First Person Vision for Activity Prediction Using Probabilistic Modeling
Journal Title: Mehran University Research Journal of Engineering and Technology - Year 2018, Vol 37, Issue 4
Abstract
Identifying activities of daily living is an important area of research with applications in smart-homes and healthcare for elderly people. It is challenging due to reasons like human self-occlusion, complex natural environment and the human behavior when performing a complicated task. From psychological studies, we know that human gaze is closely linked with the thought process and we tend to “look” at the objects before acting on them. Hence, we have used the object information present in gaze images as the context and formed the basis for activity prediction. Our system is based on HMM (Hidden Markov Models) and trained using ANN (Artificial Neural Network). We begin with extracting motion information from TPV (Third Person Vision) streams and object information from FPV (First Person Vision) cameras. The advantage of having FPV is that the object information forms the context of the scene. When context is included as input to the HMM for activity recognition, the precision increases. For testing, we used two standard datasets from TUM (Technische Universitaet Muenchen) and GTEA Gaze+ (Georgia Tech Egocentric Activities). In the first round, we trained our ANNs only with activity information and in the second round added the object information as well. We saw a significant increase in the precision (and accuracy) of predicted activities from 55.21% (respectively 85.25%) to 77.61% (respectively 93.5%). This confirmed our initial hypothesis that including the focus of attention of the actor in the form of object seen in FPV can help in predicting activities better.
Authors and Affiliations
Shaheena Noor, Vali Uddin
Keywords
Related Articles
- EP ID EP394637
- DOI 10.22581/muet1982.1804.09
- Views 112
- Downloads 0
An Efficient Computer-Aided Diagnosis System for the Analysis of DICOM Volumetric Images
Medical images are an important source of diagnosis. The brain of human analysis is now an advanced field of research for computer scientists and biomedical physicians. Services provided by the healthcare units usually v...
Information Assurance for Enterprise Resource Planning Systems: Risk Considerations in Public Sector Organizations
ERP (Enterprise Resource Planning) systems reveal and pose non-typical risks due to its dependencies of interlinked business operations and process reengineering. Understanding of such type of risks is significant conduc...
Enabling the Usability Heuristics of Agile Base Systems to Improve Quality of Local Software Industry
Many agile software development practices are promoted to improve the quality of software products. In recent years agile software development overlooked the usability features that effected system productivity.Usability...
A Direction-Based Make-Before-Break Routing Protocol for Vehicular Ad Hoc Networks-
In this paper, we present a novel ?Make-Before-Break? routing protocol for VANETs (Vehicular Ad Hoc Networks) which brings stability in route even if it contains some nodes moving opposite to the rest. Few of the existin...
Simulation Studies Relating to Rudder Roll Stabilization of a Container Ship Using Neural Networks
RRS (Rudder Roll Stabilization) of Ships is a difficult problem because of its associated non-linear dynamics, coupling effects and complex control requirements. This paper proposes a solution of this stabilization probl...