Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for status monitoring using machine vision and machine learning. In some implementations, image data representing a monitored area is obtained. Input data based on the image data is provided to one or more machine learning models trained to detect different properties of the monitored area. Output of the one or more machine learning models is received. The output of the one or more machine learning models is evaluated to detect a condition present in the monitored area. Output is provided indicating the detected condition present in the monitored area.