Difference between revisions of "SRGS 2022"

From epsciwiki
Jump to navigation Jump to search
(Created page with " ## Computer Vision * Location of images: /work/hallc/shms/spring17_angle_snaps/")
 
Line 1: Line 1:
  
 +
== Possible Projects ==
 +
* [[Media:Mini_research_projects_v2.pdf]]
  
## Computer Vision
+
== AI Feature Recognition: Extract Spectrometer Angle from Image ==
* Location of images: /work/hallc/shms/spring17_angle_snaps/
+
 
 +
Students:
 +
* Anna Rosner
 +
* William Savage
 +
 
 +
=== Useful links/info: ===
 +
* [[Media:angle-cam-image-recognition.pdf]]
 +
* Location of images: '''/work/hallc/shms/spring17_angle_snaps/'''
 +
** Time image was acquired is embedded in the image file
 +
** The numbers in the snapshot filenames are the run numbers
 +
* The value of the encoders are stored in the MYA EPICS archive
 +
** PV names are:
 +
***''ecSHMS_Angle''
 +
***''ecHMS_Angle''
 +
 
 +
=== Initial thoughts from Brad ===
 +
    I had been imagining splitting the photos into two regions: one with
 +
    the digits, and a second with the vernier scale. Each region would be
 +
    evaluated/interpreted separately with some 'optimized' algorithms.
 +
   
 +
    'Real' errors/discrepancies would be best indicated by a scanning for a
 +
    mismatch between MYA and the analysis database record and/or the value
 +
    flagged in the logbook which has generally been vetted and updated by a
 +
    human. The simplest way to test 'bad' angles would be just to
 +
    (randomly) shift the truth angle by a small amount -- that would be
 +
    indistinguishable from an observed drift in the EPICS encoder system.
 +
   
 +
    I (or the students) can also look for angle shifts in the 'real' data,
 +
    but that will take some poking around. It should be indicated by a
 +
    sharp (small) jump in the MYA value as an offset is changed to bring
 +
    the EPICS value in agreement with the camera readback.
 +
   
 +
    One other dataset that I could obtain is a movie of the angle changing
 +
    over a range (the movie is just a compilation of frame grabs). The
 +
    individual frames could be pulled out of the mp4 and evaluated
 +
    individually over a continuously varying range of angles.

Revision as of 00:56, 27 June 2022

Possible Projects

AI Feature Recognition: Extract Spectrometer Angle from Image

Students:

  • Anna Rosner
  • William Savage

Useful links/info:

  • Media:angle-cam-image-recognition.pdf
  • Location of images: /work/hallc/shms/spring17_angle_snaps/
    • Time image was acquired is embedded in the image file
    • The numbers in the snapshot filenames are the run numbers
  • The value of the encoders are stored in the MYA EPICS archive
    • PV names are:
      • ecSHMS_Angle
      • ecHMS_Angle

Initial thoughts from Brad

   I had been imagining splitting the photos into two regions: one with
   the digits, and a second with the vernier scale. Each region would be
   evaluated/interpreted separately with some 'optimized' algorithms.
   
   'Real' errors/discrepancies would be best indicated by a scanning for a
   mismatch between MYA and the analysis database record and/or the value
   flagged in the logbook which has generally been vetted and updated by a
   human. The simplest way to test 'bad' angles would be just to
   (randomly) shift the truth angle by a small amount -- that would be
   indistinguishable from an observed drift in the EPICS encoder system.
   
   I (or the students) can also look for angle shifts in the 'real' data,
   but that will take some poking around. It should be indicated by a
   sharp (small) jump in the MYA value as an offset is changed to bring
   the EPICS value in agreement with the camera readback.
   
   One other dataset that I could obtain is a movie of the angle changing
   over a range (the movie is just a compilation of frame grabs). The
   individual frames could be pulled out of the mp4 and evaluated
   individually over a continuously varying range of angles.