Target monitoring and alert systems for identifying and tracking targets within radar data. Raw frame data is filtered to remove data relating to reflections from static objects. Moving targets are identified in the filtered data and their location is tracked over time generating target data. Neural networks may process the target data, calculate a fall likelihood score and generate a fall-alert if this is above an alert-threshold. A person identification module may extract the position and motion characteristics of each target from the data and generate a probabilistic identification of the target with a person.