Mapping of plastic greenhouses and mulching films from very high resolution remote sensing imagery based on a dilated and non-local convolutional neural network

Feng, Quanlong; Niu, Bowen; Chen, Boan; Ren, Yan; Zhu, Ding; Yang, Jianyu; Liu, Jiantao; Ou, Cong; Li, Baoguo

doi:10.1016/j.jag.2021.102441

Cited by 22 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The key limitation of SVM classifiers is that they suffer from parameter assignment issues and inability to deal with the inherent noise in the input data that can affect the resulting maps (Mountrakis et al, 2011). Various pitfalls in mapping plasticulture areas using SVM classifiers have been solved in recent studies by applying ANN and CNN classification methods in recent studies (e.g., Feng et al, 2021; Sun et al, 2021).…”

Section: Remote Sensing For Plasticulture Mapping: Current Methodolog...mentioning

confidence: 99%

“…Machine learning algorithms such as ANN and deep learning algorithms such as convolutional neural networks (CNN) have been applied to remote sensing data varying from low resolution to VHR for mapping PCGs and PMFs (e.g., Feng et al, 2021; Hasituya et al, 2020; Li et al, 2020; Lin, Weng, et al, 2021; Ma et al, 2021; Sun et al, 2021). For example, Lin, Weng, et al (2021) applied machine learning algorithms to MODIS data, which is relatively a low resolution (250 m) imagery when compared to LANDSAT data (30 m), for mapping PCGs whereas Feng et al (2021) used high resolution PLEIADES‐1B data for mapping PCGs by applying DNCNN models. In the case of DNCNN, classification errors may occur where both PCGs and plastic‐mulched farmlands coexist (Feng et al, 2021).…”

Section: Remote Sensing For Plasticulture Mapping: Current Methodolog...mentioning

confidence: 99%

“…For example, Lin, Weng, et al (2021) applied machine learning algorithms to MODIS data, which is relatively a low resolution (250 m) imagery when compared to LANDSAT data (30 m), for mapping PCGs whereas Feng et al (2021) used high resolution PLEIADES-1B data for mapping PCGs by applying DNCNN models. In the case of DNCNN, classification errors may occur where both PCGs and plastic-mulched farmlands coexist (Feng et al, 2021). It is mentioned that Google Earth Engine with its massive data and cloud computing capabilities, when combined with integrated classification algorithms, can achieve high-speed mapping of greenhouse areas under complex terrain (Lin, Jin, et al, 2021).…”

Section: Ann and Deep Learning Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Remote sensing of plastic‐covered greenhouses and plastic‐mulched farmlands: Current trends and future perspectives

et al. 2022

View full text Add to dashboard Cite

The application of intensive plasticulture farming has resulted in an increased yield of horticulture crops during the last few decades in the world, particularly in China, Spain, and Italy. Proper monitoring of plastic-covered greenhouse (PCG) farming areas and plastic-mulched farmlands (PMF) is necessary for the sustainable development of horticulture, including high-quality agricultural production in limited areas with cost-effectiveness, and reduced pollution. The development of sophisticated image processing algorithms, such as pixel-based, object-based, and machine learning approaches, for mapping landscape and land use changes have revolutionized monitoring plasticulture areas in recent decades. Even though a complex task, remote sensing offers cost-effective, large-scale monitoring of plasticulture areas. Advancements in UAV technology are expected to improve the mapping and monitoring accuracy of PCGs and PMFs in the future in addition to high resolution optical data combined with digital surface models (DSM) with high vertical accuracy.

show abstract

Section: Remote Sensing For Plasticulture Mapping: Current Methodolog...mentioning

confidence: 99%

Section: Remote Sensing For Plasticulture Mapping: Current Methodolog...mentioning

confidence: 99%

Section: Ann and Deep Learning Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Remote sensing of plastic‐covered greenhouses and plastic‐mulched farmlands: Current trends and future perspectives

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Several papers have focused on detecting the greenhouses themselves, e.g. [35][36][37], while this paper also focuses on the plastic waste between the greenhouses and in abandoned areas.…”

Section: Almería Greenhouses Spainmentioning

confidence: 99%

Detection of Waste Plastics in the Environment: Application of Copernicus Earth Observation data

Lavender¹

2022

Preprint

View full text Add to dashboard Cite

The detection of waste plastics in the marine and terrestrial environment using satellite Earth Observation data offers the possibility of large-scale mapping, and reducing on-the-ground manual investigation. In addition, costs are kept to a minimum by utilizing free-to-access Copernicus data. A Machine Learning based classifier was developed to run on Sentinel-1 and -2 data. In support of the training and validation, a dataset was created with terrestrial and aquatic cases by manually digitizing varying landcover classes alongside plastics under the sub-categories of greenhouses, plastic, tyres and waste sites. The trained classifier, including an Artificial Neural Network and post-processing decision tree, was verified using five locations encompassing these different forms of plastic. Although exact matchups are challenging to digitize, the performance has generated high accuracy statistics, and the resulting land cover classifications have been used to map the occurrence of plastic waste in aquatic and terrestrial environments.

show abstract

“…Polyethylene is preferred because of its affordability, flexibility, and ease of manufacturing [33], with the plastics being transparent or translucent with vegetation below. Several papers have focused on detecting the greenhouses themselves, e.g., [34][35][36], while this paper also focuses on the plastic waste between the greenhouses and in abandoned areas.…”

Section: Almería Greenhouses Spainmentioning

confidence: 99%

Detection of Waste Plastics in the Environment: Application of Copernicus Earth Observation data

Lavender¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

Mapping of plastic greenhouses and mulching films from very high resolution remote sensing imagery based on a dilated and non-local convolutional neural network

Cited by 22 publications

References 24 publications

Remote sensing of plastic‐covered greenhouses and plastic‐mulched farmlands: Current trends and future perspectives

Remote sensing of plastic‐covered greenhouses and plastic‐mulched farmlands: Current trends and future perspectives

Detection of Waste Plastics in the Environment: Application of Copernicus Earth Observation data

Detection of Waste Plastics in the Environment: Application of Copernicus Earth Observation data

Contact Info

Product

Resources

About