SDSU Research Foundation

  • Context-aware Video Super-resolution and Summarization (56-7016)

    Req No.
    Dept/Proj Name
    Close Date
  • Overview

    This Statement of Work covers the need for the services of a college student to provide technical and/or analytical support in the fields of Computer Science, Applied Mathematics or Electrical Engineering for the Independent Laboratory In-house Research (ILIR) project titled “Context-aware video super-resolution and summarization.” The purpose of this project is to develop algorithms that can enhance both resolution and quality (remove noise, blur and turbulence) of highly dynamic videos while utilizing prior knowledge about content and context.


    • Collecting test data and criteria to analyze, score, and evaluate existing algorithms for turbulence mitigation and object detection in turbulent environments.
    • Adapt and implement one algorithm to detect small objects in turbulent environments. Demonstrate the efficacy of the algorithm by processing the data collected above.
    • Evaluate the applicability of turbulence mitigation algorithms to satisfactorily remove “constant direction” disturbance in videos caused by snow, rain etc.
    • Test and evaluate the performance of these algorithms in terms of detection performance and computational complexity during runtime.
    • Develop an algorithm to estimate the strength of optical turbulence from imagery.
    • Collect test data at test algorithm in 3.5.


    Minimum Qualifications:  


    Graduate Level 2:  Applied Mathematics/EE/CS major (working on MS/PhD).


    Additional Qualifications desired:


    Image and video processing experience.


    Skills: Python/Matlab, knowledgeable in image processing, restoration and computer vision.



    This is a student position and is limited to working 20 hours per week
    This position will remain open until filled
    San Diego State University Research Foundation is an EEO/AA/Disability/Vets Employer


    Sorry the Share function is not working properly at this moment. Please refresh the page and try again later.
    Share on your newsfeed