|Title:||Vehicle re-identification by fusion of multiple features|
|Subject:||Hong Kong Polytechnic University -- Dissertations|
Automobiles -- Electronic equipment
|Department:||Faculty of Engineering|
|Pages:||xiv, 99 pages : color illustrations|
|Abstract:||Vehicle re-identification (VRI) is concerned with matching vehicles between two points on a roadway. It plays an important role in smart transportation systems with various services such as travel time estimation, enforcement in free-flow ETC (Electronic Toll Collection) systems, detection of road accident and parking management, etc. Although there have been extensive studies on effective approaches to meet the increasing needs in real-world environment over the past decades, it remains a challenging task to develop robust classification algorithms which can handle various conditions such as noise, cluttered background, appearance variations due to illuminations, occlusions, viewpoints and complex object motion. Such algorithms are also expected to be adaptive and fast to achieve high performance. A vision based approach which adopts a new robust and adaptive detector based on the fusion of multiple features with learning capacity is regarded as effective to tackle the problems. This thesis presents a new vision based approach to vehicle re-identification (VRI) for smart transportation systems by fusion of multiple features. Unlike the conventional VRI systems which adopted loop sensors to capture inductive features for classification, we developed a hierarchical method for VRI by coarse-to-fine image matching. More specifically, VRI is performed at fine level by image matching using distinctive and anonymous features which are extracted from the large number of interesting points detected from the vehicle and its license plate images at coarse level. To achieve robustness, the thresholding of matching criteria is based on the dynamic analysis of the time series of vehicle images rather than predefined. In addition, the fusion of multiple features is conducted via a weighted probability scheme. To demonstrate the feasibility of the proposed new approach, a series of field testing were conducted, where 301 vehicles were considered for data calibration and 1699 vehicles were used for validation tests. The accuracy of matching rate reaches 73.51%. 85.52% and greater than 90% respectively by using density features, fusion of selected distinctive features and fusion of multi-modal features.|
Files in This Item:
|991022131138403411.pdf||For All Users (off-campus access for PolyU Staff & Students only)||2.96 MB||Adobe PDF||View/Open|
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: