ThŒis work introduces a multimodal multiview camera network for role identi€cation and re-identi€cation in an Intensive Care Unit (ICU) room, where identifying individuals is not permittŠed. ŒThe analysis challenges include imaging conditions such as medical isolation (where all visitors wear scrubs), poor and non-uniform illumination, or variable camera views. We propose a role representation, which combines static appearance features such as texture and color, together with a dynamic quantifi€cation of human locations and interactions that results in a semantic map. ŒThe proposed representation is easy to compute and robust to varying ICU conditions and network con€figurations, which make the methods suitable for low-power distributed sensor network deployment. Thorough evaluations and comparisons with competing methods are performed. Œe €ndings from this approach enable the compliant analysis of workƒflows in healthcare, while protecting the privacy of patients and medical sta‚ff.