Impervious Surface Information Extraction Based on Hyperspectral Remote Sensing Imagery

Tang, Fei; Xu, Hanqiu

doi:10.3390/rs9060550

Cited by 21 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA in the remote sensing field is usually used to compress the information from multiple bands and convert large amounts of information into several new images called components. This procedure is implemented to reduce the number of similar images and make the results simpler to interpret [33]. PCA has also been used to analyze the long-term trends of sea surface temperature (SST) and detect anomalies such as El Niño and La Niña events [34].…”

Section: Principal Component Analysis (Pca) Of Thermal Imagesmentioning

confidence: 99%

Visualizing the Spatiotemporal Trends of Thermal Characteristics in a Peatland Plantation Forest in Indonesia: Pilot Test Using Unmanned Aerial Systems (UASs)

Iizuka

Watanabe

Kato³

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

The high demand for unmanned aerial systems (UASs) reflects the notable impact that these systems have had on the remote sensing field in recent years. Such systems can be used to discover new findings and develop strategic plans in related scientific fields. In this work, a case study is performed to describe a novel approach that uses a UAS with two different sensors and assesses the possibility of monitoring peatland in a small area of a plantation forest in West Kalimantan, Indonesia. First, a multicopter drone with an onboard camera was used to collect aerial images of the study area. The structure from motion (SfM) method was implemented to generate a mosaic image. A digital surface model (DSM) and digital terrain model (DTM) were used to compute a canopy height model (CHM) and explore the vegetation height. Second, a multicopter drone combined with a thermal infrared camera (Zenmuse-XT) was utilized to collect both spatial and temporal thermal data from the study area. The temperature is an important factor that controls the oxidation of tropical peats by microorganisms, root respiration, the soil water content, and so forth. In turn, these processes can alter the greenhouse gas (GHG) flux in the area. Using principal component analysis (PCA), the thermal data were processed to visualize the thermal characteristics of the study site, and the PCA successfully extracted different feature areas. The trends in the thermal information clearly show the differences among land cover types, and the heating and cooling of the peat varies throughout the study area. This study shows the potential for using UAS thermal remote sensing to interpret the characteristics of thermal trends in peatland environments, and the proposed method can be used to guide strategical approaches for monitoring the peatlands in Indonesia.

show abstract

Section: Principal Component Analysis (Pca) Of Thermal Imagesmentioning

confidence: 99%

Visualizing the Spatiotemporal Trends of Thermal Characteristics in a Peatland Plantation Forest in Indonesia: Pilot Test Using Unmanned Aerial Systems (UASs)

Iizuka

Watanabe

Kato³

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…With urbanization, more than half of the world's population live in urban areas, and the proportion will reach 68% by 2050, with the strongest increases in developing countries [3,4]. Rapid urbanization has led not only to a dramatic increase in urban populations, but has also brought a series of problems, including pollution [5][6][7], shortage of resources [8,9], decrease in biodiversity [10][11][12], and so on, which have seriously affected the local climate, ecological environment and global change [13]. It is well known that urban expansion and population expansion occur at different rates; it is expected that by 2030 the speed of global urban land expansion will be three times faster than that of population expansion [14,15].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Expansion of Urban Land in China’s Coastal Zone since 2000

