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

Real-Time Hand Posture Recognition U...

Lahamy, Herve.

FindBook

Google Book

Amazon

博客來

Real-Time Hand Posture Recognition Using a Range Camera.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Real-Time Hand Posture Recognition Using a Range Camera./
作者:	Lahamy, Herve.
面頁冊數:	211 p.
附註:	Source: Dissertation Abstracts International, Volume: 75-04(E), Section: B.
Contained By:	Dissertation Abstracts International75-04B(E).
標題:	Remote sensing. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR96749
ISBN:	9780494967492

Real-Time Hand Posture Recognition Using a Range Camera.
Lahamy, Herve.

Real-Time Hand Posture Recognition Using a Range Camera. - 211 p.

Source: Dissertation Abstracts International, Volume: 75-04(E), Section: B.

Thesis (Ph.D.)--University of Calgary (Canada), 2013.

This item must not be sold to any third party vendors.

The basic goal of human computer interaction is to improve the interaction between users and computers by making computers more usable and receptive to the user's needs. Within this context, the use of hand postures in replacement of traditional devices such as keyboards, mice and joysticks is being explored by many researchers. The goal is to interpret human postures via mathematical algorithms. Hand posture recognition has gained popularity in recent years, and could become the future tool for humans to interact with computers or virtual environments.

ISBN: 9780494967492Subjects--Topical Terms:

535394
Remote sensing.

Real-Time Hand Posture Recognition Using a Range Camera.
LDR:03582nmm a2200385 4500 001 2060321
005 20150827091403.5
008 170521s2013 ||||||||||||||||| ||eng d
020 $a 9780494967492
035 $a (MiAaPQ)AAINR96749
035 $a AAINR96749
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lahamy, Herve. $3 3174467
245 1 0 $a Real-Time Hand Posture Recognition Using a Range Camera.
300 $a 211 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-04(E), Section: B.
500 $a Adviser: Derek Lichti.
502 $a Thesis (Ph.D.)--University of Calgary (Canada), 2013.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a The basic goal of human computer interaction is to improve the interaction between users and computers by making computers more usable and receptive to the user's needs. Within this context, the use of hand postures in replacement of traditional devices such as keyboards, mice and joysticks is being explored by many researchers. The goal is to interpret human postures via mathematical algorithms. Hand posture recognition has gained popularity in recent years, and could become the future tool for humans to interact with computers or virtual environments.
520 $a An exhaustive description of the frequently used methods available in literature for hand posture recognition is provided. It focuses on the different types of sensors and data used, the segmentation and tracking methods, the features used to represent the hand postures as well as the classifiers considered in the recognition process.
520 $a Those methods are usually presented as highly robust with a recognition rate close to 100%. However, a couple of critical points necessary for a successful real-time hand posture recognition system require major improvement. Those points include the features used to represent the hand segment, the number of postures simultaneously recognizable, the invariance of the features with respect to rotation, translation and scale and also the behavior of the classifiers against non-perfect hand segments for example segments including part of the arm or missing part of the palm.
520 $a A 3D time-of-flight camera named SR4000 has been chosen to develop a new methodology because of its capability to provide in real-time and at high frame rate 3D information on the scene imaged. This sensor has been described and evaluated for its capability for capturing in real-time a moving hand.
520 $a A new recognition method that uses the 3D information provided by the range camera to recognize hand postures has been proposed. The different steps of this methodology including the segmentation, the tracking, the hand modeling and finally the recognition process have been described and evaluated extensively. In addition, the performance of this method has been analyzed against several existing hand posture recognition techniques found in literature.
520 $a The proposed system is able to recognize with an overall recognition rate of 98% and in real-time 18 out the 33 postures of the American sign language alphabet. This recognition is translation, rotation and scale invariant.
590 $a School code: 0026.
650 4 $a Remote sensing. $3 535394
650 4 $a Computer engineering. $3 621879
650 4 $a Electrical engineering. $3 649834
650 4 $a Robotics. $3 519753
690 $a 0799
690 $a 0464
690 $a 0544
690 $a 0771
710 2 $a University of Calgary (Canada). $b Geomatics Engineering. $3 3170933
773 0 $t Dissertation Abstracts International $g 75-04B(E).
790 $a 0026
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR96749