Elderly care residences often have falling incidents, sometimes with dire consequences. This project aims to implement a method for detecting when people fall, an issue that has seen much research and practical implementations already. In contrast to other work, this project aims to create a non-intrusive, non-wearable solution through the use of cameras. It extends an existing patient monitoring system developed by Eya Solutions, a start-up in the medical field. Their system monitors patients and is composed of embedded systems (clients), a back-end with a database, and a web-based dashboard (the front-end) for administrators, caretakers and users. Our client wants to extend their system by introducing: (i) a video processing component which performs face recognition, (ii) functionality for indoor positioning of people, (iii) functionality to automatically determine near-optimal placement of cameras, and (iv) automatic detection of fall incidents. To understand the relevant research, we survey the field investigating five key research topics: (i) object detection, (ii) fall detection, (iii) facial recognition, (iv) floor plan modelling, and (v) camera placement optimisation. The first part of the project is detecting fall incidents in video footage. By means of image processing (in particular, subsequent frame subtraction), our system detects objects in the foreground and tracks these between frames. Based on the properties of such objects, namely size and shape, we detect fall incidents. The second part of the project is the floor plan editor. This editor is integrated into the existing dashboard, where administrators can model the building. Eya Solutions wishes to provide the product to customers as a complete package, including (i) showing where fall incidents have occurred, and (ii) how and where to place cameras. Our system allows administrators to edit the floor while allowing caretakers to see the modelled floor and see where falls are detected. Considering (ii), it is desirable to generate a configuration where the number of cameras is low while the view coverage is high. Our contribution includes a genetic algorithm which can generate automatically a suitable configuration. Alternatively, cameras can be placed manually by the administrator.