Investigates Image data fusion techniques that combine image and track data from multiple sensors to achieve improved accuracies and more specific inferences than could be achieved by the use of a single sensor alone. Our aim is to explore the state-of-the-art image processing algorithms for achieving effective data fusion as in:
Super resolution & License Plate Detection
Minjae Kim, Jaeyong Ju
1. Introduction
One promising approach is to use signal processing techniques to obtain an HR image (or sequence) from observed multiple low-resolution (LR) images. Recently, such a resolution enhancement approach has been one of the most active research areas, and it is called super resolution (SR). The SR image reconstruction is proved to be useful in many practical cases where multiple frames of the same scene can be obtained, including medical imaging, satellite imaging, and video applications.
2. Main Algorithm and Principle
- The proposed approach
i. The proposed framework consists of a learning based LPD using the Local Structure Pattern feature and dynamic SR with sequential fusion for semi-real time processing
- Appearance based License place detection
i. Robust LP detection using Local Structure Pattern(LSP) feature and Adaboost classifier for low resolution images
- Dynamic SR using Kalman filter
3. Results
4. Demo
