OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images
International audience; Spherical cameras and the latest image processing techniques open up new horizons. In particular, methods based on Convolutional Neural Networks (CNNs) now give excellent results for optical flow estimation on perspective images. However, these approaches are highly dependent on their architectures and training datasets. This paper proposes to benefit from years of improvement in perspective images optical flow estimation and to apply it to omnidirectional ones without training on new datasets. Our network, OmniFlowNet, is built on a CNN specialized in perspective images. Its convolution operation is adapted to be consistent with the equirectangular projection. Teste…
Deep Reinforcement Learning with Omnidirectional Images: application to UAV Navigation in Forests
Deep Reinforcement Learning (DRL) is highly efficient for solving complex tasks such as drone obstacle avoidance using cameras. However, these methods are often limited by the camera perception capabilities. In this paper, we demonstrate that point-goal navigation performances can be improved by using cameras with a wider Field-Of-View (FOV). To this end, we present a DRL solution based on equirectangular images and demonstrates its relevance, especially compared to its perspective version. Several visual modalities are compared: ground truth depth, RGB, and depth directly estimated from these 360°R GB images using Deep Learning methods. Next, we propose a spherical adaptation to take into …
OMNI-DRL: Learning to Fly in Forests with Omnidirectional Images
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…