Open Set Recognition of Timber Species Using Deep Learning for Embedded Systems

• Published in: Revista IEEE América Latina 2019-12, Vol.17 (12), p.2005-2012
• Main Authors: Apolinario, Marco Paul E., Urcia Paredes, Daniel A., Huaman Bustamante, Samuel G.
• Format: Article
• Language: English
• Subjects: Artificial neural networks; convolutional neural network; Convolutional neural networks; Deep learning; embedded system; Embedded systems; Energy comsumption; Energy consumption; Forest management; Forestry; Identification methods; Inspection; Maximum power; open set recognition; Recognition; Resource management; Timber; timber species; Tropical forests
• ISSN: 1548-0992; 1548-0992
• DOI: 10.1109/TLA.2019.9011545

Reliable and rapid identification of timber species is a very relevant issue for many countries in South America and especially for Peru, which is the second country with the largest extent of tropical forest, and that is because this issue is a necessity in order to develop an effective management of the forest resources, such as inspection and control of the timber commerce. Since current methods of identification are based on a closed set recognition approach, they are not reliable enough to be used in a practical application because scenarios of identification of timber species are by nature an open set recognition problem. For that reason, in this work we propose a convolutional neural network that has two main characteristics, being able to run in a real-time embedded system and being able to handle the open set recognition problem, that is, this model can discriminate between known and unknown species. In order to evaluate it, tests are performed in two timber species datasets and some experiments are developed in the embedded system Raspberry Pi3B+ to measure energy consumption. The results present high metrics, which means that it manages to discriminate the unknown species with accuracy and F1 score above 91% for two sets of images used. In addition to this, our proposed model obtain lower maximum power value (10-12%) and computational resource usage (5-13%) than a classical convolutional model and MobileNetsV2 measured on the Raspberry Pi3B+.