Towards automated remote sizing and hot steel manufacturing with image registration and fusion

Abstract

AbstractImage registration and fusion are challenging tasks needed in manufacturing, including in high-quality steel production for inspection, monitoring and safe operations. To solve some of these challenging tasks, this paper proposes computer vision approaches aiming at monitoring the direction of motion of hot steel sections and remotely measuring their dimensions in real time. Automated recognition of the steel section direction is performed first. Next, a new image registration approach is developed based on extrinsic features, and it is combined with frequency domain image fusion ofoptical images. The fused image provides information about the size of high-quality hot steel sections remotely. While the remote sizing approach keeps operators informed of the section dimensions in real time, the mill stands can be configured to provide quality assurance. The performance of the developed approaches is evaluated over real data and achieves accuracy above 95%. The proposed approaches have the potential to introduce an enhanced level of autonomy in manufacturing and provide advanced digitised solutions in steel manufacturing plants.