 This paper proposes a novel methodology for generating new 3D-based autolabeling data sets with a different point of view setup than the ones used in existing data sets such as Kitty, Waymo, etc. The methodology is based on the YOLO model trained with the Kitty data set. It is intended to autolabel new data sets while maintaining the consistency of the ground truth. The performance of the model, with respect to the manually labeled Kitty images, achieved an f-score of 0.957, 0.927 and 0.740 in the easy, moderate and hard images of the data set. The main contribution of this work is a novel methodology to autolabel autonomous driving data sets using YOLO as the main labeling system. The proposed methodology was tested under boundary conditions and the results showed that this approximation can be easily adapted to a wide variety of problems when labeled data sets are not available. This article was authored by Guillermo Escudieres Cabello, Edgar Tolivera, Guillermo Iglesias, and others. We are article.tv, links in the description below.