Visual Moving Objects Tracking Using Shape Detectors and Object Models

機構典藏 > College of Engineering > Graduate Institute & Department of Mechanical and Electro-Mechanical Engineering > Proceeding > Item 987654321/115036

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/115036

Title:	Visual Moving Objects Tracking Using Shape Detectors and Object Models
Authors:	Wang, Yin-Tien;Shen, Chin-An
Keywords:	Visual simultaneous;localization;mapping (vSLAM);Object model;Pe-destrian detectors, Visual moving object tracking
Date:	2017-08-21
Issue Date:	2018-09-27 12:11:38 (UTC+8)
Publisher:	Springer
Abstract:	This paper presents an algorithm of robot visual moving-object tracking (MOT) based on the probabilistic object model with a pe-destrian detector. Three major research topics investigated in the study include the combination of moving feature detection and pe-destrian detection, the improvement of probabilistic object model, and the tuning mechanism of object model training. The developed MOT was further integrated with the visual simultaneous localiza-tion and mapping (vSLAM) to form a simultaneous localization, mapping, and moving object tracking system. The extended Kalman filter (EKF) was used to estimate the system states and the speeded-up robust features (SURFs) were employed to represent the visual environment map. Experiments were carried out in this research to validate the performance of the developed systems.
Relation:	Mobile Web and Intelligent Information Systems - 14th MobiWIS 2017, Prague, Proceedings _ Muhammad Younas _ Springer
Appears in Collections:	[Graduate Institute & Department of Mechanical and Electro-Mechanical Engineering] Proceeding

Files in This Item:

File	Size	Format
index.html	0Kb	HTML	146	View/Open