Embedded Vision for Self-Driving on Forest Roads

05/27/2021

∙

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.

READ FULL TEXT

Embedded Vision for Self-Driving on Forest Roads

Human perception in computer vision

Real-time Scene Segmentation Using a Light Deep Neural Network Architecture for Autonomous Robot Navigation on Construction Sites

ClusterNet: Instance Segmentation in RGB-D Images

Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards

Deep Neural Network-based Cooperative Visual Tracking through Multiple Micro Aerial Vehicles

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge

Broad Area Search and Detection of Surface-to-Air Missile Sites Using Spatial Fusion of Component Object Detections from Deep Neural Networks

Embedded Vision for Self-Driving on Forest Roads

Related Research

Human perception in computer vision

Real-time Scene Segmentation Using a Light Deep Neural Network Architecture for Autonomous Robot Navigation on Construction Sites

ClusterNet: Instance Segmentation in RGB-D Images

Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards

Deep Neural Network-based Cooperative Visual Tracking through Multiple Micro Aerial Vehicles

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge

Broad Area Search and Detection of Surface-to-Air Missile Sites Using Spatial Fusion of Component Object Detections from Deep Neural Networks