基于特征融合的轻量级SSD目标检测方法

吴天成; 王晓荃; 蔡艺军; 荆有波; 陈铖颖

doi:10.37188/CJLCD.2021-0007

您当前的位置：

首页 >

文章列表页 >

基于特征融合的轻量级SSD目标检测方法

图像处理 | 更新时间：2021-09-30

- 基于特征融合的轻量级SSD目标检测方法
- Lightweight SSD object detection method based on feature fusion
- 液晶与显示 2021年36卷第10期页码：1437-1444
- 作者机构：
  
  1.厦门理工学院光电与通信工程学院, 福建厦门 361024
  2.中国科学院微电子研究所, 北京 100029
- 作者简介：
  
  [ "吴天成(1996-), 男, 浙江温州人, 硕士研究生, 2018年于武汉工程大学获得学士学位, 主要从事计算机视觉、目标检测方向的研究。E-mail:787568968@qq.com" ]
  [ "王晓荃(1997-), 男, 河南安阳人, 硕士研究生, 2019年于上海第二工业大学获得学士学位, 主要从事数据分析方向的研究。E-mail: 1820382516@qq.com" ]
- 基金信息：
  
  国家自然科学基金(61704143);国家自然科学基金(62005232);福建省自然科学基金(2018J01566);厦门市青年创新基金(3502Z20206074)
- DOI：10.37188/CJLCD.2021-0007
  中图分类号： TP91.4
- 收稿日期：2021-01-07，
  
  修回日期：2021-03-15，
  
  纸质出版日期：2021-10
- 稿件说明：
移动端阅览
吴天成, 王晓荃, 蔡艺军, 等. 基于特征融合的轻量级SSD目标检测方法[J]. 液晶与显示, 2021,36(10):1437-1444.

Tian-cheng WU, Xiao-quan WANG, Yi-jun CAI, et al. Lightweight SSD object detection method based on feature fusion[J]. Chinese journal of liquid crystals and displays, 2021, 36(10): 1437-1444.
吴天成, 王晓荃, 蔡艺军, 等. 基于特征融合的轻量级SSD目标检测方法[J]. 液晶与显示, 2021,36(10):1437-1444. DOI： 10.37188/CJLCD.2021-0007.

Tian-cheng WU, Xiao-quan WANG, Yi-jun CAI, et al. Lightweight SSD object detection method based on feature fusion[J]. Chinese journal of liquid crystals and displays, 2021, 36(10): 1437-1444. DOI： 10.37188/CJLCD.2021-0007.

摘要

针对应用于嵌入式设备的轻量级目标检测算法，本文提出了一种基于特征融合的改进方案。针对目前MobileNetV2-SSD轻量级目标检测算法检测精度低、小目标检测效果差的问题，结合FPN特征金字塔的特征融合思想，选用了MobileNetV2-SSD中包含较多语义信息的3层特征层进行融合，利用多尺度检测的原理，将融合后的特征层重新生成特征金字塔进行目标检测。使用PASCAL VOC 2007数据集对改进后的目标检测模型和原模型进行对比测试，其检测精度mAP相对原模型提高了3.9%，达到了76.5%，同时模型对于小目标的检测效果也有了显著提升。最后将模型部署至嵌入式设备Jetson AGX Xavier中进行测试，改进后的模型在网络结构更加复杂的情况下检测速度接近原模型，达到了22 FPS的检测速度，可以实现嵌入式设备上的实时目标检测。

Abstract

An improved scheme based on feature fusion for the lightweight object detection algorithm deployed in embedded devices is proposed in this paper. The algorithm is based on the MobileNetV2-SSD lightweight object detection algorithm with the idea of FPN feature fusion. It combines the three feature layers of MobileNetV2-SSD that contain more semantic information

and is regenerated based on the fused feature layer Feature pyramid for object detection. The improved model and the original model are compared and tested on the PASCAL VOC data set. Compared with the original model

the mAP is increased by 3.6%

and reaches 76.5%. At the same time

the detection effect of small targets is significantly improved. Finally

it is tested in the embedded device Jetson AGX Xavier. The improved model has a detection speed close to the original model when the network structure is more complex

reaching the detection speed of 22FPS

which can realize real-time object detection on embedded devices.

关键词

Keywords

references

张忠良 . 边海防教程 , : 北京军事科学出版社 , 2013 . 12 .

Z L ZHANG . Border and Coastal Defense Tutorial , : Beijing Military Press , 2013 . 12 .

ZHANG H, BERG A C, MAIRE M, et al . SVM-KNN: discriminative nearest neighbor classification for visual category recognition[C]// Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . New York: IEEE, 2006.

J ZHU , H ZOU , S ROSSET , 等 . Multi-class AdaBoost . Stats and its Interface , 2009 . 2 ( 3 ): 349 - 360 . DOI: 10.4310/SII.2009.v2.n3.a8 http://doi.org/10.4310/SII.2009.v2.n3.a8 .

M JONES , P VIOLA . Robust real-time object detection . International Journal of Computer Vision , 2001 . 57 ( 2 ): 87 http://ci.nii.ac.jp/naid/10027458060 http://ci.nii.ac.jp/naid/10027458060 .

P VIOLA , M J JONES . Robust real-time face detection . International Journal of Computer Vision , 2004 . 57 ( 2 ): 137 - 154 . DOI: 10.1023/B:VISI.0000013087.49260.fb http://doi.org/10.1023/B:VISI.0000013087.49260.fb .

LIENHART R, MAYDT J. An extended set of Haar-like features for rapid object detection[C]// Proceedings. International Conference on Image Processing . Rochester: IEEE, 2002.

GIRSHICK R, DONAHUE J, DARRELL T, et al . Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus: IEEE, 2014.

GIRSHICK R. Fast R-CNN[C]// Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago: IEEE, 2015: 1440-1448.

S Q REN , K M HE , R GIRSHICK , 等 . Faster R-CNN: towards real-time object detection with region proposal networks . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 . 39 ( 6 ): 1137 - 1149 . DOI: 10.1109/TPAMI.2016.2577031 http://doi.org/10.1109/TPAMI.2016.2577031 .

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: unified, real-time object detection[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas: IEEE, 2016: 779-788.

LIU W, ANGUELOV D, ERHAN D, et al . SSD: single shot MultiBox detector[C]// Proceedings of the 14 th European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016: 21-37.

SANDLER M, HOWARD A, ZHU M L, et al . MobileNetV2: inverted residuals and linear bottlenecks[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City : IEEE , 2018: 4510-4520.

HOWARD A G, ZHU M L, CHEN B, et al . MobileNets: efficient convolutional neural networks for mobile vision applications[J]. arXiv : 1704.04861, 2017.

FU C Y, LIU W, RANGA A, et al . DSSD: deconvolutional single shot detector[J]. arXiv : 1701.06659, 2017.

LIN T Y, DOLLÁR P, GIRSHICK R, et al . Feature pyramid networks for object detection[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 936-944.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于Double-Head的雾天图像目标检测

基于改进SSD的航拍飞机目标检测方法