國立虎尾科技大學 |

Trajectory-based Human Action Recognition.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Trajectory-based Human Action Recognition./
作者:	Habashi, Pejman.
面頁冊數:	1 online resource (131 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Contained By:	Dissertation Abstracts International79-10B(E).
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9780438050662

Trajectory-based Human Action Recognition.
Habashi, Pejman.

Trajectory-based Human Action Recognition. - 1 online resource (131 pages)

Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.

Thesis (Ph.D.)--University of Windsor (Canada), 2018.

Includes bibliographical references

Human activity recognition has been a hot topic for some time. It has several challenges, which makes this task hard and exciting for research. The sparse representation became more popular during the past decade or so. Sparse representation methods represent a video by a set of independent features. The features used in the literature are usually low-level features. Trajectories, as middle-level features, capture the motion of the scene, which is discriminant in most cases. Trajectories have also been proven useful for aligning small neighborhoods, before calculating the traditional descriptors. In fact, the trajectory aligned descriptors show better discriminant power than the trajectory shape descriptors proposed in the literature.

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

Mode of access: World Wide Web

ISBN: 9780438050662Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Trajectory-based Human Action Recognition.
LDR:03635ntm a2200373Ki 4500 001 916920
005 20180928111503.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438050662
035 $a (MiAaPQ)AAI10824986
035 $a (MiAaPQ)uwindsor:11832
035 $a AAI10824986
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Habashi, Pejman. $3 1190791
245 1 0 $a Trajectory-based Human Action Recognition.
264 0 $c 2018
300 $a 1 online resource (131 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: 79-10(E), Section: B.
500 $a Advisers: Boubakeur Boufama; Imran Ahmad.
502 $a Thesis (Ph.D.)--University of Windsor (Canada), 2018.
504 $a Includes bibliographical references
520 $a Human activity recognition has been a hot topic for some time. It has several challenges, which makes this task hard and exciting for research. The sparse representation became more popular during the past decade or so. Sparse representation methods represent a video by a set of independent features. The features used in the literature are usually low-level features. Trajectories, as middle-level features, capture the motion of the scene, which is discriminant in most cases. Trajectories have also been proven useful for aligning small neighborhoods, before calculating the traditional descriptors. In fact, the trajectory aligned descriptors show better discriminant power than the trajectory shape descriptors proposed in the literature.
520 $a However, trajectories have not been investigated thoroughly, and their full potential has not been put to the test before this work. This thesis examines trajectories, defined better trajectory shape descriptors and finally it augmented trajectories with disparity information.
520 $a This thesis formally define three different trajectory extraction methods, namely interest point trajectories (IP), Lucas-Kanade based trajectories (LK), and Farnback optical flow based trajectories (FB). Their discriminant power for human activity recognition task is evaluated. Our tests reveal that LK and FB can produce similar reliable results, although the FB perform a little better in particular scenarios. These experiments demonstrate which method is suitable for the future tests. The thesis also proposes a better trajectory shape descriptor, which is a superset of existing descriptors in the literature. The examination reveals the superior discriminant power of this newly introduced descriptor. Finally, the thesis proposes a method to augment the trajectories with disparity information. Disparity information is relatively easy to extract from a stereo image, and they can capture the 3D structure of the scene. This is the first time that the disparity information fused with trajectories for human activity recognition.
520 $a To test these ideas, a dataset of 27 activities performed by eleven actors is recorded and hand labelled. The tests demonstrate the discriminant power of trajectories. Namely, the proposed disparity-augmented trajectories improve the discriminant power of traditional dense trajectories by about 3.11%.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Windsor (Canada). $b COMPUTER SCIENCE. $3 1182526
773 0 $t Dissertation Abstracts International $g 79-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10824986 $z click for full text (PQDT)