東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Automated pavement inspection based ...

Zhou, Jian.

FindBook

Google Book

Amazon

博客來

Automated pavement inspection based on wavelet analysis.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automated pavement inspection based on wavelet analysis./
作者:	Zhou, Jian.
面頁冊數:	150 p.
附註:	Source: Dissertation Abstracts International, Volume: 65-09, Section: B, page: 4799.
Contained By:	Dissertation Abstracts International65-09B.
標題:	Engineering, Mechanical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3148739
ISBN:	0496077228

Automated pavement inspection based on wavelet analysis.
Zhou, Jian.

Automated pavement inspection based on wavelet analysis. - 150 p.

Source: Dissertation Abstracts International, Volume: 65-09, Section: B, page: 4799.

Thesis (Ph.D.)--State University of New York at Stony Brook, 2004.

In an automated pavement inspection system, there are two important issues: pavement image acquisition and pavement image processing. For pavement image acquisition, normally imaging sensors, such as video cameras and photo multiplier tubes, are used to capture the pavement surface information. With the development of new imaging devices and computers, the frame rate becomes fast enough for real-time screening. The problem lies in pavement image processing. A wavelet-based pavement image processing method is proposed for distress detection and isolation, pavement image compression and noise reduction, distress classification, pavement condition evaluation, and distress segmentation. A major advantage of the proposed method is that for all processing steps involved, solutions can be found in the wavelet domain of the pavement images.

ISBN: 0496077228Subjects--Topical Terms:

783786
Engineering, Mechanical.

Automated pavement inspection based on wavelet analysis.
LDR:03281nmm 2200301 4500 001 1850710
005 20051207082644.5
008 130614s2004 eng d
020 $a 0496077228
035 $a (UnM)AAI3148739
035 $a AAI3148739
040 $a UnM $c UnM
100 1 $a Zhou, Jian. $3 1907815
245 1 0 $a Automated pavement inspection based on wavelet analysis.
300 $a 150 p.
500 $a Source: Dissertation Abstracts International, Volume: 65-09, Section: B, page: 4799.
500 $a Adviser: Peisen S. Huang.
502 $a Thesis (Ph.D.)--State University of New York at Stony Brook, 2004.
520 $a In an automated pavement inspection system, there are two important issues: pavement image acquisition and pavement image processing. For pavement image acquisition, normally imaging sensors, such as video cameras and photo multiplier tubes, are used to capture the pavement surface information. With the development of new imaging devices and computers, the frame rate becomes fast enough for real-time screening. The problem lies in pavement image processing. A wavelet-based pavement image processing method is proposed for distress detection and isolation, pavement image compression and noise reduction, distress classification, pavement condition evaluation, and distress segmentation. A major advantage of the proposed method is that for all processing steps involved, solutions can be found in the wavelet domain of the pavement images.
520 $a After a pavement image is decomposed into different frequency subbands by wavelet transform, distresses are transformed into high-amplitude wavelet coefficients, and noise is transformed into low-amplitude wavelet coefficients in the high-frequency subbands. These wavelet coefficients are also called details. The background is transformed into wavelet coefficients, which are referred to as the approximation, in the low-frequency subband. First, several statistical criteria are developed for distress detection and distress image isolation, which include the high-amplitude wavelet coefficient percentage (HAWCP), the high-frequency energy percentage (HFEP), and the standard deviation. These criteria are tested on hundreds of pavement images differing by type, severity and extent of distress. Experimental results demonstrate that the proposed criteria are reliable for distress detection and isolation, and that real-time distress detection and screening is feasible at the current time.
520 $a Once distresses are detected, the images need to be saved for further analysis and evaluation, such as distress classification and quantification, which are completed offline. Since a huge number of images are expected to be collected during inspection, image compression is necessary for better efficiency in image saving and loading. In this research, a modified EZW (Embedded Zero-tree Wavelet) coding method, which is an improved version of the widely used EZW coding method, is proposed. (Abstract shortened by UMI.)
590 $a School code: 0771.
650 4 $a Engineering, Mechanical. $3 783786
650 4 $a Engineering, Civil. $3 783781
690 $a 0548
690 $a 0543
710 2 0 $a State University of New York at Stony Brook. $3 1019194
773 0 $t Dissertation Abstracts International $g 65-09B.
790 1 0 $a Huang, Peisen S., $e advisor
790 $a 0771
791 $a Ph.D.
792 $a 2004
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3148739