Lausanne tree canopy
收藏资源简介：
Tree canopy map of Lausanne at the 1m resolution obtained with DetecTree [1] from SWISSIMAGE 2016. Citation If you use this dataset, the source, i.e., SWISSIMAGE 2016 must be acknowledged. Additionally, a citation to DetecTree would certainly be appreciated. Note that DetecTree is based on the methods of Yang et al. [2], therefore it seems fair to reference their work too. An example citation in an academic paper might read as follows: The tree canopy dataset for the agglomeration of Lausanne has been obtained from the SWISSIMAGE 2016 aerial imagery dataset with the Python library DetecTree (Bosch, 2020), which is based on the approach of Yang et al. (2009). Technical specifications Source: SWISSIMAGE 2016 CRS: CH1903+/LV95 – Swiss CH1903+/LV95 (EPSG:2056) Resolution: 1m Extent: From file agglom-extent.shp. Obtained with the Urban footprinter. See the lausanne-agglom-extent repository for more details. Method: supervised learning (AdaBoost) with 4 classifiers on manually-generated ground truth masks for 7 training tiles (out of a total 499 tiles) of 512x512 pixels. See Yang et al. [2] for more details. Accuracy: 91.75%, estimated from a manually-generated ground truth mask for 1 tile of 512x512 pixels. Acknowledgements With the support of the École Polytechnique Fédérale de Lausanne (EPFL) References Bosch, M. (2020). Detectree: Tree detection from aerial imagery in Python. Journal of Open Source Software (under review). Yang, L., Wu, X., Praun, E., & Ma, X. (2009). Tree detection from aerial imagery. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 131-137). ACM.
本数据集为基于SWISSIMAGE 2016航空影像，通过DetecTree[1]生成的洛桑1米分辨率树冠覆盖图。 引用说明：若使用本数据集，需注明来源为SWISSIMAGE 2016。同时，恳请引用DetecTree相关文献。鉴于DetecTree基于Yang等人[2]的研究方法，因此一并引用其成果亦属合理。学术论文中的引用示例如下：本研究使用的洛桑都市区树冠数据集，源自SWISSIMAGE 2016航空影像数据集，通过Python库DetecTree（Bosch, 2020）生成，该工具基于Yang等人（2009）的方法开发。 技术规格： 来源：SWISSIMAGE 2016 坐标参考系统（CRS）：CH1903+/LV95——瑞士CH1903+/LV95（EPSG:2056） 分辨率：1米 覆盖范围：源自agglom-extent.shp文件，通过Urban footprinter生成，详细信息可参阅lausanne-agglom-extent代码仓库。 方法：采用基于自适应提升算法（AdaBoost）的监督学习框架，使用4个分类器，在总计499张512×512像素的瓦片中共选取7张作为训练集，训练数据采用人工生成的真值掩膜（ground truth mask）。更多细节可参阅Yang等人[2]的研究。 准确率：91.75%，基于1张512×512像素瓦片的人工生成真值掩膜估算得到。 致谢：感谢洛桑联邦理工学院（École Polytechnique Fédérale de Lausanne, EPFL）的支持。 参考文献： [1] Bosch, M. (2020). Detectree: Tree detection from aerial imagery in Python. *Journal of Open Source Software* (under review). [2] Yang, L., Wu, X., Praun, E., & Ma, X. (2009). Tree detection from aerial imagery. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 131-137). ACM.
