基于细化多尺度深度特征的目标检测网络

doi:10.3969/j.issn.0372-2112.2020.12.011

电子学报 ›› 2020, Vol. 48 ›› Issue (12): 2360-2366.DOI: 10.3969/j.issn.0372-2112.2020.12.011

基于细化多尺度深度特征的目标检测网络

李雅倩, 盖成远, 肖存军, 吴超, 刘佳甲

燕山大学工业计算机控制工程河北省重点实验室, 河北秦皇岛 066004

收稿日期:2019-10-11 修回日期:2020-06-05 出版日期:2020-12-25
- 通讯作者:
- 李雅倩
- 作者简介:
- 盖成远 男,1993年11月出生,黑龙江大兴安岭人.燕山大学硕士研究生,主要研究方向为:深度学习与模式识别.E-mail:gaichengyuan@126.com

Object Detection Networks Based on Refined Multi-scale Depth Feature

LI Ya-qian, GAI Cheng-yuan, XIAO Cun-jun, WU Chao, LIU Jia-jia

1. Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao, Hebei 066004, China

Received:2019-10-11 Revised:2020-06-05 Online:2020-12-25 Published:2020-12-25
- Corresponding author:
- LI Ya-qian

摘要/Abstract

摘要： 现有深度卷积神经网络中感受野尺度单一，无法适应目标的尺度变化和边界形变，故此本文提出了一种提取并融合多尺度特征的目标检测网络.该网络通过减少池化并在网络底层加入空间加信道压缩激励模块来突出可利用的细节信息，生成高质量的特征图；此外，在深层网络中加入可变多尺度特征融合模块，该模块具有多种尺度的感受野并可根据物体边界预测采样位置，最后通过融合多尺度特征使网络具有更强的特征表达能力并且对不同尺度实例及其边界信息更具鲁棒性.实验证明，本文结构实现了比原有结构更高的平均精度，与目前主流目标检测算法相比也具有一定优势.

关键词: 目标检测, 特征金字塔网络, 可变形卷积, 信道空间压缩激励, 多尺度特征融合

Abstract: In the existing deep convolution neural network, the scale of receptive field is single, which could not adapt to the scale change and boundary deformation of the target. Therefore, a target detection network based on multi-scale feature extraction and feature fusion is proposed in this paper. The proposed network reduces pooling and adds space as well as channel compression excitation module at the bottom of the network to highlight the details and generate high-quality feature map. Besides, a variable multi-scale feature fusion module is added to the deep network, which has a multi-scale receptive field and can predict the position according to object boundary. Finally, the multi-scale feature fusion is used to enable the network of stronger ability of feature expression and is more robust to different scale and flexible boundary of instances. Experimental results show that the proposed structure achieves higher average accuracy than the original structure, and also has certain advantages compared with the state-of-the-art algorithms.

Key words: object detection, feature pyramid network, deformable convolution, channel spatial squeeze excitation, multi-scale feature fusion

中图分类号:

TP391.41

李雅倩, 盖成远, 肖存军, 等. 基于细化多尺度深度特征的目标检测网络[J]. 电子学报, 2020, 48(12): 2360-2366.

LI Ya-qian, GAI Cheng-yuan, XIAO Cun-jun, et al. Object Detection Networks Based on Refined Multi-scale Depth Feature[J]. Acta Electronica Sinica, 2020, 48(12): 2360-2366.

