國立虎尾科技大學 |

Multi-Frame Optical Flow Estimation Using Spatio-Temporal Transformers.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Multi-Frame Optical Flow Estimation Using Spatio-Temporal Transformers./
作者:	Ferede, Fisseha Admasu.
面頁冊數:	1 online resource (56 pages)
附註:	Source: Masters Abstracts International, Volume: 84-07.
Contained By:	Masters Abstracts International84-07.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798363515736

Multi-Frame Optical Flow Estimation Using Spatio-Temporal Transformers.
Ferede, Fisseha Admasu.

Multi-Frame Optical Flow Estimation Using Spatio-Temporal Transformers. - 1 online resource (56 pages)

Source: Masters Abstracts International, Volume: 84-07.

Thesis (M.S.)--The University of Memphis, 2022.

Includes bibliographical references

Optical flow estimation is a computer vision problem which aims to estimate apparent 2D motion (flow velocities) of image intensities between two or more consecutive frames in an image sequence. Optical flow information is useful for quantifying dense motion field in numerous applications such as autonomous driving, object tracking in traffic control systems, video frame interpolation, video compression and structural biomarker development for medical diagnosis. Recent state of the art learning methods for optical flow estimation are two-frame based methods where optical flow is estimated sequentially for each image pairs in an image sequence. In this work, we introduce a learning based spatio-temporal transformers for multi-frame optical flow estimation (SSTMs). SSTM is a multi-frame based optical flow estimation algorithm which can learn and estimate non-linear motion dynamics in a scene from multiple sequential images of the scene. When compared to two-frame methods, SSTM can provide improved optical flow estimates in regions with object occlusions and near boundaries where objects may enter or leave the scene (out-of-boundary regions). Our method utilizes 3D Convolutional Gated Recurrent Networks (3D-ConvGRUs) and space-time attention modules to learn the recurrent space-time dynamics of input scenes and provide a generalized optical flow estimation. When trained using the same training datasets, our method outperforms both the existing multi-frame based optical flow estimation algorithms and the recent state of the art two-frame methods on Sintel benchmark dataset (based on a computer-animated movie) and KITTI 2015 driving benchmark datasets.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798363515736Subjects--Topical Terms:

596380
Electrical engineering.
Subjects--Index Terms:

Optical flow estimationIndex Terms--Genre/Form:

554714
Electronic books.

Multi-Frame Optical Flow Estimation Using Spatio-Temporal Transformers.
LDR:02937ntm a22003617 4500 001 1144454
005 20240611104232.5
006 m o d
007 cr mn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798363515736
035 $a (MiAaPQ)AAI30001376
035 $a AAI30001376
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ferede, Fisseha Admasu. $3 1469492
245 1 0 $a Multi-Frame Optical Flow Estimation Using Spatio-Temporal Transformers.
264 0 $c 2022
300 $a 1 online resource (56 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: Masters Abstracts International, Volume: 84-07.
500 $a Advisor: Balasubramanian, Madhusudhanan.
502 $a Thesis (M.S.)--The University of Memphis, 2022.
504 $a Includes bibliographical references
520 $a Optical flow estimation is a computer vision problem which aims to estimate apparent 2D motion (flow velocities) of image intensities between two or more consecutive frames in an image sequence. Optical flow information is useful for quantifying dense motion field in numerous applications such as autonomous driving, object tracking in traffic control systems, video frame interpolation, video compression and structural biomarker development for medical diagnosis. Recent state of the art learning methods for optical flow estimation are two-frame based methods where optical flow is estimated sequentially for each image pairs in an image sequence. In this work, we introduce a learning based spatio-temporal transformers for multi-frame optical flow estimation (SSTMs). SSTM is a multi-frame based optical flow estimation algorithm which can learn and estimate non-linear motion dynamics in a scene from multiple sequential images of the scene. When compared to two-frame methods, SSTM can provide improved optical flow estimates in regions with object occlusions and near boundaries where objects may enter or leave the scene (out-of-boundary regions). Our method utilizes 3D Convolutional Gated Recurrent Networks (3D-ConvGRUs) and space-time attention modules to learn the recurrent space-time dynamics of input scenes and provide a generalized optical flow estimation. When trained using the same training datasets, our method outperforms both the existing multi-frame based optical flow estimation algorithms and the recent state of the art two-frame methods on Sintel benchmark dataset (based on a computer-animated movie) and KITTI 2015 driving benchmark datasets.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer engineering. $3 569006
653 $a Optical flow estimation
653 $a 2D motion
653 $a SSTM
655 7 $a Electronic books. $2 local $3 554714
690 $a 0464
690 $a 0544
710 2 $a The University of Memphis. $b Electrical & Computer Engineering. $3 1469209
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 84-07.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30001376 $z click for full text (PQDT)