Intel RTF

Autonomous flight within a forest canopy represents a key challenge for generalized scene understanding on-board a future Unmanned Aerial Vehicle (UAV) platform. Here we present an approach for automatic trail navigation within such an environment that successfully generalizes across differing image resolutions - allowing UAV with varying sensor payload capabilities to operate equally in such challenging environmental conditions. Specifically, this work presents an optimized deep neural network architecture, capable of state-of-the-art performance across varying resolution aerial UAV imagery, that improves forest trail detection for UAV guidance even when using significantly low-resolution images that are representative of low-cost search and rescue capable UAV platforms.