語系:
繁體中文
English
說明(常見問題)
登入
回首頁
切換:
標籤
|
MARC模式
|
ISBD
Monocular Depth Estimation Using Deep Learning With Active Vision.
紀錄類型:
書目-語言資料,手稿 : Monograph/item
正題名/作者:
Monocular Depth Estimation Using Deep Learning With Active Vision./
作者:
Meier, Joseph Raymond.
面頁冊數:
1 online resource (34 pages)
附註:
Source: Masters Abstracts International, Volume: 85-11.
Contained By:
Masters Abstracts International85-11.
標題:
Computer science. -
電子資源:
click for full text (PQDT)
ISBN:
9798382611037
Monocular Depth Estimation Using Deep Learning With Active Vision.
Meier, Joseph Raymond.
Monocular Depth Estimation Using Deep Learning With Active Vision.
- 1 online resource (34 pages)
Source: Masters Abstracts International, Volume: 85-11.
Thesis (M.S.)--Tarleton State University, 2024.
Includes bibliographical references
Grasping the structure of an environment within images is a core challenge for machine perception. Three-dimensional data is instrumental in robotic path planning, autonomous driving, scene reconstruction, and a wide array of applications. The conventional approaches of stereo vision and laser scanning are not always the ideal selection for a particular system or available expenditure. Predicting depth from images taken with a single camera offers a potential solution to these cases albeit with inherent constraints.This research proposes a monocular depth estimation method applying deep learning techniques coupled with multiple linear regression on images captured by a 12- megapixel camera with a motorized varifocal lens. The approach simulates world coordinates projected onto the image plane with camera parameters of varying focal lengths. BoostedDepth single image relative depth estimation, YOLOv8 image detection and segmentation process the real-world images to establish an initial absolute metric depth prediction. This preliminary prediction defines the optimal range of world coordinates to train the regression model. Applying the model with the image coordinates of the base image and the magnitude of disparity between a set of images at distinct magnification produces the depth estimate.
Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024
Mode of access: World Wide Web
ISBN: 9798382611037Subjects--Topical Terms:
573171
Computer science.
Subjects--Index Terms:
Monocular depth estimation methodIndex Terms--Genre/Form:
554714
Electronic books.
Monocular Depth Estimation Using Deep Learning With Active Vision.
LDR
:02650ntm a22003857 4500
001
1149744
005
20241022112628.5
006
m o d
007
cr bn ---uuuuu
008
250605s2024 xx obm 000 0 eng d
020
$a
9798382611037
035
$a
(MiAaPQ)AAI31296543
035
$a
AAI31296543
040
$a
MiAaPQ
$b
eng
$c
MiAaPQ
$d
NTU
100
1
$a
Meier, Joseph Raymond.
$3
1476074
245
1 0
$a
Monocular Depth Estimation Using Deep Learning With Active Vision.
264
0
$c
2024
300
$a
1 online resource (34 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: 85-11.
500
$a
Advisor: Diamantas, Sotirios.
502
$a
Thesis (M.S.)--Tarleton State University, 2024.
504
$a
Includes bibliographical references
520
$a
Grasping the structure of an environment within images is a core challenge for machine perception. Three-dimensional data is instrumental in robotic path planning, autonomous driving, scene reconstruction, and a wide array of applications. The conventional approaches of stereo vision and laser scanning are not always the ideal selection for a particular system or available expenditure. Predicting depth from images taken with a single camera offers a potential solution to these cases albeit with inherent constraints.This research proposes a monocular depth estimation method applying deep learning techniques coupled with multiple linear regression on images captured by a 12- megapixel camera with a motorized varifocal lens. The approach simulates world coordinates projected onto the image plane with camera parameters of varying focal lengths. BoostedDepth single image relative depth estimation, YOLOv8 image detection and segmentation process the real-world images to establish an initial absolute metric depth prediction. This preliminary prediction defines the optimal range of world coordinates to train the regression model. Applying the model with the image coordinates of the base image and the magnitude of disparity between a set of images at distinct magnification produces the depth estimate.
533
$a
Electronic reproduction.
$b
Ann Arbor, Mich. :
$c
ProQuest,
$d
2024
538
$a
Mode of access: World Wide Web
650
4
$a
Computer science.
$3
573171
650
4
$a
Computer engineering.
$3
569006
650
4
$a
Information technology.
$3
559429
653
$a
Monocular depth estimation method
653
$a
Deep learning techniques
653
$a
Multiple linear regression
653
$a
Camera
655
7
$a
Electronic books.
$2
local
$3
554714
690
$a
0984
690
$a
0464
690
$a
0489
710
2
$a
ProQuest Information and Learning Co.
$3
1178819
710
2
$a
Tarleton State University.
$b
Department of Engineering and Computer Science.
$3
1474064
773
0
$t
Masters Abstracts International
$g
85-11.
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31296543
$z
click for full text (PQDT)
筆 0 讀者評論
多媒體
評論
新增評論
分享你的心得
Export
取書館別
處理中
...
變更密碼[密碼必須為2種組合(英文和數字)及長度為10碼以上]
登入