SmartSight AI: A Survey of Context-Aware Obstacle Detection for Visually Impaired Users

Obstacle detection for visually impaired users has progressed from simple range sensing to deep-learning-based perception on wearable and mobile platforms. The remaining gap lies less in detecting objects than in deciding which detections matter, when, and how to communicate them. This survey organized the field by sensing, perception, context, and feedback, and proposed SmartSight AI as a conceptual framework that places context-aware risk prioritization at the center of system design. Advancing this vision will require robust on-device models, representative datasets, and, above all, sustained co-design and evaluation with visually impaired users.

[1]    World Health Organization, World Report on Vision. Geneva, Switzerland: WHO, 2019. [2]    R. R. A. Bourne et al., “Magnitude, temporal trends, and projections of the global prevalence of blindness and distance and near vision impairment: a systematic review and meta-analysis,” Lancet Glob. Health, vol. 5, no. 9, pp. e888–e897, 2017. [3]    D. Dakopoulos and N. G. Bourbakis, “Wearable obstacle avoidance electronic travel aids for blind: A survey,” IEEE Trans. Syst., Man, Cybern. C, vol. 40, no. 1, pp. 25–35, 2010. [4]    W. Elmannai and K. Elleithy, “Sensor-based assistive devices for visually-impaired people: Current status, challenges, and future directions,” Sensors, vol. 17, no. 3, p. 565, 2017. [5]    M. Poggi and S. Mattoccia, “A wearable mobility aid for the visually impaired based on embedded 3D vision and deep learning,” in Proc. IEEE Symp. Comput. Commun. (ISCC), 2016, pp. 208–213. [6]    Y. H. Lee and G. Medioni, “RGB-D camera based wearable navigation system for the visually impaired,” Comput. Vis. Image Underst., vol. 149, pp. 3–20, 2016. [7]    R. Tapu, B. Mocanu, and T. Zaharia, “Wearable assistive devices for visually impaired: A state of the art survey,” Pattern Recognit. Lett., vol. 137, pp. 37–52, 2020. [8]    R. Mur-Artal, J. M. M. Montiel, and J. D. Tardós, “ORB-SLAM: A versatile and accurate monocular SLAM system,” IEEE Trans. Robot., vol. 31, no. 5, pp. 1147–1163, 2015. [9]    S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, 2017. W. Liu et al., “SSD: Single shot multibox detector,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 21–37.