Feature Investigation for Large Scale Urban Detection Using Landsat Imagery

Proceedings

Esch, Thomas²  Adam, Fathalrahman³  Datcu, Mihai⁴ 

[1] Available online: https://sciforum.net/conference/ecrs-2.;Author to whom correspondence should be addressed.;Earth Observation Center, German Aerospace Center(DLR), Münchner Str. 20, 82234 Weßling , Germany;Presented at the 2nd International Electronic Conference on Remote Sensing, 22 March–5 April 2018

关键词: Urban detection;    large scale classification;    feature selection;    L;    sat;   

DOI  :  10.3390/ecrs-2-05162

学科分类：社会科学、人文和艺术（综合）

来源: mdpi

【 摘 要 】

Many works dealing with the problem of urban detection at large scale have been published, but very little attention has been paid to the investigation of the features’ relative importance. Feature selection is known to be an NP-hard problem, which means it can not be solved in polynomial time, but there are many heuristics suggested to approximate the solution. In this paper, a survey of the features used for large scale urban detection is presented, then the question of finding the best subset of features is investigated. Using Landsat scenes of five urban areas, most common features were extracted to represent the full feature set. Employing mutual information based ranking methods, Support Vector Machine (SVM) and Random Forest feature ranking, an importance score was assigned to each feature by each method. To aggregate the individual rankings of features, a two stage voting scheme was implemented to choose a subset of size N as the most relevant features. The most important features for all five cities taken together were listed.

【 授权许可】

CC BY