Schleifscheiben - diamant-schnell abrichten mit dem LACH ...
R I T Rochester Institute of Technology Geometric Scene Reconstruction Using 3-D Point Cloud Data...
-
Upload
lauren-bailey -
Category
Documents
-
view
221 -
download
2
Transcript of R I T Rochester Institute of Technology Geometric Scene Reconstruction Using 3-D Point Cloud Data...
R I T Rochester Institute of Technology
Geometric Scene Geometric Scene Reconstruction Using 3-D Reconstruction Using 3-D
Point Cloud DataPoint Cloud Data
Research Plan
Feng Li and Steve Lach
Advanced Digital Image Processing: SIMG786
April 6, 2006
R I T Rochester Institute of Technology2
OverviewOverview
•LIDAR Basics and Terminology
•Purpose/Overview
•Research Overview
•Approach
•Schedule
•Summary
R I T Rochester Institute of Technology3
LIDAR BasicsLIDAR Basics
•LIDAR: LIght Detection And Ranging
•LIDAR works like a radar system except
it uses light instead of radio frequencies GPS: measure LIDAR sensor in the air
IMU (Inertial Measuring Unit): measure the roll, pitch and heading of the aircraft
LIDAR sensor: measure angular orientation of laser pulse; measure time-interval between light reflects off the object and returns to the sensor
www.ncfloodmaps.com
R I T Rochester Institute of Technology4
LIDAR Basics - ContinuedLIDAR Basics - Continued
• Time of flight system produces 3D spatial
imagery
– Range resolution: ability to resolve two separate objects in
depth
– More sophisticated techniques discussed elsewhere
– First return, interpolated DEM (range-based) is most
common data set produced by commercial vendors
• Intensity image
yields additional
information281989.740360 4773791.856553 134.944699 187
281990.740358 4773791.854912 134.971924 187
281991.740357 4773791.853271 135.253379 187
281992.740356 4773791.851630 136.049035 187
281993.740354 4773791.849989 136.452911 187
R I T Rochester Institute of Technology5
Some Additional TerminologySome Additional Terminology
Our Terminology
• Point Cloud – Set of irregularly spaced 3D points
• Range Image - 3D points at regular locations on an x, y grid
• Digital Elevation Model (DEM)/Digital Surface Model (DSM) – Blanket over scene
• Digital Terrain Model (DTM) – Bare Earth (remove trees, buildings, etc)
• Voids – Portions of a DEM where no elevation data is available
Image courtesy of Ma, “BUILDING MODEL RECONSTRUCTION FROM LIDAR DATA AND AERIAL PHOTOGRAPHS”, PhD
Dissertation, OSU, 2004.
R I T Rochester Institute of Technology6
Underlying ProblemUnderlying Problem
•Through courses, we have learned to
process regularly-sampled images
•However, we have a much smaller toolset
for processing point cloud data
•We will develop tools for this new “image”
type, and apply to data from RIT LIDAR
collect
R I T Rochester Institute of Technology7
Three 3D Working EnvironmentsThree 3D Working Environments
• Range Image (Interpolate irregularly distributed pointsto a regular grid)
– Traditional, Somewhat Simple
– Cost: loss information or lead to biases
(Mixture of points from different categories)
• Point Cloud– Accurate
– Difficult to Process; Can not use standard image processing routines
(median filter, FFT)
• Combination of the Two– Use Range Image to classify regions
– Use Point Cloud to produce accurate results
R I T Rochester Institute of Technology8
Purpose of ProjectPurpose of Project
• Use 3-D Point Data to geometrically reconstruct a scene
• Goal: Determine Appropriate Ways to:
1. Efficiently handle the data (relationship between the points) 2. Operate on the data (filter, interpolate, etc) 3. Extract objects (buildings and trees) 4. Reconstruct objects (buildings and trees) Focus will primarily be on Item #4, Other items will be done as required to support this task (additional work if schedule permits)
R I T Rochester Institute of Technology9
Research OverviewResearch Overview
Identify GroundPoints
Create GeometricTerrain Model
Classify Non-Ground points
Create SpectralTerrain Model
Overlay SpectralTextures
Create GeometricObject Models
Learn to Process3D Data
R I T Rochester Institute of Technology10
Approach: Goal #1 (Data Approach: Goal #1 (Data Handling)Handling)
•Use range image to isolate groupings of
points belonging to a single object
•Pixelize or Voxelize the data for each object
(unsure which is preferable)
•Add extra data fields (i.e. X, Y, Z, I, Obj,
Vox, Sub Vox, Neighbors, Distances,
Directions)
•Initial Processing Likely to be
computationally intense
R I T Rochester Institute of Technology11
ApproachApproach: Goal #2 (Point Cloud : Goal #2 (Point Cloud Filtering)Filtering)
•Use sliding window approaches – functional
relationships based on distances, not
discrete kernel
•Anticipate creating Median, Mean (low-
pass), Weighted Mean, Differencing (high-
