| LDR | | 00000nmm u2200205 4500 |
| 001 | | 000000330504 |
| 005 | | 20241101093450 |
| 008 | | 181129s2018 ||| | | | eng d |
| 020 | |
▼a 9780438402317 |
| 035 | |
▼a (MiAaPQ)AAI10845896 |
| 035 | |
▼a (MiAaPQ)umd:19377 |
| 040 | |
▼a MiAaPQ
▼c MiAaPQ
▼d 248032 |
| 049 | 1 |
▼f DP |
| 082 | 0 |
▼a 004 |
| 100 | 1 |
▼a Sun, Jin. |
| 245 | 10 |
▼a Finding Objects in Complex Scenes. |
| 260 | |
▼a [S.l.] :
▼b University of Maryland, College Park.,
▼c 2018 |
| 260 | 1 |
▼a Ann Arbor :
▼b ProQuest Dissertations & Theses,
▼c 2018 |
| 300 | |
▼a 175 p. |
| 500 | |
▼a Source: Dissertation Abstracts International, Volume: 80-02(E), Section: B. |
| 500 | |
▼a Adviser: David Jacobs. |
| 502 | 1 |
▼a Thesis (Ph.D.)--University of Maryland, College Park, 2018. |
| 520 | |
▼a Object detection is one of the fundamental problems in computer vision that has great practical impact. Current object detectors work well under certain conditions. However, challenges arise when scenes become more complex. Scenes are often clut |
| 520 | |
▼a We believe the key to tackle those challenges is to understand the rich context of objects in scenes, which includes: the appearance variations of an object due to viewpoint and lighting condition changes |
| 520 | |
▼a To facilitate collecting training data with large variations, we design a novel user interface, ARLabeler, utilizing the power of Augmented Reality (AR) devices. Instead of labeling images from the Internet passively, we put an observer in the r |
| 520 | |
▼a We also study challenges in deploying object detectors in real world scenes: detecting curb ramps in street view images. A system, Tohme, is proposed to combine detection results from detectors and human crowdsourcing verifications. One core com |
| 520 | |
▼a One of the insights from Tohme is that context is crucial in detecting objects. To understand the complex relationship between objects and their environment, we propose a standalone context model that predicts where an object can occur in an ima |
| 520 | |
▼a To take a step beyond single object based detections, we explicitly model the geometrical relationships between groups of objects and use the layout information to represent scenes as a whole. We show that such a strategy is useful in retrieving |
| 590 | |
▼a School code: 0117. |
| 650 | 4 |
▼a Computer science. |
| 690 | |
▼a 0984 |
| 710 | 20 |
▼a University of Maryland, College Park.
▼b Computer Science. |
| 773 | 0 |
▼t Dissertation Abstracts International
▼g 80-02B(E). |
| 773 | |
▼t Dissertation Abstract International |
| 790 | |
▼a 0117 |
| 791 | |
▼a Ph.D. |
| 792 | |
▼a 2018 |
| 793 | |
▼a English |
| 856 | 40 |
▼u http://www.riss.kr/pdu/ddodLink.do?id=T15000096
▼n KERIS |
| 980 | |
▼a 201812
▼f 2019 |
| 990 | |
▼a 관리자
▼b 관리자 |