Low Cost 3D Scanner Using Iterative Closest Point Algorithm

3D reconstruction is widely used to create 3D representation of 2D images. 3D scanner is a device that takes scans or images of the object or environment and creates the 3D representation of it. While industrial 3D scanners use laser technology to do the scanning, the central goal of this work is to compare cost effective ways of 3D scanning and comparing their performance. In this work we use a camera to capture RGBD images then use three different techniques namely, the hardcoded meth to reconstruct the objects, SIFT algorithm and the ICP algorithm. The results demonstrate that the ICP method yields the most reliable reconstructions, evidenced by Root Mean Square Error (RMSE) values approximately 0.0022 and fitness values reaching 0.9, indicating accuracy for objects such as a Rubik's cube and an orange fruit.