An iterative closest point method for measuring the level of similarity of 3d log scans in wood industry
This work addresses a domain-specific problem for the Canadian lumber industry by providing an incremental improvement in log processing efficiency.
The paper tackled the slow processing of large volumes of 3D log scans in the lumber industry by using an Iterative Closest Point (ICP) algorithm to measure similarity and identify the most similar already processed log, comparing it to machine learning methods like kNN and Random Forest.
In the Canadian's lumber industry, simulators are used to predict the lumbers resulting from the sawing of a log at a given sawmill. Giving a log or several logs' 3D scans as input, simulators perform a real-time job to predict the lumbers. These simulators, however, tend to be slow at processing large volume of wood. We thus explore an alternative approximation techniques based on the Iterative Closest Point (ICP) algorithm to identify the already processed log to which an unseen log resembles the most. The main benefit of the ICP approach is that it can easily handle 3D scans with a variable number of points. We compare this ICP-based nearest neighbor predictor, to predictors built using machine learning algorithms such as the K-nearest-neighbor (kNN) and Random Forest (RF). The implemented ICP-based predictor enabled us to identify key points in using the 3D scans directly for distance calculation. The long-term goal of this ongoing research is to integrated ICP distance calculations and machine learning.