Hierarchical 2-step neural-based LEGO bricks detection and labeling

LEGO bricks are extremely popular and allow the creation of almost any type of construction due to multiple shapes available. LEGO building requires however proper brick arrangement, usually done by shape. With over 3700 different LEGO parts this can be troublesome. In this paper, we propose a solution for object detection and annotation on images. The solution is designed as a part of an automated LEGO bricks arrangement. The proposed approach consists of 2 stages – object detection and labeling. The paper discusses different approaches and points out a final model. A 2-step, hierarchical model and the results are presented. An evaluation of the proposed solution is also given.