基于异步卷积分解与分流结构的单阶段检测器

doi:10.13700/j.bh.1001-5965.2018.0564

北京航空航天大学学报 ›› 2019, Vol. 45 ›› Issue (10): 2089-2098.doi: 10.13700/j.bh.1001-5965.2018.0564

基于异步卷积分解与分流结构的单阶段检测器

赵蓬辉¹, 孟春宁², 常胜江¹

1. 南开大学电子信息与光学工程学院现代光学研究所, 天津 300350;
2. 中国人民武装警察部队海警学院电子技术系, 宁波 315801

收稿日期:2018-09-27 出版日期:2019-10-20 发布日期:2019-10-31
通讯作者: 孟春宁 E-mail:mengchunning123@163.com
作者简介:赵蓬辉男,硕士研究生。主要研究方向:视频目标检测、深度学习;孟春宁男,博士,副教授。主要研究方向:图像处理、人工智能、信息安全;常胜江男,博士,教授,博士生导师。主要研究方向:数字图像处理、太赫兹功能器件、深度学习。
基金资助:
公安部技术研究计划（2017JSYJC10）

Single shot multibox detector based on asynchronous convolution factorization and shunt structure

ZHAO Penghui¹, MENG Chunning², CHANG Shengjiang¹

1. Institute of Modern Optics, College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, China;
2. Department of Electronic Technology, China Coast Guard Academy, Ningbo 315801, China

Received:2018-09-27 Online:2019-10-20 Published:2019-10-31
Supported by:
Technology Research Project of Public Security Ministry (2017JSYJC10)

摘要/Abstract

摘要： 目标检测网络SSD的多层回归特征图存在各层回归计算之间相对独立的问题，且基于SSD改进的系列算法在提高检测精度的同时难以兼顾实时性。针对上述问题，提出一种基于异步卷积分解与分流（shunt）结构的单阶段目标检测器。基于异步卷积分解算法设计了一种shunt结构，交错连接多层特征图，增强了回归计算之间的统一性与协调性。优化了原有高层主流结构，在主流结构与shunt结构中分别用最大池化和异步卷积分解2种不同的方式对特征图大小进行降维，保留空间相关信息的同时提高了特征的多样性。实验结果表明，将VOC2007trainval和VOC2012trainval中的图片统一缩小至300像素×300像素进行训练，提出的目标检测器在VOC2007test上进行检测时的平均精度均值可达到80.5%，检测速度超过30帧/s。

关键词: 目标检测, 卷积神经网络, 异步卷积分解, 分流结构, 结构优化

Abstract: Single shot multibox detector (SSD) owns the relatively independent regression computations of multi-regressive feature maps, while the object detection algorithms based on SSD cannot make a tradeoff between detection accuracy and real-time speed. To solve the problems above, a single shot mutibox detector based on asynchronous convolution factorization and shunt structure (FA-SSD) is introduced based on asynchronous convolution factorization algorithm and shunt structure. The shunt structure, based on the proposed asynchronous convolution factorization algorithm, is designed to staggerly connect the layers of regression features, enhancing the unity and coordination between regression calculations. In order to optimize the mainstream of high-level structure, the asynchronous convolution factorization algorithm and max pooling are implemented to reduce the dimension of image features in the mainstream and shunt respectively, which can hold the spatial information while improving the diversity of features. According to the experimental results from VOC2007test, FA-SSD achieves a mean average precision of 80.5% after the training of VOC2007trainval and VOC2012trainval with nominal resolution of 300×300, while the detection speed exceeds 30 frames per second.

Key words: object detection, convolutional neural networks, asynchronous convolution factorization, shunt structure, structure optimization

中图分类号:

TP391.4

赵蓬辉, 孟春宁, 常胜江. 基于异步卷积分解与分流结构的单阶段检测器[J]. 北京航空航天大学学报, 2019, 45(10): 2089-2098.

ZHAO Penghui, MENG Chunning, CHANG Shengjiang. Single shot multibox detector based on asynchronous convolution factorization and shunt structure[J]. JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2019, 45(10): 2089-2098.

