DOI | Resolve DOI: https://doi.org/10.1109/CCECE.2011.6030440 |
---|
Author | Search for: Minwalla, C.; Search for: Watters, K.; Search for: Thomas, P.; Search for: Hornsey, R.; Search for: Ellis, K.1; Search for: Jennings, S.1 |
---|
Affiliation | - National Research Council of Canada. Aerospace
|
---|
Format | Text, Article |
---|
Conference | 2011 Canadian Conference on Electrical and Computer Engineering, CCECE 2011, May 8-11, 2011, Niagara Falls, Ontario, Canada |
---|
Subject | clustering; distributed networks; feature descriptors; feature space; horizon extraction; morphological operations; pre-selected; prior measurement; region of interest; spurious cluster; collision avoidance; mathematical morphology; unmanned vehicles; distributed computer systems |
---|
Abstract | Extraction and utilization of the horizon contour is presented within the context of an optical collision avoidance instrument, comprised of individual nodes configured in a fixed-topology distributed network. The algorithm iterates between learning and application stages. Pixel neighbourhoods were classified into ground and sky regions using a vector of feature descriptors. The clusters in feature space were separated by a learnt minimal-error threshold, which was subsequently applied to the entire image, or a pre-selected region-of-interest aided by scenario-dependent constraints. Morphological operations reduced spurious clusters. The resultant contour was parametrically fitted to a polynomial for comparison to ground-truth. Adaptive operation allows inputs from prior measurements and external attitude information. © 2011 IEEE. |
---|
Publication date | 2011 |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
NPARC number | 21271254 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 6ebd57bd-461a-4664-b56f-9edad40b2c11 |
---|
Record created | 2014-03-24 |
---|
Record modified | 2020-04-21 |
---|