改进YOLOv2卷积神经网络的多类型合作目标检测

王建林; 付雪松; 黄展超; 郭永奇; 王汝童; 赵利强

doi:10.3788/OPE.20202801.0251

您当前的位置：

首页 >

文章列表页 >

改进YOLOv2卷积神经网络的多类型合作目标检测

信息科学 | 更新时间：2020-08-13

- 改进YOLOv2卷积神经网络的多类型合作目标检测
- Multi-type cooperative targets detection using improved YOLOv2 convolutional neural network
- 光学精密工程 2020年28卷第1期页码：251-260
- 作者机构：
  
  北京化工大学信息科学与技术学院，北京 100029
- 作者简介：
  
  [ "王建林 (1965-)，男，陕西西安人，教授，1993年和1997年于天津大学获得硕士和博士学位，主要从事视觉检测技术、智能检测与传感技术等方面的研究。E-mail:wangjl@mail.buct.edu.cn" ]
  [ "付雪松 (1990-)，男，内蒙古赤峰人，博士研究生，2013年于北京化工大学获得学士学位，主要从事智能检测、视觉检测等方面的研究。E-mail：2015400133@mail.buct.edu.cn" ]
- 基金信息：
  
  国家重点研发计划资助项目(2017YFF0107303)
- DOI：10.3788/OPE.20202801.0251
  中图分类号： TP394.1; TH691.9
- 收稿日期：2019-07-08，
  
  录用日期：2019-9-12，
  
  纸质出版日期：2020-01-25
- 稿件说明：
移动端阅览
王建林, 付雪松, 黄展超, 等. 改进YOLOv2卷积神经网络的多类型合作目标检测[J]. 光学精密工程, 2020,28(1):251-260.

Jian-lin WANG, Xue-song FU, Zhan-chao HUANG, et al. Multi-type cooperative targets detection using improved YOLOv2 convolutional neural network[J]. Optics and precision engineering, 2020, 28(1): 251-260.
王建林, 付雪松, 黄展超, 等. 改进YOLOv2卷积神经网络的多类型合作目标检测[J]. 光学精密工程, 2020,28(1):251-260. DOI： 10.3788/OPE.20202801.0251.

Jian-lin WANG, Xue-song FU, Zhan-chao HUANG, et al. Multi-type cooperative targets detection using improved YOLOv2 convolutional neural network[J]. Optics and precision engineering, 2020, 28(1): 251-260. DOI： 10.3788/OPE.20202801.0251.

摘要

针对大型构件三维精密测量中构件结构复杂、测量环境变化等导致的合作目标检测精度低的问题，提出一种改进YOLOv2卷积神经网络的多类型合作目标检测方法。首先，利用WGAN-GP生成对抗网络扩增合作目标图像样本数量；其次，采用卷积层密集连接代替YOLOv2基础网络的逐层连接增强图像特征信息流，引入空间金字塔池化汇聚图像局部区域特征，构建改进YOLOv2卷积神经网络的多类型合作目标检测方法；最后，采用增强的目标图像样本数据集训练改进YOLOv2卷积神经网络的多类型合作目标检测模型，实现多类型合作目标检测。实验结果表明：采用多类型合作目标图像数据集测试，多类型合作目标检测精度达到90.48%，目标检测速度为58.7 frame/s。该方法具有较高的检测精度和速度，鲁棒性好，满足大型构件三维精密测量中多类型合作目标检测的要求。

Abstract

In the three-dimensional (3D) precision measurement of large component

the detection accuracy of cooperative targets is low due to complex structure of large components and various measurement environment. To solve this problem

a multi-type cooperative target detection method using improved YOLOv2 convolutional neural network was proposed. Firstly

the data augmentation method combined with WGAN-GP was employed to amplify the number of cooperative target images. Secondly

the convolutional layer dense connection was used instead of the YOLOv2 basic network layer-by-layer connection to enhance image feature information flow

and the spatial pyramid pooled was introduced to convergence image local area feature. Base on those two parts

the multi-type cooperative targets detection method with improved YOLOv2 convolutional neural network was constructed. Finally

the multi-type cooperative targets detection model with improved YOLOv2 convolutional neural network was trained by the augmentation dataset for detecting the multi-type cooperative targets. The experimental results of multi-type cooperative target detection indicate that

detection precision of the proposed method is up to 90.48%

and detection speed is 58.7 frame per second by using image dataset of multi-type cooperative targets to test. This method has higher precision

rapid speed and strong robustness

which can satisfy the multi-type cooperation targets' detection requirements for 3D precision measurement of the large component.

