基于新型联合感知矩阵的压缩学习目标识别技术
Target Recognition Technology Based on a New Joint Sensing Matrix for Compressed Learning
- 电子学报 2021年49卷第11期 页码：2108-2116
- 作者机构：
1.钱学森空间技术实验室，北京 100094
2.河南大学河南省大数据分析与处理重点实验室，河南开封 475004
3.航天东方红卫星有限公司，北京 100094
4.中国空间技术研究院西安分院，陕西西安 710100
- 作者简介：
[ "李 峰 男，1975年生，吉林人，钱学森空间技术实验室研究员，主要研究方向为遥感图像处理与重建、压缩感知、探测效能评估等. E‑mail:lifeng@qxslab.cn" ]
[ "詹邦成（通信作者） 男，1995年生，河南信阳人. 河南大学计算机与信息工程学院，硕士研究生，主要研究方向为目标识别、图像处理. E‑mail:zbc2862333729@dingtalk.com" ]
[ "辛 蕾 女，1988年生，辽宁阜新人，毕业于北京航空航天大学仪器科学与光电工程学院，硕士研究生，主要研究方向为压缩感知与空间信息智能提取. E‑mail:xinlei@qxslab.cn" ]
[ "刘 洋 男，1992年生，山西忻州人，毕业于中国空间技术研究院西安分院，硕士研究生，主要研究方向为图像处理.E‑mail:liuandyang@aliyun.com" ]
[ "刘志佳 男，1992年生，山西忻州人，毕业于中国空间技术研究院西安分院，硕士研究生，主要研究方向为图像处理. E‑mail:lzj303@sina.com" ]
[ "肖化超 男，1985年生，湖南新邵人，毕业于中国空间技术研究院，工学博士，主要研究方向为空间数据处理.E‑mail:xiaohc@cast504.com" ]
- 基金信息：
DOI：10.12263/DZXB.20200852
中图分类号： TP391.4收稿：2020-08-05，
修回：2021-04-20，
纸质出版：2021-11-25
- 稿件说明：
移动端阅览
李峰,詹邦成,辛蕾等.基于新型联合感知矩阵的压缩学习目标识别技术[J].电子学报,2021,49(11):2108-2116.
LI Feng,ZHAN Bang-cheng,XIN Lei,et al.Target Recognition Technology Based on a New Joint Sensing Matrix for Compressed Learning[J].ACTA ELECTRONICA SINICA,2021,49(11):2108-2116.
李峰,詹邦成,辛蕾等.基于新型联合感知矩阵的压缩学习目标识别技术[J].电子学报,2021,49(11):2108-2116. DOI： 10.12263/DZXB.20200852.
LI Feng,ZHAN Bang-cheng,XIN Lei,et al.Target Recognition Technology Based on a New Joint Sensing Matrix for Compressed Learning[J].ACTA ELECTRONICA SINICA,2021,49(11):2108-2116. DOI： 10.12263/DZXB.20200852.
摘要
目标识别正逐渐成为自动化领域中提供准确目标类别信息的一项重要技术，并且当前大多数目标识别方法都是基于深度学习框架实现.通常，深度学习框架的输入数据均为原始图像数据，而在实际应用中，探测器获取原始图像数据并作为深度学习框架的输入进而实现目标识别的方式并非是高效的，数据获取并识别的过程包含了大量的冗余信息，降低了识别效率.在本文中，通过深度学习与压缩感知技术的结合，提出了一种基于联合感知矩阵的压缩学习目标识别技术（Target recognition technology based on a new joint sensing matrix for compressed learning，TRNPCL），使得探测器可快速生成目标图像多维压缩数据，且压缩数据可直接作为深度学习目标识别框架的输入数据，而无需再进行解压缩步骤.该方法不仅大大减小了深度学习框架的数据输入量，在与同等压缩比下的单空间域数据压缩学习方式相比较，还保持了较高的识别准确率.在未来，该方法有望成为一种更有效、更灵活的目标识别方法，并特别适用于指纹识别、人脸识别等应用领域.
Abstract
Target recognition is gradually becoming an important technology to provide accurate target category information in the field of automation
and most current target recognition methods are based on machine learning frameworks. Generally
the input data of the machine learning framework is raw image data
but in practical applications
the way that the detector obtains the raw image data and uses it as the input of the deep learning framework to achieve target recognition is low efficient
contains a lot of redundant information
which reduces the recognition efficiency. In this paper
by combining machine learning and compressive sensing technology
a new target recognition method named as target recognition technology based on a new joint sensing matrix for compressed learning (TRNPCL) is proposed. Through the proposed method
the detector can quickly generate multi-dimensional compressed data of the target image
and the compressed data can be directly used as the input data of the deep learning target recognition framework without further decompression steps
which not only greatly reduces the amount of data input to the machine learning framework
but also maintains a higher recognition accuracy compared with the single-space domain data compression learning method under the same compression ratio. In the future
this method is expected to become a more effective and flexible target recognition method
and especially suitable for fingerprint recognition
face recognition and other application fields.
