Full Convolution Neural Network Combined with Contextual Feature Representation for Cropland Extraction from High-Resolution Remote Sensing Images

Abstract

The quantity and quality of cropland are the key to ensuring the sustainable development of national agriculture. Remote sensing technology can accurately and timely detect the surface information, and objectively reflect the state and changes of the ground objects. Using high-resolution remote sensing images to accurately extract cropland is the basic task of precision agriculture. The traditional model of cropland semantic segmentation based on the deep learning network is to down-sample high-resolution feature maps to low resolution, and then restore from low-resolution feature maps to high-resolution ideas; that is, obtain low-resolution feature maps through a network, and then recover to high resolution by up-sampling or deconvolution. This will bring about the loss of features, and the segmented image will be more fragmented, without very clear and smooth boundaries. A new methodology for the effective and accurate semantic segmentation cropland of high spatial resolution remote sensing images is presented in this paper. First, a multi-temporal sub-meter cropland sample dataset is automatically constructed based on the prior result data. Then, a fully convolutional neural network combined with contextual feature representation (HRNet-CFR) is improved to complete the extraction of cropland. Finally, the initial semantic segmentation results are optimized by the morphological post-processing approach, and the broken spots are ablated to obtain the internal homogeneous cropland. The proposed method has been validated on the Jilin-1 data and Gaofen Image Dataset (GID) public datasets, and the experimental results demonstrate that it outperforms the state-of-the-art method in cropland extraction accuracy. We selected the comparison of Deeplabv3+ and UPerNet methods in GID. The overall accuracy of our approach is 92.03%, which is 3.4% higher than Deeplabv3+ and 5.12% higher than UperNet.

BAFormer: A Novel Boundary-Aware Compensation UNet-like Transformer for High-Resolution Cropland Extraction

“…Feature fusion-based approaches [5,[17][18][19][20][21][22][23][24][25][26] enhance the representation of cropland information by supplementing additional feature information to the model. Considering the difficulty in labeling the existing high-resolution remote sensing image samples, [17] utilized the existing medium-resolution remote sensing images as a priori knowledge to provide cross-scale relocatable samples for HR images, thus obtaining more effective high-resolution farmland samples.…”

“…To mitigate feature details due to image downsampling and noise from the same image reduces the network's ability to discriminate between useful and useless information, [19] proposed to compensate for local image features and minimize noise by bootstrapping the feature extraction module to emphasize the learning of useful information. [21] proposed a fully convolutional neural network HRNet-CRF with improved contextual feature representation to optimize the initial semantic segmentation results by morphological postprocessing methods to obtain internally homogeneous farmland. [22] proposed a boundary-enhanced segmentation network, HBRNet, with Swing-Transformer as the backbone of the pyramid hierarchy to obtain contextual information while enhancing boundary details.…”

“…However, most of them focus on specific geographic regions or a single cropland type, ignoring the regional differences of cropland parcels, and failing to achieve the purpose of generalized extraction. (2) Feature-based approaches [5,[17][18][19][20][21][22][23][24][25][26] enhance the representation and understanding of cropland information by supplementing the model with additional features. However, some redundant feature representations do not provide positive images to the model while increasing the computational burden of the model.…”

Cropland Inundation Mapping in Rugged Terrain Using Sentinel-1 and Google Earth Imagery: A Case Study of 2022 Flood Event in Fujian Provinces

“…Based on Google Earth imagery, this study employed PIDNet to extract cropland masks in Fujian Province and developed a comprehensive methodology for identifying inundated cropland events in mountainous areas. The rugged terrain and complex cropland patterns pose challenges for traditional 10-30 m spatial resolution products, which may fail to capture many crop parcels [47,51]. In contrast, the sub-meter-level extraction helps capture these fine-grained cropland units while eliminating noise interference from radar shadows and permanent water bodies.…”

Cropland Data Extraction in Mekong Delta Based on Time Series Sentinel-1 Dual-Polarized Data

“…The classification algorithms applied to cropland extraction mainly include traditional machine learning methods, including clustering [17], support vector machine [18], random forest [19], decision tree [20], and the classification models in the rapidly developing area of deep learning in recent years. For example, to reduce information loss in downsampling, Li et al [21] used a fully convolutional neural network combined with contextual feature representation (HRNet CFR) to extract cropland directly from high-resolution optical data. Xu et al [22] improved the skip connection in UNet and its loss function (HRUNet) to preserve details, especially the edge details of cropland.…”