On the basis of laser alignment and image detection technologies, an image based online surface settlement monitoring system was established to achieve the online surface settlement monitoring of ballastless track. Firstly, the operational principle of the image based settlement monitoring method was introduced and the components and working model of the online surface settlement monitoring system were described. Then, the image features of laser spot on the target surface for settlement monitoring were analyzed and the background difference method was used to improve the environmental adaptability of the monitoring system. Furthermore, the images of laser spot were preprocessed by the algorithm based on the multi-scale and generalized morphological filter with variant structuring elements. Finally, the center position of laser spot was accurately determined by a gray distribution curve fitting algorithm based on the center of gravity. The experimental results show that the combined uncertainty tested in a settlement laboratory is up to 0.198 mm and the maximum cumulate error under the field test for 10 months is less than 1 mm. The system has met the requirements of online surface settlement monitoring of ballastless track for high stabilization, reliability, precision, and capacity of resisting disturbance.