Recognizing Linked Events: Searching the Space of Feasible Explanations. Computer Vision and Pattern Recognition

Dima Damen, David Hogg

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

The ambiguity inherent in a localized analysis of events from video can be resolved by exploiting constraints between events and examining only feasible global explanations. We show how jointly recognizing and linking events can be formulated as labeling of a Bayesian network. The framework can be extended to multiple linking layers, expressing explanations as compositional hierarchies. The best global explanation is the Maximum a Posteriori (MAP) solution over a set of feasible explanations. The search space is sampled using Reversible Jump Markov Chain Monte Carlo (RJMCMC). We propose a set of general move types that is extensible to multiple layers of linkage, and use simulated annealing to find the MAP solution given all observations. We provide experimental results for a challenging two-layer linkage problem, demonstrating the ability to recognise and link drop and pick events of bicycles in a rack over five days.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition (CVPR)
DOIs
Publication statusPublished - Jun 2009

Fingerprint Dive into the research topics of 'Recognizing Linked Events: Searching the Space of Feasible Explanations. Computer Vision and Pattern Recognition'. Together they form a unique fingerprint.

Cite this