Distance Estimation to Support Assistive Drones for the Visually Impaired using Robust Calibration

2025-03-31

AI Summary

To address the challenge of inaccurate absolute distance estimation for obstacles in outdoor navigation by visually impaired individuals, this paper proposes NOVA—a real-time, high-accuracy system for estimating absolute distances to both users and dynamic obstacles (e.g., vehicles, bicycles) using an onboard RGB-D sensor and depth maps. Its core contribution is a robust, dynamically updated online depth-map calibration method that adaptively compensates for adversarial environmental factors such as illumination variations and motion blur, significantly enhancing estimation reliability in complex, dynamic scenes. NOVA integrates deep learning, geometric modeling, and regression-based modeling into an end-to-end distance estimation framework. Experimental results demonstrate sub-30 cm prediction error for visually impaired users and ≤60 cm error for typical obstacles. Moreover, NOVA achieves 5.3–14.6× faster inference speed compared to state-of-the-art depth-map-based methods.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Adversarial Attacks & Robustness
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Autonomous navigation by drones using onboard sensors, combined with deep learning and computer vision algorithms, is impacting a number of domains. We examine the use of drones to autonomously assist Visually Impaired People (VIPs) in navigating outdoor environments while avoiding obstacles. Here, we present NOVA, a robust calibration technique using depth maps to estimate absolute distances to obstacles in a campus environment. NOVA uses a dynamic-update method that can adapt to adversarial scenarios. We compare NOVA with SOTA depth map approaches, and with geometric and regression-based baseline models, for distance estimation to VIPs and other obstacles in diverse and dynamic conditions. We also provide exhaustive evaluations to validate the robustness and generalizability of our methods. NOVA predicts distances to VIP with an error<30cm and to different obstacles like cars and bicycles with a maximum of 60cm error, which are better than the baselines. NOVA also clearly out-performs SOTA depth map methods, by upto 5.3-14.6x.

Problem

• Develop robust calibration for drone-assisted visually impaired navigation
• Estimate absolute distances to obstacles using depth maps
• Improve accuracy over SOTA methods in dynamic environments

Innovation

• Robust calibration using depth maps
• Dynamic-update method for adversarial scenarios
• Outperforms SOTA depth map methods significantly