Learning Human Activities and Object Affordances from RGB-D Videos

TL;DR

This paper presents a method for jointly recognizing human sub-activities and object affordances from RGB-D videos using a Markov random field and SSVM, enabling robots to understand and assist in human environments.

Contribution

It introduces a novel joint modeling approach for activities and affordances with a structural SVM framework, improving interpretability and accuracy.

Findings

Achieved 79.4% accuracy in affordance recognition.

Obtained 63.4% accuracy in sub-activity recognition.

Demonstrated robot-assisted tasks using the descriptive labels.

Abstract

Understanding human activities and object affordances are two very important skills, especially for personal robots which operate in human environments. In this work, we consider the problem of extracting a descriptive labeling of the sequence of sub-activities being performed by a human, and more importantly, of their interactions with the objects in the form of associated affordances. Given a RGB-D video, we jointly model the human activities and object affordances 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 support vector machine (SSVM) approach, where labelings over various alternate temporal segmentations are considered as latent variables. We tested our method on a challenging dataset comprising 120 activity videos collected from 4 subjects, and obtained an accuracy of 79.4% for affordance, 63.4% for sub-activity and 75.0% for high-level activity labeling. We then demonstrate the use of such descriptive labeling in performing assistive tasks by a PR2 robot.