Multistream Convolutional Neural Network Fusion for Pixel-wise Classification of Peatland

EasyChair Preprint 10353

Abstract

Recently, Convolutional Neural Network (CNN) has shown higher performance than other machine learning methods for land classification. In this paper, we propose a CNN fusion architecture for peatland site type classification by combining multisource and multiresolution data. The data is acquired by optical and radar satellite remote sensing, airborne laser scanning data and multi-source forest inventory GIS datasets. Based on our data, we are dealing with the high-dimensional class-imbalanced dataset for solving pixel-wise classification of peatlands. To reduce the data dimension and find an optimal subset of inputs, we first applied the sequential feature selection method. Then, we proposed a window-based pixel classification approach based on the selected inputs. This approach can extract the spatial information around each training sample in a defined window region and produce a pixel-wise classfication map. Experiments are carried out for ecological classification of peatlands in Finland.

Keyphrases: Convolutional Neural Network, land cover classification, remote sensing, semantic segmentation

@booklet{EasyChair:10353,
  author    = {Fahimeh Farahnakian and Luca Zelioli and Timo Pitkänen and Jonne Pohjankukka and Maarit Middleton and Sakari Tuominen and Paavo Nevalainen and Jukka Heikkonen},
  title     = {Multistream Convolutional Neural Network Fusion for Pixel-wise Classification of Peatland},
  howpublished = {EasyChair Preprint 10353},
  year      = {EasyChair, 2023}}