Vision System for a Forestry Navigation Machine

Tiago Pereira; Tiago Gameiro; José Pedro; Carlos Viegas; N M Fonseca Ferreira

doi:10.3390/s24051475

Vision System for a Forestry Navigation Machine

Sensors (Basel). 2024 Feb 24;24(5):1475. doi: 10.3390/s24051475.

Authors

Tiago Pereira¹, Tiago Gameiro¹, José Pedro², Carlos Viegas², N M Fonseca Ferreira^{1

3}

Affiliations

¹ Polytechnic Institute of Coimbra, Coimbra Institute of Engineering, Rua Pedro Nunes-Quinta da Nora, 3030-199 Coimbra, Portugal.
² ADAI (Associação para o Desenvolvimento da Aerodinâmica Industrial), Department of Mechanical Engineering, University of Coimbra, Rua Luís Reis Santos, Pólo II, 3030-788 Coimbra, Portugal.
³ GECAD-Knowledge Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Engineering Institute of Porto (ISEP), Polytechnic Institute of Porto (IPP), 4200-465 Porto, Portugal.

Abstract

This article presents the development of a vision system designed to enhance the autonomous navigation capabilities of robots in complex forest environments. Leveraging RGBD and thermic cameras, specifically the Intel RealSense 435i and FLIR ADK, the system integrates diverse visual sensors with advanced image processing algorithms. This integration enables robots to make real-time decisions, recognize obstacles, and dynamically adjust their trajectories during operation. The article focuses on the architectural aspects of the system, emphasizing the role of sensors and the formulation of algorithms crucial for ensuring safety during robot navigation in challenging forest terrains. Additionally, the article discusses the training of two datasets specifically tailored to forest environments, aiming to evaluate their impact on autonomous navigation. Tests conducted in real forest conditions affirm the effectiveness of the developed vision system. The results underscore the system's pivotal contribution to the autonomous navigation of robots in forest environments.

Keywords: YOLOv5; autonomous mobile robot; image processing algorithms; object detection; vision system.

MeSH terms

Algorithms
Forestry
Image Processing, Computer-Assisted
Optical Devices*
Robotics* / methods

Grants and funding

The present work was funded through the projects E-Forest—Multi-agent Autonomous Electric Robotic Forest Management Framework, ref. POCI-01-0247-FEDER-047104, and F4F—Forest for Future, ref. CENTRO-08-5864-FSE-000031, co-financed by European Funds through the programs Compete 2020 and Portugal 2020, as well as by FCT (Fundação para a Ciência e a Tecnologia) under https://doi.org/10.54499/UIDP/00760/2020, project LA/P/0079/2020, https://doi.org/10.54499/LA/P/0079/2020, and https://doi.org/10.54499/UIDB/00760/2020 (accessed on 19 October 2023). Additionally, financial support was received from the Polytechnic Institute of Coimbra under the scope of Regulamento de Apoio à Publicação Científica dos Estudantes do Instituto Politécnico de Coimbra (Despacho No 5545/2020).