東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Inference Machines Parsing Scenes vi...

Munoz, Daniel.

FindBook

Google Book

Amazon

博客來

Inference Machines Parsing Scenes via Iterated Predictions.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Inference Machines Parsing Scenes via Iterated Predictions./
作者:	Munoz, Daniel.
面頁冊數:	133 p.
附註:	Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.
Contained By:	Dissertation Abstracts International75-02B(E).
標題:	Engineering, Robotics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3575513
ISBN:	9781303536748

Inference Machines Parsing Scenes via Iterated Predictions.
Munoz, Daniel.

Inference Machines Parsing Scenes via Iterated Predictions. - 133 p.

Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.

Thesis (Ph.D.)--Carnegie Mellon University, 2013.

Extracting a rich representation of an environment from visual sensor readings can benefit many tasks in robotics, e.g., path planning, mapping, and object manipulation. While important progress has been made, it remains a difficult problem to effectively parse entire scenes, i.e., to recognize semantic objects, man-made structures, and land-forms. This process requires not only recognizing individual entities but also understanding the contextual relations among them.

ISBN: 9781303536748Subjects--Topical Terms:

1018454
Engineering, Robotics.

Inference Machines Parsing Scenes via Iterated Predictions.
LDR:03138nam a2200313 4500 001 1960560
005 20140623111235.5
008 150210s2013 ||||||||||||||||| ||eng d
020 $a 9781303536748
035 $a (MiAaPQ)AAI3575513
035 $a AAI3575513
040 $a MiAaPQ $c MiAaPQ
100 1 $a Munoz, Daniel. $3 2096246
245 1 0 $a Inference Machines Parsing Scenes via Iterated Predictions.
300 $a 133 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.
500 $a Advisers: J. Andrew Bagnell; Martial Hebert.
502 $a Thesis (Ph.D.)--Carnegie Mellon University, 2013.
520 $a Extracting a rich representation of an environment from visual sensor readings can benefit many tasks in robotics, e.g., path planning, mapping, and object manipulation. While important progress has been made, it remains a difficult problem to effectively parse entire scenes, i.e., to recognize semantic objects, man-made structures, and land-forms. This process requires not only recognizing individual entities but also understanding the contextual relations among them.
520 $a The prevalent approach to encode such relationships is to use a joint probabilistic or energy-based model which enables one to naturally write down these interactions. Unfortunately, performing exact inference over these expressive models is often intractable and instead we can only approximate the solutions. While there exists a set of sophisticated approximate inference techniques to choose from, the combination of learning and approximate inference for these expressive models is still poorly understood in theory and limited in practice. Furthermore, using approximate inference on any learned model often leads to suboptimal predictions due to the inherent approximations.
520 $a As we ultimately care about predicting the correct labeling of a scene, and not necessarily learning a joint model of the data, this work proposes to instead view the approximate inference process as a modular procedure that is directly trained in order to produce a correct labeling of the scene. Inspired by early hierarchical models in the computer vision literature for scene parsing, the proposed inference procedure is structured to incorporate both feature descriptors and contextual cues computed at multiple resolutions within the scene. We demonstrate that this inference machine framework for parsing scenes via iterated predictions offers the best of both worlds: state-of-the-art classification accuracy and computational efficiency when processing images and/or unorganized 3-D point clouds. Additionally, we address critical problems that arise in practice when parsing scenes on board real-world systems: integrating data from multiple sensor modalities and efficiently processing data that is continuously streaming from the sensors.
590 $a School code: 0041.
650 4 $a Engineering, Robotics. $3 1018454
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
690 $a 0771
690 $a 0800
690 $a 0984
710 2 $a Carnegie Mellon University. $b Robotics. $3 2096237
773 0 $t Dissertation Abstracts International $g 75-02B(E).
790 $a 0041
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3575513