A full resolution deep learning network for paddy rice mapping using Landsat data

Xia, Lang; Zhao, Fen; Chen, Jin; Yu, Le; Liu, Miao; Yu, Qiangyi; Liang, Shuang; Fan, Lingling; Sun, Xiao; Wu, Shangrong; Wu, Wenbin; Yang, Peng

doi:10.1016/j.isprsjprs.2022.10.005

Cited by 34 publications

(10 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All experiments were implemented by the Python 3.8 and Pytorch 1.10.0 framework and trained on a 1 NVIDIA RTX A6000 GPU with 48 G of RAM. The batch size was set to eight, the number of working threads was four, and the cross-entropy loss function was used to calculate the loss values for all networks [54]. The optimizer used an SGD with a momentum value of 0.9 and weight decay of 0.0005.…”

Section: Implementation Detailsmentioning

confidence: 99%

ABNet: An Aggregated Backbone Network Architecture for Fine Landcover Classification

Si,

Wang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

High-precision landcover classification is a fundamental prerequisite for resource and environmental monitoring and land-use status surveys. Imbued with intricate spatial information and texture features, very high spatial resolution remote sensing images accentuate the divergence between features within the same category, thereby amplifying the complexity of landcover classification. Consequently, semantic segmentation models leveraging deep backbone networks have emerged as stalwarts in landcover classification tasks owing to their adeptness in feature representation. However, the classification efficacy of a solitary backbone network model fluctuates across diverse scenarios and datasets, posing a persistent challenge in the construction or selection of an appropriate backbone network for distinct classification tasks. To elevate the classification performance and bolster the generalization of semantic segmentation models, we propose a novel semantic segmentation network architecture, named the aggregated backbone network (ABNet), for the meticulous landcover classification. ABNet aggregates three prevailing backbone networks (ResNet, HRNet, and VoVNet), distinguished by significant structural disparities, using a same-stage fusion approach. Subsequently, it amalgamates these networks with the Deeplabv3+ head after integrating the convolutional block attention mechanism (CBAM). Notably, this amalgamation harmonizes distinct scale features extracted by the three backbone networks, thus enriching the model’s spatial contextual comprehension and expanding its receptive field, thereby facilitating more effective semantic feature extraction across different stages. The convolutional block attention mechanism primarily orchestrates channel adjustments and curtails redundant information within the aggregated feature layers. Ablation experiments demonstrate an enhancement of no less than 3% in the mean intersection over union (mIoU) of ABNet on both the LoveDA and GID15 datasets when compared with a single backbone network model. Furthermore, in contrast to seven classical or state-of-the-art models (UNet, FPN, PSPNet, DANet, CBNet, CCNet, and UPerNet), ABNet evinces excellent segmentation performance across the aforementioned datasets, underscoring the efficiency and robust generalization capabilities of the proposed approach.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

ABNet: An Aggregated Backbone Network Architecture for Fine Landcover Classification

Si,

Wang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Table 1 provides an overview of the features employed in various studies for predicting paddy yields. [37]. In some instances, researchers employ multimodal satellite imagery, incorporating Sentinel-2 multispectral data alongside Sentinel-1 radar data [24][30][34] [35].…”

Section: Features and Image Collectionmentioning

confidence: 99%

Curating Multimodal Satellite Imagery for Precision Agriculture Datasets with Google Earth Engine

Wijaya,

Munir,

Utama

2023

icdsos

View full text Add to dashboard Cite

In the era of modern agriculture, satellite imagery has been widely used to monitor crops, one of which is paddy. This paper tries to describe the vegetation indices, climate, and soil index features related to paddy plants and curates a collection of satellite imagery on the Google Earth Engine (GEE). This paper reveals how GEE can be used to collect and process multimodal satellite imagery to form a precision agriculture dataset. The objective of this study is to establish a comprehensive precision agriculture dataset by leveraging multimodal satellite imagery to monitor paddy crops. The data collected as a dataset originates from 306 locations in Karawang Regency, Indonesia, during the 2019-2020 period. In the first step, we identify the relevant features essential for paddy crop analysis. Subsequently, we carefully select image collections within GEE based on these features. Afterward, we perform data acquisition and necessary preprocessing through the Google Colab environment. The results showed that satellite imagery from Sentinel-2 outperforms Landsat 8 in terms of spatial and temporal resolution. Apart from that, the generated dataset successfully captures the growth patterns of paddy plants.

show abstract

“…Drone design depends on needs which include form, function, and supporting features [2]. One of the benefits of drones is taking photos of agricultural land to analyze crop conditions, including whether there are pest and disease attacks, area size, plant growth, remote sensing, mapping [3], and fertilizing or spraying [4][5][6][7]. The various advantages of using drones in agriculture make drones the newest tool for monitoring plant growth.…”

Section: Introductionmentioning

confidence: 99%

Measuring Agricultural Area Using YOLO Object Detection and ArUco Markers

Masykur,

Adi,

Nurhayati

2024

ISI

View full text Add to dashboard Cite

This paper discusses the use of drones in image acquisition of agricultural land to detect the presence of disease and calculate the area of infected agriculture. Calculation of the area of infected and healthy areas will be calculated by combining the You Only Look Once (Yolo) object detection algorithm version 4 with the ArUco Marker reference image. The image resulting from the detection from the Yolo v4 algorithm will be used as a reference to be referenced using a reference image in the form of an AruCo Marker to convert it to area units to determine the area of the infected area and calculate the ratio between the area of the infected area and the area of the healthy area. The coordinate points at each corner are used as the first stage in converting pixels into area units. Measuring the infected area is necessary to localize the infection so that it does not spread to healthy plant areas. Apart from that, to anticipate the spread of infection which could result in crop failure. Evaluation of the calculation of the area of the detection area with the actual area resulted in an accuracy of 97.05%.

show abstract

A full resolution deep learning network for paddy rice mapping using Landsat data

Cited by 34 publications

References 48 publications

ABNet: An Aggregated Backbone Network Architecture for Fine Landcover Classification

ABNet: An Aggregated Backbone Network Architecture for Fine Landcover Classification

Curating Multimodal Satellite Imagery for Precision Agriculture Datasets with Google Earth Engine

Measuring Agricultural Area Using YOLO Object Detection and ArUco Markers

Contact Info

Product

Resources

About