A laser Doppler velocimeter (LDV) is usually integrated with an inertial navigation system (INS) to autonomously acquire a vehicle’s position, velocity and attitude. A LDV/INS integrated navigation system can work as an alternative to the global navigation satellite system (GNSS) in non-GNSS environments, which can not only maintain the position accuracy, but also keep a continuous navigation output. Although a LDV can exhibit a higher velocity measurement accuracy, the position error of LDV/INS integrated navigation still accumulates with time due to the limitation of the dead-reckoning principle. In this manuscript, the map matching technique is utilized to help reducing the position error drift of a LDV/INS integrated navigation. An improved road conversion and translation vector correction algorithm is proposed to enhance the integrated navigation performance. The road conversion method considers the relationship between the original road segment and all the road segment candidates, which shows an enhancement in determining a right road segment. The translation vector correction algorithm can compensate the longitudinal position drift effectively. The simulation and experiment verify the correctness of the proposed method and the positioning accuracy can be greatly improved.