"Shape Activities": General HMM Models for Changing Configurations of Landmarks and Applications

The changing configuration of a group of moving "landmarks" can be modeled as a moving and deforming shape. The "landmarks" could be moving objects (people/vehicles/robots) or rigid components of an articulated shape like the human body. The term “shape activity” has been used to denote a particular stochastic model for shape deformation. We study 3 types of dynamic models: Stationary Shape Activities, NonStationary Shape Activities and Piecewise Stationary Shape Activities (special case of NSSA).  A shape based dynamical model makes our approach invariant to camera motion, under the weak perspective model (also referred to as the scaled orthographic camera) assumption. The weak perspective model is a valid assumption when the scene depth is much smaller compared to distance from the camera and the centre of the scene is near the camera's principal axis. This assumption often holds in surveillance applications. Also, the approach is sensor independent, i.e. the observation vector of object locations could be obtained by motion detection on a video sequence or using an infra-red,
radar or acoustic sensor.

• Samarjit Das and Namrata Vaswani, Nonstationary Shape Activities: Dynamic Models for Landmark Shape Change and Applications, IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), To Appear, December 2009
• Samarjit Das and Namrata Vaswani, Model-based Compression of Nonstationary Landmark Shape Sequences, IEEE Intl. Conf. Image Proc. (ICIP), 2008.
• Namrata Vaswani and Samarjit Das, Particle Filter with Efficient Importance Sampling and Mode Tracking (PF-EIS-MT) and its Application to Landmark Shape Tracking, Asilomar 2007 (invited)
• Namrata Vaswani and Rama Chellappa,  NonStationary "Shape Activities",  IEEE Conf. on Decision and Control (CDC), 2005 
• (this had an error which was fixed in the later ICIP and PAMI papers)
  

Piecewise Stationary Shape Activities (PSSA) and Applications in Tracking, Change Detection and Summarization/Indexing of Human Activity Sequences

• Bi Song, Namrata Vaswani, Amit Roy-Chowdhury, Closed-loop Tracking and Change Detection in Multi-Activity Sequences,  IEEE Intl. Conf. on Computer Vision and Pattern Recognition (CVPR), 2007.
• Bi Song, Namrata Vaswani and Amit K. Roy-Chowdhury, "Summarization and Indexing of Human Activity Sequences", IEEE Conf. on Image Processing (ICIP), 2006

• Namrata Vaswani and Rama Chellappa, "Principal Component Null Space Analysis for Image and Video Classification",  IEEE Trans. Image Processing, July 2006.
• Namrata Vaswani, Amit Roy-Chowdhury, Rama Chellappa, "Shape Activity": A Continuous State HMM for Moving/Deforming Shapes with Application to Abnormal Activity Detection, IEEE Trans. Image Processing, pp 1603-1616, October 2005
• Namrata Vaswani, Amit RoyChowdhury, Rama Chellappa, "Activity Recognition Using the Dynamics of the Configuration of Interacting Objects",  IEEE Computer Vision and Pattern Recognition (CVPR), 2003
• Namrata Vaswani, A. RoyChowdhury, R. Chellappa, " Statistical Shape Theory for Activity Modeling" , IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2003.

Talks
UC-Berkeley, Computer Vision Seminar Series, Nov 22, 2005 (invited):     Abnormal "Shape Activity" Detection & Tracking
CDC 2005, Seville, Spain, December 2005:     NonStationary Shape Activities
ICIP 2006, Atlanta GA:  Summarizing/ Indexing of Human Activity Sequences

Videos:

Tracking Human Action Sequences using NSSA:
Samarjit Das's page
Very Old NSSA videos:
Simulation sequence:   Deforming Hexagon
Human Actions:    Dancer video (normal),       Tracking and detecting abnormality

Abnormal Activity Detection using SSA
Group of People at Airport:  Normal activity,    Abnormal activity

Video Summarization using PSSA (created by Bi Song)
Yoga Sequence 
Outdoor Sequence 1  Outdoor Sequence 2 Outdoor Sequence 3 (occlusion)
Indoor Sequence