Understanding activity patterns in office environments is important in order to increase workerstextquoteright comfort and productivity. This paper proposes an automated system for discovering activity patterns of multiple persons in a work environment using a network of cheap low-resolution visual sensors (900 pixels). Firstly, the userstextquoteright locations are obtained from a robust people tracker based on recursive maximum likelihood principles. Secondly, based on the userstextquoteright mobility tracks, the high density positions are found using a bivariate kernel density estimation. Then, the hotspots are detected using a confidence region estimation. Thirdly, we analyze the individualtextquoterights tracks to find the starting and ending hotspots. The starting and ending hotspots form an observation sequence, where the usertextquoterights presence and absence are detected using three powerful Probabilistic Graphical Models (PGMs). We describe two approaches to identify the usertextquoterights status: a single model approach and a two-model mining approach. We evaluate both approaches on video sequences captured in a real work environment, where the personstextquoteright daily routines are recorded over 5 months. We show how the second approach achieves a better performance than the first approach. Routines dominating the entire grouptextquoterights activities are identified with a methodology based on the Latent Dirichlet Allocation topic model. We also detect routines which are characteristic of persons. More specifically, we perform various analysis to determine regions with high variations, which may correspond to specific events.