A Unified Framework for Enhanced 3D Spatial Localization of Weeds via Keypoint Detection and Depth Estimation

In this study, a lightweight deep neural network framework WeedLoc3D based on multi-task learning is proposed to meet the demand of accurate three-dimensional positioning of weed targets in automatic laser weeding. Based on a single RGB image, it both locates the 2D keypoints (growth points) of weeds and estimates the depth with high accuracy. This is a breakthrough from the traditional thinking. To improve the model performance, we introduce several innovative structural modules, including Gated Feature Fusion (GFF) for adaptive feature integration, Hybrid Domain Block (HDB) for dealing with high-frequency details, and Cross-Branch Attention (CBA) for promoting synergy among tasks. Experimental validation on field data sets confirms the effectiveness of our method. It significantly reduces the positioning error of 3D keypoints and achieves stable performance in diverse detection and estimation tasks. The demonstrated high accuracy and robustness highlight its potential for practical application.