1 / 28

Adaptive Tracking for Activity Monitoring Using a Forest of Sensors

This research explores the use of autonomous vision modules (AVMs) placed in a forest-like setting to monitor and classify activities. The goal is to create a system that can bootstrap itself by accurately tracking moving objects in the scene.

nbeth
Download Presentation

Adaptive Tracking for Activity Monitoring Using a Forest of Sensors

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. A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology welg@ai.mit.edu

  2. A Forest of Sensors • Given autonomous vision modules (AVMs): low power, low cost, can compute wide range of visual routines • Create a forest of disposable AVMs: • attached to trees, buildings, vehicles • dropped by air • Question: Can the forest bootstrap itself to monitor sites for activities?

  3. Multi-camera version of a forest

  4. Capabilities and components • Self calibration • building rough site models • detecting visibility • primitive detection • moving object modeling • activity detection • activity classification

  5. Working hypothesis • Can achieve all of these capabilities simply by accurately tracking moving objects in the scene.

  6. Video Frames Adaptive Background Model Pixel Consistent with Background Model? X,Y,Size,Dx,Dy X,Y,Size,Dx,Dy X,Y,Size,Dx,Dy Local Tracking Histories

  7. Pattern tracks

  8. Detect Regularities & Anomalies?

  9. A robust, real-time tracker • Model each pixel as an independent process • Model previous n samples with weighted mixture of Gaussians, using exponentially decaying time window • Background defined as set of dominant models that account for T percent of data • Update weights and parameters • Pixel > 2 sigma from background is moving • Select significant blobs as objects

  10. Adaptive tracking

  11. Dynamic calibration • Track objects in multiple cameras • use correspondences to find a homography, assuming planar motion • modify homography by fitting image features • use non-planar features to solve for epipolar geometry, and refine

  12. Dynamic calibration

  13. Activity detection & calibration • Need to find common patterns in track data

  14. Detect Regularities & Anomalies?

  15. Example track patterns • Running continuously for 1.5 years • during snow, wind, rain, … • has processed 500M images • one can observe patterns over space and over time • need a system to detect automatically

  16. Classifying objects • Simple classifiers based on feature selection Example -- people vs. cars using aspect ratio and size

  17. A B match C QUERY Template DATABASE IMAGES IN THE QUERY-CLASS Flexible template querying

  18. Example • Detection

  19. Classifying objects • Using flexible templates to detect vehicles

  20. Classifying activities • Quantize state space of continuous observations by fitting Gaussians • map sequence of observables to sequence of labels • compute co-occurrence of labels over sequences -- defines joint probability • cluster by E/M methods to find underlying probability distributions

  21. Automatic activity classification

  22. Long-term Activity Patterns

  23. Multi-camera version

  24. Mapping patterns to maps

  25. Multi-camera coordination

  26. Finding unusual events

  27. Finding similar events

  28. Future plans • continued integration of pieces • site models from dynamic tracking • activity classification from multiple views • variations on classification methods • vocabulary of activities and interactions • interactions of activity tracks • fine scale actions

More Related