A novel road detection and tracking algorithm for intelligent pilotless aircraft applications was illustrated. Initially, synthetic image was extracted from electron road maps to initialize the road areas. Then, road detection was expressed as a minimizing problem by means of using distance transformation of input image and edges of synthetic image. Finally an iterative algorithm took shape and was applied to solve the minimizing problem mentioned above to abtain road regions. Road tracking method initialized its corresponding minimizing problem utilizing the prediction image out of the detection results of previous video frames. Concerning the function of this method, strict experimental results are presented to demonstrate the satisfactory performances of our approach with its highly stability and adaptability.