On-line Monitoring of 3D Prefabricated Building Printing based on Improved Binocular System

Abstract

With the rapid development of imaging and smart intelligent processing technology, complex 3D image semantic segmentation and binocular recognition, its research results are widely used in automatic driving systems (ADS), building informatization, and information early warning. Therefore, the on-line monitoring of 3D prefabricated building printing based on improved binocular system is studied. This study considers the basic method of binocular vision algorithm, introduces the research status of semantic segmentation, which is the current research hotspot of image segmentation. Then, the novel depth estimation algorithm is proposed to modify the traditional binocular system. The Geodesic Active Contour model is also optimized to undertake the task to detailed information segmentation for the visual information. Through the testing on the location accuracy and the visualized monitoring performance, the proposed system's performance is validated.