Val Noronha University of California, Santa Barbara Centerline Extraction and Road Condition
N C R S T Asset Management #2 Why centerlines? Accurate (x,y) for ITS precision applications location based services Accurate length for compatibility with linear referencing
N C R S T Asset Management #3 Centerline Applications
N C R S T Asset Management #4 Approaches to deriving centerlines Convert old maps Convert new maps, integrate CAD plans Photogrammetry GPS
N C R S T Asset Management #5 Outline Centerlines from GPS Centerlines from hyperspectral imagery Other uses of hyperspectral analysis: early findings on road condition
N C R S T Asset Management #6 GPS for Hwy Ops Hi end Lo end
N C R S T Asset Management #7 Low-end GPS units $250$195$150
N C R S T Asset Management #8 Lane Discrimination Test
N C R S T Asset Management #9 Lane Discrimination Test
N C R S T Asset Management #10 Lane Discrimination Test
N C R S T Asset Management #11 The one to beat … $150 at CompUSA Convenience Price Can RS beat this?
N C R S T Asset Management #12 Remote sensing centerline strategy Find pixels that represent road … hyperspectral library Detect linear patterns, form centerlines Attach legacy attributes Compare costs and benefits
N C R S T Asset Management #13 3-step hyperspectral process MESMAQ-treeVectorize Additional steps: clean, revisit, conflate
Easy Street New neighborhood Little or no foliage overhang Vehicles in garage/driveway
Not so easy Repairs and surface coats Paint stripes Shadows Parked vehicles Foliage overhangs
N C R S T Asset Management #16 Multispectral sensors Reflectance Infra-red Wavebands originally optimized to sense health of Soviet wheat
N C R S T Asset Management #17 Hyperspectral sensors Reflectance … 2400 Each pixel is characterized by 200+ reflectance values
N C R S T Asset Management #18 Hyperspectral road identification Materials have unique hyperspectral signatures, based on chemistry, texture, etc What are the principal materials found in roads … what are their signatures? Study them at close range in the field (handheld spectrometer) Then see if you can detect the signatures from imagery (4m airborne AVIRIS by JPL)
N C R S T Asset Management #19 ASD full range spectrometer Field Spectrometer
N C R S T Asset Management #20 499 roof 179 road 66 sidewalk 56 parking lot 40 road paint 37 vegetation Field Spectra Collected 47 non-photosynthetic vegetation (bark, dead wood) 27 tennis court 88 bare soil and beach 50 miscellaneous other urban spectra
N C R S T Asset Management #21 Concretes
Concrete roof Parking lot Asphalt road
N C R S T Asset Management #24 Step 1 result MESMA
N C R S T Asset Management #26 Step 2 result Q-tree
N C R S T Asset Management #27 Step 3 result Vectorize
N C R S T Asset Management #28 Step 3 result
N C R S T Asset Management #29 Where it Fits in the Big Picture Global scale — Logistics Local scale, esp urban — Asset mgmt
N C R S T Asset Management #30 Road condition
N C R S T Asset Management #31 Field Data Records
N C R S T Asset Management #32 Surface Treatments
N C R S T Asset Management #33 Age
N C R S T Asset Management #34 Surface “Quality”
N C R S T Asset Management #35 In conclusion … RS for centerlines a fully automated solution is not yet here potential for the future RS for road condition much promise
1