TRANSFORMER NETWORKS TO CLASSIFY WEEDS AND CROPS IN HIGH-RESOLUTION AERIAL IMAGES FROM NORTH-EAST SERBIA

Abstract

The intricate backgrounds present in crop and field images, coupled with the minimal contrast between weed- infested areas and the background, can lead to considerable ambiguity. This, in turn, poses a significant challenge to the resilience and precision of crop identification models. Identifying and mapping weeds are pivotal stages in weed control, essential for maintaining crop health. A multitude of research efforts underscore the significance of leveraging remote sensing technologies and sophisticated machine learning algorithms to enhance weed management strategies. Deep learning techniques have demonstrated impressive effectiveness in a range of agricultural remote sensing applications, including plant classification and disease detection. High-resolution imagery was collected using a UAV equipped with a high-resolution camera, which was strategically deployed over weed, sunflower, tobacco and maize fields to collect data. The VIT models achieved commendable levels of accuracy, with test accuracies of 92.97% and 90.98% in their respective evaluations. According to the experimental results, transformers not only excel in crop classification accuracy, but also achieve higher accuracy with a smaller sample size. Swin-B16 achieved an accuracy of 91.65% on both the training and test datasets. Compared to the other two ViT models, the loss value is significantly lower by half, at 0.6450.