By the same authors

Grouping Multi-vector Streaklines for Human Activity Identification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published copy (DOI)

Author(s)

Department/unit(s)

Publication details

Title of host publicationProc. IEEE Workshop on Image, Video and Multidimensional Signal Processing
DateE-pub ahead of print - 4 Aug 2016
Pages1-5
Number of pages6
PublisherIEEE
Original languageEnglish
ISBN (Print)978-1-5090-1930-4

Abstract

In this study, human activity identification is approached as a record,
In this study, human activity identification is approached as a record,
analyze and model from the video sequence as you observe the scene
in time methodology. The computational approach has two stages:
training and identification. During the training stage, specific human
activities are identified and characterised by employing modelling
of medium-term movement flow through streaklines. Each streaklines
is formed by multiple optical flow vectors that represent and
track locally the movement in the scene. A dictionary of activities
is recorded for a given scene during the training stage. During the
testing stage, the consistency of each observed activity with those
from the dictionary is verified using the Kullback- Leibler (KL) divergence.
Moving regions that are not present in the dictionary are
identified, triggering decisions such as those specific to anomalous
human activities.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations