留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

一种可变锚框候选区域网络的目标检测方法

李承昊 茹乐 何林远 迟文升

李承昊, 茹乐, 何林远, 等 . 一种可变锚框候选区域网络的目标检测方法[J]. 北京航空航天大学学报, 2020, 46(8): 1610-1617. doi: 10.13700/j.bh.1001-5965.2019.0531
引用本文: 李承昊, 茹乐, 何林远, 等 . 一种可变锚框候选区域网络的目标检测方法[J]. 北京航空航天大学学报, 2020, 46(8): 1610-1617. doi: 10.13700/j.bh.1001-5965.2019.0531
LI Chenghao, RU Le, HE Linyuan, et al. Target detection method for region proposal network with variable anchor box[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(8): 1610-1617. doi: 10.13700/j.bh.1001-5965.2019.0531(in Chinese)
Citation: LI Chenghao, RU Le, HE Linyuan, et al. Target detection method for region proposal network with variable anchor box[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(8): 1610-1617. doi: 10.13700/j.bh.1001-5965.2019.0531(in Chinese)

一种可变锚框候选区域网络的目标检测方法

doi: 10.13700/j.bh.1001-5965.2019.0531
基金项目: 

国家自然科学基金 61701524

中国博士后科学基金 2019M653742

陕西省自然科学基础研究计划 2017JM6071

详细信息
    作者简介:

    李承昊  男, 硕士研究生。主要研究方向:计算机视觉、航空电子信息及其智能化

    茹乐  男, 博士, 教授, 博士生导师。主要研究方向:抗干扰通信、航空电子信息及其智能化

    何林远  男, 博士, 副教授。主要研究方向:图像去雾、超分辨率重建、模式识别

    通讯作者:

    茹乐. E-mail:ru-le@163.com

  • 中图分类号: V221+.3;TB553

Target detection method for region proposal network with variable anchor box

Funds: 

National Natural Science Foundation of China 61701524

China Postdoctoral Science Foundation 2019M653742

Natural Science Basic Research Program of Shaanxi 2017JM6071

More Information
  • 摘要:

    目标检测作为计算机视觉领域的热点问题,目前基于深度学习的目标检测方法可以分为2类:两步检测和一步检测,前者有着较高准确性,后者有着较好速度,但是为提高检测的性能两者都引入了锚机制。为提高目标检测系统的性能,基于深度卷积神经网络的两步检测算法引入了注意力引导(AG)模块,通过对候选区域网络(RPN)的锚机制进行引导,使得对于预选锚框形状的选择更具有多样性;同时针对传统的后处理方式非极大值抑制(NMS)算法存在的误检和漏检的问题,提出了一种置信度因子的NMS(Cf-NMS)算法,对于模型的整体性能有着很大的贡献。实验结果说明,所提方法虽然在速度性能上有略微的下降,但是无论是在RPN变体还是现有的先进算法在准确性方面都有提升。

     

  • 图 1  锚点映射

    Figure 1.  Anchor mapping

    图 2  网络框架

    Figure 2.  Network framework

    图 3  注意力引导模块

    Figure 3.  Attention guidance module

    图 4  检测结果示例

    Figure 4.  Sample of test results

    表  1  候选区域的平均查全率

    Table  1.   Average recall rate of region proposal

    方法 AR100 AR300 AR500 ARS ARM ARL 运行时间/s
    RPN+9 anchors 45.7 53.4 57.8 28.7 52.8 63.9 0.09
    RPN+12 anchors 50.2 56.6 58.3 33.9 58.2 67.5 0.09
    RPN+AG 53.2 60.2 61.3 39.6 62.3 70.2 0.11
    下载: 导出CSV

    表  2  不同NMS算法的mAP的实验结果

    Table  2.   Experimental results of mAP by different NMS algorithms

    方法 mAP/%
    RIoU=0.3 RIoU=0.4 RIoU=0.5 RIoU=0.6 RIoU=0.7
    贪心NMS 69.6 70 69.1 64.4 56.6
    Ccds-NMS[17] 70.6 70.1 69.5 64.6 56.8
    Seg-NMS[18] 71.5 71.4 68.8 64.6 57.0
    Cf-NMS 72.1 71.5 69.4 66.3 60.9
    下载: 导出CSV

