Zhaoying Wei

GEOG 8350

Comparison of Land use

detection in Niagara Falls using

LIDAR and orthoimagery

Outlines

Goal

Area of Interest

Data

Method and Result

Conclusion and

Future Work

Land use

detection

orthophoto

LIDAR

Goal

AOI

Data

Data

• point cloud Lidar data

• orthoimagery

Tools

•LAStools

•Lidar Analyst

•ArcGIS 10.0

• ArcGIS 10.0

• Erdas

• ENVI

Method (LIDAR)

Extract Bare earth

• strip the existing classes from the LAS file and

set the coordinate system and projection (noclass.las)

• classify the ground points (ground.las)

• create the only ground points (groundonly.las)

• generate DEM of groundonly .las

• extract bare earth DEM from groundonly DEM

Method (LIDAR)

From

groundonly

From raw LAS

Extract Bare earth

Method (LIDAR)

Extract buildings footprints

• compute the height above the ground• Classify trees and Buidlings (treeNbuilding.las)

• generate new bare earth for building and trees

extraction

Extract building footprints• point cloud building extraction

Method (LIDAR)

Extract building footprints• edit building

Method (LIDAR)

Before AfterRemove building

Add to building

Merge building

Before After

Extract building footprints

Method (LIDAR)

Create new building and close holes

Final

footprints

Extract tree• point cloud tree extraction

• visually edit forests and trees

Method (LIDAR)

Method (Orthophoto)

Supervised classification• Create the signature file and AOI for each class

• Combine the signature file of all classes

Method (Orthophoto)

Reclassify• manually digitize AOI

• assign new class value to water

Conclusion

LIDAR:

• vector results consistent with real

terrains

• limited classes

Orthoimage

• numerous classes

• low quality and accuracy, water

Future work

Measure accuracy of the classification result

improve the quality of signature

better water detection

object-based classification

Fusion of LIDAR and aerial image