Development of a street vehicle obstruction tracker in a moving vision environment
Static CCTV cameras are widely used for road surveillance in ITS such as detecting road obstruction or illegal parking violators. However static camera systems have limitations such as limited or fixed view and prone to occlusion. Thus, this research aims to explore the application of dashboard came...
Saved in:
| Main Author: | |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
2020
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etd_masteral/5972 https://animorepository.dlsu.edu.ph/context/etd_masteral/article/12921/viewcontent/SERRANO_FAENICOLE_11670959_1.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | Static CCTV cameras are widely used for road surveillance in ITS such as detecting road obstruction or illegal parking violators. However static camera systems have limitations such as limited or fixed view and prone to occlusion. Thus, this research aims to explore the application of dashboard cameras in detecting potential road violators. This study mainly tackles detecting vehicles in a dynamic background, tracking vehicles despite varying angle views (front, side and, back views) and extracting vehicular information (vehicle type or license plate presence). Several CNN models were compared in order to identify the architecture best suited for the set-up. Aside from extracting the vehicle type and identification tag, feasibility of plate detection was also explored against dashcam’s image quality. |
|---|