Patient surface images are acquired using a novel 3D camera when the patient is at the CT-simulation position and after setup for fractionated stereotactic treatment. The simulation and treatment images are aligned through an initial registration using several feature points followed by a refined automatic matching process using an iterative-closest-point mapping-align algorithm. All of the video-surface images could be automatically transformed to the machine coordinate according to the calibration file obtained from a template image. Phantom tests have demonstrated that we can capture surface images of patients in a second with spatial resolution of sub-millimeter. A millimeter shift and one-degree rotation relative to the treatment machine can be accurately detected. The entire process takes about two minutes. Our primary result on patients involved in a clinical trial is very promising. This research is partially supported by INH Grant 1R43CA91690-01 and NIH CA88843.