SepHRNet: Generating High-Resolution Crop Maps from Remote Sensing imagery using HRNet with Separable Convolution

TL;DR

This paper introduces SepHRNet, a deep learning model combining HRNet, separable convolutions, and self-attention to generate high-resolution crop maps from satellite imagery, achieving high accuracy and outperforming existing models.

Contribution

The paper presents a novel deep learning architecture that integrates HRNet with separable convolutions and self-attention for improved crop mapping from remote sensing data.

Findings

Achieved 97.5% classification accuracy

Obtained 55.2% IoU in crop map generation

Outperformed state-of-the-art models on Zuericrop dataset

Abstract

The accurate mapping of crop production is crucial for ensuring food security, effective resource management, and sustainable agricultural practices. One way to achieve this is by analyzing high-resolution satellite imagery. Deep Learning has been successful in analyzing images, including remote sensing imagery. However, capturing intricate crop patterns is challenging due to their complexity and variability. In this paper, we propose a novel Deep learning approach that integrates HRNet with Separable Convolutional layers to capture spatial patterns and Self-attention to capture temporal patterns of the data. The HRNet model acts as a backbone and extracts high-resolution features from crop images. Spatially separable convolution in the shallow layers of the HRNet model captures intricate crop patterns more effectively while reducing the computational cost. The multi-head attention mechanism captures long-term temporal dependencies from the encoded vector representation of the images. Finally, a CNN decoder generates a crop map from the aggregated representation. Adaboost is used on top of this to further improve accuracy. The proposed algorithm achieves a high classification accuracy of 97.5\% and IoU of 55.2\% in generating crop maps. We evaluate the performance of our pipeline on the Zuericrop dataset and demonstrate that our results outperform state-of-the-art models such as U-Net++, ResNet50, VGG19, InceptionV3, DenseNet, and EfficientNet. This research showcases the potential of Deep Learning for Earth Observation Systems.