cs 4495 computer vision activity recognition · 2014-11-30 · cs7616 pattern recognition cs 4495...
TRANSCRIPT
![Page 1: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/1.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Aaron BobickSchool of Interactive Computing
CS 4495 Computer VisionActivity Recognition
![Page 2: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/2.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Administrivia
• PS6 – due tonight!
• PS7…
![Page 3: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/3.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
The final saga continues
• As I mentioned, this year is the first time I’m using the Finals period to give the exam. Even though it will take less than 3 hours it frees up a class slot.
• But that means it’s a “real” final…
• Which makes next week a “real” dead week for this class…
• Which means the really cool PS7 (motion history images)…
• … is *optional*. We will still drop the lowest PS. But only one.
![Page 4: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/4.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Video• A video is a sequence of frames captured over time• Now our image data is a function of space
(x, y) and time (t)
![Page 5: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/5.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Video as an “Image Stack”
• Can look at video data as a spatio-temporal volume• If camera is stationary, each line through time corresponds to a single
ray in space
t0
255time
Alyosha Efros, CMU
![Page 6: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/6.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Aside: Epipolar Plane (“EPI”) images
![Page 7: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/7.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Aside: Epipolar Plane (“EPI”) images
![Page 8: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/8.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
EPI images and activity
![Page 9: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/9.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
EPI images and activity
![Page 10: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/10.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Processing video: object detection
• If the goal of “activity recognition” is to recognize the activity of the objects…
• … you (may) have to find the objects….
![Page 11: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/11.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Slide credit: Birgi Tamersoy
Background subtraction
![Page 12: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/12.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Background subtraction
• Simple techniques can do ok with static camera• …But hard to do perfectly
• Widely used:• Traffic monitoring (counting vehicles, detecting & tracking vehicles,
pedestrians),• Human action recognition (run, walk, jump, squat),• Human-computer interaction• Object tracking
![Page 13: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/13.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Simple approach: background subtraction
Slide credit: Birgi Tamersoy
![Page 14: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/14.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Frame differencing
Slide credit: Birgi Tamersoy
![Page 15: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/15.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Frame differencing
Slide credit: Birgi Tamersoy
![Page 16: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/16.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Mean filtering
Slide credit: Birgi Tamersoy
![Page 17: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/17.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Frame differences vs. background subtraction
• Toyama et al. 1999
![Page 18: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/18.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Median Filtering
Slide credit: Birgi Tamersoy
![Page 19: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/19.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Average/Median Image
Alyosha Efros, CMU
![Page 20: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/20.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Background Subtraction
-
=
Alyosha Efros, CMU
![Page 21: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/21.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Pros and cons• Advantages:• Extremely easy to implement and use!• All pretty fast.• Corresponding background models need not be constant, they
change over time.
• Disadvantages:• Accuracy of frame differencing depends on object speed and
frame rate• Median background model: relatively high memory
requirements.• Setting global threshold Th…
When will this basic approach fail?Slide credit: Birgi Tamersoy
![Page 22: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/22.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Background mixture models
• Adaptive Background Mixture Models for Real-Time Tracking, Chris Stauer & W.E.L. Grimson
Idea: model each background pixel with a mixture of Gaussians; update its parameters over time.
![Page 23: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/23.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Background subtraction with depth
How can we select foreground pixels based on depth information?
![Page 24: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/24.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Human activity in videoNo universal terminology, but approximately:
• “Event”: a single instant in time detection.
• “Actions” or “Movements” : atomic motion patterns --often gesture-like, single clear-cut trajectory, single nameable behavior (e.g., sit, wave arms)
• “Activity”: series or composition of actions (e.g., interactions between people)
Adapted from Venu Govindaraju and A.Bobick
![Page 25: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/25.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Surveillance
http://users.isr.ist.utl.pt/~etienne/mypubs/Auvinetal06PETS.pdf
![Page 26: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/26.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Human activity in video: basic approaches• Model-based action recognition:
• Use human body tracking and pose estimation techniques, relate to action descriptions (or learn)
• Major challenge: accurate tracks in spite of occlusion, ambiguity, low resolution
• Model-based activity recognition:• Given some lower level detection of actions (or events) recognize the activity by
comparing to some structural representation of the activity• Needs to handle uncertainty.
