A Study on Traffic Sign Recognition in Outdoor Environment
碩士 === 國立交通大學 === 電機與控制工程系 === 87 === In this thesis, the hue, saturation, intensity (HSI) coordinate system and saturation enhancement are used to get the better segmentation between the traffic sign and other objects in the image. The conventional pattern recognition methods...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
1999
|
Online Access: | http://ndltd.ncl.edu.tw/handle/70089231036466076391 |
id |
ndltd-TW-087NCTU0591027 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-087NCTU05910272016-07-11T04:13:50Z http://ndltd.ncl.edu.tw/handle/70089231036466076391 A Study on Traffic Sign Recognition in Outdoor Environment 戶外交通號誌辨識之研究 Yao-Sheng Chang 張耀升 碩士 國立交通大學 電機與控制工程系 87 In this thesis, the hue, saturation, intensity (HSI) coordinate system and saturation enhancement are used to get the better segmentation between the traffic sign and other objects in the image. The conventional pattern recognition methods only extract the feature vectors which are invariant to translation, rotation, and scale but are not invariant to distortion or occlusion in outdoor environment. This thesis describes a traffic sign recognition system capable of tolerating the above variations. The feature extraction is based on the techniques of the Fourier transform, Log-polar transform, and the of the discrete cosine transform (DCT). Because of the energy compaction of DCT, the DCT can be used as feature extraction for shape recognition. The features are used as the inputs of the neural network which is a classifier. The performance of the proposed system is evaluated by examining the effect of various conditions which may occur in natural outdoor environment. Sheng-Fuu Lin 林昇甫 1999 學位論文 ; thesis 76 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 電機與控制工程系 === 87 === In this thesis, the hue, saturation, intensity (HSI) coordinate system and saturation enhancement are used to get the better segmentation between the traffic sign and other objects in the
image. The conventional pattern recognition methods only extract the feature vectors which are invariant to translation, rotation, and scale but are not invariant to distortion or occlusion in outdoor environment. This thesis describes a traffic sign recognition system capable of tolerating the above variations. The feature extraction is based on the techniques of the Fourier transform, Log-polar transform, and the of the discrete cosine transform (DCT). Because of the energy compaction of DCT, the DCT can be used as feature extraction for shape recognition. The features are used as the inputs of the neural network which is a classifier. The performance of the proposed system is evaluated by examining the effect of
various conditions which may occur in natural outdoor environment.
|
author2 |
Sheng-Fuu Lin |
author_facet |
Sheng-Fuu Lin Yao-Sheng Chang 張耀升 |
author |
Yao-Sheng Chang 張耀升 |
spellingShingle |
Yao-Sheng Chang 張耀升 A Study on Traffic Sign Recognition in Outdoor Environment |
author_sort |
Yao-Sheng Chang |
title |
A Study on Traffic Sign Recognition in Outdoor Environment |
title_short |
A Study on Traffic Sign Recognition in Outdoor Environment |
title_full |
A Study on Traffic Sign Recognition in Outdoor Environment |
title_fullStr |
A Study on Traffic Sign Recognition in Outdoor Environment |
title_full_unstemmed |
A Study on Traffic Sign Recognition in Outdoor Environment |
title_sort |
study on traffic sign recognition in outdoor environment |
publishDate |
1999 |
url |
http://ndltd.ncl.edu.tw/handle/70089231036466076391 |
work_keys_str_mv |
AT yaoshengchang astudyontrafficsignrecognitioninoutdoorenvironment AT zhāngyàoshēng astudyontrafficsignrecognitioninoutdoorenvironment AT yaoshengchang hùwàijiāotōnghàozhìbiànshízhīyánjiū AT zhāngyàoshēng hùwàijiāotōnghàozhìbiànshízhīyánjiū AT yaoshengchang studyontrafficsignrecognitioninoutdoorenvironment AT zhāngyàoshēng studyontrafficsignrecognitioninoutdoorenvironment |
_version_ |
1718343804110503936 |