High impedance fault in distribution networks is difficult to detect and locate by traditional methods due to the weak electrical quantity characteristics. With the large number of access to distributed power sources, the distribution of currents and harmonic components in the active distribution network are becoming more and more complex, which puts forward higher requirements for the high impedance fault detection and localization. To slove this problem, this paper proposes a high impedance fault location method of active distribution networks based on line parameter identification and feature matching. Firstly, the line parameter identification method is used to construct the distribution network fault feature set when HIF occurs. On this basis, the mapping relationship between line parameter information and HIF fault location is further mined, and the HIF localization model is constructed using random forest. Finally, a large number of simulations are carried out in an IEEE 33-bus distribution network, the results show that the proposed method can accurately achieve the identification and localization of HIF, and it has a certain degree of generalization ability in the case of noise-containing situations.