Computer Vision Research Group

Real Time Vehicle License Plate Detection and Tracking

The number of on-road motor vehicles has increased with the rapid growth of world's economy and with this augmentation the need for security and monitoring of vehicles has also increased. It is a necessity for officials to continuously examine the traffic to avoid congestion, over speeding and unlawful activities that involve any vehicle or to find and track a stolen vehicle. Video indexing is another modern application that can be efficiently done by vehicle's number plate recognition for road surveillance videos.

We propose an efficient real time Automatic License Plate Recognition (ALPR) framework, particularly designed to work on CCTV video footage obtained from cameras that are not dedicated for the use in ALPR. At present license plate detection, tracking and recognition are reasonably well tackled problems with many successful commercial solutions being available. However the existing ALPR algorithms are based on the assumption that the input video will be obtained via a dedicated high resolution, high speed camera and/or supported by a controlled capture environment, with appropriate camera height, focus, exposure/shutter-speed and lighting settings.

However typical video forensic applications may require searching for a vehicle having particular number plate on noisy CCTV video footage obtained via non dedicated, medium to low resolution cameras, working under poor illumination conditions. ALPR in such video content possess severe challenges in license plate localization. A special feature of the proposed approach is that it is intelligent enough to automatically adjust for varying camera distances and diverse lighting conditions, a requirement for a video forensic tool that may operate on videos obtained by a diverse set of unspecified, distributed CCTV cameras.

Though most of these solutions are plausibly fast and efficient, however, almost all of the existing real time systems either deal with only a single problem at a time; detection, tracking, recognition or they are not efficient enough to work well for low quality surveillance videos. The aim of our work is to address all three tasks for low quality videos in real time.

A novel approach has been developed for efficient localization of license plate in video sequence and slightly adapted existing techniques have been applied for tracking and recognition. The implemented system is intelligent enough to automatically adjust for varying camera distances and diverse lighting conditions.

The above figure shows three steps of license plate detection and tracking.

  1. Finding Connected Components.
  2. Filtering candidate regions for license plate based on geometry.
  3. Using classifier for final decision.

Sample run of algorithm on CCTV footage for License Plate Detetcion



© 2010 Department of Electrical Engineering, CIIT Lahore  |  Terms and Conditions