TY - JOUR

T1 - Adaptive Multiscale Superpixel Embedding Convolutional Neural Network for Land Use Classification

AU - Zhang, Huaizhong

AU - Altham, Callum

AU - Trovati, Marcello

AU - Zhang, Ce

AU - Rolland, Iain

AU - Lawal, Lanre

AU - Wegbu, Dozien

AU - Ajienka, Nemitari

PY - 2022/9/5

Y1 - 2022/9/5

N2 - Currently, a large number of remote sensing images with different resolutions are available for Earth observation and land monitoring, which are inevitably demanding intelligent analysis techniques for accurately identifying and classifying land use (LU). This article proposes an adaptive multiscale superpixel embedding convolutional neural network architecture (AMUSE-CNN) for tackling LU classification. Initially, the images are parsed via the superpixel representation so that the object-based analysis (via a superpixel embedding convolutional neural network scheme) can be carried out with the pixel context and neighborhood information. Then, a multiscale convolutional neural network (MS-CNN) is proposed to classify the superpixel-based images by identifying object features across a variety of scales simultaneously, in which multiple window sizes are used to fit to the various geometries of different LU classes. Furthermore, a proposed adaptive strategy is applied to best exert the classification capability of the MS-CNN. Subsequently, two modules are developed to fully implement the AMUSE-CNN architecture. More specifically, Module I is to determine the most suitable classes for each window size (scale) by applying majority voting to a series of MS-CNNs Module II carries out the classification of the classes identified in Module I for the given scale used in the MS-CNN and, therefore, complete the LU classification of the entire classes. The proposed AMUSE-CNN architecture is both quantitatively and qualitatively validated using remote sensing data collected from two cities, Kano and Lagos in Nigeria, due to the spatially complex LU distribution. Experimental results show the superior performance of our approach against several state-of-the-art techniques.

AB - Currently, a large number of remote sensing images with different resolutions are available for Earth observation and land monitoring, which are inevitably demanding intelligent analysis techniques for accurately identifying and classifying land use (LU). This article proposes an adaptive multiscale superpixel embedding convolutional neural network architecture (AMUSE-CNN) for tackling LU classification. Initially, the images are parsed via the superpixel representation so that the object-based analysis (via a superpixel embedding convolutional neural network scheme) can be carried out with the pixel context and neighborhood information. Then, a multiscale convolutional neural network (MS-CNN) is proposed to classify the superpixel-based images by identifying object features across a variety of scales simultaneously, in which multiple window sizes are used to fit to the various geometries of different LU classes. Furthermore, a proposed adaptive strategy is applied to best exert the classification capability of the MS-CNN. Subsequently, two modules are developed to fully implement the AMUSE-CNN architecture. More specifically, Module I is to determine the most suitable classes for each window size (scale) by applying majority voting to a series of MS-CNNs Module II carries out the classification of the classes identified in Module I for the given scale used in the MS-CNN and, therefore, complete the LU classification of the entire classes. The proposed AMUSE-CNN architecture is both quantitatively and qualitatively validated using remote sensing data collected from two cities, Kano and Lagos in Nigeria, due to the spatially complex LU distribution. Experimental results show the superior performance of our approach against several state-of-the-art techniques.

KW - Convolutional neural network (CNN)

KW - land use (LU) classification

KW - superpixel embedding CNN

KW - very fine spatial resolution remotely sensed imagery

U2 - 10.1109/JSTARS.2022.3203234

DO - 10.1109/JSTARS.2022.3203234

M3 - Journal article

VL - 15

SP - 7631

EP - 7642

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

ER -