To address the challenges of harvest crate localization caused by varying illumination, partial occlusion, and background interference in unstructured farmland environments, as well as the high costs and low efficiency associated with traditional manual harvesting, this paper proposes FAL-YOLO, a lightweight keypoint detection model. Using YOLOv8n-Pose as the baseline framework, the model integrates a C2f-ContextGuided backbone and a Slim-Neck feature fusion layer. Furthermore, a LSCD-LQE lightweight detection head is designed, and an Inner-MPDIoU loss function is introduced to enhance keypoint detection performance under complex backgrounds and occluded conditions. Experimental results on the self-constructed farmland harvest crate dataset indicate that FAL-YOLO requires only 1.71 M parameters and 4.5 GFLOPs of computational cost, representing reductions of 44.5% and 45.8% compared to YOLOv8n-Pose, while achieving an mAP@0.5 of 94.9%, corresponding to an improvement of 1.2%. Additionally, by establishing correspondences between keypoints and the 3D model through the PnP algorithm, the 3D pose of the crate can be reconstructed, providing reliable spatial input for robotic arm manipulation. The results demonstrate that FAL-YOLO achieves an effective balance between model lightweightness and detection accuracy, providing an efficient solution for automatic identification and grasping of harvest crates in farmland environments.
Huang et al. (Mon,) studied this question.