Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi class activity classification in videos using Motion History Image generation

Senthilkumar Gopal

TL;DR

This work utilizes MHI to produce sample data to train a classifier and demonstrate its effectiveness for action classification across six different activities in a single multi-action video.

Abstract

Human action recognition has been a topic of interest across multiple fields ranging from security to entertainment systems. Tracking the motion and identifying the action being performed on a real time basis is necessary for critical security systems. In entertainment, especially gaming, the need for immediate responses for actions and gestures are paramount for the success of that system. We show that Motion History image has been a well established framework to capture the temporal and activity information in multi dimensional detail enabling various usecases including classification. We utilize MHI to produce sample data to train a classifier and demonstrate its effectiveness for action classification across six different activities in a single multi-action video. We analyze the classifier performance and identify usecases where MHI struggles to generate the appropriate activity image and discuss mechanisms and future work to overcome those limitations.

Multi class activity classification in videos using Motion History Image generation

TL;DR

This work utilizes MHI to produce sample data to train a classifier and demonstrate its effectiveness for action classification across six different activities in a single multi-action video.

Abstract

Human action recognition has been a topic of interest across multiple fields ranging from security to entertainment systems. Tracking the motion and identifying the action being performed on a real time basis is necessary for critical security systems. In entertainment, especially gaming, the need for immediate responses for actions and gestures are paramount for the success of that system. We show that Motion History image has been a well established framework to capture the temporal and activity information in multi dimensional detail enabling various usecases including classification. We utilize MHI to produce sample data to train a classifier and demonstrate its effectiveness for action classification across six different activities in a single multi-action video. We analyze the classifier performance and identify usecases where MHI struggles to generate the appropriate activity image and discuss mechanisms and future work to overcome those limitations.

Paper Structure

This paper contains 16 sections, 5 equations, 9 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Temporal Templates
  4. Binary Images and background subtraction
  5. Motion-history images
  6. Moments
  7. Importance of Tau
  8. Image processing Pipeline
  9. Classification
  10. K Nearest Neighbors Classifier
  11. Multi-layer Perceptron Classifier
  12. Results
  13. Analysis
  14. why the method works on some images and not on others
  15. Future Work
  16. ...and 1 more sections

Figures (9)

  • Figure 1: Multi Action video frames with their predicted action labels
  • Figure 2: Illustrative binary difference images for various actions
  • Figure 3: Cumulative binary images (Motion Energy Response) for various actions
  • Figure 4: Motion History Image (MHI) for various actions
  • Figure 5: Image processing pipeline to generate moments
  • ...and 4 more figures