关键词
Keywords
references
Krizhevsky A , Sutskever I , GE Hinton . ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .
Szegedy C , Liu W , Jia Y , et al . Going deeper with convolutions [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. Boston, Massachusetts : IEEE , 2015 . 1 - 9 .
Lee S , Huh S , Yoo D , et al . Rich feature hierarchies from omni-directional RGB-DI information for pedestrian detection [A]. International Conference on Ubiquitous Robots and Ambient Intelligence [C]. Korea : IEEE , 2015 . 362 - 367 .
He K , Zhang X , Ren S , et al . Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence , 2014 , 37 ( 9 ): 1904 - 1916 .
Ren 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 K , Girshick R , et al . You only look once: Unified, real-time object detection [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. Palace : IEEE , 2016 . 779 - 788 .
Hang Du , Hailin Shi , Dan Zeng , Tao Mei . The elements of end-to-end deep face recognition: A survey of recent advances [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. Seattle, USA : IEEE , 2020 . 1 - 44 .
Li H . Feature extraction, recognition, and matching of damaged fingerprint: Application of deep learning network [J]. Concurrency and Computation: Practice and Experience , 2021 , 33 : E6057 .1 - E6057. 9 .
Starck Jean-Luc , Candes E J , Donoho D L . The curvelet transform for image denoising [J]. IEEE Transactions on Image Processing , 2002 , 11 ( 6 ): 670 - 684 .
Said A , Pearlman W A . A new, fast, and efficient image codec based on set partitioning in hierarchical trees [J]. IEEE Transactions on Circuits and Systems for Video Technology , 1996 , 6 ( 3 ): 243 - 250 .
CANDES E J , ROMBERG J , TAO T . Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information [J]. IEEE Transactions on Information Theory , 2006 , 52 ( 2 ): 489 - 509 .
Duarte M F , Davenport M A , et al . Single-pixel imaging via compressive sampling [J]. IEEE Signal Processing Magazine , 2008 , 25 : 83 - 91 .
Aes F M , Araújo F M , et al . Active illumination single-pixel camera based on compressive sensing [J]. Applied Optics , 2011 , 50 ( 4 ): 405 - 414 .
焦李成 , 杨淑媛 , 刘芳 , 等 . 压缩感知回顾与展望 [J]. 电子学报 , 2011 , 39 ( 7 ): 1651 - 1662 .
JIAO Li-cheng , YANG Shu-yuan , LIU Fang , et al . Devleopment and prospect of compressive sensing [J]. Acta Electronica Sinica , 2011 , 39 ( 7 ): 1651 - 1662 . (in Chinese)
Tran D T , et al . Multilinear compressive learning [J]. IEEE Transactions on Neural Networks and Learning Systems , 2020 , 32 ( 4 ): 1512 - 1524 .
Davenport M A , Duarte M F , et al . The smashed filter for compressive classification and target recognition [A]. IEEE Conference on Computational Imaging V [C]. San Jose, CA : IEEE , 2007 . 64980 H. 1 - 64980 H. 12 .
Lohit S , Kulkarni K , et al . Reconstruction-free inference on compressive measurements [A]. Conference on Computer Vision and Pattern Recognition Workshops [C]. Boston, Massachusetts : IEEE , 2015 . 16 - 24 .
Jiangtao Wen , Zhuoyuan Chen , Yuxing Han , et al . A compressive sensing image compression algorithm using quantized DCT and noiselet information [A]. International Conference on Acoustics, Speech and Signal Processing [C]. Dallas, TX, USA : IEEE , 2010 . 1294 - 1297 .
Tian Z , Luo C , Qiu J , et al . A distributed deep learning system for web attack detection on edge devices [J]. IEEE Transactions on Industrial Informatics , 2020 , 16 ( 3 ): 1963 - 1971 .
Lecun Y , Boser B E , Denker J S , et al . Backpropagation applied to handwritten zip code recognition [J]. Neural Computation , 1989 , 1 ( 4 ): 541 - 551 .
Glorot X , Bordes A , Bengio Y , et al . Deep sparse rectifier neural networks [A]. International Conference on Artificial Intelligence and Statistics [C]. USA : IEEE , 2011 . 315 - 323 .
Srivastava Nitish , Hinton Geoffrey , et al . Dropout: A simple way to prevent neural networks from overfitting [J]. Journal of Machine Learning Research , 2014 , 15 ( 56 ): 1929 - 1958 .
Rumelhart D , Hinton G , Williams R . Learning representations by back-propagating errors [J]. Nature , 1986 , 323 ( 6088 ): 533 - 536 .
Liang X , Wang X , et al . Soft-margin softmax for deep recognition [A]. International Conference on Neural Information Processing [C]. Guangzhou, China : Springer , 2017 . 413 - 421 .
Krizhevsky A . Learning multiple layers of features from tiny images [D]. Department of Computer Science , University of Toronto , 2009 .
Lecun Y , Bottou L , et al . Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .
0
浏览量
19
下载量
1
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies