國立虎尾科技大學 |

Multi-Perspective Image and Video Processing for Human-Machine Interaction.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Multi-Perspective Image and Video Processing for Human-Machine Interaction./
作者:	Ding, Sihao.
面頁冊數:	1 online resource (148 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
Contained By:	Dissertation Abstracts International78-10B(E).
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9781369838879

Multi-Perspective Image and Video Processing for Human-Machine Interaction.
Ding, Sihao.

Multi-Perspective Image and Video Processing for Human-Machine Interaction. - 1 online resource (148 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

Cameras nowadays are ubiquitously deployed and widely used in our daily life, from the static ones for indoor surveillance, to the dynamic ones mounted on mobile platforms. This brings the opportunity to design and develop systems based on image and video processing, to improve the quality of human-machine interaction. Such interaction covers a wide range, including interaction with computers, robots, vehicles, and infrastructures. We use the term machine to indicate these camera-equipped devices and systems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369838879Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Multi-Perspective Image and Video Processing for Human-Machine Interaction.
LDR:03543ntm a2200385Ki 4500 001 910804
005 20180517112611.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369838879
035 $a (MiAaPQ)AAI10610154
035 $a (MiAaPQ)OhioLINK:osu1488462115943949
035 $a AAI10610154
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Ding, Sihao. $3 1182267
245 1 0 $a Multi-Perspective Image and Video Processing for Human-Machine Interaction.
264 0 $c 2017
300 $a 1 online resource (148 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Yuan Zheng.
502 $a Thesis (Ph.D.) $c The Ohio State University $d 2017.
504 $a Includes bibliographical references
520 $a Cameras nowadays are ubiquitously deployed and widely used in our daily life, from the static ones for indoor surveillance, to the dynamic ones mounted on mobile platforms. This brings the opportunity to design and develop systems based on image and video processing, to improve the quality of human-machine interaction. Such interaction covers a wide range, including interaction with computers, robots, vehicles, and infrastructures. We use the term machine to indicate these camera-equipped devices and systems.
520 $a Four main subjects are covered in this work: video-based face recognition with sequential sampling; simultaneous body part and motion identification for human-following robots; human retrieval in surveillance videos; and computer generated holograms. These four subjects are closely related and all support the long term goal of practical intelligent multimedia systems and environments for human to interact with and live in. The introduced algorithms share the same philosophy of multi perspective, which is determined by the high dimensional and ambiguous nature of image and video data.
520 $a Recent development in computer vision and robotics enables advanced Human-Robot-Interaction (HRI) to become realistic. In most HRI applications, two key questions the robots face are what is the identity of human and what is the action being performed by human, i.e., "who is doing what?". Recent literatures on video-based face, body part and motion recognition are briefly reviewed. To answer the question, two approaches called Sequential sample consensus for video-based face recognition, and simultaneous body part and motion identification for human-following robots are described. On the other hand, the statically mounted cameras in infrastructures usually serve the purpose of surveillance and produce a large amount of data. A system that utilizes encoded information in compressed domain for fast processing video data is introduced. Lastly, an approach that transforms RGB-D data into computer generated holograms, from which images of different viewpoints and focal depths can be reconstructed, is described for potential application in interactive virtual reality display.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Engineering. $3 561152
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0537
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The Ohio State University. $b Electrical and Computer Engineering. $3 845530
773 0 $t Dissertation Abstracts International $g 78-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10610154 $z click for full text (PQDT)