Location-based service (LBS) for both security and commercial use is becoming more and more important with the rise of 5G. Fingerprint localization (FL) is one of the most efficient positioning methods for both indoor and outdoor localization. However, the positioning time of previous research cannot achieve real-time requirement and the positioning error is meter level. In this paper, we concentrated on high-performance in massive multiple-in-multiple-out (MIMO) systems. Principal Component Analysis (PCA) is applied to reduce the dimension of fingerprint, so that the positioning time is about tens of milliseconds with lower storage. What’s more, a novel fingerprint called Angle Delay Fingerprint (ADF) is proposed. Simulation result of the positioning method based on ADF shows the positioning error is about 0.3 meter and the positioning time is about hundreds of milliseconds, which is much better than other previous known methods. (Foundation items: Social Development Projects of Jiangsu Science and Technology Department (No.BE2018704).)