An electronic device and an operating method thereof according to various embodiments are intended to detect a three-dimensional (3D) object based on camera module and radar sensor fusion, and may be configured to extract a first region of interest (RoI) from a first feature map extracted from first sensing data obtained through a camera module, extract a second RoI from a second feature map extracted from second sensing data obtained through a radar sensor, generate a third RoI by fusing the first RoI and the second RoI, and detect a 3D object based on the third RoI.