Comparative analysis of adaptive and general labeling methods for soybean leaf detection.

Abstract

Soybeans are important due to their nutritional benefits, economic role, agricultural contributions, and various industrial applications. Effective leaf detection plays a crucial role in analyzing soybean growth within precision agriculture. This study examines the influence of different labeling methods on the efficiency of artificial intelligence (AI) based soybean leaf detection. We compare a traditional general labeling technique against a new context-aware method that utilizes information about leaf length and bottom extremities. Both approaches were employed to train a YOLOv5L deep learning model using high-resolution soybean imagery. Results show that the general labeling method excelled with soybean varieties that have wider internodes and distinctly separated leaves. In contrast, the context-aware labeling method outperformed the general approach for medium soybean varieties characterized by narrower internodes and overlapping leaves. By optimizing labeling strategies, the accuracy and efficiency of AI-based soybean growth analysis can be significantly improved, particularly in high-throughput phenotyping systems. Ultimately, the findings suggest that a thoughtful approach to labeling can enhance agricultural management practices, contributing to better crop monitoring and improved yields.

Code and data availability

The supplied blocks describe soybean image collection from the RDA Crop phenomics research center, YOLOv5L training, and labeling methods, but contain no data availability statement, no public repository deposit, no author code release, and no public URL for datasets, images, annotations, or trained models. The Data/代码

No evidence-backed public reproduction asset is currently recorded.