Regional snow-avalanche detection using object-based image analysis of near-infrared aerial imagery

Korzeniowska, Karolina; Bühler, Yves; Marty, Mauro; Korup, Oliver

doi:https://doi.org/10.5194/nhess-17-1823-2017

Articles | Volume 17, issue 10

https://doi.org/10.5194/nhess-17-1823-2017

© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.

https://doi.org/10.5194/nhess-17-1823-2017

© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.

Articles | Volume 17, issue 10

Research article

|

23 Oct 2017

Research article |

| 23 Oct 2017

Regional snow-avalanche detection using object-based image analysis of near-infrared aerial imagery

Karolina Korzeniowska, Yves Bühler, Mauro Marty, and Oliver Korup

Download

Final revised paper (published on 23 Oct 2017)
Preprint (discussion started on 10 Apr 2017)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Review of the manuscript by K. Korzeniowska et al.', Anonymous Referee #1, 24 May 2017
- AC1: 'Response to reviewer comments', Karolina Korzeniowska, 10 Aug 2017
RC2: 'Review nhess-2017-120', Olivier Jaquet, 08 Aug 2017
- AC2: 'Response to reviewer comments', Karolina Korzeniowska, 10 Aug 2017

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

ED: Publish as is (24 Aug 2017) by Rosa Lasaponara

AR by Karolina Korzeniowska on behalf of the Authors (30 Aug 2017) Author's response Manuscript

Short summary

In this study, we have focused on automatically detecting avalanches and classifying them into release zones, tracks, and run-out zones based on aerial imagery using an object-based image analysis (OBIA) approach. We compared the results with manually mapped avalanche polygons, and obtained a user’s accuracy of > 0.9 and a Cohen’s kappa of 0.79–0.85. Testing the method for a larger area of 226.3 km², we estimated producer’s and user’s accuracies of 0.61 and 0.78, respectively.