HEADS-UP: Head-Mounted Egocentric Dataset for Trajectory Prediction in Blind Assistance Systems

TL;DR

This paper introduces HEADS-UP, a novel egocentric dataset from head-mounted cameras for trajectory prediction in blind assistance, and proposes a semi-local prediction method validated through real-time tests and user studies.

Contribution

The paper presents the first egocentric dataset for trajectory prediction in blind assistance and a semi-local approach for real-time collision risk assessment.

Findings

The dataset effectively captures egocentric perspectives for trajectory prediction.

The proposed method operates efficiently in real-time on embedded hardware.

Real-world tests confirm the robustness of the approach.

Abstract

In this paper, we introduce HEADS-UP, the first egocentric dataset collected from head-mounted cameras, designed specifically for trajectory prediction in blind assistance systems. With the growing population of blind and visually impaired individuals, the need for intelligent assistive tools that provide real-time warnings about potential collisions with dynamic obstacles is becoming critical. These systems rely on algorithms capable of predicting the trajectories of moving objects, such as pedestrians, to issue timely hazard alerts. However, existing datasets fail to capture the necessary information from the perspective of a blind individual. To address this gap, HEADS-UP offers a novel dataset focused on trajectory prediction in this context. Leveraging this dataset, we propose a semi-local trajectory prediction approach to assess collision risks between blind individuals and pedestrians in dynamic environments. Unlike conventional methods that separately predict the trajectories of both the blind individual (ego agent) and pedestrians, our approach operates within a semi-local coordinate system, a rotated version of the camera's coordinate system, facilitating the prediction process. We validate our method on the HEADS-UP dataset and implement the proposed solution in ROS, performing real-time tests on an NVIDIA Jetson GPU through a user study. Results from both dataset evaluations and live tests demonstrate the robustness and efficiency of our approach.