MeViT: Medium-Resolution Vision Transformer for Semantic Segmentation on Landsat Satellite Imagery for Agriculture in Thailand

Abstract

Semantic segmentation is a fundamental task in remote sensing image analysis that aims to classify each pixel in an image into different land use and land cover (LULC) segmentation task. In this paper, We propose MeViT (Medium-Resolution Vision Transformer) on Landsat satellite imagery for the main economic crops in Thailand as follows: (i) para rubber, (ii) corn, and (iii) pineapple. Therefore, our proposed MeViT enhances Vision Transformers (ViTs), one of the modern deep learning on computer vision tasks, to learn semantically rich and spatially-precise multi-scale representations by integrating medium-resolution multi-branch architectures with ViTs. We revised mixed-scale convolutional feedforward networks (MixCFN) by incorporating multiple depth-wise convolution paths to extract multi-scale local information to balance the model’s performance and efficiency. To evaluate the effectiveness of our proposed method, we conduct extensive experiments on the publicly available dataset of Thailand scenes and compare the results with several state-of-the-art deep learning methods such as AutoDeeplab1, SwinTransformer2, Twins3, CSWinTransformer4, SegFormer5, and HRViT6. The experimental results demonstrate that our proposed MeViT outperforms existing methods and performs better in the semantic segmentation of Thailand scenes The evaluation metrics used are precision, recall, F1 score, and mean Intersection over Union (IoU). Among the models compared, MeViT, our proposed model, achieves the best performance in all evaluation metrics. MeViT achieves a precision of 0.9222, a recall of 0.9469, an F1 score of 0.9344, and a mean IoU of 0.8363. These results demonstrate the effectiveness of our proposed approach in accurately segmenting Thai Landsat-8 data. The achieved F1 score of overall using our proposed MeViT is 93.44% that is a major significance of this work.