Visual Diver Recognition for Underwater Human-Robot Collaboration

TL;DR

This paper introduces a visual recognition system for underwater robots to detect and identify multiple divers, facilitating human-robot collaboration in underwater environments.

Contribution

It combines Faster R-CNN detection with feature-based clustering to distinguish individual divers, a novel approach for underwater human identification.

Findings

High accuracy in diver detection and identification

Effective differentiation of multiple divers in underwater scenes

Potential for improved underwater human-robot collaboration

Abstract

This paper presents an approach for autonomous underwater robots to visually detect and identify divers. The proposed approach enables an autonomous underwater robot to detect multiple divers in a visual scene and distinguish between them. Such methods are useful for robots to identify a human leader, for example, in multi-human/robot teams where only designated individuals are allowed to command or lean a team of robots. Initial diver identification is performed using the Faster R-CNN algorithm with a region proposal network which produces bounding boxes around the divers' locations. Subsequently, a suite of spatial and frequency domain descriptors are extracted from the bounding boxes to create a feature vector. A K-Means clustering algorithm, with k set to the number of detected bounding boxes, thereafter identifies the detected divers based on these feature vectors. We evaluate the performance of the proposed approach on video footage of divers swimming in front of a mobile robot and demonstrate its accuracy.