TY - GEN
T1 - Road network identification by means of the Hough transform
AU - Salerno, E.
AU - Singh, T.
AU - Singla, P.
AU - Scalzo, M.
AU - Bubalo, A.
AU - Alford, M.
AU - Jones, E.
PY - 2012
Y1 - 2012
N2 - Knowledge of roadmaps can provide an indication of how information, materials, and people move. Historically, maps have equated to a static look at a network that contains only established and sanctioned routes. Even now, Google map images and hand held Global Positioning System (GPS) units represent a somewhat static look at roadmaps, requiring either recapturing images or manually updating units. In order to have a more up to date, information rich representation of transportation networks or roadmaps this effort has explored the use of movement information, specifically Ground Moving Target Indicator (GMTI) data, for accurately estimating the topology of these networks. This data lends itself to being able to provide not only a single snapshot of the topology of the network, but to provide additional information concerning densities and direction of movement through the network. The novel approach employed for synthesizing the data into a complete estimate of the network is through the use of Hough transforms to identify line segments which collectively represent the road network. Then the total least squares is used to characterize the uncertainty associated with this line segment representation of the road network.
AB - Knowledge of roadmaps can provide an indication of how information, materials, and people move. Historically, maps have equated to a static look at a network that contains only established and sanctioned routes. Even now, Google map images and hand held Global Positioning System (GPS) units represent a somewhat static look at roadmaps, requiring either recapturing images or manually updating units. In order to have a more up to date, information rich representation of transportation networks or roadmaps this effort has explored the use of movement information, specifically Ground Moving Target Indicator (GMTI) data, for accurately estimating the topology of these networks. This data lends itself to being able to provide not only a single snapshot of the topology of the network, but to provide additional information concerning densities and direction of movement through the network. The novel approach employed for synthesizing the data into a complete estimate of the network is through the use of Hough transforms to identify line segments which collectively represent the road network. Then the total least squares is used to characterize the uncertainty associated with this line segment representation of the road network.
UR - http://www.scopus.com/inward/record.url?scp=84869399817&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84869399817&partnerID=8YFLogxK
U2 - 10.1109/SDF.2012.6327917
DO - 10.1109/SDF.2012.6327917
M3 - Conference contribution
AN - SCOPUS:84869399817
SN - 9781467330114
T3 - 2012 Workshop on Sensor Data Fusion: Trends, Solutions, Applications, SDF 2012
SP - 105
EP - 110
BT - 2012 Workshop on Sensor Data Fusion
T2 - 2012 Workshop on Sensor Data Fusion: Trends, Solutions, Applications, SDF 2012
Y2 - 4 September 2012 through 6 September 2012
ER -