A time-series classification approach based on change detection for rapid land cover mapping

Yan, Jining; Wang, Lizhe; Song, Wenzhe; Chen, Yunliang; Chen, Xiaodao; Deng, Ze

doi:10.1016/j.isprsjprs.2019.10.003

Cited by 115 publications

(39 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Landsat was chosen because it is the satellite with the longest earth observing history. The satellite images were ortho-rectified and subjected to atmospheric and radiometric corrections using ArcGIS 10.5 from the Environmental Systems Research Institute (ESRI), Redlands, California, United States of America (USA) [53,54]. Land cover for both images was classified and quantified using a pixel-based random forest supervised classification in ArcGIS 10.5.…”

Section: Land-cover Mapping and Analysismentioning

confidence: 99%

“…Land cover for both images was classified and quantified using a pixel-based random forest supervised classification in ArcGIS 10.5. Random forest was chosen because it is robust, efficient, and produces better results as demonstrated in other studies [53,54]. Training samples were used to train the images for classification.…”

Section: Land-cover Mapping and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Survey of Community Livelihoods and Landscape Change along the Nzhelele and Levuvhu River Catchments in Limpopo Province, South Africa

Musakwa

Wang

Wei

et al. 2020

Land

View full text Add to dashboard Cite

Landscape-change studies have attracted increasing interest because of their importance to land management and the sustainable livelihoods of rural communities. However, empirical studies on landscape change and its drivers are often poorly understood, particularly, in small rural communities in developing countries such as South Africa. The present study surveyed local community livelihoods and perceptions of landscape change in the Nzhelele and Levuvhu river catchments in Limpopo Province, South Africa. These areas have experienced land reform and are also characterized by environmental degradation, poverty, inequality and environmental justice concerns among other issues. Land-cover maps derived from Landsat satellite imagery were used for purposes of correlating and validating the survey data findings and results. The survey results showed that education levels, working status and marital status have statistically significant effects on community livelihoods (indicated by levels of income, p < 0.05). Maize, fruits and vegetables are the main cultivated crop varieties in the study area, and these crops are mainly used for subsistence to meet household self-consumption requirements. Moreover, local community members and stakeholders argue that the landscape has changed over the past 20 years mainly as a result of urban expansion, deforestation, agricultural diversification and forestry intensification. These landscape changes were largely confirmed by the land-cover change maps derived from satellite imagery. Soil erosion as a result of landscape changes was identified as a major threat and hazard in the study area. Political, natural, economic and cultural factors have been identified as the major underlying drivers for the observed landscape changes. These results have implications for understanding landscape change, coupled with human–nature relationships as well as informing government policy with respect to advancing land management and further promotion of the sustainable livelihoods of rural communities. Overall, the study proposes a multiple stakeholders’ approach and ecosystem-based approach to promote the sustainable management of landscapes in rural areas.

show abstract

Section: Land-cover Mapping and Analysismentioning

confidence: 99%

Section: Land-cover Mapping and Analysismentioning

confidence: 99%

Survey of Community Livelihoods and Landscape Change along the Nzhelele and Levuvhu River Catchments in Limpopo Province, South Africa

Musakwa

Wang

Wei

et al. 2020

Land

View full text Add to dashboard Cite

show abstract

“…Time series classification is a thriving area of study. Existing algorithms find applications in computer‐aided decision‐making systems, online monitoring in areas such as human activity recognition , automation and control , remote sensing , manufacturing , astronomy , and many other areas of science and engineering.…”

Section: Literature Reviewmentioning

confidence: 99%

Lagged encoding for image‐based time series classification using convolutional neural networks

Jastrzębska

2020

Statistical Analysis

View full text Add to dashboard Cite

Time series classification is a thriving area of research in machine learning. Among many applications, it is frequently applied to human activity analysis. Time series describing a human in motion are ubiquitously collected via omnipresent mobile devices and can be subjected to further processing. In this paper, we propose a novel, deep learning approach to time series classification. It is based on a lagged time series representation stored as images andConvolutional Neural Network used to image classification. We present a comparative study on different variants of lagged time series representation and we evaluate their effectiveness in a series of empirical experiments. We show that the developed method provides satisfying classification accuracy. The proposed image-based time series encoding is less resource-consuming than encodings used in other image-based approaches to time series classification. It is worth to emphasize that the proposed time series encoding conceals original time series values. Images are saved without scales and the order of observations cannot be reconstructed. Thus, the method is particularly suitable for systems that need to store sensitive information. K E Y W O R D S classification, convolutional neural network, image recognition, time series 1 Stat Anal Data Min: The ASA Data Sci Journal. 2020;13:245-260. wileyonlinelibrary.com/sam

show abstract

“…Considering the potential complexity of land cover and the spectral similarity between different species of vegetation, using only a single image to classify regional vegetation types can be severely restrictive [20,21]. In recent years, a large number of studies have attempted to classify land cover using time series of remote sensing images [22][23][24][25][26]. Compared with traditional classification methods, this approach more comprehensively considers the phenological characteristics of plants and offers improved classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Identification of Apple Orchard Planting Year Based on Spatiotemporally Fused Satellite Images and Clustering Analysis of Foliage Phenophase

Zhu

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The planting year of apple orchard not only determines the fruit output but also provides information for the governmental management of the fruit industry. However, considering that different orchards use different management and cultivation methods, this may result in some trees having similar outlines but different planting years, and it is, therefore, difficult to effectively determine the actual planting year based on textural or structural characteristics. Therefore, the monitoring method provided in this paper is not to monitor the growing year positively from the planting of orchard seedlings but to use time series remote sensing data to reverse determine the continuous growth age of each existing orchard. The city of Qixia, Shandong Province, China, was used as a case study. Firstly, the spatial distribution of apple orchards was accurately extracted using the Sentinel-2 normalized difference vegetation index (NDVI) spatiotemporally fused images and phenological vegetation information. Secondly, using region of interest (ROI) data for different vegetation types obtained from a field survey, NDVI time series were extracted from the Sentinel-2 NDVI spatiotemporally fused image. Among them, three characteristic phenological periods were selected, and the NDVI time series for apple orchards was used as a template to extract the apple orchard distribution area from 2000 to 2017. Then, the distribution area of apple orchards was defined as the area of interest in the planting year, combined with the Landsat NDVI time series image composed of three characteristic phenological periods each year from 2000 to 2017, and the apple orchard phenological curve. Subsequently, a Euclidean distance (ED) method was used to calculate the distribution area of apple orchards for each year between 2000 and 2017. Finally, a pixel-by-pixel inverse time series calculation method was used to obtain the planting year of apple orchards in the study area. This study provides a new way to accurately identify the planting year of apple orchards using satellite remote sensing images.

show abstract

A time-series classification approach based on change detection for rapid land cover mapping

Cited by 115 publications

References 50 publications

Survey of Community Livelihoods and Landscape Change along the Nzhelele and Levuvhu River Catchments in Limpopo Province, South Africa

Survey of Community Livelihoods and Landscape Change along the Nzhelele and Levuvhu River Catchments in Limpopo Province, South Africa

Lagged encoding for image‐based time series classification using convolutional neural networks

Identification of Apple Orchard Planting Year Based on Spatiotemporally Fused Satellite Images and Clustering Analysis of Foliage Phenophase

Contact Info

Product

Resources

About