東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Methods for robust driver pose estim...

Marx, Jason M.

Linked to FindBook

Google Book

Amazon

博客來

Methods for robust driver pose estimation.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Methods for robust driver pose estimation./
Author:	Marx, Jason M.
Description:	105 p.
Notes:	Source: Masters Abstracts International, Volume: 42-05, page: 1823.
Contained By:	Masters Abstracts International42-05.
Subject:	Engineering, Electronics and Electrical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1418562

Methods for robust driver pose estimation.
Marx, Jason M.

Methods for robust driver pose estimation. - 105 p.

Source: Masters Abstracts International, Volume: 42-05, page: 1823.

Thesis (M.S.E.)--University of Michigan-Dearborn, 2004.

This thesis presents methods for monitoring a driver's pose while he or she operates a vehicle. The driver pose is found by analyzing a video of a driver taken from a dash-board mounted video camera. Image frames are extracted from the video and used for analysis. The investigated approaches can be broadly divided into the following categories: (a) Pose estimation methods, which are used to determine the driver pose for each frame of the video. (b) Combination of classifiers, which use independent pose estimation algorithms to determine the driver pose for each frame of the video. These classifiers also have the option of rejecting video frames which cannot confidently be classified.Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Methods for robust driver pose estimation.
LDR:01997nmm 2200289 4500 001 1864408
005 20041217072326.5
008 130614s2004 eng d
035 $a (UnM)AAI1418562
035 $a AAI1418562
040 $a UnM $c UnM
100 1 $a Marx, Jason M. $3 1951901
245 1 0 $a Methods for robust driver pose estimation.
300 $a 105 p.
500 $a Source: Masters Abstracts International, Volume: 42-05, page: 1823.
500 $a Adviser: Paul Watta.
502 $a Thesis (M.S.E.)--University of Michigan-Dearborn, 2004.
520 $a This thesis presents methods for monitoring a driver's pose while he or she operates a vehicle. The driver pose is found by analyzing a video of a driver taken from a dash-board mounted video camera. Image frames are extracted from the video and used for analysis. The investigated approaches can be broadly divided into the following categories: (a) Pose estimation methods, which are used to determine the driver pose for each frame of the video. (b) Combination of classifiers, which use independent pose estimation algorithms to determine the driver pose for each frame of the video. These classifiers also have the option of rejecting video frames which cannot confidently be classified.
520 $a In addition, a method for estimating driver motion is presented. The principle contributions of this thesis are a new innovative pose estimation approach, a motion estimation algorithm, and three combination of classifiers which have a rejection mechanism. Additionally, this thesis investigates the analysis of the driver under two sets of pose classification guidelines.
520 $a Simulation results show the performance of the system with respect to six driver video databases.
590 $a School code: 1472.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Engineering, Automotive. $3 1018477
690 $a 0544
690 $a 0540
710 2 0 $a University of Michigan-Dearborn. $3 1951902
773 0 $t Masters Abstracts International $g 42-05.
790 1 0 $a Watta, Paul, $e advisor
790 $a 1472
791 $a M.S.E.
792 $a 2004
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1418562