Cellular signaling data is widely available in mobile communications and contains abun-dant movement sensing information of individual travelers. Using cellular signaling data to esti-mate the trajectories of mobile users can benefit many location-based applications, including infec-tious disease tracing and screening, network flow sensing, traffic scheduling, etc. However, conven-tional methods rely too much on heuristic hypotheses or hardware-dependent network fingerprinting approaches. To address the above issues, NF-Track (Network-wide Fingerprinting based Track-ing) is proposed to realize accurate online map-matching of cellular location sequences. In particu-lar, neither prior assumptions such as arterial preference and less-turn preference or extra hard-ware-relevant parameters such as RSS and SNR are required for the proposed framework. There-fore, it has a strong generalization ability to be flexibly deployed in the cloud computing environ-ment of telecom operators. In this architecture, a novel segment-granularity fingerprint map is put forward to provide sufficient prior knowledge. Then, a real-time trajectory estimation process is developed for precise positioning and tracking. In our experiments implemented on the urban road network, NF-Track can achieve a recall rate of 91.68% and a precision rate of 90.35% in sophisticated traffic scenes, which are superior to the state-of-the-art model-based unsupervised learning ap-proaches.