一种多视角高精度图片的深度估计方法

doi:10.13190/j.jbupt.2020-255

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (5): 101-106.doi: 10.13190/j.jbupt.2020-255

一种多视角高精度图片的深度估计方法

李剑, 陈宇航

北京邮电大学人工智能学院, 北京 100876

收稿日期:2020-12-01 出版日期:2021-10-28 发布日期:2021-09-06
作者简介:李剑(1976-),男,教授,博士生导师,E-mail:lijian@bupt.edu.cn.
基金资助:
国家自然科学基金项目（U1636106）；北京市自然科学基金项目（4182006）

A Depth Estimation Method for Multi View and High Precision Images

LI Jian, CHEN Yu-hang

School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2020-12-01 Online:2021-10-28 Published:2021-09-06

摘要/Abstract

摘要： 针对多视图的重建中高精度图片难以有效重建的问题，提出了基于学习的深度估计方法.该方法利用空洞卷积神经网络对图片进行特征提取，利用长短期记忆网络构建并优化三维代价体，并且采取有监督和无监督2种方式进行训练.在2个真实场景中的多视角图片数据集上的实验结果表明，相比于传统方法和其他基于学习的方法，该网络所需的显存大大减少，因此能用于高精度图片的重建，同时，提高了模型深度预测的准确性和完整性.

关键词: 多视图重建, 循环神经网络, 高精度图片

Abstract: High-precision images are challenging to reconstruct effectively in dense multi view reconstruction. To solve the problem, a learning-based depth estimation method is proposed. In the method,the dilated convolution neural network is used to extract image features,and the long short-term memory network is applied to construct and optimize the cost volume. Besides,the supervised and unsupervised training methods are adopted. Experimental results on two real scene multi view image datasets show that the proposed method not only outperforms state-of-the-arts methods,but also is several times less in GPU memory application compared with traditional methods and other learning-based methods. Therefore, the proposed method can reconstuct high-precision images, while improving the accuracy and integrity of model depth prediction.

Key words: multi view reconstruction, recursive neural network, high-precision images

中图分类号:

TP391

李剑, 陈宇航. 一种多视角高精度图片的深度估计方法[J]. 北京邮电大学学报, 2021, 44(5): 101-106.

LI Jian, CHEN Yu-hang. A Depth Estimation Method for Multi View and High Precision Images[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(5): 101-106.

参考文献

[1] 焦宏宇. 基于Openstack的新型蜜场系统[D]. 南京:南京邮电大学, 2018:2-3.
[2] Liao H J, Lin C H R, Lin Y C, et al. Intrusion detection system:a comprehensive review[J]. Journal of Network and Computer Applications, 2013, 36(1):16-24.
[3] Wang Wei, Sheng Yiqiang, Wang Jinlin, et al. HAST-IDS:learning hierarchical spatial-temporal features using deep neural networks to improve intrusion detection[J]. IEEE Access, 2017, 6:1792-1806.
[4] Zhang Fengli, Wang Dan. An effective feature selection approach for network intrusion detection[C]//2013 IEEE Eighth International Conference on Networking, Architecture and Storage. Piscataway:IEEE, 2013:307-311.
[5] Hubballi N, Suryanarayanan V. False alarm minimization techniques in signature-based intrusion detection systems:a survey[J]. Computer Communications, 2014, 49:1-17.
[6] Ma Tao, Wang Fen, Cheng Jianjun, et al. A hybrid spectral clustering and deep neural network ensemble algorithm for intrusion detection in sensor networks[J]. Sensors, 2016, 16(10):1701.
[7] Javaid A, Niyaz Q, Sun Weiqing, et al. A deep learning approach for network intrusion detection system[J]. EAI Endorsed Transactions on Security and Safety, 2016, 3(9):e2.
[8] Tan Zhiyuan, Jamdagni A, He Xiangjian, et al. Detection of denial-of-service attacks based on computer vision techniques[J]. IEEE Transactions on Computers, 2014, 64(9):2519-2533.
[9] Torres P, Catania C, Garcia S, et al. An analysis of recurrent neural networks for botnet detection behavior[C]//2016 IEEE Biennial Congress of Argentina (ARGENCON). Piscataway:IEEE, 2016:1-6.
[10] Zhang Jianwu, Ling Yu, Fu Xingbing, et al. Model of the intrusion detection system based on the integration of spatial-temporal features[J]. Computers & Security, 2020, 89:101681.
[11] Lotfollahi M, Siavoshani M J, Zade R S H, et al. Deep packet:a novel approach for encrypted traffic classification using deep learning[J]. Soft Computing, 2020, 24(3):1999-2012.
[12] Yao Zhongjiang, Ge Jingguo, Wu Yulei, et al. Encrypted traffic classification based on Gaussian mixture models and hidden Markov models[J]. Journal of Network and Computer Applications, 2020, 166:102711.
[13] Iliofotou M, Kim H, Faloutsos M, et al. Graption:a graph-based P2P traffic classification framework for the internet backbone[J]. Computer Networks, 2011, 55(8):1909-1920.
[14] Moore A W, Papagiannaki K. Toward the accurate identification of network applications[C]//International Workshop on Passive and Active Network Measurement. Berlin:Springer, 2005:41-54.
[15] Li Ao, Qin Zhou, Liu Runshi, et al. Spam review detection with graph convolutional networks[C]//28th ACM International Conference on Information and Knowledge Management. New York:ACM, 2019:2703-2711.
[16] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems. New York:Curran Associates, 2017:5998-6008.
[17] Lippmann R, Cunningham R K, Fried D J, et al. Results of the DARPA 1998 offline intrusion detection evaluation[C]//Recent Advances in Intrusion Detection. Berlin:Springer, 1999:829-835.
[18] Shiravi A, Shiravi H, Tavallaee M, et al. Toward developing a systematic approach to generate benchmark datasets for intrusion detection[J]. Computers & Secu-rity, 2012, 31(3):357-374.
[19] Xu Xin. Adaptive intrusion detection based on machine learning:feature extraction, classifier construction and sequential pattern prediction[J]. International Journal of Web Services Practices, 2006, 2(1-2):49-58.
[20] Farid D M, Harbi N, Rahman M Z. Combining naive Bayes and decision tree for adaptive intrusion detection[J]. International Journal of Network Security & Its Applications, 2010, 2(2):12-25
[21] Wang Wei, Zhu Ming, Wang Jinlin, et al. End-to-end encrypted traffic classification with one-dimensional convolution neural networks[C]//2017 IEEE International Conference on Intelligence and Security Informatics(ISI). Piscataway:IEEE, 2017:43-48.

一种多视角高精度图片的深度估计方法

A Depth Estimation Method for Multi View and High Precision Images

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	蒲悦逸, 王文涵, 朱强, 陈朋朋. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9-14.
[2]	王雅青, 郭彩丽, 楚云霏, 周洪弘, 冯春燕. 面向会话型推荐系统的个性化分层循环模型[J]. 北京邮电大学学报, 2019, 42(6): 142-148.
[3]	苏放, 王晓宇, 张治. 基于注意力机制的评论摘要生成[J]. 北京邮电大学学报, 2018, 41(3): 7-13.