Hao Teng

Automatic inspection of small, irregular stamped parts remains challenging due to their compact size, random orientation on conveyors, and susceptible metallic surface reflections, coupled with local, weak, and densely distributed defects. This study presents an integrated vision-based dynamic defect detection and robotic sorting system to address these issues. The framework seamlessly unifies conveyor-based image acquisition, YOLO-CGMS-based defect recognition, hand–eye coordinate mapping, and Delta robot trajectory planning. To drive real-time visual perception, the YOLO-CGMS architecture modifies the YOLOv8n baseline by incorporating C2f-CRM, GRF-SPPF, MCA, and Inner-GIoU modules, optimizing small-defect feature extraction and bounding-box regression. Evaluated on a factory-collected dataset, YOLO-CGMS achieved an mAP50 of 88.7% and an inference speed of 236.23 frames/s, using only 2.8 M parameters and 7.3 GFLOPs. Compared with YOLOv8n, mAP and execution speed increased by 5.1 percentage points and 12.18 frames/s, respectively, while the parameter size and computational cost dropped by 0.2 M and 0.8 GFLOPs. Furthermore, physical sorting capability was validated on a developed prototype platform, yielding a mean hand–eye positioning error of 2.66 mm. Across 200 dynamic trials, the system successfully sorted 161 defective workpieces, translating to an 80.5% success rate and a mean cycle time of 2.6 s per part. These findings confirm that the proposed system reliably links closed-loop visual perception with physical execution, providing a practical foundation for the automated quality control of complex stamped components.

To reduce confusion between adjacent maturity categories, as well as false detections and low detection accuracy caused by complex backgrounds in tomato object detection, this study develops an improved YOLOv7-based model, named YOLO-RCM (Reduce classes misjudgment). First, a stability-enhanced ECANet channel attention module is embedded into the feature pyramid network (FPN) to strengthen discriminative channel responses. Second, a DCNv2-based deformable convolution enhancement module, namely DCNConv with adaptive magnitude constraints, is incorporated into the backbone network to alleviate feature misalignment caused by shape variation, partial occlusion, and fine-grained appearance differences in tomato maturity detection. Third, the WIoU v3 loss function is adopted to refine bounding box regression stability. The model was evaluated on the public Laboro Tomato dataset and TomatOD dataset. Experimental results indicate that YOLO-RCM obtains 83.7% Precision and 89.6% mAP@0.5, exceeding the baseline by 3.3 and 1.2 percentage points, respectively. Its Recall is 80.5%, with a decrease of 0.8 percentage points, whereas GFLOPs are reduced to 96.9, 6.3 lower than the baseline. These results indicate that the proposed method improves detection accuracy and computational efficiency while maintaining an almost unchanged model scale. The confusion matrix and PR curves further show that YOLO-RCM can effectively mitigate misdetections associated with adjacent maturity stages and complex scenes. In the external-dataset robustness test, Precision and mAP@0.5 are improved by 5.8 and 4.0 percentage points over the baseline, respectively, confirming the generalization ability of the proposed model. The main contribution of this study lies in improving tomato maturity detection from three complementary aspects: channel feature discrimination, local geometric perception, and bounding box regression stability. The study offers a practical technical reference for intelligent tomato harvesting systems in complex agricultural environments.

Strawberry detection in complex orchard environments remains a challenging task due to frequent leaf occlusion, fruit overlap, and illumination variability. To address these challenges, this study presents an improved lightweight detection framework, DS-YOLO, based on YOLOv8n. First, the backbone network of YOLOv8n is replaced with the lightweight StarNet to reduce the number of parameters while preserving the model’s feature representation capability. Second, the Conv and C2f modules in the Neck section are replaced with SlimNeck’s GSConv (hybrid convolution module) and VoVGSCSP (cross-stage partial network) modules, which effectively enhance detection performance and reduce computational burden. Finally, the original CIoU loss function is substituted with WIoUv3 to improve bounding box regression accuracy and overall detection performance. To validate the effectiveness of the proposed improvements, comparative experiments were conducted with six mainstream object detection models, four backbone networks, and five different loss functions. Experimental results demonstrate that the DS-YOLO achieves a 1.7 percentage point increase in mAP50, a 1.5 percentage point improvement in recall, and precision improvement of 1.3 percentage points. In terms of computational efficiency, the number of parameters is reduced from 3.2M to 1.8M, and computational cost decreases from 8.1G to 4.9G, corresponding to reductions of 43% and 40%, respectively. The improved DS-YOLO model enables real-time and accurate detection of strawberry fruits in complex environments with a more compact network architecture, providing valuable technical support for automated strawberry detection and lightweight deployment.