1 / 16

Imagers as sensors… and what makes this Computer Science

This proposal discusses the use of imagers as sensors to estimate environmental phenomena that cannot be measured by traditional sensors, with a specific focus on measuring moss photosynthesis and tracking pollinators. The application of computer science algorithms, such as non-linear regression, color image feature extraction, background subtraction, and template matching, is explored. The talk highlights the interdisciplinary nature of this research, combining computer vision, statistics, and software engineering.

sscanlon
Télécharger la présentation

Imagers as sensors… and what makes this Computer Science

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. Imagers as sensors…and what makes this Computer Science Josh Hyman UCLA Department of Computer Science

  2. Problem Statement • Some natural phenomena can be measured without harming the environment: • Temperature • Rainfall • Humidity • Others, require destructive instrumentation: • CO2 flux from single plant,meadow, or soil • Pollinators visiting a flowerin a field The site at James Reserve where mosscam is located

  3. Proposal • Construct a procedure that uses an imager to estimate phenomena that other sensors cannot measure

  4. Why this is Computer Science • Borrows from various fields of CS, specifically Computer Vision • Like all most sensing work, it is not only Computer Science; its also Statistics and Software Engineering • Specific algorithms borrowed from these fields will be discussed throughout this talk

  5. Application: Measuring Moss Photosynthesis Tortula princeps Ecologists want to determine the effect of short summer rain events on the moss’ ability to survive • There are no available sensors • Methods suggested by previously ecological studies have insufficient temporal resolution 16:45 16:50 Photosynthesis begins to occur 5 minutes after being hydrated

  6. a b c d Application: Measuring Moss Photosynthesis “Field” Experimental Setup: • Collect moss from JR • Hydrate moss and allow to dry over time • Collect samples: • illumination • spectral reflectance • high-quality images • low-quality images Samples acquired every 15 min for ~6 hrs (23 samples total)

  7. Application: Measuring Moss Photosynthesis Lab Experimental Setup: • Measured CO2 flux of the moss as it dries down over time • Use these measurements to train our models Moss in a temperature controlled chamber Infrared gas analyzer

  8. Application: Measuring Moss Photosynthesis Lab-measured features Putting it all together: • Account for the difference in cameras and lighting (right) • Use “registered” images to predict CO2 (below) “Field”-measure features

  9. Key Algorithms Non-linear Regression Color Image Feature Extraction

  10. Application: Tracking Pollinators Biologists want to perform studies about pollinator behavior over lengthy periods of time • There are no available sensors • Currently data is acquired by physically watching flowers and counting pollinators

  11. Application: Tracking Pollinators • Step 1: Automatically “segment” and “register” the images

  12. Application: Tracking Pollinators • Step 1: Automatically “segment” and “register” the images • Step 2: “Learn” what the background looks like Background Model

  13. Application: Tracking Pollinators • Step 1: Automatically “segment” and “register” the images • Step 2: “Learn” what the background looks like • Step 3: Subtract the background Background Model

  14. Application: Tracking Pollinators • Step 1: Automatically “segment” and “register” the images • Step 2: “Learn” what the background looks like • Step 3: Subtract the background • Step 4: Look for sequential frames containing the target …

  15. Key Algorithms Background Subtraction Template Matching

  16. Questions?

More Related