WalkSentry

Articles & Links

Our research papers, the resources around them, and news from the lab.

Research papers

  • Coming soon

    Research #1

    WalkSentry Team

    Abstract

    Details about this project will be added soon.

    • Paper
    • arXiv
    • DOI
    • Code
    • Dataset
  • Under review2026

    From White Canes to Edge AI: A Survey of Assistive Navigation Technologies for Blind and Low-Vision Individuals

    Abtin Zandi, Arian Ashrafi, Sarvin Nami, Seyed Sina Neghahban, Amirabbas Entezari, Parsa Abbasian, Ariyan Azami, Parisa Taherzadeh, Bardia Sabbagh Kermani, Roza Ghanjipour, Hamed Farbeh

    Abstract

    We systematically review 108 peer-reviewed studies, published between 2008 and 2026, on assistive navigation technologies for blind and low-vision (BLV) individuals. We organize the field into four eras: passive aids, electronic travel aids, deep learning, and edge-native AI. We consolidate the object-detector families used in assistive systems and 13 model-compression strategies for on-device deployment, and we outline open challenges and a roadmap toward user-centered assistive navigation.

    • Paper
    • arXiv
    • DOI
    • Code
    • Dataset
  • Under review2026

    ROD-Dataset: A Pedestrian-Perspective Benchmark of 25 Urban Obstacle Classes for Real-Time Detection

    Abtin Zandi, Ariyan Azami, Bardia Sabbagh Kermani, Parsa Abbasian, Roza Ganjipour, Sarvin Nami, Hamed Farbeh

    Abstract

    ROD-Dataset is a pedestrian-perspective benchmark for real-time obstacle detection. It contains more than 24,000 eye-level images and over 40,000 human-verified obstacle annotations across 25 classes, from vehicles and people to stairs, manholes, traffic cones and benches. It unifies 29 public collections under a single taxonomy and adds new captures from Tehran and Toronto. We benchmark six nano-scale YOLO detectors, all of which exceed 0.86 recall: YOLO12n achieves the best recall (0.889), YOLO26n the best precision (0.925), and YOLOv9t the best mAP@0.50 (0.882).

    • Paper
    • arXiv
    • DOI
    • Code
    • Dataset
  • In progress

    Research #4

    WalkSentry Team

    Abstract

    This is our current project. Details are coming soon.

    • Paper
    • arXiv
    • DOI
    • Code
    • Dataset

Links

Dataset pages, repositories, press and posts.

Datasets

  • ROD-Dataset (coming soon)

    Pedestrian-perspective obstacle detection dataset with 25 urban obstacle classes. Download page coming soon.

Code & repositories

Posts & social

Articles & news