Automatic elevator shaft inspection using a multi-sensor measuring system and computer vision techniques

Abstract

The present work introduces a system capable of automatically measuring the dimensions of an elevator shaft using computer vision approaches and optical sensors without human intervention. Miscomputations on the available volume of the elevator shaft could lead to the manufacturing of a cabin that cannot be utilized due to the customization of the product. Hereupon, it is crucial to calculate the smallest cross-section in the shaft since this area affects the maximum floor space of the elevator. The suggested methodology employs a low cost multisensor measuring system incorporating a Jetson Nano, a LiDAR, laser sensors, and a Micro Processor Unit (MPU) that scans the whole elevator shaft in one single run and reconstructs it, evaluating the examined shaft. The arrangement descents through a pulley into the investigated shaft using one string on each side, with a weight hanging at the end to increase stability and avoid rotations. Finally, validation experiments were performed in a test elevator shaft, which was manually measured in each floor to provide a ground truth. The acquired results showed sufficient accuracy of less than 1 % and reliability, assuring the proper dimensioning of the elevator shaft and the high standards of the lift industry.