参考文献

[1] VIOLA P,JONES M.Rapid object detection using a boosted cascade of simple features[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2003:511-518.
[2] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2005:886-893.
[3] FELZENSZWALB P,MCALLESTER D,RAMANAN D.A discriminatively trained,multiscale,deformable part model[C]//IEEE Computer,Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2008:1-8.
[4] EVERINGHAM M,GOOL L V,WILLIAMS C K I,et al.The pascal,visual object classes (VOC) challenge[J].International Journal of Computer Vision,2010,88(2):303-338.
[5] 李旭冬,叶茂,李涛.基于卷积神经网络的目标检测研究综述[J].计算机应用研究,2017,34(10):2881-2886.LI X D,YE M,LI T. Review of object detection based on convolutional neural networks[J].Application Research of Computers,2017,34(10):2881-2886(in Chinese).
[6] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2014:580-587.
[7] 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):346-361.
[8] GIRSHICK R.Fast R-CNN[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE Press,2015:1440-1448.
[9] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems.Cambridge:MIT Press,2015:91-99.
[10] LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2017:936-944.
[11] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2015:779-788.
[12] REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2017:6517-6525.
[13] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[C]//European Conference on Computer Vision.Berlin:Springer,2016:21-37.
[14] REDMON J,FARHADI A.YOLOv3:An incremental improvement[EB/OL].(2018-04-08)[2018-09-21].http://cn.arxiv.org/pdf/1804.02767v1.
[15] FU C Y,LIU W,RANGA A,et al.DSSD:Deconvolutional single shot detector[EB/OL].(2017-01-23)[2018-09-21].http://cn.arxiv.org/pdf/1701.06659.
[16] SHEN Z,LIU Z,LI J,et al.DSOD:Learning deeply supervised object detectors from scratch[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE Press,2017:1937-1945.
[17] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].(2015-03-10)[2018-09-21].http://cn.arxiv.org/pdf/1409.1556.
[18] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE Press,2015:770-778.
[19] SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2016:2818-2826.
[20] IOFFE S,SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[EB/OL].(2015-03-02)[2018-09-26].https://arxiv.org/abs/1502.03167.
[21] RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet large scale visual recognition challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[22] BELL S,ZITNICK C L,BALA K,et al.Inside-outside Net:Detecting objects in context with skip pooling and recurrent neural networks[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2016:2874-2883.
[23] DAI J,LI Y,HE K,et al.R-FCN:Object detection via region-based fully convolutional networks[EB/OL].(2016-06-21)[2018-09-26].https://arxiv.org/abs/1605.06409.
[24] HE K,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE Press,2017:1-13.

基于异步卷积分解与分流结构的单阶段检测器

Single shot multibox detector based on asynchronous convolution factorization and shunt structure

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孙宇航, 曾国奇, 刘春辉, 张多纳. 基于深度学习的无人机数据链信噪比估计算法[J]. 北京航空航天大学学报, 2019, 45(9): 1855-1863.
[2]	厉铮泽, 杨小远, 朱日东, 王敬凯. 基于深度卷积的残差三生网络研究与应用[J]. 北京航空航天大学学报, 2019, 45(9): 1864-1873.
[3]	邓昊宇, 王春洁. 三维点阵结构等效热分析与优化方法[J]. 北京航空航天大学学报, 2019, 45(6): 1122-1128.
[4]	洪杰, 栗天壤, 倪耀宇, 吕春光, 马艳红. 复杂转子系统支点动载荷模型及其优化设计[J]. 北京航空航天大学学报, 2019, 45(5): 847-854.
[5]	罗利龙, 王立凯, 聂小华. 一种面向模块化可重构机翼的分步补偿优化方法[J]. 北京航空航天大学学报, 2019, 45(5): 930-935.
[6]	张鹏, 张嘉峰, 刘涛. 基于相干度优化的极化顺轨干涉SAR慢小目标CFAR检测[J]. 北京航空航天大学学报, 2019, 45(3): 575-587.
[7]	张新峰, 郭宇桐, 蔡轶珩, 孙萌. 基于DCNN和全连接CRF的舌图像分割算法[J]. 北京航空航天大学学报, 2019, 45(12): 2364-2374.
[8]	翟宇轩, 刘怡桑, 徐艺文, 陈忠辉, 房颖, 赵铁松. 基于HTTP自适应流媒体传输的3D视频质量评价[J]. 北京航空航天大学学报, 2019, 45(12): 2456-2462.
[9]	杨彬, 李和平, 曾慧. 基于视频的三维人体姿态估计[J]. 北京航空航天大学学报, 2019, 45(12): 2463-2469.
[10]	张梦琴, 孟权令, 张维刚. 基于深度视觉语义嵌入的视频缩略图推荐[J]. 北京航空航天大学学报, 2019, 45(12): 2479-2486.
[11]	佟骏超, 吴熙林, 丁丹丹. 时空域上下文学习的视频多帧质量增强方法[J]. 北京航空航天大学学报, 2019, 45(12): 2506-2513.
[12]	贾瑞明, 刘圣杰, 李锦涛, 王赟豪, 潘海侠. 基于编解码双路卷积神经网络的视觉自定位方法[J]. 北京航空航天大学学报, 2019, 45(10): 1965-1972.
[13]	郭琳, 秦世引. 遥感图像飞机目标高效搜检深度学习优化算法[J]. 北京航空航天大学学报, 2019, 45(1): 159-173.
[14]	肖志鹏, 钱文敏, 周磊. 考虑壁板刚度匹配的大型飞机复合材料机翼气动弹性优化设计[J]. 北京航空航天大学学报, 2018, 44(8): 1629-1635.
[15]	王俊, 郑彤, 雷鹏, 张原, 樵明朗. 基于卷积神经网络的手势动作雷达识别方法[J]. 北京航空航天大学学报, 2018, 44(6): 1117-1123.