基于多尺度融合網(wǎng)絡(luò)的高速公路能見度估計(jì)

doi:10.12306/2022jms.0074

首頁 > 過刊瀏覽>2022年第42卷第5期 >668-675. DOI:10.12306/2022jms.0074

基于多尺度融合網(wǎng)絡(luò)的高速公路能見度估計(jì)
DOI:
                        10.12306/2022jms.0074
                    
CSTR:
                        
                    
作者:
                        
                        
                    
作者單位:
作者簡(jiǎn)介:
通訊作者:
中圖分類號(hào):P409
基金項(xiàng)目:中國(guó)氣象局創(chuàng)新發(fā)展專項(xiàng)(CXFZ2022J069);江蘇省氣象局科研項(xiàng)目(KZ202105;KQ202110)

Highway visibility estimation based on multi-scale fusion network

Author:

Affiliation:

Fund Project:

摘要

圖/表

訪問統(tǒng)計(jì)

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

資源附件

文章評(píng)論

摘要:

為了實(shí)現(xiàn)近實(shí)時(shí)公里級(jí)的高速公路能見度監(jiān)測(cè),提出了一種基于多尺度融合網(wǎng)絡(luò)的能見度估計(jì)方法。首先,從道路監(jiān)控視頻中提取道路場(chǎng)景圖像,并對(duì)圖像進(jìn)行質(zhì)量控制;分別采用引導(dǎo)濾波、光譜濾波、景深估計(jì)模型從路面場(chǎng)景圖像中提取細(xì)節(jié)結(jié)構(gòu)特征、光譜特征與場(chǎng)景深度特征;然后,構(gòu)建多尺度融合網(wǎng)絡(luò)自適應(yīng)融合結(jié)構(gòu)特征、光譜特征與場(chǎng)景深度特征,并從中提取能見度特征;最后在網(wǎng)絡(luò)末端輸出圖像場(chǎng)景所對(duì)應(yīng)的能見度等級(jí)。此外,為了訓(xùn)練與測(cè)試模型,構(gòu)建了真實(shí)道路場(chǎng)景圖像數(shù)據(jù)集,共包含18 000張標(biāo)注圖像。實(shí)驗(yàn)結(jié)果表明,多尺度融合網(wǎng)絡(luò)可顯著提升高速公路能見度估計(jì)的準(zhǔn)確性,能見度等級(jí)分類準(zhǔn)確率可達(dá)81.76%。

Abstract:

In order to realize near real-time kilometer-level highway visibility monitoring, in this paper, propose a new method of visibility estimation based on multi-scale fusion network was proposed in this study deep network architecture that directly estimates the visibility from highway surveillance images. Specifically,the road scene images were firstly extracted from road surveillance videos with quality control, then used the estimation models are applies for extracting multiple image detailed structure and spectral features, as well as scene depth features extraction methods to extract the detailed structural, spectral, and scene depth features from images. After that, the multi-scale fusion network is designed to extract and fuse important features for visibility estimation adaptively, and the visibility level corresponding to the image scene is output at the end of the network. Besides, constructed a real-scene dataset, which contains a total of 18 000 annotated images, for model learning and performance evaluation. The experimental results demonstrate that the multi-scale fusion network can significantly improve the accuracy of highway visibility estimation, and the accuracy of visibility classification can be reach promoted to 81.76% with this new method.

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

引用本文

黃亮,肖鵬飛,薛梅,張振東,孫家清,周雪城.基于多尺度融合網(wǎng)絡(luò)的高速公路能見度估計(jì).氣象科學(xué),2022,42(5):668-675 HUANG Liang, XIAO Pengfei, XUE Mei, ZHANG Zhendong, SUN Jiaqing, ZHOU Xuecheng. Highway visibility estimation based on multi-scale fusion network. Journal of the Meteorological Sciences,2022,42(5):668-675

復(fù)制

文章指標(biāo)

點(diǎn)擊次數(shù):
下載次數(shù):
HTML閱讀次數(shù):
引用次數(shù):

歷史

收稿日期:2022-05-06
最后修改日期:2022-06-30
錄用日期:
在線發(fā)布日期: 2022-11-03
出版日期:

文章二維碼

您是第位訪問者
氣象科學(xué) ® 2026 版權(quán)所有
技術(shù)支持：北京勤云科技發(fā)展有限公司

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標(biāo)

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒 激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標(biāo)

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说