• Activity as motion, space-time appearance patterns• Describe overall patterns, but no explicit body tracking• Typically learn a classifier
• Recently: “Activity-recognition” from static image• Imagine a picture of a person holding a flute.
What are they doing?
![Page 27: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/27.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
What we’re not going to cover?
![Page 28: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/28.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Motion and perceptual organization
• Even “impoverished” motion data can evoke a strong percept
![Page 29: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/29.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Motion and perceptual organization
• Even “impoverished” motion data can evoke a strong percept
![Page 30: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/30.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Example• Even “impoverished” motion data can evoke a strong percept
Video from Davis & Bobick
![Page 31: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/31.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Motion energy images• Spatial accumulation of motion.• Collapse over specific time window.• Motion measurement method not critical (e.g.
motion differencing). Time
![Page 32: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/32.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Motion history images• Motion history images are a
different function of temporal volume.
• Pixel operator is replacement decay:
if moving Iτ (x,y,t) = τotherwiseIτ(x,y,t) = max(Iτ(x,y,t-1)-1 ,0)
• Trivial to construct Iτ−k(x,y,t) from Iτ(x,y,t) so can process multiple time window lengths without more search.
• MEI is thresholded MHI
Movedt-1
Movedt-15
![Page 33: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/33.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Temporal-templates• MEI+ MHI = Temporal template
motion history image
motion energyimage
![Page 34: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/34.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Aerobics examples
![Page 35: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/35.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Davis & Bobick 1999: The Representation and Recognition of Action Using Temporal Templates
Motion Energy Images
![Page 36: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/36.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
How to recognize these images?
• These are gray scale blob like images.
• 100 years of computer vision for recognizing gray blobs (for small values of a hundred).
• Old style computer vision: 1. compute some summarization statistics of the pattern2. construct generative model3. recognize based upon those statistics.
![Page 37: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/37.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Image moments
Moments summarize a shape given image I(x,y)
Central moments are translation invariant:
( , )i jij
x yyM x y I x= ∑∑
) ((( ) , )p qpq
x yx x yy I x yµ = −−∑∑
10 01
00 00
M Mx yM M
= =
![Page 38: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/38.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Hu moments
• Set of 7 moments• Apply to Motion History Image for global space-time “shape”
descriptor• Translation and rotation and scale invariant
],,,,,,[ 7654321 hhhhhhh
![Page 39: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/39.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
=1h
=2h=3h
=4h=5h
=6h
Hu moments
![Page 40: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/40.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
=7h
![Page 41: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/41.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Build a classifier• Generative or Discriminative?
• Generative – builds model of each class; compare all• Discriminative – builds model of the boundary between classes
• How would you build decent generative models of each class of action?• Use a Gaussian in Hu-moment feature space• Compare likelihoods p(data | model of action i)• If have priors, use them by Bayes rule
• Otherwise just use likelihood.
• Or use NN? (Problem Set!)
(model | data) p(data | model ) p(model )i i ip ∝
![Page 42: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/42.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Recognizing temporal templates
• Collect statistics on distribution of the Hu moments for each movement over variety people.
• At run time, construct MEIs and MHIs backwards in time.• Recognizing movements as soon as they complete.
• Linear time scaling.• Compute range of 𝝉𝝉 using the min and max of training data.
• Simple recursive formulation so very fast.• Filter implementation obvious, so biologically “relevant”.• Best reference is PAMI 2001, Bobick and Davis
![Page 43: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/43.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Virtual PAT (Personal Aerobics Trainer)
• Uses MHI recognition• Portable IR background subtraction system (CAPTECH ‘98)
![Page 44: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/44.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
The KidsRoom
A narrative, interactive children’s playspace.Ported to the Millenium Dome, London, 2001Summary and critique in Presence, August 1999.
![Page 45: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/45.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Recognizing Movement in the KidsRoom
• First teach the kids, then observe.
• Temporal templates “plus” (but in paper).
• Monsters always do something, but only speak it when sure.
