國立虎尾科技大學 |

Towards Efficient 3D Reconstructions from High-resolution Satellite Imagery.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Towards Efficient 3D Reconstructions from High-resolution Satellite Imagery./
作者:	Wang, Ke.
面頁冊數:	1 online resource (134 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Contained By:	Dissertation Abstracts International79-10B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780438002586

Towards Efficient 3D Reconstructions from High-resolution Satellite Imagery.
Wang, Ke.

Towards Efficient 3D Reconstructions from High-resolution Satellite Imagery. - 1 online resource (134 pages)

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

Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2018.

Includes bibliographical references

Recent years have witnessed the rapid growth of commercial satellite imagery. Compared with other imaging products, such as aerial or streetview imagery, modern satellite images are captured at high resolution and with multiple spectral bands, thus provide unique viewing angles, global coverage, and frequent updates of the Earth surfaces. With automated processing and intelligent analysis algorithms, satellite images can enable global-scale 3D modeling applications.

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

Mode of access: World Wide Web

ISBN: 9780438002586Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Towards Efficient 3D Reconstructions from High-resolution Satellite Imagery.
LDR:04259ntm a2200373Ki 4500 001 918308
005 20181114145235.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438002586
035 $a (MiAaPQ)AAI10283656
035 $a (MiAaPQ)unc:17122
035 $a AAI10283656
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Wang, Ke. $3 1064805
245 1 0 $a Towards Efficient 3D Reconstructions from High-resolution Satellite Imagery.
264 0 $c 2018
300 $a 1 online resource (134 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: Jan-Michael Frahm; Enrique Dunn.
502 $a Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2018.
504 $a Includes bibliographical references
520 $a Recent years have witnessed the rapid growth of commercial satellite imagery. Compared with other imaging products, such as aerial or streetview imagery, modern satellite images are captured at high resolution and with multiple spectral bands, thus provide unique viewing angles, global coverage, and frequent updates of the Earth surfaces. With automated processing and intelligent analysis algorithms, satellite images can enable global-scale 3D modeling applications.
520 $a This dissertation explores computer vision algorithms to reconstruct 3D models from satellite images at different levels: geometric, semantic, and parametric reconstructions. However, reconstructing satellite imagery is particularly challenging for the following reasons: 1) Satellite images typically contain an enormous amount of raw pixels. Efficient algorithms are needed to minimize the substantial computational burden. 2) The ground sampling distances of satellite images are comparatively low. Visual entities, such as buildings, appear visually small and cluttered, thus posing difficulties for 3D modeling. 3) Satellite images usually have complex camera models and inaccurate vendor-provided camera calibrations. Rational polynomial coefficients (RPC) camera models, although widely used, need to be appropriately handled to ensure high-quality reconstructions.
520 $a To obtain geometric reconstructions efficiently, we propose an edge-aware interpolation-based algorithm to obtain 3D point clouds from satellite image pairs. Initial 2D pixel matches are first established and triangulated to compensate the RPC calibration errors. Noisy dense correspondences can then be estimated by interpolating the inlier matches in an edge-aware manner. After refining the correspondence map with a fast bilateral solver, we can obtain dense 3D point clouds via triangulation.
520 $a Pixel-wise semantic classification results for satellite images are usually noisy due to the negligence of spatial neighborhood information. Thus, we propose to aggregate multiple corresponding observations of the same 3D point to obtain high-quality semantic models. Instead of just leveraging geometric reconstructions to provide such correspondences, we formulate geometric modeling and semantic reasoning in a joint Markov Random Field (MRF) model. Our experiments show that both tasks can benefit from the joint inference.
520 $a Finally, we propose a novel deep learning based approach to perform single-view parametric reconstructions from satellite imagery. By parametrizing buildings as 3D cuboids, our method simultaneously localizes building instances visible in the image and estimates their corresponding cuboid models. Aerial LiDAR and vectorized GIS maps are utilized as supervision. Our network upsamples CNN features to detect small but cluttered building instances. In addition, we estimate building contours through a separate fully convolutional network to avoid overlapping building cuboids.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of North Carolina at Chapel Hill. $b Computer Science. $3 1192598
773 0 $t Dissertation Abstracts International $g 79-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10283656 $z click for full text (PQDT)