Monitoring Plastic-Mulched Farmland by Landsat-8 OLI Imagery Using Spectral and Textural Features

Hasituya,; Chen, Zhongxin; Wang, Limin; Wu, Wenbin; Jiang, Zhiwei; Li, He

doi:10.3390/rs8040353

Cited by 75 publications

(20 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following improvements could be considered in the future. If only single-phase UAV RGB images can be acquired, we could try to transform the DN value to different indices, or we could extract the different texture information of the image to enhance the difference between the tobacco films and the roads/buildings [29]. We also could try to use an object-oriented classification method to first extract building objects [30,31], remove the buildings from the UAV RGB images, and then use our proposed method to extract the tobacco fields.…”

Section: Discussionmentioning

confidence: 99%

Mapping Tobacco Fields Using UAV RGB Images

Zhu

Xiao

Ping³

et al. 2019

Sensors

View full text Add to dashboard Cite

Tobacco planting information is an important part of tobacco production management. Unmanned aerial vehicle (UAV) remote sensing systems have become a popular topic worldwide because they are mobile, rapid and economic. In this paper, an automatic identification method for tobacco fields based on UAV images is developed by combining supervised classifications with image morphological operations, and this method was used in the Yunnan Province, which is the top province for tobacco planting in China. The results show that the produce accuracy, user accuracy, and overall accuracy of tobacco field identification using the method proposed in this paper are 92.59%, 96.61% and 95.93%, respectively. The method proposed in this paper has the advantages of automation, flow process, high accuracy and easy operation, but the ground sampling distance (GSD) of the UAV image has an effect on the accuracy of the proposed method. When the image GSD was reduced to 1 m, the overall accuracy decreased by approximately 10%. To solve this problem, we further introduced the convolution method into the proposed method, which can ensure the recognition accuracy of tobacco field is above 90% when GSD is less than or equal to 1 m. Some other potential improvements of methods for mapping tobacco fields were also discussed in this paper.

show abstract

Section: Discussionmentioning

confidence: 99%

Mapping Tobacco Fields Using UAV RGB Images

Zhu

Xiao

Ping³

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…This study found out that 902-hectare area is suitable to be used for upcoming agriculture area in Gokceada. Landsat 8 has also been used by Hasituya et al to monitor plasticmulched farmland [4]. Plastic mulch is widely used all over the world, especially in China to suppress weeds and conserve water in crops, fruits and vegetables production.…”

Section: Agriculture and Forestrymentioning

confidence: 99%

“…Plastic-mulched farmland is identified as it has the same spectrum curve shape as soil but with a higher reflectance than other classes on SWIR bands. A new scheme is proposed in [4] which integrates spectral and textual features that is able to monitor the plastic-mulched farmland and at the same time evaluating the performance of Support Vector Machine algorithm using OLI, Google Earth imagery and ancillary data.…”

Section: Agriculture and Forestrymentioning

confidence: 99%

Applications of Landsat-8 Data: a Survey

Ridwan¹,

Radzi²,

Ahmad³

et al. 2018

IJET

View full text Add to dashboard Cite

Landsat 8 was launched in 2013 by the National Aeronautics and Space Administration (NASA). On board of the Landsat 8 is the Operational Land Imager (OLI) and Thermal Infrared Sensor (TIRS). Data for visible, panchromatic band, short-wave infrared spectral bands are collected by the OLI while TIRS collect images in the thermal region. As data for Landsat 8 is available to be used for public, researchers have utilized the data for numerous applications. However, to the best of our knowledge, there is yet a review paper on the various applications of Landsat 8 data. Hence, this paper presented an innovative survey on Landsat 8 data in the application of agriculture and forestry, land use and mapping, geology, hydrology, coastal resources and environmental monitoring. The potential of utilizing Landsat 8 data for power utility companies is also discussed in this paper. As Landsat 8 data is predicted to be available for more years to come, this paper provides insight for researchers to utilize the data better for their research.

show abstract

“…SVMs are a supervised non-parametric statistical learning technique that makes no assumptions on the underlying data distribution [53]. We decided to use SVMs for this classification because compared to more traditional classification approaches (e.g., Maximum Likelihood Classifier), SVMs were found to perform better for a variety of classifications in different contexts (e.g., different classification scopes, classification schemes, and classification features) [53][54][55][56][57][58][59][60][61]. In general, SVMs are binary classifiers that delineate two classes by fitting an optimal separating hyperplane to the training data in multidimensional feature space [52].…”

Section: Support Vector Machines For Change Detectionmentioning

confidence: 99%

Mapping the Expansion of Boom Crops in Mainland Southeast Asia Using Dense Time Stacks of Landsat Data

et al. 2017

View full text Add to dashboard Cite

Abstract:We performed a multi-date composite change detection technique using a dense-time stack of Landsat data to map land-use and land-cover change (LCLUC) in Mainland Southeast Asia (MSEA) with a focus on the expansion of boom crops, primarily tree crops. The supervised classification was performed using Support Vector Machines (SVM), which are supervised non-parametric statistical learning techniques. To select the most suitable SMV classifier and the related parameter settings, we used the training data and performed a two-dimensional grid search with a three-fold internal cross-validation. We worked in seven Landsat footprints and found the linear kernel to be the most suitable for all footprints, but the most suitable regularization parameter C varied across the footprints. We distinguished a total of 41 LCLUCs (13 to 31 classes per footprint) in very dynamic and heterogeneous landscapes. The approach proved useful for distinguishing subtle changes over time and to map a variety of land covers, tree crops, and transformations as long as sufficient training points could be collected for each class. While to date, this approach has only been applied to mapping urban extent and expansion, this study shows that it is also useful for mapping change in rural settings, especially when images from phenologically relevant acquisition dates are included.

show abstract

Monitoring Plastic-Mulched Farmland by Landsat-8 OLI Imagery Using Spectral and Textural Features

Cited by 75 publications

References 44 publications

Mapping Tobacco Fields Using UAV RGB Images

Mapping Tobacco Fields Using UAV RGB Images

Applications of Landsat-8 Data: a Survey

Mapping the Expansion of Boom Crops in Mainland Southeast Asia Using Dense Time Stacks of Landsat Data

Contact Info

Product

Resources

About