A customized density map model and segment anything model for cotton boll number, size, and yield prediction in aerial images

Chenjiao Tan, Jin Sun, Huaibo Song, Changying Li

Abstract: Highlights•A density map model was customized to accurately count and localize cotton bolls.•Segmentation anything model was employed to estimate boll size with point prompts.•The proposed approach surpasses other four methods, achieving lowest error.•Boll number has a higher correlation with seed cotton yield compared to boll size.