Integrating Offline Object Tracking, Signal Processing, and Artificial Intelligence to Classify Relevant Events in Sawmilling Operations

Abstract

Sawmilling operations are typically one of the most important cells of the wood supply chain as they take the log assortments as inputs to which they add value by processing lumber and other semi-finite products. For this kind of operations, and especially for those developed at a small scale, long-term monitoring data is a prerequisite to make decisions, to increase the operational efficiency and to enable the precision of operations. In many cases, however, collection and handling of such data is limited to a set of options which may come at high costs. In this study, a low-cost solution integrating offline object tracking, signal processing and artificial intelligence was tested to evaluate its capability to correctly classify in the time domain the events specific to the monitoring of wood sawmilling operations. Discrete scalar signals produced from media files by tracking functionalities of the Kinovea® software (13,000 frames) were used to derive a differential signal, then a filtering-to-the-root procedure was applied to them. Both, the raw and filtered signals were used as inputs in the training of an artificial neural network at two levels of operational detail: fully and essentially documented data. While the addition of the derived signal made sense because it improved the outcomes of classification (recall of 92–97%) filtered signals were found to add less contribution to the classification accuracy. The use of essentially documented data has improved substantially the classification outcomes and it could be an excellent solution in monitoring applications requiring a basic level of detail. The tested system could represent a good and cheap solution to monitor sawmilling facilities aiming to develop our understanding on their technical efficiency.