Gait analysis is often used as part of the rehabilitation program for post-stoke recovery assessment. Since current optical diagnostic and patient assessment tools tend to be expensive and not portable, this paper proposes a novel marker-based tracking system using a single depth camera which provides a cost-effective solution suitable for home and clinic use. The proposed system can simultaneously generate motion patterns even within a complex background using the proposed geometric model-based algorithm and autonomously provide gait analysis results. The processed rehabilitation data can be accessed by cross-platform mobile devices using cloud-based services enabling emerging tele-rehabilitation practices. Experimental validation shows a good agreement with state-of-the-art non-portable and expensive industrial standards.