基于卷积神经网络的视觉闭环检测研究

杨孟军; 苏成悦; 陈静; 张洁鑫

doi:10.12052/gdutxb.180068

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于卷积神经网络的视觉闭环检测研究

综合研究 | 更新时间：2026-05-27

- 基于卷积神经网络的视觉闭环检测研究
- Loop Closure Detection for Visual SLAM Using Convolutional Neural Networks
- 广东工业大学学报 2018年35卷第5期页码：31-37
- 作者机构：
  
  广东工业大学　物理与光电工程学院,广东,广州,510006
- 作者简介：
  
  杨孟军(1988–)，男，硕士研究生，主要研究方向为机器人控制技术、机器视觉
  苏成悦(1961–)，男，教授，硕士生导师，主要研究方向为应用物理、机器视觉. E-mail：scy.gdut@163.com
- 基金信息：
  
  国家自然科学基金青年科学基金资助项目(61305069);广东省信息产业发展专项现代信息服务业项目(2150510)
- DOI：10.12052/gdutxb.180068
  中图分类号： TP242
- 网络首发：2018-07-10，
  
  纸质出版：2018
- 稿件说明：
移动端阅览
杨孟军, 苏成悦, 陈静, 张洁鑫. 基于卷积神经网络的视觉闭环检测研究[J]. 广东工业大学学报, 2018, 35(5): 31-37.

Yang Meng-jun, Su Cheng-yue, Chen Jing, et al. Loop Closure Detection for Visual SLAM Using Convolutional Neural Networks[J]. 2018, 35(5): 31-37.
杨孟军, 苏成悦, 陈静, 张洁鑫. 基于卷积神经网络的视觉闭环检测研究[J]. 广东工业大学学报, 2018, 35(5): 31-37. DOI： 10.12052/gdutxb.180068.

Yang Meng-jun, Su Cheng-yue, Chen Jing, et al. Loop Closure Detection for Visual SLAM Using Convolutional Neural Networks[J]. 2018, 35(5): 31-37. DOI： 10.12052/gdutxb.180068.

摘要

闭环检测是视觉SLAM中很重要的一部分

成功地检测出闭环能减小定位算法所产生的累积里程漂移. 鉴于深度卷积神经网络在分类问题上的优越表现

本文首次将应用于图像分类的vgg16-places365 卷积神经网络模型应用于视觉SLAM闭环检测中

将配准数据输入训练好的该卷积神经网络

其各个隐藏层的输出对应于图像特征表示. 然后通过实验比较选用匹配精度较高的中间层完成场景特征提取

通过计算场景特征的相似性得到闭环区域. 最后在闭环检测数据集上进行实验测试. 测试结果表明

相比于传统的闭环检测方法

vgg16-places365 卷积神经网络模型在相同召回率条件下准确率要高约3%; 对于特征提取时间

在CPU上要快约5~10倍

而在GPU上更是比传统人工设计特征的闭环检测快近100倍.

Abstract

The detection of loop closure is a very important part of visual slam. Successful detection of loop closure can reduce the accumulated mileage drift generated by positioning algorithms. In view of the superior performance of deep convolutional neural networks in classification

the network of VGG16-Places 365 is used

which is widely used in image classification to the area of loop closure detection for the first time. The registration data are input into a trained convolutional neural network

and the output of each hidden layer corresponds to the image feature representation. Then

experiments are implemented to get an intermediate layer with higher matching accuracy

which is used to complete scene feature extraction

and then the loop closure region is obtained by calculating the similarity of the scene feature; finally

experimental tests are performed on loop closure detection dataset. Test results show that the accuracy rate of the VGG16-Places 365 convolutional neural network model is about 3% higher than the traditional ways under the same recall rate; and the the feature extraction time is about 5 to 10 times faster on the CPU and 100 times on the GPU.

关键词

Keywords

references

BAILEY T, DURRANT-WHYTE H. Simultaneous localization and papping: part I [J]. IEEE Robotics Automation Magazine, 2006, 13(2): 99-110.

