scholarly journals An Ensemble Learning Approach for Urban Land Use Mapping Based on Remote Sensing Imagery and Social Sensing Data

2020 ◽  
Vol 12 (19) ◽  
pp. 3254
Author(s):  
Zhou Huang ◽  
Houji Qi ◽  
Chaogui Kang ◽  
Yuelong Su ◽  
Yu Liu

Urban land use mapping is crucial for effective urban management and planning due to the rapid change of urban processes. State-of-the-art approaches rely heavily on the socioeconomic, topographical, infrastructural and land cover information of urban environments via feeding them into ad hoc classifiers for land use classification. Yet, the major challenge lies in the lack of a universal and reliable approach for the extraction and combination of physical and socioeconomic features derived from remote sensing imagery and social sensing data. This article proposes an ensemble-learning-approach-based solution of integrating a rich body of features derived from high resolution satellite images, street-view images, building footprints, points-of-interest (POIs) and social media check-ins for the urban land use mapping task. The proposed approach can statistically differentiate the importance of input feature variables and provides a good explanation for the relationships between land cover, socioeconomic activities and land use categories. We apply the proposed method to infer the land use distribution in fine-grained spatial granularity within the Fifth Ring Road of Beijing and achieve an average classification accuracy of 74.2% over nine typical land use types. The results also indicate that our model outperforms several alternative models that have been widely utilized as baselines for land use classification.

Author(s):  
A. S. Anugraha ◽  
H.-J. Chu

<p><strong>Abstract.</strong> Large amounts of data can be sensed and analyzed to discover patterns of human behavior in cities for the benefit of urban authorities and citizens, especially in the areas of traffic forecasting, urban planning, and social science. In New York, USA, social sensing, remote sensing, and urban land use information support the discovery of patterns of human behavior. This research uses two types of openly accessible data, namely, social sensing data and remote sensing data. Bike and taxi data are examples of social sensing data, whereas sentinel remote sensed imagery is an example of remote sensing data. This research aims to sense and analyze the patterns of human behavior and to classify land use from the combination of remote sensing data and social sensing data. A decision tree is used for land use classification. Bike and taxi density maps are generated to show the locations of people around the city during the two peak times. On the basis of a geographic information system, the maps also reflect the residential and office areas in the city. The overall accuracy of land use classification after the consideration of social sensing data is 85.3%. The accuracy assessment shows that the combination of remote sensing data and social sensing data facilitates accurate urban land use classification.</p>


2018 ◽  
Vol 10 (3) ◽  
pp. 446 ◽  
Author(s):  
Yuanxin Jia ◽  
Yong Ge ◽  
Feng Ling ◽  
Xian Guo ◽  
Jianghao Wang ◽  
...  

2020 ◽  
Vol 11 (5) ◽  
pp. 529-535
Author(s):  
Dan Abudu ◽  
Nigar Sultana Parvin ◽  
Geoffrey Andogah

Conventional approaches for urban land use land cover classification and quantification of land use changes have often relied on the ground surveys and urban censuses of urban surface properties. Advent of Remote Sensing technology supporting metric to centimetric spatial resolutions with simultaneous wide coverage, significantly reduced huge operational costs previously encountered using ground surveys. Weather, sensor’s spatial resolution and the complex compositions of urban areas comprising concrete, metallic, water, bare- and vegetation-covers, limits Remote Sensing ability to accurately discriminate urban features. The launch of Sentinel-1 Synthetic Aperture Radar, which operates at metric resolution and microwave frequencies evades the weather limitations and has been reported to accurately quantify urban compositions. This paper assessed the feasibility of Sentinel-1 SAR data for urban land use land cover classification by reviewing research papers that utilised these data. The review found that since 2014, 11 studies have specifically utilised the datasets.


Author(s):  
J. R. Bergado ◽  
C. Persello ◽  
A. Stein

Abstract. Updated information on urban land use allows city planners and decision makers to conduct large scale monitoring of urban areas for sustainable urban growth. Remote sensing data and classification methods offer an efficient and reliable way to update such land use maps. Features extracted from land cover maps are helpful on performing a land use classification task. Such prior information can be embedded in the design of a deep learning based land use classifier by applying a multitask learning setup—simultaneously solving a land use and a land cover classification task. In this study, we explore a fully convolutional multitask network to classify urban land use from very high resolution (VHR) imagery. We experimented with three different setups of the fully convolutional network and compared it against a baseline random forest classifier. The first setup is a standard network only predicting the land use class of each pixel in the image. The second setup is a multitask network that concatenates the land use and land cover class labels in the same output layer of the network while the other setup accept as an input the land cover predictions, predicted by a subpart of the network, concatenated to the original input image patches. The two deep multitask networks outperforms the other two classifiers by at least 30% in average F1-score.


1989 ◽  
Vol 17 (3) ◽  
pp. 11-22 ◽  
Author(s):  
S. K. Pathan ◽  
P. Jothimahi ◽  
D. Sampat Kumar ◽  
S. P. Pendharkar

Sign in / Sign up

Export Citation Format

Share Document