications

References 48 publications

One View Per City for Buildings Segmentation in Remote-Sensing Images via Fully Convolutional Networks: A Proof-of-Concept Study

One View Per City for Buildings Segmentation in Remote-Sensing Images via Fully Convolutional Networks: A Proof-of-Concept Study

Comparison of Approaches for Urban Functional Zones Classification Based on Multi-Source Geospatial Data: A Case Study in Yuzhong District, Chongqing, China

Improving the Accuracy of Fine-Grained Population Mapping Using Population-Sensitive POIs

Contact Info

Product

Resources

About