![Page 46: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/46.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
So far…
• Background subtraction: • Essential low-level processing tool to segment moving
objects from static camera’s video
• Action recognition: • Increasing attention to actions as motion and appearance
patterns• For instrumented/constrained environments, relatively
simple techniques allow effective gesture or action recognition
![Page 47: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/47.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
A little philosophy…
![Page 48: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/48.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
What is the goal of a representation of activity/behaviors?
• Recognition implies representation
• Representations can talk about what events *ARE*:• Definitional – but sometimes not “real” because primitives not grounded• Permits specification of reasoning mechanism • Context can be made explicit (but is not usually)• Hard to learn
• Representations can talk about what events *LOOK LIKE*:• Sometimes learnable, always well defined primitives• Typically not guaranteed to be complete• Have no explanatory power• Often leverages (ie is wholly dependent upon) context – makes it learnable
from specific data
![Page 49: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/49.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Data-driven vs Knowledge-taught
Data-driven KnowledgeStatistical Structural
Movement
Activity
MHI’s
PHMM’s
SCFG’s
P-Net’s
Action BN’sPNF
Event N-gramsSuffix Trees
Temporaland
relational complexity SIN’s
![Page 50: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/50.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Skip to P-Nets?
![Page 51: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/51.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Data-driven vs Knowledge-taught
Data-driven KnowledgeStatistical Structural
Movement
Activity
MHI’s
PHMM’s
SCFG’s
P-Net’s
Action BN’sPNF
Event N-gramsSuffix Trees
Temporaland
relational complexity SIN’s
![Page 52: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/52.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Structure and Statistics
• Grammar-based representation and parsing• Highly expressive for activity description • Easy to build higher level activity from reused low level vocabulary.
• P-Net (Propagation nets) – really stochastic Petri nets• Specify the structure – with some annotation can learn detectors and
triggering probabilities
• Statistics of events • Low level events are statistically sequenced – too hard to learn full model.• N-grams or suffix trees
![Page 53: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/53.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
"Higher-level" Activities: Known structure, uncertain elements• Many activities are comprised of a priori defined sequences of
primitive elements.• Dancing, conducting, pitching, stealing a car from a parking lot.• The states are not hidden.
• The activities can be described by a set of grammar-like rules; often ad hoc approaches taken.
• But, the sequences are uncertain:• Uncertain performance of elements• Uncertain observation of elements
![Page 54: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/54.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
The basic idea and approach
• Low-level primitives with uncertain feature detection (individual elements might be HMMs)
• High-level description found by parsing input stream of uncertain primitives.
• Extend Stochastic Context Free Grammars to handle perceptually relevant uncertainty.
Idea: split the problem into:
Approach:
![Page 55: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/55.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Stochastic CFGs• Traditional SCFGs have probabilities associated with the
production rules. Traditional parsing yields most likely parse given a known set of input symbols.
• PIECE -> BAR PIECE | [0.5]• BAR [0.5]• BAR -> TWO | [0.5]• THREE [0.5]• THREE -> down3 right3 up3 [1.0]• TWO -> down2 up2 [1.0]
• Thanks to Andreas Stolcke’spriori work on parsing SCFGsusing efficient Earley parser.
![Page 56: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/56.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Extending SCFGs (Ivanov and Bobick, PAMI)
• Within the parser we handle:• Uncertainty about input symbols
• Input is multi-valued string (vector of likelihoods)• Deletion, substitution, and insertion errors
• Introduce error rules • Individually recognized primitives typically temporally inconsistent
• Introduce penalty for overlap.• Spatial and temporal consistency enforced.
• Need to define when a symbol has been generated. We have some level primitives or even HMMs.
• How do we learn production probabilities? (Not many examples.) Make sure not too sensitive to them.
![Page 57: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/57.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Video Sample
![Page 58: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/58.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
![Page 59: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/59.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Event Grammar and Parsing
• Tracker generates events: ENTER, LOST, FOUND, EXIT, STOP. Tracks have properties (e.g. size) and trajectories.
• Tracker assigns class to each event, though only probabilistically.
• Parser parses single stream that contains interleaved events: (CAR-ENTER, CAR-STOP, PERSON-FOUND, CAR-EXIT, PERSON-EXIT)
• Parser enforces spatial and temporal consistency for each object class and interactions (e.g. to be a PICK-UP, the PERSON-FOUND event must be close to CAR-STOP)
• Spatial and temporal consistency eliminates symbolic ambiguity.
