浏览全部资源
扫码关注微信
63726部队,宁夏 银川 750004
Received:08 October 2020,
Revised:20 November 2020,
Published:15 April 2021
移动端阅览
刘可佳,马荣生,唐子木等.采用优化卷积神经网络的红外目标识别系统[J].光学精密工程,2021,29(04):822-831.
LIU Ke-jia,MA Rong-sheng,TANG Zi-mu,et al.Design of infrared target recognition system with optimized convolutional neural network[J].Optics and Precision Engineering,2021,29(04):822-831.
刘可佳,马荣生,唐子木等.采用优化卷积神经网络的红外目标识别系统[J].光学精密工程,2021,29(04):822-831. DOI: 10.37188/OPE.20212904.0822.
LIU Ke-jia,MA Rong-sheng,TANG Zi-mu,et al.Design of infrared target recognition system with optimized convolutional neural network[J].Optics and Precision Engineering,2021,29(04):822-831. DOI: 10.37188/OPE.20212904.0822.
针对视频数据利用低效和光测设备目标识别能力较弱的问题,提出一种使用海量视频数据建立数据库进而构建红外目标识别系统的方法。首先设计快速红外目标检测算法,提取目标并分类建立数据库;然后结合特定任务建立一组较匹配且结构不同的卷积神经网络,并提出基于测试准确度均值统计分析和参数规模的选型策略,选出泛化能力较好且结构简单的卷积神经网络以及适当的训练轮数;最后加载优选模型及其参数作为分类器,与检测器结合实现红外目标特征事件实时检测分类。仿真结果表明,目标分类准确率均值可达95%以上,速率约为50 pixel/s。卷积神经网络结构的设计和选型策略有效,构建的系统可以满足红外目标识别的精度和实时性要求。
To improve the low efficiency of video data utilization and the weak target recognition ability of optical measuring equipment, we propose a method to establish a database with massive amounts of video and then construct an infrared target recognition system. Firstly, a fast infrared target detector to extract the target region from video frames and establish a database by classifying these subimages is designed. Secondly, according to a specific task, a cluster of convolutional neural networks with different structures is designed, and a selection strategy based on a mean value statistical analysis of test accuracy and parameter scale is designated. Consequently, we obtain a simple network with good generalization ability and a reasonable number of training epochs. Finally, the optimized model and its parameters are loaded as a classifier, which is combined with the detector to perform real-time detection and classification of infrared target events. Simulation results show that the average target classification accuracy can exceed 95% and the rate is approximately 50 FPS. The design scheme and selection strategy from the convolutional neural network structure is effective, and the constructed system exhibits real-time infrared target recognition while meeting accuracy requirements.
ZOU Z , SHI Z , GUO Y , et al . Object dfetection in 20 years: A survey [J]. arXiv: 1905.05055 , 2019 .
SULTANA F , SUFIAN A , DUTTA P . A review of object detection models based on convolutional neural network [J]. arXiv: 1905.01614 , 2019 .
范丽丽 , 赵宏伟 , 赵浩宇 , 等 . 基于深度卷积神经网络的目标检测研究综述 [J]. 光学 精密工程 , 2020 , 28 ( 5 ): 1152 - 1164 .
FAN L L , ZHAO H W , ZHAO H Y , et al . A review of target detection based on deep convolutional neural network [J]. Opt. Precision Eng. , 2020 , 28 ( 5 ): 1152 - 1164 . (in Chinese)
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 & Machine Intelligence , 2017 , 39 ( 6 ): 1137 - 1149 .
HUI Z , YU D U , SHU R N , et al . Pedestrian detection method based on Faster R-CNN [J]. Transducer and Microsystem Technologies , 2019 .
LIU W , ANGUELOV D , ERHAN D , et al . SSD: Single Shot MultiBox Detector [C]. European Conference on Computer Vision. Springer International Publishing , 2016 : 21 - 37 .
HWANG Y J , LEE J G , MOON U C , et al . SSD-TSEFFM: New SSD using trident feature and squeeze and extraction feature fusion [J]. Sensors , 2020 , 20 ( 13 ): 3630 .
REDMON J , DIVVALA S , GIRSHICK R , et al . You only look once: unified, real-time object detection [J]. arXiv: 1506.02640 , 2015 .
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 ): 252 - 260 .
WANG J L , FU X S , HUANG ZH CH , et al . Multi-type cooperative target detection based on improved YOLOv2 convolutional neural network [J]. Opt. Precision Eng. , 2020 , 28 ( 1 ): 252 - 260 . (in Chinese)
马立 , 巩笑天 , 欧阳航空 . Tiny YOLOV3目标检测改进 [J]. 光学 精密工程 , 2020 , 28 ( 4 ): 988 - 995 .
MA L , GONG X T , OU YANG H K . Improvement on tiny YOLOV3 target detection [J]. Opt. Precision Eng. , 2020 , 28 ( 4 ): 988 - 995 . (in Chinese)
BOCHKOVSKIY A , WANG C Y , LIAO H Y M . YOLOv4: optimal speed and accuracy of object detection [J]. arXiv: 2004.10934 , 2020 .
YI Z , YONG L S , JUN Z . An improved tiny-yolov3 pedestrian detection algorithm [J]. Optik-International Journal for Light and Electron Optics , 2019 : 17 - 23 .
TAN M , PANG R , LE Q V . EfficientDet: Scalable and efficient object detection [J]. arXiv: 1911.09070 , 2020 .
