See, L. ORCID: https://orcid.org/0000-0002-2665-7065, Perger, C., Dresel, C., Saad, M., Subash, A., Mora, B., Pascaud, M., Ligeard, F., Joshi, N., & Fritz, S. ORCID: https://orcid.org/0000-0003-0420-8549 (2019). LACO-Wiki Mobile: An Open Source Application for In situ DataCollection and Land Cover Validation. In: European Geosciences Union (EGU) General Assembly 2019, 7–12 April 2019, Vienna, Austria.
Preview |
Text
LACO-WikiMobile2019.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
LACO-Wiki Mobile is a smartphone application for in situ data collection, which is being developed as a freeand open source software project in the framework of the European Space Agency funded project CrowdVal. Themobile application works in tandem with the online land cover validation tool LACO-Wiki (https://www.laco-wiki.net), where users can generate a statistically robust sample for validation purposes. The land cover legend isread directly from the map uploaded to LACO-Wiki for generating the sample. The user must also indicate the typeof validation to be undertaken. Blind validation is where the user chooses the land cover type from a pre-definedlegend, plausibility validation is where users can see the land cover type from the map while on the ground andcan then choose to accept it as correct or not, while enhanced plausibility allows users to indicate the correct landcover type when it is incorrectly specified in the land cover map. This sample is then transferred to the mobileapplication, which directs users to specific locations on the ground to collect the validation data, i.e. operating in a‘directed’ mode. The user can see the locations of the points on the mobile phone, and as they approach a point, theuser is given the option to validate the land cover. These points can then be used in the accuracy assessment of theland cover map. The application also operates in ‘opportunistic’ mode, i.e. allowing the user to collect land coverat any location of their choice, e.g. while driving along a road. Such data collection can be useful for verifyingvisually interpreted samples or complementing training data for the development of land cover maps. Although theopen source application is still under development, a version will be openly accessible in github by the time of theconference.
Item Type: | Conference or Workshop Item (Lecture) |
---|---|
Research Programs: | Ecosystems Services and Management (ESM) |
Depositing User: | Luke Kirwan |
Date Deposited: | 16 Apr 2019 05:41 |
Last Modified: | 19 Oct 2022 05:01 |
URI: | https://pure.iiasa.ac.at/15860 |
Actions (login required)
View Item |