Improving the Detection of Burnt Areas in Remote Sensing using Hyper-features Evolved by M3GP

@article{Batista2020ImprovingTD,
  title={Improving the Detection of Burnt Areas in Remote Sensing using Hyper-features Evolved by M3GP},
  author={Jo{\~a}o E. Batista and Sara Silva},
  journal={2020 IEEE Congress on Evolutionary Computation (CEC)},
  year={2020},
  pages={1-8}
}
  • J. BatistaSara Silva
  • Published 31 January 2020
  • Computer Science, Environmental Science, Mathematics
  • 2020 IEEE Congress on Evolutionary Computation (CEC)
One problem found when working with satellite images is the radiometric variations across the image and different images. Intending to improve remote sensing models for the classification of burnt areas, we set two objectives. The first is to understand the relationship between feature spaces and the predictive ability of the models, allowing us to explain the differences between learning and generalization when training and testing in different datasets. We find that training on datasets built… 
[PDF] Semantic Reader
6 Citations
Highly Influential Citations
1
Background Citations
3
Methods Citations
4
Results Citations
2

Figures and Tables from this paper

6 Citations

Improving Land Cover Classification Using Genetic Programming for Feature Construction

It is shown that adding the M3GP hyperfeatures to the reference datasets brings better results than adding the well-known spectral indices NDVI, NDWI, and NBR, and is compared with other feature construction methods such as FFX and EFS.

Improving Land Cover Classification Using Genetic Programming

It is shown that adding the M3GP hyper-features to the reference datasets brings better results than adding the well-known spectral indices NDVI, NDWI and NBR, and is compared with those created by other Feature Construction methods like FFX and EFS.

Optical time series for the separation of land cover types with similar spectral signatures: cocoa agroforest and forest

This work focused on the separation of two cover types with similar spectral signatures, cocoa agroforest and forest, over an area in Pará, Brazil, and indicates that, out of seven classifiers, the popular random forest algorithm ranked fourth, while XGBoost (×GB) obtained the best results.

Comparative study of classifier performance using automatic feature construction by M3GP

The results show that automatic feature construction with M3GP, when compared to using the standalone classifiers without feature construction, achieves statistically significant improvements in the majority of the test cases, sometimes by a very large margin, while degrading the weighted f-measure in only one out of 48 cases.

Towards effective GP multi-class classification based on dynamic targets

DTC is the first GP classifier that defines the fitness of individuals by using the synergistic combination of linear scaling and the hinge-loss function (commonly used by SVM).

Recent Advances in Forest Insect Pests and Diseases Monitoring Using UAV-Based Data: A Systematic Review

: Unmanned aerial vehicles (UAVs) are platforms that have been increasingly used over the last decade to collect data for forest insect pest and disease (FIPD) monitoring. These machines provide…

References

SHOWING 1-10 OF 27 REFERENCES

A Semi-Supervised Crop-Type Classification Based on Sentinel-2 NDVI Satellite Image Time Series And Phenological Parameters

This paper presents an approach that works at object-level and exploits both spatial and temporal information coded in NDVI time series and phenological parameters and takes advantage of a semi-supervised paradigm by combining a new hierarchical correlation clustering with an artificial neural network.

Studying the behavior of neural and statistical classifiers by interaction in feature space

A software tool to study the training and classification processes in n-dimensional feature space of statistical as well as neural network classifiers and gives an example of a combined classification scheme where visualization is used in order to validate the approach.

Effective Feature Extraction and Data Reduction in Remote Sensing Using Hyperspectral Imaging [Applications Corner]

Several variations and extensions of conventional PCA are discussed to address the aforementioned challenges of hyperspectral imaging and some non-PCA-based approaches for feature extraction and data reduction, based on techniques such as band selection, random projection, singular value decomposition, and machine-learning approaches such as the support vector machine (SVM).

Unsupervised Deep Feature Extraction for Remote Sensing Image Classification

The proposed algorithm clearly outperforms standard principal component analysis and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data.

Improved mapping of forest type using spectral-temporal Landsat features

Burned area estimations derived from Landsat ETM+ and OLI data: Comparing Genetic Programming with Maximum Likelihood and Classification and Regression Trees

A Review of Techniques for Extracting Linear Features from Imagery

The automated extraction of linear features from remotely sensed imagery has been the subject of extensive research over several decades. Recent studies show promise for extraction of feature…

M3GP - Multiclass Classification with GP

Experimental results show that M3GP can automatically determine a good value for \(d\) depending on the problem, and achieves excellent performance when compared to state-of-the-art-methods like Random Forests, Random Subspaces and Multilayer Perceptron on several benchmark and real-world problems.

Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification

An end-to-end framework for the dense, pixelwise classification of satellite imagery with convolutional neural networks (CNNs) and design a multiscale neuron module that alleviates the common tradeoff between recognition and precise localization is proposed.

A semi-supervised Genetic Programming method for dealing with noisy labels and hidden overfitting