Blind and low-vision (BLV) people rely on GPS-based systems for outdoor navigation. GPS's inaccuracy, however, causes them to veer off track, run into unexpected obstacles, and struggle to reach precise destinations. While prior work has made precise navigation possible indoors via additional hardware installations, enabling precise navigation outdoors remains a challenge. Ironically, many outdoor environments of interest such as downtown districts are already instrumented with hardware such as street cameras. In this work, we explore the idea of repurposing street cameras for outdoor navigation, and investigate the effectiveness of such an approach. Our resulting system, StreetNav, processes the cameras' video feeds using computer vision and gives BLV pedestrians real-time navigation assistance. Our user evaluations in the COSMOS testbed with eight BLV pedestrians show that StreetNav guides them more precisely than GPS, but its performance is sensitive to lighting conditions and environmental occlusions. We discuss future implications for deploying such systems at scale.

翻译：盲人和低视力（BLV）人群依赖基于GPS的系统进行室外导航。然而，GPS的不准确性导致他们偏离路线、遇到意外障碍物，且难以精确到达目的地。尽管先前的工作已通过额外硬件安装实现了室内精准导航，但实现室外精准导航仍是一个挑战。讽刺的是，许多感兴趣的室外环境（如市中心区域）已配备街道摄像头等硬件设备。在本研究中，我们探索了将街道摄像头重新用于室外导航的构想，并评估了此类方法的有效性。我们最终实现的系统StreetNav利用计算机视觉处理摄像头的视频流，为BLV行人提供实时导航辅助。我们在COSMOS实验台上对八名BLV行人进行的用户评估表明，StreetNav比GPS更精确地引导他们，但其性能受光照条件和环境遮挡的影响。我们讨论了未来大规模部署此类系统的启示。