Gihan Chanaka Jayatilaka : Projects


Major Projects

  1. Vision Transformers for implicit groundtruth tasks
  2. Computer vision for combatting COVID-19 spread
  3. Algorithms for low light image enhancement and interpretation
  4. Deeplight : Screen to camera communication using computer vision
  5. Non invasive infant sleep apnea detection
  6. Foreground estimation in dynamic background conditions
  7. Hyper Spectral Imagergy for remote sensing
  8. Algorithm improvement for finite element based structural analysis technique
  9. Brain Computer Interfacing : Visual cortex EEG Analysis
  10. Performance improvement of signal level genome sequencing algorithms
  11. Galvans - autonomous robots
  12. Theseus - autonomous robot
  13. Other mini projects
No. Project Links
1.

Vision Transformers for implicit groundtruth tasks

Content to be added after seeking permission from Futurewei.
2.

Computer vision for combatting COVID-19 spread


[PDF Slides]

3.

Dark arts

Dark arts: exploration of the techniques and theory for processing and interpretation of low light images.

4.

5.

Deeplight : Screen to camera communication using computer vision

Trying to achieve robust and imperceptible visible light communication from computer screen to the camera by a pipeline consisting of modified deep learning based computer vision algorithms.


6.

Non invasive infant sleep apnea detection

A portable device that can detect infant sleep apnea by video processing. Two video processing algotihms were developed.

7.

Foreground estimation in dynamic background conditions

Dynamic background cancellation is a fundamental problem in video processing. Eventhough estimating the foreground is trivial in static background conditions, estimating the foreground can be tricky when the background is dynamic as well. In this project we try differrent approaches to detect the background and foreground in a video. We start with classical approaches and try to evaluate their pros and cons. Finally, we propose the most suitable combination of video processing operations to get the most accurate results.


Algorithms used

  • PBAS Pixel based adaptive segmentation
  • GMM Gaussian mixture model
  • EM Expectatation maximization algorithm
  • AGMM Adaptive gaussian mixture model
  • FCMM Free Cylindrical mixture model
  • AFCMM Adaptive free cylinder mixture model
  • HVS Hierarchial video segmentation
  • RPCA Robust Principle Component Analysis
  • Morphological filtering
  • SCC Strongly connected component analysis
8.

Hyper Spectral Imagergy for remote sensing

  • Contributing to a researh group developing a hybrid (supervised-unsupervised) algorithm for HSI remote sensing pixel based classification based on pixel spectrums for Pavia University dataset. (Algorithm implementation, testing, benchmarking, comparision)
  • Working on developing gneralized algorithms for HSI remote sensing pixel classification for multiple datasets incorporating spectral and spatial data. (Algorithm development, implementation, testing, benchmarking, etc:)

Algorithms

  • Spectral clustering
  • CNN
  • DNN
  • Random forests
  • LDA

9.

Algorithm improvement for finite element based structural analysis technique

Attempting to improve the time and space efficiency of a new structural analysis algorithm based on finite element technique.

10.

Brain Computer Interfacing : Visual cortex EEG Analysis

Mapping the EEG signals from Visual Cortex to what a person is seeing.

11.

Performance improvement of signal level genome sequencing algorithms

Accelerating a part of Genome sequencing algorithm for high performance servers and low powered embedded devices.

12.

Galvans - autonomous robots

Two robots (one stationary and one moving). Moving robot had capabilities to follow a line maze, identify coloured boxes and transmit the colour to the stationary bot that could shoot a ball to the colored target. The mobile bot could follow a wall as well.

13.

Theseus - autonomous robot

A robot that can find it’s way through a wall maze, pick up a coloured payload and deliver it along a path marked by the particular coloured arrow.

Mini Projects

No. Project Links
1. Image Segmentation using random walks
2. Musical instrument spectrum analysis to find harmonics
3. Neural Network based inverted pendulum control system
4. CPU implementation in Verilog HDL
5. ALU implementation in Verilog HDL
6. Basic image manipulator in ARM Assembly
7. Multi threaded fractal visualizer in JAVA
8. Multi threaded socket server in JAVA
9. Desktop app for moodle notifications in JAVA
10. Speaker identification program with basic signal processing
11. Optical music instrument