一种改进的单步多框目标检测算法

王燕妮 1; 刘祥 1; 刘江 2

doi:10.7652/xjtuxb202104016

您当前的位置：

首页 >

文章列表页 >

一种改进的单步多框目标检测算法

更新时间：2025-07-09

- 一种改进的单步多框目标检测算法
- An Improved Single Shot MultiBox Detector
- 西安交通大学学报 2021年55卷第4期页码：145-153
- 作者机构：
  
  西安建筑科技大学信息与控制工程学院,西安,710055
- 作者简介：
- 基金信息：
  
  : 2020-10-27。作者简介: 王燕妮(1975—),女,副教授,硕士生导师;刘祥(通信作者),男,硕士生。基金项目: 陕西省自然科学基础研究资助项目(2020JM-499,2020JQ-684)
- DOI：10.7652/xjtuxb202104016
  中图分类号： TP391
- 网络首发：2021-04-10，
  
  纸质出版：2021
- 稿件说明：
移动端阅览
王燕妮 1, 刘祥 1, 刘江 2. 一种改进的单步多框目标检测算法[J]. 西安交通大学学报, 2021,55(4):145-153.

An Improved Single Shot MultiBox Detector[J]. 2021, 55(4): 145-153.
王燕妮 1, 刘祥 1, 刘江 2. 一种改进的单步多框目标检测算法[J]. 西安交通大学学报, 2021,55(4):145-153. DOI： 10.7652/xjtuxb202104016.

An Improved Single Shot MultiBox Detector[J]. 2021, 55(4): 145-153. DOI： 10.7652/xjtuxb202104016.

摘要

针对单步多框目标检测算法(SSD)中存在的误检、漏检以及检测精度不够高等问题

提出了一种改进的SSD目标检测算法。该算法通过空洞卷积替换conv4_3卷积层及之前的两次标准卷积

扩大感受野

使用反卷积对不同尺度的特征图进行融合

使融合形成的特征图具有丰富的上下文信息

最后为特征图添加注意力模型

有效提取感兴趣区域的特征。仿真实验结果表明

改进算法在VOC2007数据集上较原算法检测精度提升0.9%

检测结果更加准确

一定程度上改善了误检、漏检等问题

同时仍满足实时性的要求。

Abstract

Aiming at the problems of false detection

missing detection and low detection accuracy in single shot multibox detector(SSD)

an improved SSD object detection algorithm is proposed. The conv4_3 convolution layer and the previous two standard convolutions are replaced by dilated convolution to expand the receptive field. The deconvolution is used to fuse the feature maps of different scales

so that the feature maps formed by fusion contain rich context information. The attention model is added to the feature map to effectively extract the features of regions of interest. Simulation results show that the detection accuracy of the improved algorithm is 0.9% higher than that of the original algorithm

and the detection effect is better. To some extent

it solves the problems of false detection and missing detection

and still meets the requirements of real-time.

关键词

Keywords

references

王好贤, 董衡, 周志权. 红外单帧图像弱小目标检测技术综述 [J]. 激光与光电子学进展, 2019, 56(8): 1-14.

WANG Haoxian, DONG Heng, ZHOU Zhiquan. Review on dim small target detection technologies in infrared single frame images [J]. Laser & Optoelectronics Progress, 2019, 56(8): 1-14.

黄凯奇, 陈晓棠, 康运锋, 等. 智能视频监控技术综述 [J]. 计算机学报, 2015, 38(6): 1093-1118.

HUANG Kaiqi, CHEN Xiaotang, KANG Yunfeng, et al. Intelligent visual surveillance: a review [J]. Chinese Journal of Computers, 2015, 38(6): 1093-1118.

欧攀, 张正, 路奎, 等. 基于卷积神经网络的遥感图像目标检测 [J]. 激光与光电子学进展, 2019, 56(5): 051002.

OU Pan, ZHANG Zheng, LU Kui, et al. Object detection of remote sensing images based on convolutional neural networks [J]. Laser Optoelectronics Progress, 2019, 56(5): 051002.

杨洁, 陈灵娜, 陈宇韶, 等. 基于深度学习的医学目标检测与识别 [J]. 信息技术, 2018, 42(10): 81-87.

YANG Jie, CHEN Lingna, CHEN Yushao, et al. Target detection and recognition based on depth learning [J]. Information Technology, 2018, 42(10): 81-87.

LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

VIOLA P, JONES M J. Robust real-time face detection [J]. International Journal of Computer Vision, 2004, 57(2): 137-154.

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. Piscataway, NJ, USA: IEEE, 2014: 580-587.

GIRSHICK R. Fast R-CNN [C]∥Proceedings of 2015 IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2015: 1440-1448.

REN Shaoqing, HE Kaiming, 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.

LIN C F, WANG S D. Fuzzy support vector machines [J]. IEEE Transactions on Neural Networks, 2002, 13(2): 464-471.

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. Piscataway, NJ, USA: IEEE, 2016: 779-788.

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

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [EB/OL].[2020-09-26]. http:∥arXiv.org/abs/1409.155 6v6.

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, USA: IEEE Computer Society, 2014: 580-587.

YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions [EB/OL].[2020-10-01]. https:∥arXiv.org/abs/1511.07122.

PENG L Y, ZHANG L, ZHANG Y, et al. Deep deconvolution neural network for image super-resolution [J]. Journal of Software, 2018, 29(4): 927-934.

JADERBERG M, SIMONYAN K, ZISSERMAN A, et al. Spatial transformer networks [C]∥Advances in Neural Information Processing Systems. Montreal, Canada: [s.n.], 2015: 2008-2016.

HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 7132-7141.

WANG Fei, JIANG Mengqing. Residual attention network for image classification [EB/OL]. [2020-09-22]. https:∥arXiv.org/abs/1704.06904

FU Chengyang, LIU Wei, RANGA A, et al. DSSD: deconvolutional single shot detector [EB/OL]. [2020-09-22]https:∥arXiv.org/abs/1701.06659.

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

机械滥用场景下锂离子电池温度多模态神经网络预测方法

基于关系提示的单模块单步骤实体关系抽取方法研究

采用轻量级卷积神经网络的H.266/通用视频编码跨分量预测

采用感受野优化与渐进特征融合的图像超分辨率算法

复杂天气下铁轨异物入侵目标检测研究