WONG A , SHAFIEE M J , LI F , et al . Tiny SSD: a tiny single-shot detection deep convolutional neural network for real-time embedded object detection [J]. arXiv: 1802.06488 , 2018 .
WU B , WAN A , IANDOLA F , et al . Squeezedet: unified, small, low power fully convolutional neural networks for real-time object detection for autonomous driving [J]. arXiv: 1612.01051 , 2019 .
沈西挺 , 于晟 , 董瑶 , 等 . 基于深度学习的人体动作识别方法 [J]. 计算机工程与设计 , 2020 , 41 ( 4 ): 1153 - 1157 .
SHEN X T , YU SH , DONG Y , et al . Human motion recognition method based on deep learning [J]. Computer Engineering and Design , 2020 , 41 ( 4 ): 1153 - 1157 . (in Chinese)
BHOI A . Spatio-temporal action recognition: a survey [J]. arXiv: 1901.09403 , 2019 .
TRAN D , BOURDEV L , FERGUS R , et al . Learning spatiotemporal features with 3d convolutional networks [J]. arXiv: 1412.0767 , 2015 .
CAI J , HU J . 3D RANs: 3D Residual attention networks for action recognition [J]. The Visual Computer , 2019 , 36 ( 6 ): 1261 - 1270 .
SIMONYAN K , ZISSERMAN A . Two-stream convolutional networks for action recognition in videos [J]. arXiv: 1406.2199 , 2014 .
CRASTO N , WEINZAEPFEL P , ALAHARI K , et al . MARS: Motion-augmented rgb stream for action recognition [C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , 2019 : 7874 – 7883 .
DU W , WANG Y L , QIAO Y . RPAN: An end-to-end recurrent pose-attention network for action recognition in videos [C]. Proceedings of the IEEE International Conference on Computer Vision (ICCV) , 2017 : 3725 - 3734 .
张春雷 . 基于并行卷积神经网络的军事目标图像分类技术 [J]. 电子设计工程 , 2019 , 27 ( 8 ): 76 - 80 .
ZHANG CH L . Military target image classification based on parallel convolutional neural network [J]. Electronic Design Engineering , 2019 , 27 ( 8 ): 76 - 80 . (in Chinese)
张号逵 , 李映 , 姜晔楠 . 深度学习在高光谱图像分类领域的研究现状与展望 [J]. 自动化学报 , 2018 , 44 ( 6 ): 3 - 19 .
ZHANG H K , LI Y , JIANG Y N . Research status and Prospect of deep learning in hyperspectral image classification [J]. Acta Automatica Sinica , 2018 ,v. 44 ( 06 ): 3 - 19 . (in Chinese)
王全东 , 常天庆 , 张雷 , 等 . 基于深度学习算法的坦克装甲目标自动检测与跟踪系统 [J]. 系统工程与电子技术 , 2018 ,v.40;No. 468 ( 09 ): 252 - 265 .
WANG Q D , CHANG T Q , ZHANG L , et al . Tank armor target detection and tracking system based on deep learning algorithm [J]. Journal of Systems Engineering and Electronics , 2018 ,v.40;No. 468 ( 09 ): 252 - 265 . (in Chinese)
单连平 , 窦强 . 基于深度学习的海战场图像目标识别 [J]. 指挥控制与仿真 , 2019 , 41 ( 1 ): 7 - 11 .
SHAN L P , DOU Q . Target recognition of naval battle field image based on deep learning [J]. Command Control & simulation , 2019 , 41 ( 1 ): 7 - 11 . (in Chinese)
程嘉晖 . 基于深度卷积神经网络的飞行器图像识别算法研究 [D]. 浙江 : 浙江大学出版社 , 2017 .
CHENG J H . Aircraft Image Recognition Based on Deep Convolution Neural Network [D]. Zhejiang : Zhejiang University Press , 2017 . (in Chinese)
许妍敏 . 让战场数据“开口说话 ”[J]. 军事文摘 , 2018 , 421 ( 13 ): 32 - 35 .
XU Y M . Let battlefield data "speak " [J]. Military Digest , 2018 , 421 ( 13 ): 32 - 35 . (in Chinese)
郑泽宇 , 梁博文 , 顾思宇 . TensorFlow实战Google深度学习框架 [M]. 北京 : 电子工业出版社 , 2018 .
ZHENG Z Y , LIANG B W , GU S Y . TensorFlow Practice Google deep learning framewor k [M]. Beijing : Electronic Industry Press , 2018 . (in Chinese)
SZEGEDY C , LIU W , JIA Y , et al . Going deeper with convolutions [C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , 2015 : 1 - 9 .
LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J]. 1998 , 86 ( 11 ), 2278 – 2324 .
张万征 , 胡志坤 , 李小龙 . 基于LeNet-5的卷积神经图像识别算法 [J]. 液晶与显示 , 2020 , 35 ( 5 ): 486 - 490 .
ZHANG W ZH , HU Z K , LI X L . Convolutional neural image recognition algorithm based on LeNet-5 [J]. Chinese Journal of Liquid Crystals and Displays , 2020 , 35 ( 5 ): 486 - 490 ..
汤姆·奥普 . TensorFlow学习指南:深度学习系统构建详解 [M]. 北京 : 机械工业出版社 , 2018 .
HOPE T . Learning TensorFlow : A Guide ti Build Deep Learning Systems [M]. Beijing : China Machine Press , 2018 . (in Chinese) .
0
Views
891
下载量
4
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution