A vehicle comprises an interior Infrared (IR) camera and optionally a visible light camera. Images of an interior of the vehicle are captured using the cameras both before 302 and after 308 a passenger rides in the vehicle. The IR images from before and after are subtracted to obtain a difference image 310. Pixels above a threshold intensity may be clustered 312. Clusters having an above-threshold size are determined to be anomalies 314. Portions of images from the visible light camera corresponding to the anomalies are sent to a dispatcher 318, who may then clear the vehicle to pick up another passenger 320 or proceed to a cleaning station. Anomalies may be identified based on a combination of the IR images and visible light images. The system is particularly intended for use in an autonomous vehicle, where anomalies such as a spilled liquid can be detected remotely prior to the vehicle picking up the next occupant.