Recently unmanned aerial vehicle (UAV) are more widely applied so that those demanding of function upgrade is required, such as increasing the payload, reducing its weight, the stability of control system, and battery life. In this study, there two key areas, landing target and embedded system, are focused to improve the UAV system. This study uses specific landing mark to provide better guidance information to UAV control system. The landing mark, which combines color and geometry, is designed for image processing algorithms so that the control system can estimate position and direction of the landing target for modifying landing position. On the other hand, embedded system is ideally suited for the development of UAV flight system, because there are several features, for example, small size, light weight, low power consumption, processing speed and stability. The purpose of this research is to develop a machine vision system which can help unmanned aerial helicopter (UAH) can takeoff and landing automatically by identifying the landing mark by using the embedded system hardware architecture, and developing the required program through image recognition algorithms.