基于Inception-SSD算法的零件识别

余永维; 韩鑫; 杜柳青

doi:10.3788/OPE.20202808.1799

您当前的位置：

首页 >

文章列表页 >

基于Inception-SSD算法的零件识别

信息科学 | 更新时间：2020-08-14

- 基于Inception-SSD算法的零件识别
- Target part recognition based Inception-SSD algorithm
- 光学精密工程 2020年28卷第8期页码：1799-1809
- 作者机构：
  
  重庆理工大学机械工程学院, 重庆 400054
- 作者简介：
  
  [ "余永维(1973-), 男, 重庆长寿人, 博士, 教授, 2014年于四川大学获得博士学位, 主要从事光学检测及机器视觉等方面的研究。E-mail:weiyy@cqut.edu.cn" ]
  杜柳青(1975-), 男, 重庆长寿人, 博士, 教授, 2015于四川大学获得博士学位, 主要从事机床精度分析及智能制造等方面的研究。E-mail:lqdu@cqut.edu.cn DU Liu-qing, E-mail: lqdu@cqut.edu.cn
- 基金信息：
  
  重庆市基础与前沿研究计划基金资助项目(cstc2017jcyjAX0344);国家自然科学基金资助项目(51775074)
- DOI：10.3788/OPE.20202808.1799
  中图分类号： TP273.5
- 收稿日期：2019-11-07，
  
  修回日期：2020-01-04，
  
  录用日期：2020-1-4，
  
  纸质出版日期：2020-08-25
- 稿件说明：
移动端阅览
余永维, 韩鑫, 杜柳青. 基于Inception-SSD算法的零件识别[J]. 光学精密工程, 2020,28(8):1799-1809.

Yong-wei YU, Xin HAN, Liu-qing* DU. Target part recognition based Inception-SSD algorithm[J]. Optics and precision engineering, 2020, 28(8): 1799-1809.
余永维, 韩鑫, 杜柳青. 基于Inception-SSD算法的零件识别[J]. 光学精密工程, 2020,28(8):1799-1809. DOI： 10.3788/OPE.20202808.1799.

Yong-wei YU, Xin HAN, Liu-qing* DU. Target part recognition based Inception-SSD algorithm[J]. Optics and precision engineering, 2020, 28(8): 1799-1809. DOI： 10.3788/OPE.20202808.1799.

摘要

针对传统目标检测方法不能兼顾目标识别精度和检测实时性，且在实际生产复杂工况下识别效果不佳的问题，提出一种基于Inception-SSD框架的零件深度学习识别方法。首先，提出了融合Inception预测结构的SSD优化框架Inception-SSD，将Inception网络结构引入到SSD网络额外层中，并使用批量标准化模块（BN）和残差结构连接，从而捕获更多目标信息而又不会增加网络复杂性，以提高检测准确率而又不影响其检测速度，并增加算法鲁棒性；然后提出在原损失函数基础上增加排斥损失项以改进损失函数，同时采用一种基于加权算法的非极大值抑制方法，克服模型表达能力不足的缺点。最后，将改进前后SSD算法在自制零件数据集上进行训练和测试，实验结果表明：本文方法在实际生产过程复杂情况下检测准确率达到97.8%，相比原SSD算法提升11.7%，检测速率41 frame/s。在提高检测精度同时还保证了实时性，能够满足实际生产环境零件检测需求。

Abstract

In traditional target detection methods

there is a trade-off that exists between target detection accuracy and real-time detection

and the recognition accuracy is inferior under actual

complex production scenarios. To address this

a deep learning detection method based on the Inception-SSD framework was herein proposed.In this framework

an inception network structure was introduced into the extra layer of the SSD network

and batch normalization (BN) and residual structure connection were used to capture target information without increasing network complexity. Owing to this

detection accuracy was improved without the real-time detection performance being affected and the algorithm also becomes more robust. Subsequently

the exclusion loss term based on the original loss function increases

which in turn improves the loss function. Furthermore

a non-maximum suppression weighting method was used to overcome the shortcomings of insufficient expression ability of the model. Finally

the improved SSD algorithm was trained and tested on a self-made dataset and compared with the original and the latest inception-SSD algorithms.Experimental results show that the detection accuracy of the proposed method is 97.8% in an actual production process

which is an improvement of 11.7 percentage points over the original SSD algorithm

and the detection speed is 41 fps. Therefore

the proposed method exhibits superior real-time performance

thereby meeting actual production demands.

