Aerial reconstruction of 3D object mapping involves utilizing drones or Unmanned Aerial Vehicles (UAVs) equipped with cameras to capture images for high-resolution 3D model reconstruction of various objects and terrains. This technique is applicable across various fields, such as Urban Planning, Vehicle Navigation, Environmental Studies, Civil Engineering, and Cultural Heritage Conservation. Drones capture hundreds of overlapping aerial photos, which are then processed to generate photorealistic 3D representations of topographic surfaces using photogrammetry software. However, the reconstruction process is time-consuming and computationally intensive, especially when processing large datasets. This research addresses these challenges by employing parallel computing using the Message Passing Interface (MPI) to distribute the computational workload across multiple nodes. By utilizing MPI, the computational tasks are efficiently divided among four nodes, significantly reducing processing time and alleviating the burden on individual CPUs. The study demonstrates that parallel computing with MPI reduces the reconstruction time from 74 minutes to 27 minutes, achieving a speedup of 2.74 times. This research demonstrates a novel application of MPI to the domain of aerial 3D reconstruction, achieving a specific and substantial reduction in processing time. Additionally, it provides insights into future enhancements, such as parallel texture reconstruction and automation of translation processes.