参考文献

[1] Liu W,Anguelov D,Erhan D,et al.SSD:Single shot multibox detector[A].European Conference on Computer Vision (ECCV)[C].Amsterdam,Netherlands:Springer,2016.21-37.
[2] Lin T Y,Dollar P,Girshick R,et al.Feature pyramid networks for object detection[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].Honolulu,USA:IEEE Computer Society Press,2017.963-944.
[3] He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].Boston,USA:IEEE Computer Society Press,2015.770-778.
[4] Dai J F,Qi H Z,Xiong Y W,et al.Deformable Convolutional Networks[EB/OL].http://openaccess.thecvf.com/content_ICCV_2017/papers/Dai_Deformable_Convolutional_Networks_ICCV_2017_paper.pdf.2018-10-6.
[5] 刘颖,刘红燕,范九伦,等.基于深度学习的小目标检测研究与应用综述[J].电子学报,2020,48(03):590-601. Liu Y,Liu H Y,Fan J L,et al.A survey of research and application of small object detection based on deep learning[J].Acta Electronica Sinica,2020,48(03):590-601.(in Chinese)
[6] Hu J,Shen L,Albanie S,et al.Squeeze-and-Excitatio-n Networks[EB/OL].https://arxiv.org/abs/1709.01507.2018-7-11.
[7] Christina S,Vincent V,Sergey I,et al.Rethinking the inception architecture for computer vision[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].Las Vegas,USA:IEEE Computer Society Press,2016.2818-2826.
[8] Russakovsky O,Deng J,Su H,et al.ImageNet large scale visual recognition challenge[J].International Joural of Computer Vision,2015,115(3):211-252.
[9] He K M,Zhang X Y,Ren S Q,et al.Delving deep into rectifiers:Surpassing human-level performance on imagenet classification[A].IEEE International Conference on Computer Vision (ICCV)[C].Santiago,Chile:IEEE Computer Society Press,2015.596-604.
[10] Girshick R.Fast R-CNN[A].IEEE International Confe-rence on Computer Vision (ICCV)[C].Santiago,Chile:IEEE Computer Society Press,2015.1440-1448.
[11] Ramprasaath R,Michael C,Abhishek D,et al.Grad-CAM:Visual Explanations from Deep Networks via Gradient-based Localization[EB/OL].https://arxiv.org/abs/1610.02391.2019-1-12.
[12] Cai Z W,Vasconcelos N.Cascade R-CNN:Delving into high quality object detection[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].Salt Lake City,USA:IEEE Computer Society Press,2018.2603-2611.
[13] Dai J F,Li Y,He K M,et al.R-FCN:Object Detection via Region-based Fully Convolutional Networks[EB/OL].https://arxiv.org/abs/1605.06409.2018-7-29.
[14] Fu C Y,Liu W,Ranga A,et al.DSSD:Deconvolutional Single Shot Detector[EB/OL].https://arxiv.org/abs/1701.06659.2018-6-15.
[15] Redmon J,Farhadi A.YOLOv3:An Incremental Improve-ment[EB/OL].https://pjreddie.com/media/files/papers/YOLOv3.pdf.2019-4-11.

基于细化多尺度深度特征的目标检测网络

Object Detection Networks Based on Refined Multi-scale Depth Feature

PDF

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

[1]	贺军义, 吴梦翔, 宋成, 张敏, 张俊楠. 双目视觉辅助PDR的组合导航定位方法[J]. 电子学报, 2023, 51(3): 736-745.
[2]	范兵兵, 何庭建, 张聪炫, 陈震, 黎明. 联合遮挡约束与残差补偿的特征金字塔光流计算方法[J]. 电子学报, 2023, 51(3): 648-657.
[3]	唐维伟, 钟胜, 卢金仪, 颜露新, 谭富中, 邹旭, 徐文辉. 基于FPGA的Skynet网络结构优化及高时效实现[J]. 电子学报, 2023, 51(2): 314-323.
[4]	柳长源, 张玉亮, 毕晓君. 基于多阶段提议稀疏区域卷积网络的城市交通目标检测[J]. 电子学报, 2023, 51(1): 26-31.
[5]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.
[6]	李超, 黄新宇, 王凯. 基于特征融合和自学习锚框的高分辨率图像小目标检测算法[J]. 电子学报, 2022, 50(7): 1684-1695.
[7]	包中华, 卢建斌, 田永华, 田树森. 密集杂波背景下雷达微弱海面目标的修正Hough变换TBD检测新方法[J]. 电子学报, 2022, 50(7): 1735-1743.
[8]	肖进胜, 张舒豪, 陈云华, 王元方, 杨力衡. 双向特征融合与特征选择的遥感影像目标检测[J]. 电子学报, 2022, 50(2): 267-272.
[9]	李斌, 齐延荣, 周清雷. 基于Winograd算法的目标检测加速器设计与优化[J]. 电子学报, 2022, 50(10): 2387-2397.
[10]	罗会兰, 袁璞, 童康. 基于深度学习的显著性目标检测方法综述[J]. 电子学报, 2021, 49(7): 1417-1427.
[11]	程旭, 宋晨, 史金钢, 周琳, 张毅锋, 郑钰辉. 基于深度学习的通用目标检测研究综述[J]. 电子学报, 2021, 49(7): 1428-1438.
[12]	周勇, 陈思霖, 赵佳琦, 张迪, 王瀚正. 基于弱语义注意力的遥感图像可解释目标检测[J]. 电子学报, 2021, 49(4): 679-689.
[13]	王洪雁, 张海坤, 罗宇华, 汪祖民. 复杂动态背景下基于群稀疏的运动目标检测方法[J]. 电子学报, 2021, 49(12): 2330-2338.
[14]	杨红红, 王刘丽, 张玉梅, 吴晓军, 党允彤. 基于序列多尺度特征融合表示的层级舞蹈动作姿态估计方法[J]. 电子学报, 2021, 49(12): 2428-2436.
[15]	罗大鹏, 杜国庆, 曾志鹏, 魏龙生, 高常鑫, 陈应, 肖菲, 罗琛. 基于少量样本学习的多目标检测跟踪方法[J]. 电子学报, 2021, 49(1): 183-191.