Maciel-Pearson, B.G. and Breckon, T.P. (2017) 'An optimised deep neural network approach for forest trail navigation for UAV operation within the forest canopy.', in UK-RAS Conference: 'Robots working for & among us' proceedings. , pp. 19-21.
Autonomous flight within a forest canopy represents a key challenge for generalised 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 generalises across differing image resolutions - allowing UAV with varying sensor payload capabilities to operate equally in such challenging environmental conditions. Specifically, this work presents an optimised deep neural network architecture, capable of stateof-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.
|Item Type:||Book chapter|
|Full text:||(AM) Accepted Manuscript|
Download PDF (2283Kb)
|Publisher Web site:||https://www.ukras.org/wp-content/uploads/2018/10/UK-RAS-CONFERENCE-PROCEEDINGS-2017-copy-1.pdf|
|Date accepted:||No date available|
|Date deposited:||06 December 2017|
|Date of first online publication:||December 2017|
|Date first made open access:||No date available|
Save or Share this output
|Look up in GoogleScholar|