國立虎尾科技大學 |

Machine Learning Techniques for Outdoor and Indoor Layout Estimation.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Machine Learning Techniques for Outdoor and Indoor Layout Estimation./
作者:	Ren, Yuzhuo.
面頁冊數:	1 online resource (128 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.
Contained By:	Dissertation Abstracts International79-05B(E).
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355574869

Machine Learning Techniques for Outdoor and Indoor Layout Estimation.
Ren, Yuzhuo.

Machine Learning Techniques for Outdoor and Indoor Layout Estimation. - 1 online resource (128 pages)

Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.

Thesis (Ph.D.)--University of Southern California, 2017.

Includes bibliographical references

In this dissertation, we study three research problems: 1) Outdoor geometric labeling, and 2) Indoor layout estimation and 3) 3D object detection.

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

Mode of access: World Wide Web

ISBN: 9780355574869Subjects--Topical Terms:

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

554714
Electronic books.

Machine Learning Techniques for Outdoor and Indoor Layout Estimation.
LDR:04495ntm a2200373Ki 4500 001 916839
005 20180928111502.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355574869
035 $a (MiAaPQ)AAI10684245
035 $a (MiAaPQ)usc:15982
035 $a AAI10684245
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ren, Yuzhuo. $3 1106043
245 1 0 $a Machine Learning Techniques for Outdoor and Indoor Layout Estimation.
264 0 $c 2017
300 $a 1 online resource (128 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: 79-05(E), Section: B.
500 $a Adviser: C.-C. Jay Kuo.
502 $a Thesis (Ph.D.)--University of Southern California, 2017.
504 $a Includes bibliographical references
520 $a In this dissertation, we study three research problems: 1) Outdoor geometric labeling, and 2) Indoor layout estimation and 3) 3D object detection.
520 $a A novel method that extracts global attributes from outdoor images to facilitate geometric layout labeling is proposed in Chapter 3. The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes. First, by following a classical method, we use local features to provide initial labels for all super-pixels. Then, we develop a set of techniques to extract global attributes from 2D outdoor images. They include sky lines, ground lines, vanishing lines, etc. Finally, we propose the GAL system that integrates global attributes in the conditional random field (CRF) framework to improve initial labels so as to offer a more robust labeling result. The performance of the proposed GAL system is demonstrated and benchmarked with several state-of-the-art algorithms against a popular outdoor scene layout dataset.
520 $a The task of estimating the spatial layout of cluttered indoor scenes from a single RGB image is addressed in Chapter 4. Existing solutions to this problem largely rely on handcraft features and vanishing lines. They often fail in highly cluttered indoor scenes. The proposed coarse-to-fine indoor layout estimation (CFILE) method consists of two stages: 1) coarse layout estimation; and 2) fine layout localization. In the first stage, we adopt a fully convolutional neural network (FCN) to obtain a coarse-scale room layout estimate that is close to the ground truth globally. The proposed FCN considers the combination of the layout contour property and the surface property so as to provide a robust estimate in the presence of cluttered objects. In the second stage, we formulate an optimization framework that enforces several constraints such as layout contour straightness, surface smoothness and geometric constraints for layout detail refinement. The proposed CFILE system offers the state-of-the-art performance on two common benchmark datasets.
520 $a Given a RGB-D image, we study the problem of 3D object detection from RGB-D images so as to achieve localization (i.e., producing a bounding box around the object) and classification (i.e., determining the object category) simultaneously Chapter 5. Its challenges arise from high intra-class variability, illumination change, background clutter and occlusion. To solve this problem, we propose a novel solution that integrates the 2D information (RGB images), the 3D information (RGB-D images) and the object/scene context information together, and call it the Context-Assisted 3D (C3D) Method. In the proposed C3D method, we first use a convolutional neural network (CNN) to jointly detect a 3D object in a scene and its scene category. Then, we improve the detection result furthermore with a Conditional Random Field (CRF) model that incorporates the object potential, the scene potential, the scene/object context, the object/object context, and the room geometry. Extensive experiments are conducted to demonstrate that the proposed C3D method achieves the state-of-the-art performance for 3D object detection against the SUN RGB-D benchmark dataset.
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 Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Southern California. $b Electrical Engineering. $3 845473
773 0 $t Dissertation Abstracts International $g 79-05B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10684245 $z click for full text (PQDT)