Normal view MARC view ISBD view

Object motion tracking on a cluttered background: a further enhancement of the condensation algorithm / John Paul D. Ang and Johneric Anselmo B. Razon. 6

By: John Paul D. Ang and Johneric Anselmo B. Razon. 4 0 16, [, ] | [, ] |

Contributor(s): 5 6 [] |

Language: Unknown language code Summary language: Unknown language code Original language: Unknown language code Series: ; March 2005.46Edition: Description: 28 cm. 30 ppContent type: text Media type: unmediated Carrier type: volumeISBN: ISSN: 2Other title: 6 []Uniform titles: | | Related works: 1 40 6 []Subject(s): -- 2 -- 0 -- -- | -- 2 -- 0 -- 6 -- | 2 0 -- | -- -- 20 -- | | -- -- -- -- 20 -- | -- -- -- 20 -- --Genre/Form: -- 2 -- Additional physical formats: DDC classification: | LOC classification: | | 2Other classification:

Contents:

Action note: In: Summary: ABSTRACT: Almost all people rely on vision to know what is happening in the environment, and with this, it becomes more logical to apply vision as a medium for inputting commands on a computer. Research on computer vision has greatly increase since the last decade due to the need for a more effective medium for interfacing with the a computer. For a computer to see, it must process and analyze images coming from a camera or any input device. Computer vision is most useful in translating gestures, movements, expressions and actions into input commands. Most of the existing motion tracking systems uses the Kalman filter to process moving objects. One downside of the Kalman filter is that it is very slow, and it cannot process objects that move fast and has difficulty isolating random noises from the actual object in motion. Motion trackers that use the condensation algorithm shows satisfactory results, but a lot of improvements are still possible because of the visible problems that arise from its implementation. The system under study, processes images in real-time through a camera and from a saved file in multiple viode format. Moving objects are detected and shown using squares to track its movement. Tracking multiple moving objects is one of the capabilities of the system. It can still track objects in a highly cluttered background where there is a high density of noise present. The aim of this study is to enhance the performance and accuracy of the previous system by improving the algorithm behind the codes. The proponents will try enhance, if not, develop a new algorithm that will comply with what they are trying to pursue. Other editions:

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 1 )
Title notes
Comments ( 0 )

Item type	Current location	Home library	Collection	Call number	Status	Date due	Barcode	Item holds
Book	PLM	PLM Archives	Filipiniana-Thesis	QA76.9.A43 An4 2005 (Browse shelf)	Available		FT3952

Total holds: 0

Undergraduate Thesis: (Bachelor of Science in Computer Science) - Pamantasan ng Lungsod ng Maynila, 2005. 56

ABSTRACT: Almost all people rely on vision to know what is happening in the environment, and with this, it becomes more logical to apply vision as a medium for inputting commands on a computer. Research on computer vision has greatly increase since the last decade due to the need for a more effective medium for interfacing with the a computer. For a computer to see, it must process and analyze images coming from a camera or any input device. Computer vision is most useful in translating gestures, movements, expressions and actions into input commands. Most of the existing motion tracking systems uses the Kalman filter to process moving objects. One downside of the Kalman filter is that it is very slow, and it cannot process objects that move fast and has difficulty isolating random noises from the actual object in motion. Motion trackers that use the condensation algorithm shows satisfactory results, but a lot of improvements are still possible because of the visible problems that arise from its implementation. The system under study, processes images in real-time through a camera and from a saved file in multiple viode format. Moving objects are detected and shown using squares to track its movement. Tracking multiple moving objects is one of the capabilities of the system. It can still track objects in a highly cluttered background where there is a high density of noise present. The aim of this study is to enhance the performance and accuracy of the previous system by improving the algorithm behind the codes. The proponents will try enhance, if not, develop a new algorithm that will comply with what they are trying to pursue.

There are no comments for this item.

to post a comment.