Hou

2022

Remote Sensing

View full text Add to dashboard Cite

Although a major region with strong urbanization, there is not yet a systematic and comprehensive understanding of urban expansion during the last 20 years for China’s coastal zone. In this paper, based on remote sensing techniques, and using indicators such as new urban land proportion, annual urban increase, and annual growth rate, as well as a landscape expansion index reflecting the urban expansion type (e.g., edge-expansion, infilling, and outlying), we measured the dynamic expansion of urban land in China’s coastal zone since 2000. The results indicated that: (1) China’s coastal zone experienced rapid urbanization from 2000 to 2020, with the new urban land and annual urban growth rate at 17,979.72 km2 and 4.83%, respectively. The new urban land was mainly concentrated in economically advanced regions, such as Bohai Rim, Shandong Peninsula, the Yangtze River delta, and the Pearl River delta. (2) The urban growth rates of coastal cities in Liaoning, Hebei, Shandong, southeast Fujian, and Taiwan became slower over time, with a sharp decline during 2015–2020. In the mid and south of China’s coastal zone, such as coastal cities in Jiangsu, Guangxi, and Hainan, there was slow urbanization before 2015, and urban land expanded dramatically during 2015–2020. (3) The urban expansion of China’s coastal zone was dominated by edge-expansion after 2000, but it went through a low-speed and intensive development stage during 2010–2015, with an increase in urban land less than 50% of that in the other three five-year periods, and the most significant filling of urban space compared with the other three five-year periods, which was probably caused by the global financial crisis. (4) The spatial-temporal differences in the urbanization process in China’s coastal zone were largely consequent on national economic development strategies and regional development plans implemented in China’s coastal zone.

show abstract

“…For example, to improve the accuracy of impervious surface extraction, Feng and Fan proposed a hierarchical extraction method of impervious surface based on NDVI thresholding integrated with multispectral and high-resolution remote sensing imageries [19]. Impervious surface extraction methods based on HSRRSIs mainly include four categories, namely, pixel-based, geographic object-based, impervious surface indexes-based and machine learning-based methods [2], [19]- [24].…”

Section: Introductionmentioning

confidence: 99%

Semantic Network-Based Impervious Surface Extraction Method for Rural-Urban Fringe From High Spatial Resolution Remote Sensing Images

Wang

Huang

Zhao

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Impervious surfaces, as a key indicator of urban spatial environmental factors, have great significance in exploring the distribution law and spatial pattern of rural-urban fringe areas. To handle the increasingly rich feature information and complicated urban spatial structure in high spatial resolution remote sensing images (HSRRSIs), a semantic network modelguided extraction method for HSRRSI impervious surfaces in rural-urban fringes is proposed. The proposed method mainly includes three parts: (1) Construction of a semantic network model of ground covers in the rural-urban fringe and dimensionality reduction of its features. (2) Optimization of a multi-scale segmentation algorithm based on the estimation of scale parameter 2 (ESP2) method and the fitness function. (3) Proposal of a feature reduction method based on the ReliefF feature selection algorithm for spectral, texture, and geometry features to reduce the data redundancy in HSRRSIs. Finally, with the Geoeye-1 image of the rural-urban fringe of Zhanggong District as the data source, CART, RF, and SVM classifiers are used to extract the impervious surfaces of two different areas (named as Q1 and Q2), Q1 comprises the edge of rural-urban fringe with densely distributed industrial plants, and Q2 comprises a rural-urban fringe with a pronounced transition from urban to rural areas. Results show that the highest impervious surface extraction accuracy of the SVM classifier based on the semantic network model is obtained when the segmentation scale is at 210 and 215. The producer accuracy and overall accuracy for Q1 and Q2 are (94.27%, 86.41%) and (94.46%, 89.47%), respectively.

show abstract

Impervious Surface Information Extraction Based on Hyperspectral Remote Sensing Imagery

Cited by 21 publications

References 33 publications

Visualizing the Spatiotemporal Trends of Thermal Characteristics in a Peatland Plantation Forest in Indonesia: Pilot Test Using Unmanned Aerial Systems (UASs)

Visualizing the Spatiotemporal Trends of Thermal Characteristics in a Peatland Plantation Forest in Indonesia: Pilot Test Using Unmanned Aerial Systems (UASs)

Dynamic Expansion of Urban Land in China’s Coastal Zone since 2000

Semantic Network-Based Impervious Surface Extraction Method for Rural-Urban Fringe From High Spatial Resolution Remote Sensing Images

Contact Info

Product

Resources

About