With the growth of Internet of Things (IoT) applications, the need for accurate indoor positioning systems (IPS) has become urgent. While GPS has limitations in indoor scenarios, Visible Light Positioning (VLP) presents promising results. This paper addresses the challenge of estimating the receiver's height in three-dimensional (3D) positioning scenarios, a crucial problem in VLP. We propose a novel 3D VLP algorithm, adopting a multiple estimation strategy for height estimation to minimize random errors.