关键词

Keywords

references

苑津莎 , 崔克彬 , 李宝树 . 基于ASIFT算法的绝缘子视频图像的识别与定位 . 电测与仪表 , 2015 . ( 7 ): 113 - 119 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dcyyb201507021 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dcyyb201507021 .

J SH YUAN , K B CUI , B SH LI . Identification and location of insulator video images based on ASIFT algorithm . Electrical Measurement & Instrumentation , 2015 . ( 7 ): 113 - 119 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dcyyb201507021 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dcyyb201507021 .

万源 , 李欢欢 , 吴克风 , 等 . LBP和HOG的分层特征融合的人脸识别 . 计算机辅助设计与图形学学报 , 2015 . ( 4 ): 640 - 650 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201504010 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201504010 .

Y WAN , H H LI , K F WU , 等 . Fusion with Layered Features of LBP and HOG for face recognition . Journal of Computer-Aided Design & Computer Graphics , 2015 . ( 4 ): 640 - 650 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201504010 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201504010 .

王丹 , 张祥合 . 基于HOG和SVM的人体行为仿生识别方法 . 吉林大学学报(工学版) , 2013 . 43 ( S1 ): 489 - 492 . http://www.cnki.com.cn/Article/CJFDTotal-JLGY2013S1104.htm http://www.cnki.com.cn/Article/CJFDTotal-JLGY2013S1104.htm .

D WANG , X H ZHANG . Biomimetic recognition method of human behavior based on HOG and SVM . Journal of Jilin University(Engineering and Technology Edition) , 2013 . 43 ( S1 ): 489 - 492 . http://www.cnki.com.cn/Article/CJFDTotal-JLGY2013S1104.htm http://www.cnki.com.cn/Article/CJFDTotal-JLGY2013S1104.htm .

G E HINTON , S OSINDERO , Y W TEH . A fast learning algorithm for deep belief nets . MIT Press Journals , 2006 . 18 ( 7 ): 1527 - 1554 . http://cn.bing.com/academic/profile?id=17d47c184b5c67d42650a0aa38117d73&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=17d47c184b5c67d42650a0aa38117d73&encoded=0&v=paper_preview&mkt=zh-cn .

S REN , K HE , R GIRSHICK , 等 . Faster R-CNN:Towards real-time object detection with region proposal Networks . IEEE Transactions on Pattern Analysis & Machine Intelligence , 2015 . 39 ( 6 ): 1137 - 1149 . http://cn.bing.com/academic/profile?id=89bacd206ab7340f74ac7e7ea03ff929&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=89bacd206ab7340f74ac7e7ea03ff929&encoded=0&v=paper_preview&mkt=zh-cn .

K HE , G GEORGIA , D PIOTR , 等 . Mask R-CNN . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 . 1 - 1 .

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: Unified, real-time object detection[C]. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Piscataway: IEEE , 2016: 779-788.

LIU W, ANGUELOV D, ERHAN D, et al . SSD: single shot multibox detector[C]. Proceedings of the 2016 European Conference on Computer Vision, Cham: Springer , 2016: 21-37.

张博 , 韩广良 . 基于Mask R-CNN的ORB去误匹配方法 . 液晶与显示 , 2018 . 33 ( 8 ): 690 - 696 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201808009 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201808009 .

B ZHANG , G L HAN . ORB removal mis-matching method based on Mask R-CNN . Chinese Journal of Liquid Crystals and Displays , 2018 . 33 ( 8 ): 690 - 696 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201808009 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yjyxs201808009 .

