An Attention-Enhancing Cascading RetNet Framework for Vegetation Conservation

Vegetation protection is a crucial task in agricultural production. Due to the diversity of tree species and their varied growth conditions, the demand for protective ash spray varies greatly, posing multifaceted challenges of experience and technology for manual operations. This paper proposes a framework that integrates an attention mechanism with RetNet for predicting tree growth conditions. It extracts and fuses core visual features from both tree species and growth conditions to achieve high-quality classification of tree growth status, thereby guiding the concentration of ash spray. Quantitative experimental results demonstrate that the proposed approach outperforms the baseline in accuracy, recall, and other metrics. These results indicate that the proposed framework is helpful for the optimization of vegetation protection workflow in the context of human-machine collaboration.