Multi-label affordance mapping from egocentric vision

TL;DR

This paper introduces a novel multi-label affordance segmentation method from egocentric videos, creating a comprehensive dataset and enabling spatial mapping and task-oriented navigation in interaction-rich environments.

Contribution

It presents a new approach for pixel-level multi-label affordance detection, a large annotated dataset, and a method for spatial mapping and navigation based on affordance hotspots.

Findings

Multi-label detection improves affordance segmentation accuracy.

The dataset EPIC-Aff is the largest with detailed annotations.

Spatial affordance maps enable task-oriented navigation.

Abstract

Accurate affordance detection and segmentation with pixel precision is an important piece in many complex systems based on interactions, such as robots and assitive devices. We present a new approach to affordance perception which enables accurate multi-label segmentation. Our approach can be used to automatically extract grounded affordances from first person videos of interactions using a 3D map of the environment providing pixel level precision for the affordance location. We use this method to build the largest and most complete dataset on affordances based on the EPIC-Kitchen dataset, EPIC-Aff, which provides interaction-grounded, multi-label, metric and spatial affordance annotations. Then, we propose a new approach to affordance segmentation based on multi-label detection which enables multiple affordances to co-exists in the same space, for example if they are associated with the same object. We present several strategies of multi-label detection using several segmentation architectures. The experimental results highlight the importance of the multi-label detection. Finally, we show how our metric representation can be exploited for build a map of interaction hotspots in spatial action-centric zones and use that representation to perform a task-oriented navigation.