Tree Detection from Aerial Imagery. Yang, L., Wu, X., Praun, E., & Ma, X. In pages 131-137. doi abstract bibtex We propose an automatic approach to tree detection from aerial imagery. First a pixel-level classifier is trained to assign a (tree, non-tree) label to each pixel in an aerial image. The pixel-level classification is then refined by a partitioning algorithm to a clean image segmentation of tree and non-tree regions. Based on the refined segmentation results, we adopt template matching followed by greedy selection to locate individual tree crowns. As training a pixel-level classifier requires manual generation of ground-truth tree masks, we propose methods for automatic model and training data selection to minimize the manual work and scale the algorithm to the entire globe. We test the algorithm on thousands of production aerial images across different countries. We demonstrate high-quality tree detection results as well as good scalability of the proposed approach.
@inproceedings{ yan09b,
crossref = {acmgis2009},
author = {Lin Yang and Xiaqing Wu and Emil Praun and Xiaoxu Ma},
title = {Tree Detection from Aerial Imagery},
doi = {10.1145/1653771.1653792},
pages = {131-137},
abstract = {We propose an automatic approach to tree detection from aerial imagery. First a pixel-level classifier is trained to assign a (tree, non-tree) label to each pixel in an aerial image. The pixel-level classification is then refined by a partitioning algorithm to a clean image segmentation of tree and non-tree regions. Based on the refined segmentation results, we adopt template matching followed by greedy selection to locate individual tree crowns. As training a pixel-level classifier requires manual generation of ground-truth tree masks, we propose methods for automatic model and training data selection to minimize the manual work and scale the algorithm to the entire globe. We test the algorithm on thousands of production aerial images across different countries. We demonstrate high-quality tree detection results as well as good scalability of the proposed approach.}
}
Downloads: 0
{"_id":{"_str":"53ff72c27c90ec6e130013c3"},"__v":0,"authorIDs":[],"author_short":["Yang, L.","Wu, X.","Praun, E.","Ma, X."],"bibbaseid":"yang-wu-praun-ma-treedetectionfromaerialimagery","bibdata":{"downloads":0,"role":"author","bibbaseid":"yang-wu-praun-ma-treedetectionfromaerialimagery","type":"inproceedings","title":"Tree Detection from Aerial Imagery","pages":"131-137","key":"yan09b","id":"yan09b","doi":"10.1145/1653771.1653792","crossref":"acmgis2009","bibtype":"inproceedings","bibtex":"@inproceedings{ yan09b,\n crossref = {acmgis2009},\n author = {Lin Yang and Xiaqing Wu and Emil Praun and Xiaoxu Ma},\n title = {Tree Detection from Aerial Imagery},\n doi = {10.1145/1653771.1653792},\n pages = {131-137},\n abstract = {We propose an automatic approach to tree detection from aerial imagery. First a pixel-level classifier is trained to assign a (tree, non-tree) label to each pixel in an aerial image. The pixel-level classification is then refined by a partitioning algorithm to a clean image segmentation of tree and non-tree regions. Based on the refined segmentation results, we adopt template matching followed by greedy selection to locate individual tree crowns. As training a pixel-level classifier requires manual generation of ground-truth tree masks, we propose methods for automatic model and training data selection to minimize the manual work and scale the algorithm to the entire globe. We test the algorithm on thousands of production aerial images across different countries. We demonstrate high-quality tree detection results as well as good scalability of the proposed approach.}\n}","author_short":["Yang, L.","Wu, X.","Praun, E.","Ma, X."],"author":["Yang, Lin","Wu, Xiaqing","Praun, Emil","Ma, Xiaoxu"],"abstract":"We propose an automatic approach to tree detection from aerial imagery. First a pixel-level classifier is trained to assign a (tree, non-tree) label to each pixel in an aerial image. The pixel-level classification is then refined by a partitioning algorithm to a clean image segmentation of tree and non-tree regions. Based on the refined segmentation results, we adopt template matching followed by greedy selection to locate individual tree crowns. As training a pixel-level classifier requires manual generation of ground-truth tree masks, we propose methods for automatic model and training data selection to minimize the manual work and scale the algorithm to the entire globe. We test the algorithm on thousands of production aerial images across different countries. We demonstrate high-quality tree detection results as well as good scalability of the proposed approach."},"bibtype":"inproceedings","biburl":"http://dret.net/biblio/dret.bib","creationDate":"2014-08-28T18:19:46.671Z","downloads":0,"keywords":[],"search_terms":["tree","detection","aerial","imagery","yang","wu","praun","ma"],"title":"Tree Detection from Aerial Imagery","year":null,"dataSources":["mL7NKvaepNEWFcMvG"]}