Search results for "deep reinforcement learning"

showing 2 items of 2 documents

On the use of Deep Reinforcement Learning for Visual Tracking: a Survey

2021

This paper aims at highlighting cutting-edge research results in the field of visual tracking by deep reinforcement learning. Deep reinforcement learning (DRL) is an emerging area combining recent progress in deep and reinforcement learning. It is showing interesting results in the computer vision field and, recently, it has been applied to the visual tracking problem yielding to the rapid development of novel tracking strategies. After providing an introduction to reinforcement learning, this paper compares recent visual tracking approaches based on deep reinforcement learning. Analysis of the state-of-the-art suggests that reinforcement learning allows modeling varying parts of the tracki…

General Computer ScienceComputer scienceFeature extractionMachine learningcomputer.software_genreField (computer science)video-surveillanceMinimum bounding boxReinforcement learningGeneral Materials ScienceSettore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionideep reinforcement learningComputer vision machine learning video-surveillance deep reinforcement learning visual tracking.business.industryGeneral EngineeringTracking systemvisual trackingVisualizationActive appearance modelTK1-9971machine learningEye trackingComputer visionArtificial intelligenceElectrical engineering. Electronics. Nuclear engineeringbusinesscomputer
researchProduct

OMNI-DRL: Learning to Fly in Forests with Omnidirectional Images

2022

Perception is crucial for drone obstacle avoidance in complex, static, and unstructured outdoor environments. However, most navigation solutions based on Deep Reinforcement Learning (DRL) use limited Field-Of-View (FOV) images as input. In this paper, we demonstrate that omnidirectional images improve these methods. Thus, we provide a comparative benchmark of several visual modalities for navigation: ground truth depth, ground truth semantic segmentation, and RGB images. These exhaustive comparisons reveal that it is superior to use an omnidirectional camera to navigate with classical DRL methods. Finally, we show in two different virtual forest environments that adapting the convolution to…

Perception and sensingDeep Reinforcement LearningControl and Systems EngineeringMobile robots and vehicles[INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO]Omnidirectional sensorsLearning robot control
researchProduct