![Page 60: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/60.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Advantages of SCFGs• What grammar can do (simplified):
CAR_PASS -> CAR_ENTER CAR_EXIT |CAR_ENTER CAR_HIDDEN CAR_EXIT
CAR_HIDDEN -> CAR_LOST CAR_FOUND | CAR_LOST CAR_FOUND CAR_HIDDEN
• Skip allows concurrency (and junk):PERSON_LOST -> person_lost | SKIP person_lost
• Concurrent parse:Events: ce pe cl cf cs px pl cxPICKUP -> ce pe cl cf cs px pl cxP_PASS -> ce pe cl cf cs px pl cx
![Page 61: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/61.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Parsing System
![Page 62: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/62.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Parse 1: Person-pass- through
![Page 63: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/63.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Parse 2: Drive-in
![Page 64: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/64.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Parse 3: Car-pass-through
![Page 65: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/65.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Parse 4: Drop-off
![Page 66: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/66.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Advantages of STCFG approach
• Structure and components of activities defined a priori and are the right levels of annotation to recover (compare to HMMs).
• FSM vs CFG is not the point. Rather explicit representation of structural elements and uncertainties.
• Often many (enough) examples of each primitive to support training, but not of higher level activity.
• Allows for integration of heterogeneous primitive detectors; only assumes likelihood generation.
• More robust than ad-hoc rule based techniques: handles errors through probability.
• No notion of causality, or anything other than (multi-stream) sequencing.
![Page 67: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/67.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Advantages of STCFG approach• Structure and components of activities defined a priori
and are the right levels of annotation to recover (compare to HMMs).
• FSM vs CFG is not the point. Rather explicit representation of structural elements and uncertainties.
• Often many (enough) examples of each primitive to support training, but not of higher level activity.
• Allows for integration of heterogeneous primitive detectors; only assumes likelihood generation.
• More robust than ad-hoc rule based techniques: handles errors through probability.
• No notion of causality, or anything other than (multi-stream) sequencing.
![Page 68: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/68.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
P-Nets (Propagation Networks) (Shi and Bobick, ’04 and ’06)
•Nodes represent activationintervals
• Active vs. inactive: Token propagation
•More than one node can be active at a time!•Links represent partial order as well logical constraint•Duration model on each link and node:
•Explicit model on length of activation •Explicit model on length between successive intervals
•Observation model on each node
![Page 69: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/69.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Conceptual Schema
• Logical relation• Autonomous assumption: logic constraint only exists at
start/end points of any intervals• Condition probability function can represent any logical
function
Examples of logic constraint
![Page 70: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/70.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Propagation Net – Computing
• Computational SchemaA DBN style rollout to compute corresponding conceptual
schema
![Page 71: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/71.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Experiment: Glucose Project
• Task: monitor an user to calibrate a glucose meter and point out operating error as feedback.
• Constructed 16 node P-Net as representation• 3 subjects with total of 21 perfect sequences, 10
missing_1_step sequences and 10 missing_6_steps sequences
![Page 72: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/72.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
D-CondensationInitiate 1 particle at dummy starting nodeRepeat
For each particlegenerate all possible consequent statescalculate the probability for each states
EndSelect n particles to survive
Until the final time steps is reachedOutput the path represented by the particle with highest
probability
![Page 73: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/73.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Experiment: Glucose Meter Calibration
![Page 74: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/74.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Experiment: Classification Performance
![Page 75: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/75.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
Experiment: Label individual frames
Labeling individual nodes Labels on Node J: Insert
![Page 76: CS 4495 Computer Vision Activity Recognition · 2014-11-30 · CS7616 Pattern Recognition CS 4495 Computer Vision ––A. BobickA. Bobick. Activity Recognition. Prototype methods](https://reader033.vdocuments.mx/reader033/viewer/2022043002/5f7d1ae304f85124d5198691/html5/thumbnails/76.jpg)
Prototype methodsCS7616 Pattern Recognition – A. Bobick Activity RecognitionCS 4495 Computer Vision – A. Bobick
The End?