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

Intelligent perception in virtual se...

Qureshi, Faisal Zubair.

FindBook

Google Book

Amazon

博客來

Intelligent perception in virtual sensor networks and space robotics.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Intelligent perception in virtual sensor networks and space robotics./
作者:	Qureshi, Faisal Zubair.
面頁冊數:	244 p.
附註:	Source: Dissertation Abstracts International, Volume: 68-06, Section: B, page: 3909.
Contained By:	Dissertation Abstracts International68-06B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR27914
ISBN:	9780494279144

Intelligent perception in virtual sensor networks and space robotics.
Qureshi, Faisal Zubair.

Intelligent perception in virtual sensor networks and space robotics. - 244 p.

Source: Dissertation Abstracts International, Volume: 68-06, Section: B, page: 3909.

Thesis (Ph.D.)--University of Toronto (Canada), 2007.

Intelligent perception is a fundamental requirement of systems that exhibit sophisticated autonomous operation in complex dynamic worlds. It combines low-level, bottom-up, data-driven vision with high-level, top-down, knowledge-based processes. This thesis develops two embodied, task-oriented vision systems that exhibit autonomous, intelligent, goal-driven behavior through intelligent perception.

ISBN: 9780494279144Subjects--Topical Terms:

626642
Computer Science.

Intelligent perception in virtual sensor networks and space robotics.
LDR:03084nam 2200277 a 45 001 954955
005 20110622
008 110622s2007 ||||||||||||||||| ||eng d
020 $a 9780494279144
035 $a (UMI)AAINR27914
035 $a AAINR27914
040 $a UMI $c UMI
100 1 $a Qureshi, Faisal Zubair. $3 1278418
245 1 0 $a Intelligent perception in virtual sensor networks and space robotics.
300 $a 244 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-06, Section: B, page: 3909.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2007.
520 $a Intelligent perception is a fundamental requirement of systems that exhibit sophisticated autonomous operation in complex dynamic worlds. It combines low-level, bottom-up, data-driven vision with high-level, top-down, knowledge-based processes. This thesis develops two embodied, task-oriented vision systems that exhibit autonomous, intelligent, goal-driven behavior through intelligent perception.
520 $a In Part I of the thesis, we develop a prototype surveillance system featuring a visual sensor network comprising wide field-of-view (FOV) passive cameras and pan/tilt/zoom active cameras. Novel multicamera control strategies enable the camera nodes to collaborate both in tracking pedestrians of interest that move across the FOVs of different cameras and in acquiring close-up videos of pedestrians as they travel across extended areas. Impediments to deploying and experimenting with appropriately extensive camera networks in large, busy public spaces would make our research more or less infeasible in the real world. However, a unique centerpiece of our approach is the virtual vision paradigm, in which we employ a visually and behaviorally realistic simulator in the design and evaluation of our surveillance systems. In particular, we employ a virtual train station populated by autonomous, lifelike virtual pedestrians, wherein easily reconfigurable virtual cameras generate synthetic video feeds that emulate those acquired by real surveillance cameras monitoring public spaces.
520 $a In Part II of the thesis, we develop a cognitively-controlled vision system that combines low-level object recognition and tracking with high-level symbolic reasoning to tackle difficult space robotics problems, specifically satellite rendezvous and docking. There is significant interest in performing these operations autonomously, and our work is a step in this direction. Reasoning and related elements, among them intention, context, and memory, contribute to improve performance. We demonstrate the vision system controlling a robotic arm that autonomously captures a free-flying satellite. To date, this is the only satellite-capturing system that relies exclusively on vision to estimate the pose of the satellite and can deal with an uncooperative satellite.
590 $a School code: 0779.
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, Robotics. $3 1018454
690 $a 0771
690 $a 0984
710 2 $a University of Toronto (Canada). $3 1017674
773 0 $t Dissertation Abstracts International $g 68-06B.
790 $a 0779
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR27914