Transfer Learning Models for Land Cover and Land Use Classification in Remote Sensing Image

Drivers of land use change were captured by the use of DPSIR model where Drivers (D) represented human needs, Pressures (P), human activities, State (S), the ecosystem, Impact (I) services from the ecosystem and Response (R), the decisions taken by land users. Land sat MSS and Land sat ETM+ (path 185, row 31) were used in this study. The Land sat ETM+ image (June 1987, May, 2000 and July, 2014) was downloaded from USGS Earth Resources Observation Systems data website. Remote sensing image processing was performed by using ERDAS Imagine 9.1. Two land use/land cover (LULC) classes were established as forest and shrub land. Severe land cover changes was found to have occurred from 1987-2000, where shrub land reduced by -19%, and forestry reduced by -72%. In 2000 – 2014 shrub land reduced by-45%, and forestry reduced by -64%. Forestry and shrub land were found to be consistently reducing.

Download Full-text

A Study on Object-Oriented Classification of Land Use/Land Cover of Remote Sensing Image

2010 2nd International Workshop on Intelligent Systems and Applications ◽

10.1109/iwisa.2010.5473696 ◽

2010 ◽

Author(s):

Cairong Yue ◽

Rong Zhang

Keyword(s):

Remote Sensing ◽

Land Use ◽

Land Cover ◽

Object Oriented ◽

Remote Sensing Image ◽

Land Use Land Cover

Download Full-text

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

Remote Sensing ◽

10.3390/rs12193254 ◽

2020 ◽

Vol 12 (19) ◽

pp. 3254

Author(s):

Zhou Huang ◽

Houji Qi ◽

Chaogui Kang ◽

Yuelong Su ◽

Yu Liu

Keyword(s):

Remote Sensing ◽

Land Use ◽

Land Cover ◽

Ensemble Learning ◽

Urban Land ◽

Urban Land Use ◽

Learning Approach ◽

Land Use Classification ◽

Remote Sensing Imagery ◽

Sensing Data

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.

Download Full-text