TY - JOUR

T1 - FADNet

T2 - Greenhouse Identification with Fusion Attention Mechanism and Deformable Convolution

AU - Liu, Jun

AU - Xu, Xiaolong

AU - Bilal, Muhammad

AU - Jiang, Jielin

PY - 2024/4/1

Y1 - 2024/4/1

N2 - With the development of agricultural modernization, strengthening the supervision of agricultural production activities plays a crucial role in social security management and economic development. However, the current monitoring of greenhouse usage and planning in agricultural production lacks effective regulation. Existing technological approaches involve the analysis and monitoring of agricultural activities using machine learning and simple neural networks, but their detection accuracy is limited. In this paper, we present a novel deep learning model called FADNet, which fusion attention mechanism and variable convolution techniques. FADNet utilizes remotely sensed images obtained from satellite sensors as input for training. It employs variable convolution and feature pyramid networks to achieve accurate segmentation of small-scale greenhouse targets. Spatial attention mechanism is employed to address the interference caused by similar features in urban areas for greenhouse identification. Additionally, data augmentation techniques are utilized to address the scarcity of greenhouse datasets and the disparity in the distribution of positive and negative samples, thereby enhancing the reliability of the dataset. FADNet achieves greenhouse segmentation by performing pixel-level classification on the images. Extensive experiments have demonstrated that FADNet performs exceptionally well in greenhouse segmentation tasks.

AB - With the development of agricultural modernization, strengthening the supervision of agricultural production activities plays a crucial role in social security management and economic development. However, the current monitoring of greenhouse usage and planning in agricultural production lacks effective regulation. Existing technological approaches involve the analysis and monitoring of agricultural activities using machine learning and simple neural networks, but their detection accuracy is limited. In this paper, we present a novel deep learning model called FADNet, which fusion attention mechanism and variable convolution techniques. FADNet utilizes remotely sensed images obtained from satellite sensors as input for training. It employs variable convolution and feature pyramid networks to achieve accurate segmentation of small-scale greenhouse targets. Spatial attention mechanism is employed to address the interference caused by similar features in urban areas for greenhouse identification. Additionally, data augmentation techniques are utilized to address the scarcity of greenhouse datasets and the disparity in the distribution of positive and negative samples, thereby enhancing the reliability of the dataset. FADNet achieves greenhouse segmentation by performing pixel-level classification on the images. Extensive experiments have demonstrated that FADNet performs exceptionally well in greenhouse segmentation tasks.

KW - Attention Mechanism

KW - Convolution

KW - Decoding

KW - Deep Learning

KW - Deformable Convolution

KW - Feature extraction

KW - Green products

KW - Greenhouse Identification

KW - Image segmentation

KW - Remote Satellite Sensing

KW - Task analysis

KW - Training

U2 - 10.1109/jstars.2024.3374630

DO - 10.1109/jstars.2024.3374630

M3 - Journal article

VL - 17

SP - 7170

EP - 7178

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

ER -