基于改进YOLOv11n-seg的木椅腿实例分割方法OA
Instance Segmentation Method for Wooden Chair Legs Based on Improved YOLOv11n-seg
准确识别木椅腿并定位抓取位置是实现机器人高效上料作业的关键,然而现有的基于实例分割图像处理算法难以兼具精度与速度,且模型参数量庞大,不利于工业场景实际部署,在复杂场景下还容易出现漏检和误检情况.针对上述问题,提出一种基于改进的YOLOv11n-seg模型,通过引入轻量化模块并结合新的损失函数,使其兼具精度与效率,优化部署性能.具体改进方法为,首先引入RepViT作为骨干网络,增强特征提取能力并降低计算复杂度;其次在颈部网络中使用轻量化动态上采样器DySample,提升特征融合效率;最后使用Shape-IoU替换传统CIoU Loss损失函数,优化检测框的回归精度.消融试验和对比试验结果表明,改进后的YOLOv11n-seg算法较原算法相比在推理速度和分割精度上均有提升,其中,模型整体参数量下降11.31%,浮点运算量下降9.62%,分割平均精度均值mAP0.5:0.95增长4.61个百分点,验证了改进算法的有效性,为实现下一步机器人精准定位并抓取木椅腿提供技术支持.
Accurate identification of wooden chair legs and localization of grasping positions are crucial for achieving effi-cient robotic loading operations.However,existing instance segmentation-based image processing algorithms often struggle to balance accuracy and speed,and their large number of parameters hinders practical deployment in industrial scenarios.Furthermore,these algorithms are prone to missed detections and false detections in complex environments.To address the aforementioned issues,this paper proposes an improved YOLOv11n-seg model.By incorporating light-weight modules and a novel loss function,the model achieves a favorable balance between accuracy and efficiency,thereby optimizing its deployment performance.The specific improvements are as follows:firstly,RepViT is introduced as the backbone network to enhance feature extraction capability while reducing computational complexity.Secondly,the lightweight dynamic upsampler DySample is adopted in the neck network to improve feature fusion efficiency.Fi-nally,Shape-IoU is used to replace the traditional CIoU Loss loss function,optimizing the regression accuracy of bound-ing boxes.Results of ablation experiments and comparative experiments demonstrate that the improved YOLOv11n-seg algorithm outperforms the original model in both inference speed and segmentation accuracy.Specifically,the total num-ber of model parameters is reduced by 11.31%,the floating-point operations(FLOPs)are decreased by 9.62%,and the mean average precision for segmentation(mAP@0.5:0.95)is increased by 4.61 percentage points.These findings vali-date the effectiveness of the improved algorithm and provide technical support for the subsequent precise positioning and grasping of wooden chair legs by robots.
徐冀策;王海艳;王宁;魏泽辉;吴哲
东北林业大学 机电工程学院,哈尔滨 150040东北林业大学 机电工程学院,哈尔滨 150040东北林业大学 机电工程学院,哈尔滨 150040东北林业大学 机电工程学院,哈尔滨 150040东北林业大学 机电工程学院,哈尔滨 150040
农业科技
木椅腿加工实例分割YOLO轻量化深度学习
Wooden chair leg machininginstance segmentationYOLOlightweightdeep learning
《森林工程》 2026 (5)
1022-1032,11
国家重点研发计划项目(2024YFD2200700).
评论