方明 , 孙腾腾 , 邵桢 . 基于改进YOLOv2的快速安全帽佩戴情况检测 . 光学精密工程 , 2019 . 27 ( 5 ): 1196 - 1205 . http://ope.lightpublishing.cn/thesisDetails?columnId=1425752&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1425752&Fpath=&index=-1&l=zh .

M FANG , T T SUN , ZH SHAO . Fast helmet-wearing-condition detection based on improved YOLOv2 . Opt. Precision Eng. , 2019 . 27 ( 5 ): 1196 - 1205 . http://ope.lightpublishing.cn/thesisDetails?columnId=1425752&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1425752&Fpath=&index=-1&l=zh .

王中宇 , 倪显扬 , 尚振东 . 利用卷积神经网络的自动驾驶场景语义分割 . 光学精密工程 , 2019 . 27 ( 11 ): 2429 - 2438 . http://ope.lightpublishing.cn/thesisDetails?columnId=1453147&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1453147&Fpath=&index=-1&l=zh .

ZH Y WANG , X Y NI , ZH D SHANG . Autonomous driving semantic segmentation with convolution neural networks . Opt. Precision Eng. , 2019 . 27 ( 11 ): 2429 - 2438 . http://ope.lightpublishing.cn/thesisDetails?columnId=1453147&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1453147&Fpath=&index=-1&l=zh .

SZEGEDY C, LIU W, JIA Y, et al .. Going deeper with convolutions[C]. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Piscataway: IEEE , 2015: 1-9.

C SZEGEDY , V VANHOUCKE , S IOFFE , 等 . Rethinking the inception architecture for computer vision . IEEE Conference on Computer Vision and Pattern Recognition , 2015 . 2818 - 2826 . http://cn.bing.com/academic/profile?id=1f84f3aab15347ef7b1ebf501d0070d9&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=1f84f3aab15347ef7b1ebf501d0070d9&encoded=0&v=paper_preview&mkt=zh-cn .

C SZEGEDY , S IOFFE , V VANHOUCKE , 等 . Inception-v4, inception-ResNet and the impact of residual connections on learning . Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) , 2016 . 4278 - 4284 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=Arxiv000001372706 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=Arxiv000001372706 .

WANG X, XIAO T, JIANG Y, et al . Repulsion loss: Detecting pedestrians in a crowd[C]. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Piscataway: IEEE , 2018: 7774-7783.

DENG J, DONG W, SOCHER R, et al . Imagenet: A large-scale hierarchical image database[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, New York: IEEE Press , 2009: 248-255.

O VINYALS , A TOSHEV , S BENGIO , 等 . Show and tell:lessons learned from the 2015 mscoco image captioning challenge . IEEE Transactions on Pattern Analysis & Machine Intelligence , 2016 . 39 ( 4 ): 652 - 663 . http://dl.acm.org/citation.cfm?id=3069249 http://dl.acm.org/citation.cfm?id=3069249 .

XIANG Y, MOTTAGHI R, SAVARESE S. Beyond PASCAL: A benchmark for 3D object detection in the wild[C]. IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE Computer Society , 2014: 75-82.

郑志强 , 刘妍妍 , 潘长城 , 等 . 改进YOLO V3遥感图像飞机识别应用 . 电光与控制 , 2019 . 26 ( 4 ): 32 - 36 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz201904006 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz201904006 .

ZH Q ZHENG , Y Y LIU , CH CH PAN , 等 . Application of improved YOLO V3 in aircraft recognition of remote sensing images . Electronics Optics & Control , 2019 . 26 ( 4 ): 32 - 36 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz201904006 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz201904006 .

浏览量

466

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于多分支残差注意力网络的水下图像增强

基于策略梯度和伪孪生网络的异源图像匹配

面向点云分类和分割的形状自适应特征聚合网络

基于机载的红外动态目标视频实时超分辨率重建

数据驱动的多模复合制导信息融合及其试验验证