    表  3  检测性能比较

    Table  3.   Comparison of detection performance

    算法 AP AP50 AP75 APS APM APL
    FPN[10] 36.2 59.1 39.0 18.2 39.0 48.2
    Mask R-CNN[9] 39.8 62.3 43.4 22.1 43.2 51.2
    Cascade R-CNN[8] 42.8 62.1 46.3 23.7 45.5 55.2
    AG+Cf-NMS+
    Faster R-CNN
    43.6 62.8 47.4 24.1 46.8 55.3
    下载: 导出CSV
  • [1] 方路平, 何杭江, 周国民.目标检测算法研究综述[J].计算机工程与应用, 2018, 54(13):11-18. doi: 10.3778/j.issn.1002-8331.1804-0167

    FANG L P, HE H J, ZHOU G M.Research overview of object detection methods[J].Computer Engineering and Applications, 2018, 54(13):11-18(in Chinese). doi: 10.3778/j.issn.1002-8331.1804-0167
    [2] 刘栋, 李素, 曹志冬.深度学习及其在图像物体分类与检测中的应用综述[J].计算机科学, 2016, 43(12):13-23. doi: 10.11896/j.issn.1002-137X.2016.12.003

    LIU D, LI S, CAO Z D.State-of-the-art on deep learning and its application in image object classification and detection[J].Computer Science, 2016, 43(12):13-23(in Chinese). doi: 10.11896/j.issn.1002-137X.2016.12.003
    [3] REDMON J, DIVVALA S, GIRSHICK R, et al.You only look once: Unified, real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway: IEEE Press, 2016: 779-788.
    [4] LIU W, ANGUELOV D, ERHAN D, et al.SSD: Single shot multibox detector[C]//European Conference on Computer Vision.Berlin: Springer, 2016: 21-37.
    [5] CHEN C, LIU M Y, TUZEL O, et al.R-CNN for small object detection[C]//Asian Conference on Computer Vision.Berlin: Springer, 2016: 214-230
    [6] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway: IEEE Press, 2015: 1440-1448.
    [7] 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. doi: 10.1109/TPAMI.2016.2577031
    [8] CAI Z, VASCONCELOS N.Cascade R-CNN: Delving into high quality object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway: IEEE Press, 2018: 6154-6162.
    [9] HE K, GKIOXARI G, DOLLÁR P, et al.Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway: IEEE Press, 2017: 2961-2969.
    [10] LIN T Y, DOLLÁR P, GIRSHICK R, et al.Feature pyramid networks for object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway: IEEE Press, 2017: 2117-2125.
    [11] YAN Q, GONG D, SHI Q, et al.Attention-guided network for ghost-free high dynamic range imaging[EB/OL].(2019-04-23)[2019-09-20].https://arxiv.org/abs/1904.10293.
    [12] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al.Graph attention networks[EB/OL].(2018-02-04)[2019-09-20].https://arxiv.org/abs/1710.10903.
    [13] GUAN Q, HUANG Y, ZHONG Z, et al.Diagnose like a radiologist: Attention guided convolutional neural network for thorax disease classification[EB/OL].(2018-01-30)[2019-09-20].https://arxiv.org/abs/1801.09927.
    [14] LIN T Y, MAIRE M, BELONGIE S, et al.Microsoft COCO: Common objects in context[C]//European Conference on Computer Vision.Berlin: Springer, 2014: 740-755.
    [15] DALAL N, TRIGGS B.Histograms of oriented gradients for human detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway: IEEE Press, 2005: 886-893.
    [16] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004, 60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94
    [17] 张强, 张陈斌, 陈宗海.一种改进约束条件的简化非极大值抑制[J].中国科学技术大学学报, 2016, 46(1):6-11. http://www.cqvip.com/QK/94257X/201601/669806218.html

    ZHANG Q, ZHANG C B, CHEN Z H.A simplified non-maximum suppression with improved constraints[J].Journal University of Science and Technology of China, 2016, 46(1):6-11(in Chinese). http://www.cqvip.com/QK/94257X/201601/669806218.html
    [18] 赵文清, 严海, 邵绪强.改进的非极大值抑制算法的目标检测[J].中国图象图形学报, 2018, 23(11):1676-1685. doi: 10.11834/jig.180275

    ZHAO W Q, YAN H, SHAO X Q.Object detection based on improved non-maximums suppression algorithm[J].Journal of Image and Graphics, 2018, 23(11):1676-1685(in Chinese). doi: 10.11834/jig.180275
    [19] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems.Red Hook: Curran Associates Inc., 2012: 1097-1105.
  • 加载中
图(4) / 表(3)
计量
  • 文章访问数:  379
  • HTML全文浏览量:  7
  • PDF下载量:  177
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-09-29
  • 录用日期:  2019-11-01
  • 刊出日期:  2020-08-20

目录

    /

    返回文章
    返回
    常见问答