pass)
R I T Rochester Institute of Technology12
ApproachApproach: Goal #3 (Object : Goal #3 (Object Extraction)Extraction)
3 Steps in achieving this goal:
• First Step: Generate range image - may need to
work on interpolation techniques, right now will
use pre-packaged routine
R I T Rochester Institute of Technology13
ApproachApproach: Goal #3 (Object : Goal #3 (Object Extraction)Extraction)
• Second Step: Use range image to generate DTM via
Median Filtering and High-Passs Filtering
R I T Rochester Institute of Technology14
Generating DTMGenerating DTM
LIDAR Point DataInitial
Data Filtering
Remove Non-ground pixels
FinalData Filtering
• Thresholding above Global Estimated Ground Polynomial
• Thresholding above Local Estimated Ground Polynomial
• Threshold along rows/columns
• Modified Median/Thresholding
• High-Pass Filtering (Gradient, Laplacian)
• Nearest Neighbor, Triangular, Bilinear…
• Weighted value techniques based on Delaunay triangulation, Natural Neighbor, etc…
• Kriging
Identify Non-ground pixels
Interpolate to Grid
Interpolate AcrossRemoved Points
R I T Rochester Institute of Technology15
Result of Median FilterResult of Median Filter
Baseline Range Image (2m Centers)
Flagged Points with Modified Median Filter (Center 10m,
Outer 40m)
R I T Rochester Institute of Technology16
Result of Median Filter Plus HP Result of Median Filter Plus HP FilterFilter
Baseline Range Image Flagged Points with Modified Median Filter and High Pass
Filter
R I T Rochester Institute of Technology17
High Points RemovedHigh Points Removed
Baseline Range Image Scatter Plot with Flagged Points Removed
R I T Rochester Institute of Technology18
Interpolation and Low-Pass Filtering Interpolation and Low-Pass Filtering (Final DTM)(Final DTM)
Baseline Range Image (2m Centers)
Final Terrain Model after re-interpolation and
smoothing
R I T Rochester Institute of Technology19
Object Extraction: Segmenting Buildings Object Extraction: Segmenting Buildings and Treesand Trees
Building/Tree Map using only morphological techniques
• Third Step: Differentiate High Points
• Can continue to work with range image, or go back to Point Cloud
• A host of features available:
• Length of edges
• Homogeneity of height (HP Filtering)
• Plane matching
• Morphological Techniques
• Exploitation of co-registered Spectral Image
R I T Rochester Institute of Technology20
ApproachApproach: Goal #4 (Object : Goal #4 (Object Reconstruction)Reconstruction)
Trees
• Use blurred Lidar Height Information
• Find local maxima to identify potential tree centers
• Use “Circle” functions at various scales to isolate features with high radial symmetry (Correlation Technique); confirm tree location and determine spread
• Use results to pick tree from library of objects
• This technique will also help extract cylindrical features for use in building reconstruction
Tree Extraction Algorithm
* Ref Gray et al: “Scene Construction Methodologies and Techniques for Simulating Forest Areas”, 11th Annual Ground Targets Modeling and Validation Conference, 2000.
R I T Rochester Institute of Technology21
ApproachApproach: Goal #4 (Object : Goal #4 (Object Reconstruction)Reconstruction)
Buildings
• Method 1: Use range image and corner detector to find critical vertices (fairly simple)
• Method 2: Planar Patch Extraction, find edges via plane intersections (More Accurate) – Anticipate significant effort here (Ref: Schenk, “Detecting Planes by Hough Transform”)
• Method 3: Rectangular (and 3D Primatives) Reconstruction:
Images Courtesy of Morgan and Habib, “Interpolation of Lidar Data and Automatic Building Extraction”, ASPRS Annual Conf,
2002
and
Haala, “Laser Data for Virtual Landscape Generation”, IAPRS, Vol 32, 1999
R I T Rochester Institute of Technology22
Planar Feature Planar Feature Extraction/ReconstructionExtraction/Reconstruction
• Several techniques can be used to detect planar determine
parameters
– Segment images of roof gradient directions
– Hough-based techniques
– Clustering (based on the meshes of a Delaunay triangulation) – we will explore this
first
R I T Rochester Institute of Technology23
ScheduleSchedule
Literature Search
Data Handling
Operating on Data
Extracting Objects
Simple Processing on Range Image
Use of Height Features for Segmentation
Reconstructing Objects
Range Image Techniques
Planar Extraction Techniques
Rectangular Fitting Technique
Reports
4/2 4/9 4/16 4/23 4/30 5/7 5/14 5/21
R I T Rochester Institute of Technology24
SummarySummary
• We will be using 3-D Point Data to
geometrically reconstruct a desired scene
• Basic technique is to use range image to
isolate points, then process point cloud to
do the reconstruction
• Focus on feature extraction rather than
point analysis