YOLO-Sp: A Novel Transformer-Based Deep Learning Model for Achnatherum splendens Detection

The growth of Achnatherum splendens (A. splendens) inhibits the dominant grassland herbaceous species, resulting in a loss biomass and worsening ecological environment. Therefore, it is crucial to identify dynamic development A. adequately. This study intended offer transformer-based detection model named YOLO-Sp through ground-based visible spectrum proximal sensing images. achieved 98.4% 95.4% AP values object image segmentation for splendens, respectively, outperforming previous SOTA algorithms. research indicated that Transformer had great potential monitoring splendens. Under identical training settings, value was greater by more than 5% YOLOv5. model’s average accuracy 98.6% trials conducted at genuine test sites. experiment revealed factors such as amount light, degree grass growth, camera resolution would affect accuracy. could contribute assessing plant grasslands.