用单目深度估计帮视障者实时避障，轻量高效可嵌入设备
An Embedded Real-time Object Alert System for Visually Impaired: A Monocular Depth Estimation based Approach through Computer Vision
- 基于迁移学习与量化技术，融合深度估计与目标检测模型
- 实现轻量级实时推理，mAP50达0.801，支持嵌入式部署
- 专为孟加拉城市道路设计，适合视障人群日常出行辅助
孟加拉城市中视障人士在日常通勤时面临大量障碍物威胁，每日频发的交通事故凸显了提前预警系统的重要性。为此，本文提出一种新型实时物体告警系统，通过计算机视觉实现单目深度估计，帮助视障者避免近距离碰撞。系统采用迁移学习训练深度估计与目标检测模型，并结合两者构建新方案。通过量化技术优化模型，显著降低计算开销，便于在嵌入式设备上部署。实验表明，该系统在保持实时性的同时，实现了mAP50为0.801的高精度检测性能，具备轻量化、高效、低延迟特点，适用于复杂城市环境中的视障者导航。
原文摘要 · Abstract (English)
Visually impaired people face significant challenges in their day-to-day commutes in the urban cities of Bangladesh due to the vast number of obstructions on every path. With many injuries taking place through road accidents on a daily basis, it is paramount for a system to be developed that can alert the visually impaired of objects at close distance beforehand. To overcome this issue, a novel alert system is proposed in this research to assist the visually impaired in commuting through these busy streets without colliding with any objects. The proposed system can alert the individual to objects that are present at a close distance. It utilizes transfer learning to train models for depth estimation and object detection, and combines both models to introduce a novel system. The models are optimized through the utilization of quantization techniques to make them lightweight and efficient, allowing them to be easily deployed on embedded systems. The proposed solution achieved a lightweight real-time depth estimation and object detection model with an mAP50 of 0.801.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。