two methods for semi-automated feature extraction
TRANSCRIPT
![Page 1: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/1.jpg)
Two methods forsemi-automated feature extraction
from lidar-derived DEMdesigned for cairn-fields and burial mounds
Benjamin ŠTULAR
![Page 2: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/2.jpg)
• The most time consuming part of the lidar data processing in archaeology is archaeological interpretation.
• This CANNOT be automated.
Methodological Considerations
![Page 3: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/3.jpg)
• Sometimes the transcription of archaeological features (“vectorization”) is time consuming.
• This CAN BE automated in certain cases.
Methodological Considerations
![Page 4: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/4.jpg)
• paths (Vletter 2014)
• pits (TRIER, PILØ 2015)
• kilns (Schneider et al. 2015)
• burial mounds and cairn-fields
Suitable Types of Archaeological Features
![Page 5: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/5.jpg)
Visoko
Knežak Slovenia
Case Studies
![Page 6: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/6.jpg)
MethodInput DEM
Extracting features
Binary values extraction
Shape and size detection
DEM analysis
![Page 7: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/7.jpg)
Input DEM
Extracting features
Binary values extraction
Shape and size detection
DEM analysis
Method
![Page 8: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/8.jpg)
Input DEM
DEM analysis
Extracting features
Binary values extraction
Shape and size detection
Method
![Page 9: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/9.jpg)
Input DEM
DEM analysis
Extracting features
Binary values extraction
Shape and size detection
Method
![Page 10: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/10.jpg)
Input DEM
DEM analysis
Extracting features
Binary values extraction
Shape and size detection
Method
![Page 11: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/11.jpg)
Input DEM
DEM analysis
Extracting features
Binary values extraction
Shape and size detection
Method
![Page 12: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/12.jpg)
Binary values extraction Shape and size detection Extracting features
![Page 13: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/13.jpg)
Input DEM
DEM analysis
Extracting features
Binary values extraction
Shape and size detection
Peakedness
Elevation residuals
Method
![Page 14: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/14.jpg)
Peakedness is defined as a degree of belonging to a peak. Value 1 defines the summit and it decreases towards 0 down the side
of the peak as it approaches the foot of a hill.
Peakedness
–Wood, J. 1996, The Geomorphological Characterisation of Digital Elevation Models. PhD Thesis, City University London
![Page 15: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/15.jpg)
![Page 16: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/16.jpg)
![Page 17: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/17.jpg)
Elevation Residuals
Elevation residuals are topographic indices derived from DEMs using spatial filtering techniques (i.e. a roving window of radius r is
centered on each grid cell in the DEM) to quantify the spatial pattern of topographic position or ruggedness within the context of a
surrounding area.
![Page 18: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/18.jpg)
Elevation Residuals
![Page 19: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/19.jpg)
Difference between the window center's elevation and its mean elevation; elevation
difference is normalized by:
D = size of the windowz0: elevation of the window center cell
zD: window mean elevation.
Deviation from mean elevation (DEV)
![Page 20: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/20.jpg)
• Mean of difference between height at centre and its quadratic approximation
• Standard deviation of difference between height at centre and its quadratic approximation
Quadratic Approximation
![Page 21: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/21.jpg)
DEV• single-scale• radius (circular)
Quadratic• multi-scale• cell (square)
Elevation Residuals
![Page 22: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/22.jpg)
DEV DQuadraticDeviation from mean elevation
r = 15 mStandard deviation (quadratic)
window size = 109
![Page 23: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/23.jpg)
Visoko
Knežak Slovenia
Case Studies
![Page 24: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/24.jpg)
1st Case Study:Visoko
![Page 25: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/25.jpg)
1st
![Page 26: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/26.jpg)
26
448 Cairns1st
![Page 27: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/27.jpg)
27
1st
448 Cairns
![Page 28: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/28.jpg)
28
1st
448 Cairns
Peakedness
![Page 29: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/29.jpg)
29
1st
448 Cairns
Deviation
![Page 30: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/30.jpg)
30
1st
448 Cairns
Quadratic -Mean
![Page 31: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/31.jpg)
1st
448 Cairns
Quadratic - StDev
![Page 32: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/32.jpg)
Results: 1st Case StudyManualdetection
PositiveNo.
Positive%
False positive
False positive
Peak 448 424 94,6 2527 5,96
Deviation 448 433 96,7 1588 3,58
Q - Mean 448 443 98,9 1244 2,81
Q - StDev 448 426 95,1 597 1,40
![Page 33: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/33.jpg)
Visoko
Knežak Slovenia
Case Studies
![Page 34: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/34.jpg)
2nd Case Study:Knežak
![Page 35: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/35.jpg)
2nd
![Page 36: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/36.jpg)
![Page 37: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/37.jpg)
Results: 2nd Case StudyManualdetection
PositiveNo.
Positive%
False positive
False positive
Peak 403 271 67,2 1793 6,62
Deviation 403 350 86,8 2444 6,98
Q -Mean 403 304 75,4 1042 3,43
Q - StDev 403 243 60,3 684 2,81
![Page 38: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/38.jpg)
Take-Home Message
![Page 39: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/39.jpg)
Workflow (cca. 500 cairns)
• Manual point-detection of cairns (½ hour)• Semi-automatic feature extraction (1 hour or
more*)• Manual “desk-based-truthing” (½ hour)• Data extraction, e.g. size, shape, height
(minutes)
![Page 40: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/40.jpg)
TOTAL: 2 ¼ hours*
Total manual: 5-8 hours
![Page 41: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/41.jpg)
Makes sense?
98,9% / 1,4 x 86,8% / 2,8 x
![Page 42: Two methods for semi-automated feature extraction](https://reader038.vdocuments.net/reader038/viewer/2022110108/58f15fa41a28ab6d4c8b4605/html5/thumbnails/42.jpg)
Help with feature extraction - YES
Archaeological interpretation - NO
Semi-automated Feature Extraction