國立虎尾科技大學 |

Active Attention for Target Detection and Recognition in Robot Vision.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Active Attention for Target Detection and Recognition in Robot Vision./
作者:	Luan, Wentao.
面頁冊數:	1 online resource (131 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.
Contained By:	Dissertation Abstracts International78-11B(E).
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355060713

Active Attention for Target Detection and Recognition in Robot Vision.
Luan, Wentao.

Active Attention for Target Detection and Recognition in Robot Vision. - 1 online resource (131 pages)

Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.

Thesis (Ph.D.)--University of Maryland, College Park, 2017.

Includes bibliographical references

In this thesis, we address problems in building an efficient and reliable target detection and recognition system for robot applications, where the vision module is only one component of the overall system executing the task. The different modules interact with each other to achieve the goal. In this interaction, the role of vision is not only to recognize but also to select what and where to process. In other words, attention is an essential process for efficient task execution. We introduce attention mechanisms into the recognition system that serve the overall system at different levels of the integration and formulate four problems as below.

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

Mode of access: World Wide Web

ISBN: 9780355060713Subjects--Topical Terms:

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

554714
Electronic books.

Active Attention for Target Detection and Recognition in Robot Vision.
LDR:05682ntm a2200397Ki 4500 001 919553
005 20181129115237.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355060713
035 $a (MiAaPQ)AAI10254613
035 $a (MiAaPQ)umd:17811
035 $a AAI10254613
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Luan, Wentao. $3 1194161
245 1 0 $a Active Attention for Target Detection and Recognition in Robot Vision.
264 0 $c 2017
300 $a 1 online resource (131 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: 78-11(E), Section: B.
500 $a Adviser: John S. Baras.
502 $a Thesis (Ph.D.)--University of Maryland, College Park, 2017.
504 $a Includes bibliographical references
520 $a In this thesis, we address problems in building an efficient and reliable target detection and recognition system for robot applications, where the vision module is only one component of the overall system executing the task. The different modules interact with each other to achieve the goal. In this interaction, the role of vision is not only to recognize but also to select what and where to process. In other words, attention is an essential process for efficient task execution. We introduce attention mechanisms into the recognition system that serve the overall system at different levels of the integration and formulate four problems as below.
520 $a At the most basic level of integration, attention interacts with vision only. We consider the problem of detecting a target in an input image using a trained binary classifier of the target and formulate the target detection problem as a sampling process. The goal is to localize the windows containing targets in the image, and attention controls which part of the image to process next. We observe that detectors' response scores of sampling windows fade gradually from the peak response window in the detection area and approximate this scoring pattern with an exponential de- cay function. Exploiting this property, we propose an active sampling procedure to efficiently detect the target while avoiding an exhaustive and expensive search of all the possible window locations.
520 $a With more knowledge about the target, we describe the target as template graphs over segmented surfaces. Constraint functions are also defined to find the node and edge's matching between an input scene graph and target's template graph. We propose to introduce the recognition early into the traditional candidate proposal process to achieve fast and reliable detection performance. The target detection thence becomes finding subgraphs from the segmented input scene graph that match the template graphs. In this problem, attention provides the order of constraints in checking the graph matching, and a reasonable sequence can help filter out negatives early, thus reducing computational time. We put forward a sub-optimal checking order, and prove that it has bounded time cost compared to the optimal checking sequence, which is not obtainable in polynomial time. Experiments on rigid and non-rigid object detection validate our pipeline.
520 $a With more freedom in control, we allow the robot to actively choose another viewpoint if the current view cannot deliver a reliable detection and recognition result. We develop a practical viewpoint control system and apply it to two human-robot interaction applications, where the detection task becomes more challenging with the additional randomness from the human. Attention represents an active process of deciding the location of the camera. Our viewpoint selection module not only considers the viewing condition constraints for vision algorithms but also incorporates the low-level robot kinematics to guarantee the reachability of the desired viewpoint. By selecting viewpoints fast using a linear time cost score function, the system can deliver smooth user interaction experience. Additionally, we provide a learning from human demonstration method to obtain the score function parameters that better serves the task's preference.
520 $a Finally, when recognition results from multiple sources under different environmental factor are available, attention means how to fuse the observations to get reliable output. We consider the problem of object recognition in 3D using an ensemble of attribute-based classifiers. We propose two new concepts to improve classification in practical situations, and show their implementation in an approach implemented for recognition from point-cloud data. First, we study the impact of the distance between the camera and the object and propose an approach to classifier's accuracy performance, which incorporates distance into the decision making. Second, to avoid the difficulties arising from lack of representative training examples in learning the optimal threshold, we set in our attribute classifier two threshold values to distinguish a positive, a negative and an uncertainty class, instead of just one threshold value. We prove the theoretical correctness of this approach for an active agent who can observe the object multiple times.
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 Computer engineering. $3 569006
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0464
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Maryland, College Park. $b Electrical Engineering. $3 845418
773 0 $t Dissertation Abstracts International $g 78-11B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10254613 $z click for full text (PQDT)