关键词

Keywords

references

HAN J, ZHANG D, CHENG G, et al .. Advanced Deep-Learning techniques for salient and category-specific object detection: a survey[J]. IEEE Signal Processing Magazine , 2018, 35(1):84-100.

FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al .. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.

李新德, 杨伟东, DEZERT JEAN.一种飞机图像目标多特征信息融合识别方法[J].自动化学报, 2012, 38(8):1298-1307.

Li X D, YANG W D, DEZERT J. An airplane image target's multi-feature fusion recognition method[J]. Acta Automatica Sinica , 2012, 38(8):1298-1307. (in Chinese)

初广丽, 王延杰, 邸男, 等.复杂场景中航天器靶标的快速识别[J].光学精密工程, 2016, 24(4):865-872.

CHU G L, WANG Y J, DI N, et al .. Fast recognition of aircraft target in complex scenes[J]. Opt. Precision Eng ., 2016, 24(4): 865-872. (in Chinese)

罗志伟, 杨玉龙, 李志红. BGA焊球视觉检测算法及系统设计[J].光学精密工程, 2018, 26(9):63-70.

LUO ZH W, YANG Y L, LI ZH H. Design of vision detection algorithm and system for BGA welding balls[J]. Opt. Precision Eng ., 2018, 26(9): 63-70. (in Chinese)

王慧利, 朱明, 蔺春波, 等.光学遥感图像中复杂海背景下的舰船检测[J].光学精密工程, 2018(3):723-732.

WANG H L, ZHU M, LIN CH B, et al .. Ship detection of complex sea background in optical remote sensing image[J]. Opt. Precision Eng. , 2018, 26(3): 723-732. (in Chinese)

GIRSHICK R, DONAHUE J, DARRELL T, et al .. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Columbus , OH , USA : IEEE , 2014: 580-587.

GIRSHICK R. Fast R-CNN[C]. 2015 International Conference on Computer Vision ( ICCV ). Santiago , Chile : IEEE , 2015: 1440-1448.

RE S, HE K, GIRSHICK R, et al .. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017, 39(6): 1137-1149.

REDMON J, DIVVALA S, GIRSHICK R, et al .. You Only Look Once: Unified, Real-time Object Detection[C]. 2016 ( CVPR ). Las Vegas , NV , USA : IEEE , 2016: 779-788.

LIU W, ANGUELOV D, ERHAN D, et al .. SSD: Single Shot Multi-box Detector[C]. 2016 European Conference on Computer Vision ( ECCV ). Amsterdam , The Netherlands : Springer , 2016, 9905: 21-37.

REDMON J, FARHADI A. YOLO9000: Better, Faster, Stronger[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Honolulu , HI , USA : IEEE , 2017: 6517-6525.

FU C-Y, LIU W, RANGA A, et al .. DSSD: Deconvolutional single shot detector[J]. arXiv:1701.06659, 2017.

REDMON J, FARHADI A. YOLOv3: An incremental improvement[J]. arXiv:1804.02767, 2018.

HE K, ZHANG X, REN S, et al ..Deep Residual Learning for Image Recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Las Vegas , NV , USA : IEEE , 2016: 770-778.

ZHOU P, NI B, GENG C, et al .. Scale-Transferrable Object Detection[C]. 2018 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Salt Lake City , Utah , USA : IEEE , 2018: 528-537.

HUANG G, LIU Z, LAURENS V D M, et al .. Densely Connected Convolutional Networks[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Honolulu , HI , USA : IEEE , 2017: 2261-2269.

JEONG J, PARK H, KWAK N. Enhancement of Ssd by Concatenating Feature Maps for Object Detection[C]. British Machine Vision Conference , 2017

GULRAJANI I, AHMED F, ARJOVSKY M, et al .. Improved training of wasserstein GANs[C]. Advances in Neural Information Processing Systems , 2017: 5767-5777.

GOODFELLOW I J, POUGET A J, MIRZA M, et al .. Generative Adversarial Nets[C]. Neural Information Processing Systems , 2014: 2672-2680.

HE K, ZHANG X, REN S, et al .. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015, 37(9): 1904-1916.

浏览量

346

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

电力巡检中的偏振图像特征融合

超融合残差行进几何感知的遥感目标检测

半监督式野生动物夜间目标端到端检测

伪标签置信度调控结直肠癌病理图像半监督语义分割

融合生成对抗网络的大气无线光信道密钥提取