RESEARCH

Image & Vision

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 image Reconstruction

Admin    2021-04-08    👁️ 207

1. Introduction
- Super-Resolution is a process that reconstructs high resolution image from one or more low resolution images. This also
      includes image denoising, deblurring and up-scaling process.

2. Main algorithm and principle
- General Super-Resolution algorithm structure

1.      Compensate motion between low resolution images.

2.      Fuses aligned low resolution images to get high resolution image.

3.      Apply post-processing for deblurring or other artifacts.

  - Sequential Super-Resolution based on Kalman filter approach

1.      Recursive image acquisition modeling

2.      Consider only translational motion for faster processing

3.      Enable to process color video input

   - Super-Resolution for moving object

1.      Detection/tracking for moving object

2.      Image registration using SIFT/Optical flow.

3.      Data fusion based on ML estimation.

4.      Enhance the reconstruction result by Patch-based Super-Resolution.

3. Experiment Results
- Sequential Super-Resolution

   - Super-Resolution for moving object

 4. Demo