This paper presents a method for three dimension (3D) drone location estimation based on measured signals transmitted from a flying drone. During the experiment, we considered a single antenna mounted on the drone for signal transmission and a 4-by-4 rectangular array positioned at a known stationary location for receiving the incoming signal. Once the signal strength from the source is measured, the 3D position of the drone is estimated using the MUltiple SIgnal Classification (MUSIC) algorithm. The estimated values are then fed into an Extended Kalman Filter (EKF) as a measurement model, and the movement of the drone is formulated in a 3D trajectory plane. In order to evaluate the performance of our approach, we considered a histogram distribution and probability density function (pdf) of the drone position estimation error during its trajectory. The estimated 3D position of the drone is compared with the GPS values, and we ensure that the drone is localized based on the received signal from the experimental setup by first estimating the direction of the signal using MUSIC, and then tracking it using EKF in the predefined drone trajectory area.