Embedded Vision for Self-Driving on Forest Roads
This work addresses the problem of monitoring deforestation and damage on forest roads for environmental protection, but it is incremental as it applies existing methods to a specific domain.
The paper tackles autonomous navigation on forest roads for environmental inspection by developing an embedded vision system that combines a multi-task DNN for segmentation with handcrafted features for SLAM, achieving real-time performance on an NVIDIA AGX Xavier board.
Forest roads in Romania are unique natural wildlife sites used for recreation by countless tourists. In order to protect and maintain these roads, we propose RovisLab AMTU (Autonomous Mobile Test Unit), which is a robotic system designed to autonomously navigate off-road terrain and inspect if any deforestation or damage occurred along tracked route. AMTU's core component is its embedded vision module, optimized for real-time environment perception. For achieving a high computation speed, we use a learning system to train a multi-task Deep Neural Network (DNN) for scene and instance segmentation of objects, while the keypoints required for simultaneous localization and mapping are calculated using a handcrafted FAST feature detector and the Lucas-Kanade tracking algorithm. Both the DNN and the handcrafted backbone are run in parallel on the GPU of an NVIDIA AGX Xavier board. We show experimental results on the test track of our research facility.