Application of Vision Attention Mechanism in Freight Car License Location

GE Li; ZHAO Xin-bo

Chinese

您当前的位置：

首页 >

文章列表页 >

Application of Vision Attention Mechanism in Freight Car License Location

更新时间：2026-09-04

- Application of Vision Attention Mechanism in Freight Car License Location
- Vol. 31, Issue 8, Pages: 34-39(2014)
- 作者机构：
  
  西北工业大学计算机学院,陕西,西安,710072
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2014
- 稿件说明：
移动端阅览
葛莉, 赵歆波. 视觉注意力机制在货运列车车号定位中的应用[J]. 微电子学与计算机, 2014, 31(8): 34-39.

GE Li, ZHAO Xin-bo. Application of Vision Attention Mechanism in Freight Car License Location[J]. 2014, 31(8): 34-39.
葛莉, 赵歆波. 视觉注意力机制在货运列车车号定位中的应用[J]. 微电子学与计算机, 2014, 31(8): 34-39. DOI：

GE Li, ZHAO Xin-bo. Application of Vision Attention Mechanism in Freight Car License Location[J]. 2014, 31(8): 34-39. DOI：

摘要

为了定位货运列车车厢上的车号信息

提出并实现一种基于视觉注意力机制的定位新方法.该方法利用眼动跟踪技术获取真实眼动数据

结合提炼的车厢图像显著特征

建立车号注意力机制模型

并利用该模型预测车号显著区域

最后采用图像处理技术完成车号区域的分析定位.实验表明

相比传统基于灰度的处理方法

该算法更能适应不同光照条件下各类车厢的车号定位

具有更好的鲁棒性和普适性.

Abstract

To locate license number of every freight car

a novel localization method is presented and implemented based on the visual attention mechanism.The method utilizes eye-tracking technology to collects real eye movement data

combines eye-tracking data with salient features extracted from car images to establish a visual attention model of car license.Then

the model is used to predict salient license areas and.Finally

image processing technology is applied to analyze and locate the license area.As experimental results show

this algorithm is more insensitive to different types of car and illumination variance

and performs better in robustness and universality than traditional methods based on intensity.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Microservices anomaly detection based on the correlation of monitoring metrics

Lightweight countermeasures against Spectre attacks on the branch prediction unit

Simulation on the DC characteristics of double heterojunction p-GaN HEMT with AlN/GaN hybrid buffer layer

Steganography model guided by attention mechanism and improved dense convolution

High gain stability high temperature operational amplifier based on reverse body bias

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