Internship | Image processing for Sensor Tracking
Scan&Paint 2D is a tool to visualize stationary sound fields using a single probe solution. The system is suitable for solving many engineering problems, from troubleshooting to acoustic benchmarking. It only takes a few minutes to complete and entire measurement campaign. Results of the scan are translated by the software into a color map, superimposed on a photograph of the measured object. The current software uses color-based image algorithms to follow the position of the probe during the measurements.
In this project a novel algorithm to extract the position of a moving sensor from a video should be designed and implemented using a combination of RGB and depth sensors. The main goal is to introduce an efficient tracking algorithm to find the probe position suitable for different light conditions. Computer simulations and experimental measurements should be carried out to validate the proposed algorithm and evaluate the limitations of the implemented approach. If the work and findings are of good quality, preparing a publication for an international congress or journal will be encouraged. In summary, the work should include a good description of image tracking techniques, computer simulations, test measurements and assessment of experimental results.
The candidate should:
- be proficient programming in MatLab
- be proficient in Signal processing and/or computer vision
- have prior knowledge in physical acoustics