Extraction of Agricultural Fields via DASFNet with Dual Attention Mechanism and Multi-scale Feature Fusion in South Xinjiang, China

Abstract

Agricultural fields are essential in providing human beings with paramount food and other materials. Quick and accurate identification of agricultural fields from the remote sensing images is a crucial task in digital and precision agriculture. Deep learning methods have the advantages of fast and accurate image segmentation, especially for extracting the agricultural fields from remote sensing images. This paper proposed a deep neural network with a dual attention mechanism and a multi-scale feature fusion (Dual Attention and Scale Fusion Network, DASFNet) to extract the cropland from a GaoFen-2 (GF-2) image of 2017 in Alar, south Xinjiang, China. First, we constructed an agricultural field segmentation dataset from the GF-2 image. Next, seven evaluation indices were selected to assess the extraction accuracy, including the location shift, to reveal the spatial relationship and facilitate a better evaluation. Finally, we proposed DASFNet incorporating three ameliorated and novel deep learning modules with the dual attention mechanism and multi-scale feature fusion methods. The comparison of these modules indicated their effects and advantages. Compared with different segmentation convolutional neural networks, DASFNet achieved the best testing accuracy in extracting fields with an F1-score of 0.9017, an intersection over a union of 0.8932, a Kappa coefficient of 0.8869, and a location shift of 1.1752 pixels. Agricultural fields can be extracted automatedly and accurately using DASFNet, which reduces the manual record of the agricultural field information and is conducive to further farmland surveys, protection, and management.

Edge Detection With Direction Guided Postprocessing for Farmland Parcel Extraction

“…Researches have shown that semantic segmentation methods have a better accuracy and robust prediction in high resolution satellite or aerial imagery [38][39][40][41][42]. Semantic segmentation models are applied and modified in farmland extraction [43][44][45][46][47], based on context representations, multi-scale or pyramid features, and attention modules. These networks have the benefits of enhancing [6] semantic representations by larger receptive fields and deeper networks.…”

EDPNet: An Encoding–Decoding Network with Pyramidal Representation for Semantic Image Segmentation

“…Fox example, in medical image processing [ 1 , 2 ], semantic segmentation is utilized in tumor border extraction and organ/tissue measurement, which helps doctors to make scientific judgments quickly and efficiently. In agricultural fields [ 3 , 4 , 5 ], semantic segmentation of remote sensing images helps to map and monitor land use and land cover (LULC) changes for sustainable land development, planning, and management. In the autonomous driving system applications [ 6 , 7 ], vehicles need the semantic information of the surrounding scene to assist their understanding and perception of complex traffic situations.…”

Deep-agriNet: a lightweight attention-based encoder-decoder framework for crop identification using multispectral images

“…Wang et al (2022) proposed a novel architecture called Coupled CNN and Transformer Network (CCTNet), which combines the local details of CNN and the global context of the transformer to achieve a 72.97% mIoU score on the Barley remote-sensing dataset. Lu et al (2022) proposed a deep neural network with Dual Attention and Scale Fusion (DASFNet) to extract farmland from GF-2 images of southern Xinjian. The result shows that the dual attention mechanism module can correct the shape and boundary of the fields effectively.…”