Inverse synthetic aperture radar (ISAR) imaging of the non-cooperative maneuvering target is a challenging task due to its time-varying orientation and rotation velocity which denies accurate measuring. This paper investigates the general principles of ISAR imaging of maneuvering targets, and proposes an algorithm for application in situations when the maneuverability is not too serious and the Doppler variation of sub-echoes from scatterers can be approximated as a first order polynomial. The imaging results using real data show the effectiveness of the new method.