1 / 18

Recognition, Tracking, and Data Acquisition for Microscopic Worms

Recognition, Tracking, and Data Acquisition for Microscopic Worms. ECPE 491: Senior Design Professor Mani Mina. Client : Dr. Santosh Pandey , Microfluidics Lab Graduate Supervisor: Roy Lycke Ryan Alley, Team Leader Colin Ray, Communicator Laith Abbas, Webmaster Shan Zhong

gur
Download Presentation

Recognition, Tracking, and Data Acquisition for Microscopic Worms

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Recognition, Tracking, and Data Acquisition for Microscopic Worms ECPE 491: Senior Design Professor Mani Mina

  2. Client: Dr. SantoshPandey, Microfluidics Lab • Graduate Supervisor: Roy Lycke • Ryan Alley, Team Leader • Colin Ray, Communicator • Laith Abbas, Webmaster • Shan Zhong • ShushengXu Group 03: Worm Tracking

  3. Background • C. elegans • What are C. elegans? • Why are C. elegansuseful? • How are C. elegansstudied? • Behavior • Qualitative vs. quantitative data • How to gather quantitative data? Problem Statement Group 03: Worm Tracking

  4. Group 03: Worm Tracking • Academic research • MBFBioscience—WormLab • Similarities between existing solutions • Distinguishing characteristics Market Survey

  5. Group 03: Worm Tracking • The software shall support the following video compression codecs: • Microsoft Video 1 • Intel Indeo • The software shall support input video frame-rates between 1 and 30 frames-per-second. • The software shall prompt the user to enter video parameters. • The interface shall support singular and batch selection and processing of video files. Functional Requirements

  6. Group 03: Worm Tracking • Upon completion of analysis, the software shall provide a confidence level in its worm assessments, based upon video quality (resolution, noise, etc..). • The software shall identify C. eleganswith a success rate of at least the aforementioned confidence level, as confirmed by human judgment of the video*. In addition, it shall not give a false-positive for any non-worm artifact. Functional Requirements *A bed of test-bench videos shall be chosen for this assessment by the client, Selected to test a variety of situations

  7. Group 03: Worm Tracking • Analysis shall provide, at a minimum, the X-Y coordinates of worm centroid, head, and tail over the duration of a given video, as well as the derived velocity and acceleration from the aforementioned worm data. • Additionally, the analysis shall also fit a spline to each worm’s curvature for each frame and present this spline graphically. Functional Requirements

  8. Group 03: Worm Tracking • The software shall be well-documented • The software shall run on the target computers without additional hardware • The software shall be easy-to-use by a lab technician • The software shall process video at no less than 10 MB of video data per second • The software and any support files shall be wrapped in a single installer Non-Functional Requirements

  9. Group 03: Worm Tracking • Input videos must be a minimum of 20 frames in length. • No more than five worms per unit volume (1 cm x 1 cm x 100 microns). • Potential Risks • In the case that our software fails, data will have to extracted from the video manually. Non-Functional Requirements

  10. Group 03: Worm Tracking • Typical Usecase: • Lab technician records videos, noting magnification and scale • Lab technician starts program, is prompted for file(s) and relevant information (magnification and scale) • Video is analyzed by software and outputs data as file, informs user System Design

  11. Group 03: Worm Tracking • Details Detailed Design

  12. Group 03: Worm Tracking • Currently reads and processes pre-recorded video • Performs background subtraction • Finds centroid and outputs coordinates to CSV • Graphically fits spline • Limitations: • Number of worms • No collision-detection TODO: add screenshots~! Prototype

  13. Group 03: Worm Tracking • Ryan Alley • Interface Description, Methodology • Colin Ray • Video Input Layer, Background Subtractor • Laith Abbas • Webpage, Documentation • Shan Zhong • Centroid Finder, Spline Fitting • ShushengXu • Centroid Finder, Spline Fitting Individual Contributions

  14. Group 03: Worm Tracking • Play a video!!!! • Metrics (human comparison, quality of videos, etc…) Test Plan

  15. Group 03: Worm Tracking • Hardware purchase not considered. • Open-Source platform provides free license. • Labor… free.  Cost Estimate

  16. Group 03: Worm Tracking • Prototype version 1.0 implemented • Lessons learned: • Need to further explore potential algorithms • Frame-by-frame processing • Model-based approach • Image analysis utilities Project Status

  17. Group 03: Worm Tracking • Gantt chart. Project Milestones

  18. Group 03: Worm Tracking References

More Related