排爆车智能视觉目标检测系统

论文摘要

对复杂环境而言，排爆车所作的作业要同时完成两项任务：查清爆炸物、确定机械臂可用的位置。文中将实时检测同6D位姿估计结合起来，设计为车载视觉方案。检测部分是经过改良的YOLOv5s——在SPPF之前利用坐标注意力、把边界框回归损失由CIOU改作EIOU，以类别及边界框形式给出结果；判断为高威胁的物体按框截取区域后即用FoundationPose处理，结合已知三维模型的特征做6自由度位姿解算。所涉两个模块用优先级异步调度器连接。检测端针对未爆弹数据所获的指标是精确率85.3%、召回率67.7%、mAP77.0%，比原版YOLOv5s各项数值分别多0.7、1.4、1.1个点，其结果满足机械臂自动定位的需要，验证了该方法的可行性与效率。

参考文献

• [1]曾俊,卢瑞涛,杨小冈,等.六旋翼无人机空基智能排爆系统设计与实现[J].电光与控制,2023,30(5):61-65.
• [2]于涵,李一染,毕书博,等.一种基于随动视觉的排爆机器人自主抓取系统[J].计算机工程,2021,47(1):298-304,311.
• [3]REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:779-788.
• [4]LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the European Conference on Computer Vision,2016:21-37.
• [5]MA N, ZHANG X, ZHENG H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision,2018:116-131.
• [6]邱锦,刘健,沈芸亦,等.基于YOLOv5手榴弹检测算法的轻量化研究[J].兵器装备工程学报,2023,44(6):35-41.
• [7]范凤欢.基于YOLOv5s的未爆弹识别算法研究[D].廊坊:北华航天工业学院,2025.
• [8]XIANG Y, SCHMIDT T, NARAYANAN V, et al. PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes[C]//Robotics: Science and Systems XIV,2018.
• [9]PENG S, LIU Y, HUANG Q, et al. PVNet: pixel-wise voting network for 6DoF pose estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2019:4561-4570.
• [10]WEN B, YANG W, KAUTZ J, et al. FoundationPose: unified 6D pose estimation and tracking of novel objects[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2024:17868-17879.
• [11]JOCHER G. Ultralytics YOLOv5[EB/OL]. (2020-06-26) [2026-08-10].github.com
• [12]HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2021:13713-13722.
• [13]ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J].Neurocomputing,2022,506:146-157.
• [14]LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the European Conference on Computer Vision,2014:740-755.
• [15]LAINE S, HELLSTEN J, KARRAS T, et al. Modular primitives for high-performance differentiable rendering[J].ACM Transactions on Graphics,2020,39(6):194.
• [16]HINTERSTOISSER S, LEPETIT V, ILIC S, et al. Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes[C]//Proceedings of the Asian Conference on Computer Vision,2012:548-562.
• [17]HODAN T, MICHEL F, BRACHMANN E, et al. BOP: benchmark for 6D object pose estimation[C]//Proceedings of the European Conference on Computer Vision,2018:19-34.

出版声明与信息公开

标准学术引用格式