A mobile floor cleaning robot includes a robot body supported by a drive system configured to maneuver the robot over a floor surface. The robot also includes a cleaning system supported by the robot body, an imaging sensor disposed on the robot body, and a controller in communicates with the drive system and the imaging sensor. The controller receives a sequence of images of the floor surface; each image has an array of pixels. For each image, the controller segments the image into color blobs by color quantizing pixels of the image, determines a spatial distribution of each color of the image based on corresponding pixel locations; and for each image color, identifies areas of the image having a threshold spatial distribution for that color. The controller then tracks a location of the color blobs with respect to the imaging sensor across the sequence of images.