Monocular depth estimation improves prosthetic limb vision in complex terrains
Zero-Shot Monocular Depth Estimation for Visual Perception in Lower-Limb Prostheses
Computer Vision and Pattern Recognition
Summary
People who use lower-limb prosthetics often face difficulties when walking on stairs or uneven ground because they can’t easily gauge how far away things are. The authors created a new dataset to test how well current AI models estimate depth from the viewpoint of a prosthetic knee. They tested four advanced depth estimation models and showed how these methods perform in prosthetic vision scenarios. This work highlights both the challenges and possibilities of using AI to help prosthetics better perceive the environment around them.
What this means in practice
- •For prosthetic device engineers: Evaluate and enhance depth perception algorithms from a prosthetic viewpoint using the LP benchmark dataset and tested models.
- •For robotics developers: Incorporate tested monocular depth estimation models into robotic mobility systems that navigate uneven or complex environments.
Authors
Ishi Vijayvergiya, Marc Hölle, Youssef Dawoud, Amir El-Ghoussani, Michele De Vita, Rohan Asthana, Philipp Beckerle, Vasileios Belagiannis
Abstract
Monocular depth estimation has advanced rapidly with the development of foundation models that demonstrate strong zero-shot generalisation across diverse visual domains. However, the applicability of these models to visual perception for lower-limb prosthetics remains largely unexplored. Reliable depth perception is particularly important for prosthesis users, who often experience significant challenges when navigating stairs, uneven terrain, and other complex environments. To address this gap, we introduce the Lower-Limb Prosthesis (LP) dataset, a benchmark designed to evaluate depth perception from an emulated knee-level prosthetic viewpoint. Using this dataset, we evaluate four state-of-the-art monocular depth estimation foundation models. Our results provide the first systematic benchmark of monocular depth estimation performance from a prosthetic viewpoint, while highlighting both the challenges and the potential of deploying foundation models in prosthetic perception systems. The code and dataset are available at https://github.com/Ishivijay/lp_dataset.