Download presentation
Presentation is loading. Please wait.
Published byAmos Dennis Modified over 10 years ago
1
A Fully Automated Approach to Classifying Urban Land Use and Cover from LiDAR, Multi-spectral Imagery, and Ancillary Data Jason Parent Qian Lei University of Connecticut
2
Land cover and land use Land cover: the physical material on the earth’s surface (e.g. water, grass, asphalt, etc.) Land use: the use of the land by humans (e.g. reservoir, agriculture, parking lot, etc.) Fundamental to landscape analyses and urban planning. 2
3
Opportunities and challenges for high resolution data Increasing availability of airborne light detection and ranging (LiDAR) and aerial imagery offers opportunities to study landscapes in great detail. Technically challenging to process… require lots of hard drive space. datasets must be divided into small subsets for processing. conventional algorithms not well suited to processing large numbers of subsets
4
Study objectives and justification Develop fully automated algorithm to classify high resolution (1-meter) land cover / land use which is applicable over large areas. no previously presented algorithm has been feasible to apply over large areas. Specifically, we developed python scripts with ArcGIS to… classify 1-meter land cover from LiDAR and multispectral data. infer land use from object geometry and spatial context of land cover features. 4
5
Study area Located in eastern Connecticut in the northeastern U.S. Semi-random stratified sample of 30 1x1 km tiles. Stratified by % impervious cover (according to Connecticut’s Changing Landscape land cover data). 5 0 - 33 33 - 66 66 – 100 % impervious 4800 km 2
6
Data LiDAR 2010 leaf-off fall acquisition Small footprint (44 cm) Near-infrared (1064 nm) > 1.5 pts/m 2 6 Aerial orthophotos 2012 leaf-off spring acquisition Blue, green, red, and NIR 0.3 meter resolution
7
Land cover classification rules 7 Land coverPrimary characteristics BuildingHeight > 2.5m; no ground returns Low impervious cover (low IC) Low NDVI; no returns 2 to 4.5 meters above ground Deciduous forestHeight > 3m; high NDVI Coniferous forestHeight > 3m; very high NDVI Medium vegetationHeight 0.5 to 3m; high NDVI WaterNo returns Riparian wetlandsLow reflectance in all bands; adjacent to water Low vegetationHigh return intensity Pixel- and object-based rules using structural and spectral properties
8
Land cover classification example 8 deciduous coniferous med. veg. low veg. water wetland building low IC
9
Land cover class accuracies ClassUser acc. (%)Prod. acc. (%) Water 9685 Building 9997 Low vegetation 9194 Wetland 2635 Low impervious 9391 Med. vegetation 6160 Coniferous trees 9076 Deciduous trees 9596 93% overall Kappa = 0.90 n = 3200 User accuracy: probability that a cell label is correct. Producer accuracy: probability that a cell is correctly labelled.
10
Land use classification rules 10 Building usePrimary characteristic Non-ResidentialLarge parking area; flat roof; large building size Multi-family residentialLarge parking area; narrow building width; similar building shapes Single family residentialSmall parking area; peak roof; small building size Parcel cadastral information not used because of limited availability. Object- and parcel- based rules using object shape/size and parcel land cover composition
11
Land use preliminary results deciduous coniferous med. veg. low veg. water wetland building low IC multi-family non-resid. single-family
12
Land use classification assessment 12 small commercial buildings misclassified as single family due to similar structural characteristics problems caused by mismatch between land cover and parcel data Qualitative assessment notes… 12
13
Conclusions and future work Land cover classification: Use of airborne LiDAR and multi-spectral data proved highly effective in classification of high resolution land cover. Developed fully automated algorithm that performs well over large area. 13 Land use classification: Use of building shape and context is promising Future work will develop rules for classification of… roads vs. parking lots urban vs. non-urban forest agriculture vs. turf
14
A Fully Automated Approach to Classifying Urban Land Use and Cover from LiDAR, Multi-spectral Imagery, and Ancillary Data Jason Parent Qian Lei University of Connecticut Questions?
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.