Robocentric Conversational Group Discovery

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

3 Citations (Scopus)
133 Downloads (Pure)

Abstract

Detecting people interacting and conversing with each other is essential to equipping social robots with autonomous navigation and service capabilities in crowded social scenes. In this paper, we introduced a method for unsupervised conversational group detection in images captured from a mobile robot’s perspective. To this end, we collected a novel dataset called Robocentric Indoor Crowd Analysis (RICA). The RICA dataset features over 100,000 RGB, depth, and wideangle camera images as well as LIDAR readings, recorded during a social event where the robot navigated between participants and captured interactions among groups using its on-board sensors. Using the RICA dataset, we implemented an unsupervised group detection method based on agglomerative hierarchical clustering. Our results show that incorporating the depth modality and using normalised features in the clustering algorithm improved group detection accuracy by a margin of 3% on average.
Original languageEnglish
Title of host publicationThe 29th IEEE International Conference on Robot & Human Interactive Communication
PublisherIEEE
Publication statusPublished - 2020

Fingerprint

Dive into the research topics of 'Robocentric Conversational Group Discovery'. Together they form a unique fingerprint.

Cite this