WANG H, Hou Z, CHENG L, TAN M. Online mapping with a mobile robot in dynamic and unknown environments [J]. International Journal of Modelling Identification Control, 2008, 4(4): 415-423.

FILLIAT D. A visual bag of words method for interactive qualitative localization and mapping [C]//Robotics and Automation, IEEE International Conference. Roma: IEEE, 2007: 3921-3926.

LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

BAY H, TUYTELAARS T, GOOL L. SURF: Speeded up robust features BT - Computer Vision–ECCV 2006 [J]. Computer Vision-ECCV, 2006, 3951: 404-417.

RUBLEE E, RABAUD V, KONOLIGE K. Orb: an efficient alternative to sift or surf [C]// Computer Vision, IEEE International Conference. Barcelona, Spain: IEEE, 2011: 2564-2571.

CUMMINS M, NEWMAN P. Highly scalable appearance-only SLAM - FAB-MAP 2.0 [M]// Proceedings of Robotics: Science and Systems. Seattle, 2009: 1-8.

CUMMINS M, NEWMAN P. FAB-MAP: Probabilistic localization and mapping in the space of appearance [J]. International Journal of Robotics Research, 2008, 27(6): 647-665.

LIU Y, ZHANG H. Visual loop closure detection with a compact image descriptor [J]. IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura-Algarve, Portugal: IEEE, 2012: 1051-1056.

GAO X, ZHANG T. Unsupervised learning to detect loops using deep neural networks for visual SLAM system [J]. Autonomous Robots, 2017, 41(1): 1-18.

GAO X, ZHANG T. Loop closure detection for visual slam systems using deep neural networks [C]// Technical commitee on control theory, Chinese control conference. Hangzhou: Chinese Association of Automation, 2015: 5851-5856.

CHATFIELD K, SIMONYAN K, VEDALDI A, et al . Return of the devil in the details: delving deep into convolutional nets [J ] . Computer Science, 2014: 1-11.

WAN J, WANG D Y. Deep learning for content-based image retrieval: a comprehensive study [C]// Multimedia, ACM International Conference. Istanbul: ACM, 2014: 157-166.

KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks [C]// Internationl Conference on Neural Information Processing. Doha, Qatar: ACM, 2012, 60(2): 1097-1105.

BABENKO A, SLESAREV A, CHIGORIN A. Neural codes for image retrieval [C]// Computer Vision, European Conference. Zurich: Springer, 2014: 584-599 .

HE Y L, CHEN J T, ZENG B. A fast loop closure detection method based on lightweight convolutional neural network [J]. Computer Engineering, 2018, 44(6): 182-187.

XIA Y, LI J, QI L, et al. Loop closure detection for visual SLAM using PCANet features [C] // Neural Networks, IEEE International Joint Conference. Vancouver, Canada: IEEE, 2016: 2274-2281.

HOU Y, ZHANG H, ZHOU S. Convolutional neural network-based image representation for visual loop closure detection [C]// Information and Automation, IEEE International Conference. Lijiang, China: IEEE, 2015: 2238-2245.

JIA Y Q, SHELHAMER E, JEFF D. Caffe: convolutional architecture for fast feature embedding [C]// Multimedia, ACM International Conference. Istanbul: ACM, 2014: 675-678.

SHANG W, SOHN K, ALMEIDA D, et al. Understanding and improving convolutional neural networks via concatenated rectified linear units [C]// Machine Learning, IEEE International Conference. New York: IEEE, 2016: 1-17.

ZHOU B, KHOSLA A, LAPEDRIZA A, et al . Places: An image database for deep scene understanding [J ] . Journal of Vision, 2016, 17(10): 1-12.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种基于多尺度的多层卷积稀疏编码网络

基于YOLOv4-MP的绝缘子爆裂缺陷检测方法

基于特征融合的深度学习目标检测算法研究

基于受限样本的深度学习综述与思考

一种轻量级的高光谱遥感图像分类方法