Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Faculty of Construction and Environment | en_US |
| dc.contributor.advisor | Shi, John (LSGI) | - |
| dc.contributor.advisor | Chen, Wu (LSGI) | - |
| dc.creator | Yang, Zi | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/8348 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Vehicle detection and speed measurement using video image sequences | en_US |
| dcterms.abstract | As an important part of ITS, vehicle detection has received considerable attention in recent years. The dissertation presents an approach for detecting vehicles and speed measurement from video image sequences. CCTV cameras are utilized as sensors for data acquisition. Vehicles detection is divided into two parts image preprocessing and object extraction. Image preprocessing aims to remove background interference by a region mask, and reduce unwanted noise through the Gaussian smooth filter. In the object extraction part, vehicles are detected using color and edge. Prominent vehicles are detected using selected RGB ranges and the Sobel edge detector. By finding horizontal and vertical range of a detected box, vehicle(s) can be finally detected from video image sequences. After finding possible vehicle candidates, vehicle speed is computed using pre-computed distance and fixed time interval. Corresponding coordinates are found in video image and Google Earth to establish a proportional relationship between image and reality, known as pre-computed distance. Computed vehicle speed is compared with speed display unit recorded by a mobile phone as evaluation. In the experiments, proposed methods are evaluated on two scenarios,sparse traffic condition and congested traffic condition. Target vehicles are green minibuses in both cases.Experimental results show vehicle(s) can be stably and efficiently detected from video image sequences. The proposed methods also work fairly to measure vehicle speed. | en_US |
| dcterms.extent | x, 93 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2015 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Vehicle detectors. | en_US |
| dcterms.LCSH | Image processing -- Digital techniques. | en_US |
| dcterms.LCSH | Automobiles -- Speed -- Measurement. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b28315972.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.99 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/8348