國立虎尾科技大學 |

Bayesian Multi-Modal Fusion of Unlabeled Data for Aerial Tracking of Dislocated Ground Targets.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Bayesian Multi-Modal Fusion of Unlabeled Data for Aerial Tracking of Dislocated Ground Targets./
作者:	Kanlapuli Rajasekaran, Ramya.
面頁冊數:	1 online resource (126 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
Contained By:	Dissertations Abstracts International84-11B.
標題:	Robotics. -
電子資源:	click for full text (PQDT)
ISBN:	9798379527976

Bayesian Multi-Modal Fusion of Unlabeled Data for Aerial Tracking of Dislocated Ground Targets.
Kanlapuli Rajasekaran, Ramya.

Bayesian Multi-Modal Fusion of Unlabeled Data for Aerial Tracking of Dislocated Ground Targets. - 1 online resource (126 pages)

Source: Dissertations Abstracts International, Volume: 84-11, Section: B.

Thesis (Ph.D.)--University of Colorado at Boulder, 2023.

Includes bibliographical references

Small Uncrewed Aircraft Systems (sUAS) are valuable for various military, commercial, and Search and Rescue (SAR) operations that involve monitoring and tracking in inaccessible, hazardous and communication-limited environments. Objects that are tracked typically have radio frequency (RF) emitters that are small, portable, can remain active for extended periods, and can be detected using RF sensors. Larger objects, such as vehicles or people, carry these emitters, and these objects can be detected by a complementary sensor like a camera. Incorporating complementary sensors mitigates challenges associated with using standalone sensors for tracking. Due to the size and portability of RF emitters, they can be exchanged between different carriers and change appearance in the visual sensor space. Such targets are referred to as dislocated targets, and they may make abrupt maneuvers and experience quick changes in speeds and directions. Tracking dislocated ground targets presents a challenging problem that is further compounded by the need to enable fully autonomous sUAS operation for real-time tracking, in the absence of reliable communication. This research designs, develops and assesses a multi-modal Bayesian Fusion estimation architecture to solve the problem of continuous, real-time, on-board autonomous tracking of dislocated ground targets using sUAS. This is achieved by developing a particle-based data association and estimation algorithm that introduces a Target Association Variable to perform informed data association. This variable is simultaneously estimated with target position and velocity. This estimation algorithm is one component of a broader fusion architecture that combines RF sensor measurements with the estimator to create a tracking solution for ground targets from sUAS. Assessment of the fusion data association estimation algorithm is performed using detailed simulations. Successful field testing also validates the utility of the architecture for on-board, real-time use on a sUAS.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379527976Subjects--Topical Terms:

561941
Robotics.
Subjects--Index Terms:

Autonomous robotsIndex Terms--Genre/Form:

554714
Electronic books.

Bayesian Multi-Modal Fusion of Unlabeled Data for Aerial Tracking of Dislocated Ground Targets.
LDR:03472ntm a22003977 4500 001 1142931
005 20240513061027.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379527976
035 $a (MiAaPQ)AAI30421488
035 $a AAI30421488
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kanlapuli Rajasekaran, Ramya. $3 1467461
245 1 0 $a Bayesian Multi-Modal Fusion of Unlabeled Data for Aerial Tracking of Dislocated Ground Targets.
264 0 $c 2023
300 $a 1 online resource (126 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: Dissertations Abstracts International, Volume: 84-11, Section: B.
500 $a Advisor: Frew, Eric;Ahmed, Nisar.
502 $a Thesis (Ph.D.)--University of Colorado at Boulder, 2023.
504 $a Includes bibliographical references
520 $a Small Uncrewed Aircraft Systems (sUAS) are valuable for various military, commercial, and Search and Rescue (SAR) operations that involve monitoring and tracking in inaccessible, hazardous and communication-limited environments. Objects that are tracked typically have radio frequency (RF) emitters that are small, portable, can remain active for extended periods, and can be detected using RF sensors. Larger objects, such as vehicles or people, carry these emitters, and these objects can be detected by a complementary sensor like a camera. Incorporating complementary sensors mitigates challenges associated with using standalone sensors for tracking. Due to the size and portability of RF emitters, they can be exchanged between different carriers and change appearance in the visual sensor space. Such targets are referred to as dislocated targets, and they may make abrupt maneuvers and experience quick changes in speeds and directions. Tracking dislocated ground targets presents a challenging problem that is further compounded by the need to enable fully autonomous sUAS operation for real-time tracking, in the absence of reliable communication. This research designs, develops and assesses a multi-modal Bayesian Fusion estimation architecture to solve the problem of continuous, real-time, on-board autonomous tracking of dislocated ground targets using sUAS. This is achieved by developing a particle-based data association and estimation algorithm that introduces a Target Association Variable to perform informed data association. This variable is simultaneously estimated with target position and velocity. This estimation algorithm is one component of a broader fusion architecture that combines RF sensor measurements with the estimator to create a tracking solution for ground targets from sUAS. Assessment of the fusion data association estimation algorithm is performed using detailed simulations. Successful field testing also validates the utility of the architecture for on-board, real-time use on a sUAS.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Robotics. $3 561941
650 4 $a Aerospace engineering. $3 686400
653 $a Autonomous robots
653 $a Dislocated targets
653 $a Multi modal fusion
653 $a Sensor fusion
653 $a Small Uncrewed Aircraft Systems
653 $a Target tracking
655 7 $a Electronic books. $2 local $3 554714
690 $a 0538
690 $a 0771
710 2 $a University of Colorado at Boulder. $b Aerospace Engineering. $3 1179005
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 84-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30421488 $z click for full text (PQDT)