eduzhai > Applied Sciences > Engineering >

Land Use and Land Cover Classification using a Human Group based Particle Swarm Optimization Algorithm with a LSTM classifier on hybrid-pre-processing Remote Sensing Images

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 21 pages

Abstract: Land use and land cover (LULC) classification using remote sensing imageryplays a vital role in many environment modeling and land use inventories. Inthis study, a hybrid feature optimization algorithm along with a deep learningclassifier is proposed to improve the performance of LULC classification,helping to predict wildlife habitat, deteriorating environmental quality,haphazard, etc. LULC classification is assessed using Sat 4, Sat 6 and Eurosatdatasets. After the selection of remote sensing images, normalization andhistogram equalization methods are used to improve the quality of the images.Then, a hybrid optimization is accomplished by using the Local Gabor BinaryPattern Histogram Sequence (LGBPHS), the Histogram of Oriented Gradient (HOG)and Haralick texture features, for the feature extraction from the selectedimages. The benefits of this hybrid optimization are a high discriminativepower and invariance to color and grayscale images. Next, a Human Group basedParticle Swarm Optimization (PSO) algorithm is applied to select the optimalfeatures, whose benefits are fast convergence rate and easy to implement. Afterselecting the optimal feature values, a Long Short Term Memory (LSTM) networkis utilized to classify the LULC classes. Experimental results showed that theHuman Group based PSO algorithm with a LSTM classifier effectively welldifferentiates the land use and land cover classes in terms of classificationaccuracy, recall and precision. An improvement of 2.56 in accuracy is achievedcompared to the existing models GoogleNet, VGG, AlexNet, ConvNet, when theproposed method is applied.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...