Human Activity Learning using Object Affordances from RGB-D Videos

08/04/2012
by   Hema Swetha Koppula, et al.
0

Human activities comprise several sub-activities performed in a sequence and involve interactions with various objects. This makes reasoning about the object affordances a central task for activity recognition. In this work, we consider the problem of jointly labeling the object affordances and human activities from RGB-D videos. We frame the problem as a Markov Random Field where the nodes represent objects and sub-activities, and the edges represent the relationships between object affordances, their relations with sub-activities, and their evolution over time. We formulate the learning problem using a structural SVM approach, where labeling over various alternate temporal segmentations are considered as latent variables. We tested our method on a dataset comprising 120 activity videos collected from four subjects, and obtained an end-to-end precision of 81.8 activities.

READ FULL TEXT

page 2

page 3

page 8

research
10/04/2012

Learning Human Activities and Object Affordances from RGB-D Videos

Understanding human activities and object affordances are two very impor...
research
07/12/2021

Human-like Relational Models for Activity Recognition in Video

Video activity recognition by deep neural networks is impressive for man...
research
01/27/2020

rCRF: Recursive Belief Estimation over CRFs in RGB-D Activity Videos

For assistive robots, anticipating the future actions of humans is an es...
research
04/19/2023

Automatic Interaction and Activity Recognition from Videos of Human Manual Demonstrations with Application to Anomaly Detection

This paper presents a new method to describe spatio-temporal relations b...
research
03/03/2021

Learning Asynchronous and Sparse Human-Object Interaction in Videos

Human activities can be learned from video. With effective modeling it i...
research
08/09/2017

What Actions are Needed for Understanding Human Actions in Videos?

What is the right way to reason about human activities? What directions ...
research
01/26/2015

3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks

Human activity understanding with 3D/depth sensors has received increasi...

Please sign up or login with your details

Forgot password? Click here to reset