Algorithms for Improving Speed and Accuracy of Automated Three-Dimensional Reconstruction With a Depth Camera Mounted on An Industrial Robot

Abstract

3D reconstruction technology is used in a wide variety of applications. Currently, automatically creating accurate pointclouds for large parts requires expensive hardware. We are interested in using low-cost depth cameras mounted on commonly available industrial robots to create accurate pointclouds for large parts automatically. Manufacturing applications require fast cycle times. Therefore, we are interested in speeding up the 3D reconstruction process. We present algorithmic advances in 3D reconstruction that achieve a sub-millimeter accuracy using a low-cost depth camera. Our system can be used to determine a pointcloud model of large and complex parts. Advances in camera calibration, cycle time reduction for pointcloud capturing, and uncertainty estimation are made in this work. We continuously capture pointclouds at an optimal camera location with respect to part distance during robot motion execution. The redundancy in pointclouds achieved by the moving camera significantly reduces errors in measurements without increasing cycle time. Our system produces sub-millimeter accuracy.

A Decomposition Algorithm for Dynamic Car Sequencing Problems with Buffers

“…The greedy algorithm (GDA) is an algorithm that takes the best or optimal choice in the current state at each step of selection, and thus, hopes that the result is the best or optimal. GDA is not considered in terms of overall optimality, and the solution obtained each time is a local optimal solution based on some strategy [35,36]. GDA has been studied in solving static car sequencing problems [37], but its performance on dynamic car sequencing problems still needs to be further explored.…”

Optimal Position of Cameras Design in a 4D Foot Scanner

“…The arrangement should guarantee the free movement of the users to be able to track the targeted features. The feature points (generally detectable via passive or active landmarks) are identified from camera outputs which give the 3D position of the landmarks through triangulation between the multiple camera outputs [22][23][24]. Apparently, the accuracy and the quality of the 3D reconstructed point-clouds [25,26] rely on the number of the employed cameras and their configuration.…”