基于SqueezeNet卷积神经网络的车辆检测

魏泽发; 崔华

doi:10.11959/j.issn.2096-3750.2020.00175

您当前的位置：

首页 >

文章列表页 >

基于SqueezeNet卷积神经网络的车辆检测

专题：智慧交通物联网 | 更新时间：2024-06-05

- 基于SqueezeNet卷积神经网络的车辆检测
- Vehicle detection based on SqueezeNet convolutional neural network
- 物联网学报 2020年4卷第3期页码：120-125
- 作者机构：
  
  1. 长安大学教育技术与网络中心，陕西西安 710064
  2. 长安大学信息工程学院，陕西西安 710064
- 作者简介：
  
  [ "魏泽发（1992- ），男，河北衡水人，长安大学助理工程师，主要研究方向为智能交通、深度学习、图像处理等" ]
  [ "崔华（1977- ），女，陕西西安人，博士，长安大学教授，主要研究方向为图像分析、数据挖掘、机器学习、深度学习及其在智能交通中的应用研究等" ]
- 基金信息：
  
  陕西省科技厅重点研发计划;The Key R＆D Plan of Shaanxi Provincial Science and Technology Department(2018ZDXM-GY-047)
- DOI：10.11959/j.issn.2096-3750.2020.00175
  中图分类号： TP389.1
- 纸质出版日期：2020-09-30，
  
  网络出版日期：2020-09，
- 稿件说明：
移动端阅览
魏泽发, 崔华. 基于SqueezeNet卷积神经网络的车辆检测[J]. 物联网学报, 2020,4(3):120-125.

ZEFA WEI, HUA CUI. Vehicle detection based on SqueezeNet convolutional neural network. [J]. Chinese journal on internet of things, 2020, 4(3): 120-125.
魏泽发, 崔华. 基于SqueezeNet卷积神经网络的车辆检测[J]. 物联网学报, 2020,4(3):120-125. DOI： 10.11959/j.issn.2096-3750.2020.00175.

ZEFA WEI, HUA CUI. Vehicle detection based on SqueezeNet convolutional neural network. [J]. Chinese journal on internet of things, 2020, 4(3): 120-125. DOI： 10.11959/j.issn.2096-3750.2020.00175.

摘要

在智能交通系统中，针对车辆目标检测算法可移植性不高、检测速度较慢等问题，提出了一种基于SqueezeNet卷积神经网络的车辆检测方法。通过融合SqueezeNet与SSD（single shot multibox detector）算法的车辆检测方法，在UA-DETRAC数据集上进行训练，实现了车辆目标的快速检测，提升了模型的可移植性，缩短了单帧检测时间。实验结果表明，所提模型在保证准确率的同时，模型单帧检测时间可达22.3 ms，模型大小为16.8 MB，相较于原SSD算法，模型大小减少了约8/9。

Abstract

In the intelligent transportation system

aiming at the problem of low portability and speed of detection in vehicle target detection algorithm

a vehicle detection method based on SqueezeNet convolutional neural network was proposed.In order to realize the rapid detection of vehicle targets

improve the portability and shorten the detection time of the single frame

the model was trained on the UA-DETRAC dataset by fusing the SqueezeNet with the single shot multibox detector (SSD) algorithm.The experimental results showed that the time of the single frame detection could reach 22.3 ms and the model size was 16.8 MB.Compared with the original SSD algorithm

the model size was reduced by about 8/9.At the same time

the accuracy of the proposed model was guaranteed.

关键词

智能交通卷积神经网络SqueezeNet车辆检测

Keywords

intelligent transportationconvolutional neural networkSqueezeNetvehicle detection

references

DALAL N, TRIGGS B . Histograms of oriented gradients for human detection[J]. IEEE Computer Society, 2015,1: 886-893.

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 . Rapid object detection using a boosted cascade of simple features[J]. Institute of Electrical and Electronics Engineers Computer Society, 2001,1(1): 1511-1518.

BAY H, ESS A, TUYTELAARS T ,et al. SURF:speeded up robust features[J]. Computer Vision and Image Understanding, 2008,110(3): 346-359.

SÁNCHEZ A V . Advanced support vector machines and kernel methods[J]. Neurocomputing, 2003,55(1): 5-20.

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]// 2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2014: 580-587.

UIJLINGS J R R, SANDE K E A V D, GEVERS T ,et al. Selective search for object recognition[J]. International Journal of Computer Vision, 2013,104(2): 154-171.

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

REDMON J, FARHADI A . YOLO9000:better,faster,stronger[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2017: 6517-6525.

REDMON J, FARHADI A . YOLOv3:an incremental improvement[J]. arXiv:1804.02767, 2018

LIU W, ANGUELOV D, ERHAN D ,et al. SSD:single shot MultiBox detector[M]. Berlin: SpringerPress, 2016.

IANDOLA F N, HAN S, MOSKEWICZ M ,et al. SqueezeNet:AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size[J]. International Conference on Learning Representations, 2017

WEN L Y, DU D W, CAI Z W ,et al. UA-DETRAC:a new benchmark and protocol for multi-object detection and tracking[J]. Computer Vision and Image Understanding, 2020,193:102907.

JIA Y Q, SHELHAMER E, DONAHUE J ,et al. Caffe:convolutional architecture for fast feature embedding[C]// ACM International Conference on Multimedia. ACM, 2014: 675-678.

ZEILER M D, TAYLOR G W, FERGUS R . Adaptive deconvolutional networks for mid and high level feature learning[C]// 2011 International Conference on Computer Vision. IEEE, 2011: 2018-2025.

IOFFE S, SZEGEDY C . Batch normalization:accelerating deep network training by reducing internal covariate shift[J]. Journal of Machine Learning Research, 2015: 448-456.

JISOO J, HYOJIN P, NOJUN K . Enhancement of SSD by concatenating feature maps for object detection[J]. Computer Vision and Pattern Recognition, 2017

浏览量

582

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CNN-BiGRU的复杂连续人体活动Wi-Fi感知方法

面向车联网的智能数据传输新方法