Vehicle model fine recognition algorithm based on local features and multiple losses

LI Zhe; HU Pengli; DENG Junyong

doi:10.13873/J.1000-9787(2021)04-0142-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Vehicle model fine recognition algorithm based on local features and multiple losses

更新时间：2025-09-11

- Vehicle model fine recognition algorithm based on local features and multiple losses
- Issue 4, Pages: 142-145(2021)
- 作者机构：
  
  1. 西安邮电大学电子工程学院
  2. 延安大学物理与电子信息学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2021)04-0142-04
  CLC： U495;TP183;TP391.41
- Published：2021
- 稿件说明：
移动端阅览
LI Zhe, HU Pengli, DENG Junyong. Vehicle model fine recognition algorithm based on local features and multiple losses[J]. 2021, (4): 142-145.
DOI：

LI Zhe, HU Pengli, DENG Junyong. Vehicle model fine recognition algorithm based on local features and multiple losses[J]. 2021, (4): 142-145. DOI： 10.13873/J.1000-9787(2021)04-0142-04.

摘要

针对车型精细识别率低的问题

提出基于局部特征与多损失融合的车型精细识别算法。首先通过Faster RCNN获取区分度较大的车脸区域;然后在识别网络中

借助VGG16提取车脸特征

在输出层对Soft Max损失和中心损失进行加权融合

有效地引导网络学习类内距离较小、类间距离较大的特征。实验结果表明:所提算法在中山大学VRID—1数据集的识别准确率为98.80%

车型精细识别准确率得到了明显的提升。

Abstract

Aiming at the problem of low recognition rate of vehicle model

a vehicle model fine recognition algorithm based on local features and multiple losses is proposed.Firstly

the car face area with large degree of discrimination is obtained by faster region-based CNN（ Faster RCNN）.Then

in the identification network

the car face feature is extracted by VGG 16

and the Soft Max loss and the center loss are weighted and fused at the output layer

effectively guiding the distance within the network learning class to be small.

the characteristics of the distance between the classes is large.The experimental results show that the recognition accuracy of the algorithm in the VRID—1 dataset of Zhongshan University is 98.80 %

and the accuracy of the vehicle model fine recognition has been significantly improved.

关键词

Keywords

references

Views

147

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Expression recognition algorithm introducing attention mechanism and center loss

Facial expression recognition algorithm based on CNN and features of key regions

Related Author

ZHANG Xiang

SHI Zhicai

CHEN Liang

XUE Jianming

LIU Hongzhe

YUAN Jiazheng

WANG Xueqiao

LI Qing

Related Institution

College of Electronic and Electrical Engineering,Shanghai University of Engineering Science

Beijing Key Laboratory of Information Service Engineering, Beijing Union University

Beijing Open University

Institute of Computer Technology,Beijing Union University

⁰