光学精密工程2024，Vol.32Issue(10)：1595-1605,11.DOI:10.37188/OPE.20243210.1595
改进YOLOv7的服务机器人密集遮挡目标识别
A method for dense occlusion target recognition of service robots based on improved YOLOv7
摘要
Abstract
Aiming at the problem of poor recognition effect due to dense occlusion of the target to be recog-nized during visual grasping of service robots,we propose to improve the dense occlusion target recogni-tion method for service robots with YOLOv7.First,in order to improve the problem of recognition diffi-culties caused by the loss of feature information of densely occluded targets,a deep over-parameterized convolution was used to construct a deep over-parameterized high-efficiency aggregation network,and dif-ferent convolution kernels were used to operate on each channel to enhance the network sensing ability,so that the network focused on the features of the target's uncovered area;second,in order to suppress the influ-ence caused by dense occlusions and indistinguishable target boundaries on recognition,the coordinate atten-tion mechanism was embedded into the backbone network.This enabled the network to obtain target posi-tion information and paid more attention to the important areas in the feature map,thereby enhancing the ca-pability of the network to extract features;finally,the Ghost network was used to improve the lightweight-ing,reduce the number of parameters of the network model and the number of floating-point operations to re-alize the lightweighting,reduce the memory occupation of the model,and increase the model operation effi-ciency.Comparison experiments were conducted on the model in the self-constructed dataset and the public dataset respectively,and the experimental results show that the improved model achieves a mAP of 92.9%on the self-constructed dataset and 87.8%on the public dataset,which is better than the original method and the other commonly used methods.In this paper,the model reduces the memory footprint while the recogni-tion accuracy and recognition efficiency are improved,and the overall performance is better.关键词
密集遮挡/改进YOLOv7/服务机器人/目标识别Key words
dense occlusion/improved YOLOv7/service robots/target recognition分类
计算机与自动化引用本文复制引用
陈仁祥,邱天然,杨黎霞,余腾伟,贾飞,陈才..改进YOLOv7的服务机器人密集遮挡目标识别[J].光学精密工程,2024,32(10):1595-1605,11.基金项目
国家自然科学基金(No.51975079) （No.51975079）
重庆市教委科学技术研究项目(No.KJZD-M202200701) （No.KJZD-M202200701）
重庆市自然科学基金创新发展联合基金(No.CSTB2023NSCQ-LZX0127) （No.CSTB2023NSCQ-LZX0127）
重庆市研究生联合培养基地项目(No.JDLHPYJD2021007) （No.JDLHPYJD2021007）
重庆市专业学位研究生教学案例库(No.JDALK2022007) （No.JDALK2022007）
重庆市研究生科研创新项目(No.CYS23509) （No.CYS23509）
重庆科技大学科研启动项目(No.ckre202212030) （No.ckre202212030）
