What does it look like? An artificial neural network model to predict the physical dense 3D appearance of a large-scale object. (1st December 2022)

• Record Type: Journal Article
• Authors: Wang, Shih-Yuan; Sung, Fei-Fan; Liong, Sze-Teng; Sheng, Yu-Ting; Gan, Y.S.
• Is Part Of: Expert systems with applications. Volume 208(2022)
• Publication Date: 2022-12-01
• Subjects: Artificial neural network -- Robot arm -- Surface reconstruction -- Metal twisting -- ArUco marker; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.118106
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Object 3D reconstruction is a well-known ill-posed problem that has been extensively studied and making compelling progress, especially in recent years. This is owing to the rise of computational capability in enabling the efficient processing of neural networks. This article presents a benchmark for image-based 3D reconstruction in a realistic condition. Particularly, a novel pipeline is developed to localize the dense surface of a large-scale object at different twisting angles. A shallow artificial neural network with a single hidden layer is devised to learn the correlation between the simulated frame and ground-truth data points. As a result, the proposed framework demonstrates the robustness of the model by providing a valid and reasonable prediction performance in practical problems. Notably, remarkably low RMSE of 8 and a high R 2 of 1 are yielded when evaluated in a dataset of 211 sample data. Specifically, a curvature dataset is constructed by twisting a 90 kg metal board at several angles, using two six-axis articulated industrial robots. Graphical abstract: Highlights: A benchmark for image-based 3D reconstruction in a realistic condition is presented. The surface of a large-scale object at several twisting angles is densely localized. Both the descriptive statistics and qualitative analysis are reported. Prediction of bending level of an object without knowing the material's properties. A remarkably low RMSE of 8 and a high R 2 of 1 were yielded when tested on 211 data.