Abstract: The ability to detect the status of pedestrian signals at street intersections is a critical aspect of safe outdoor navigation for the blind and visually-impaired, especially in unfamiliar environments. Existing outdoor navigation devices for the blind prove insufficient in providing such guidance due to their reliance on limited mobile computational resources. In this work, we propose a mobile-cloud collaborative approach for context- aware outdoor navigation, where we use the computational power of resources made available by cloud computing providers for real-time image processing. The system architecture we propose also has the advantages of being extensible and having minimal infrastructural reliance, thus allowing for wide usability. We have developed an outdoor navigation application with integrated support for pedestrian crossing guidance and report experiment results, which suggest that the proposed approach is promising for real-time crossing guidance for blind pedestrians.