Speaker
Description
The industrial sector is focused on efficiency of an industrial vision through automation as one of the most popular solutions as in recent decades. The main bottleneck of the process is image processing due to high speed and precision. Graphic processing units (GPUs) and Field-Programmable Gate Array (FPGAs) have been proposed for real-time detection, where tasks are now performed repeatedly by machines assisting or replacing humans, reducing the occurrence of errors. New frameworks are trying to be in pace with Industry 5.0 advancements and to rely heavily on real-time sensor systems, with integration to Smart Factory which are essential for assessing dynamics of industrial data. In the paper, the research project focuses on developing an application of innovative combined 3D and line-scan camera system capable of simultaneously capturing visual and 3D information and identifying wood properties such as fiber direction and resin pockets. The camera employs laser triangulation and controlled LED illumination for precise wood structure analysis, while high-speed Field-Programmable Gate Array (FPGA) with High-performance computing (HPC) technologies enables real-time image analysis in-camera. Additionally, the research will focus on presenting fully functional prototype with discussion on modular system architecture scalability and parallel development of FPGA and AI components in simulation, moving closer to industrial implementation in subsequent stages. As the critical step for framework elaboration, the development of a functional application in manufacturing environment of FPGA firmware, laser triangulation, line-scan imaging, controlled illumination, trigger boards, and AI modules and evaluation of technological options that would ensure effective recognition of wood defects, as well as creation of a basis for further technological development are performed.