While person re-identification (Re-ID) has achieved remarkable progress in controlled laboratory settings, its widespread deployment in real-world urban surveillance remains impeded by the significant domain gaps caused by environmental dynamics and sparse camera topologies. In such operational scenarios, relying solely on visual appearance leads to severe visual ambiguity, while the continuous expansion of camera networks induces catastrophic forgetting. To bridge this “lab-to-real” gap, we present a robust, street-surveillance-oriented Re-ID solution validated across a diverse array of benchmarks. Our framework incorporates three key innovations: (1) We construct a deployable Teacher–Student framework to ensure stable feature transfer from labeled source domains to noisy target environments, enabling robust adaptation without manual supervision; (2) Addressing system sustainability, we design a diversity-preserving Dynamic Data Replay mechanism based on Farthest Point Sampling (FPS) to prevent catastrophic forgetting as the network continuously expands; (3) A Spatiotemporal Feature Fusion (STFF) module is developed to resolve visual ambiguity in sparse networks by imposing explicit physical constraints to filter out spatiotemporally infeasible candidates. Extensive evaluations on a proprietary benchmark derived from the live Hainan surveillance system and a series of mainstream datasets demonstrate that our method significantly outperforms existing approaches, offering a superior solution for practical deployment in smart city infrastructure.