arXiv · cs.AI · Abtin Zandi, Sarvin Nami, Roza Ganjipour, Bardia Sabagh Kermani, Amirreza Tarabkhah, Hamed Farbeh2026-11-03 13:00 · 8 小时前模型评分38

基于 YOLOv8 的 Android 应用实现智能手机实时障碍物检测与距离估计

Real-Time Obstacle Detection and Distance Estimation on Smartphones for Visually Impaired and Distracted Pedestrians

导读

一款基于 Kotlin 的 Android 应用利用重训练的 YOLOv8 检测器识别 18 类常见城市障碍物，为视障人士和分心行人提供实时预警。

分类置信度

中 · 待人工复核

来源级别：媒体与个人

应用领域：其他

事件类型：研究发布

证据摘录

“We present a Kotlin-based Android application that uses a YOLOv8 detector, retrained to recognize eighteen common urban obstacle classes, to deliver real-time obstacle alerts for both user groups.”
“The application combines the optimized detector with ARCore-based or monocular focal-length distance estimation, so it works with a single smartphone camera and requires no LiDAR, depth camera, or other specialized sensor.”

来源：arXiv · cs.AI · arxiv.org