國立虎尾科技大學 |

3D Object Understanding from RGB-D Data.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	3D Object Understanding from RGB-D Data./
Author:	Feng, Jie.
Description:	1 online resource (157 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
Subject:	Artificial intelligence. -
Online resource:	click for full text (PQDT)
ISBN:	9780355386660

3D Object Understanding from RGB-D Data.
Feng, Jie.

3D Object Understanding from RGB-D Data. - 1 online resource (157 pages)

Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.

Thesis (Ph.D.)--Columbia University, 2017.

Includes bibliographical references

Understanding 3D objects and being able to interact with them in the physical world are essential for building intelligent computer vision systems. It has tremendous potentials for various applications ranging from augmented reality, 3D printing to robotics. It might seem simple for human to look and make sense of the visual world, it is however a complicated process for machines to accomplish similar tasks. Generally, the system is involved with a series of processes: identify and segment a target object, estimate its 3D shape and predict its pose in an open scene where the target objects may have not been seen before. Although considerable research works have been proposed to tackle these problems, they remain very challenging due to a few key issues: 1) most methods rely solely on color images for interpreting the 3D property of an object; 2) large labeled color images are expensive to get for tasks like pose estimation, limiting the ability to train powerful prediction models; 3) training data for the target object is typically required for 3D shape estimation and pose prediction, making these methods hard to scale and generalize to unseen objects.

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

Mode of access: World Wide Web

ISBN: 9780355386660Subjects--Topical Terms:

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

554714
Electronic books.

3D Object Understanding from RGB-D Data.
LDR:03954ntm a2200349K 4500 001 913994
005 20180628100933.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355386660
035 $a (MiAaPQ)AAI10637905
035 $a (MiAaPQ)columbia:14267
035 $a AAI10637905
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Feng, Jie. $3 1187051
245 1 0 $a 3D Object Understanding from RGB-D Data.
264 0 $c 2017
300 $a 1 online resource (157 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: 79-04(E), Section: B.
500 $a Adviser: Shih-Fu Chang.
502 $a Thesis (Ph.D.)--Columbia University, 2017.
504 $a Includes bibliographical references
520 $a Understanding 3D objects and being able to interact with them in the physical world are essential for building intelligent computer vision systems. It has tremendous potentials for various applications ranging from augmented reality, 3D printing to robotics. It might seem simple for human to look and make sense of the visual world, it is however a complicated process for machines to accomplish similar tasks. Generally, the system is involved with a series of processes: identify and segment a target object, estimate its 3D shape and predict its pose in an open scene where the target objects may have not been seen before. Although considerable research works have been proposed to tackle these problems, they remain very challenging due to a few key issues: 1) most methods rely solely on color images for interpreting the 3D property of an object; 2) large labeled color images are expensive to get for tasks like pose estimation, limiting the ability to train powerful prediction models; 3) training data for the target object is typically required for 3D shape estimation and pose prediction, making these methods hard to scale and generalize to unseen objects.
520 $a Recently, several technological changes have created interesting opportunities for solving these fundamental vision problems. Low-cost depth sensors become widely available that provides an additional sensory input as a depth map which is very useful for extracting 3D information of the object and scene. On the other hand, with the ease of 3D object scanning with depth sensors and open access to large scale 3D model database like 3D warehouse and ShapeNet, it is possible to leverage such data to build powerful learning models. Third, machine learning algorithm like deep learning has become powerful that it starts to surpass state-of-the-art or even human performance on challenging tasks like object recognition. It is now feasible to learn rich information from large datasets in a single model.
520 $a The objective of this thesis is to leverage such emerging tools and data to solve the above mentioned challenging problems for understanding 3D objects with a new perspective by designing machine learning algorithms utilizing RGB-D data. Instead of solely depending on color images, we combine both color and depth images to achieve significantly higher performance for object segmentation. We use large collection of 3D object models to provide high quality training data and retrieve visually similar 3D CAD models from low-quality captured depth images which enables knowledge transfer from database objects to target object in an observed scene. By using content-based 3D shape retrieval, we also significantly improve pose estimation via similar proxy models without the need to create the exact 3D model as a reference.
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 Columbia University. $b Computer Science. $3 1179509
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10637905 $z click for full text (PQDT)