Land Covers Classification from LiDAR-DSM Data Based on Local Kernel Matrix Features of Morphological Profiles

Document Type : Original Article

Authors

Department of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics, K. N. Toosi University of Technology, Tehran, Iran

Abstract

Accurate land cover classification from the digital surface model (DSM) obtained from LiDAR sensors is a challenging topic that researchers have considered in recent years. In general, the classification accuracy of land covers leads to low accuracy using a single-band DSM image. Hence, it seems necessary to develop efficient methods to extract relevant spatial information, which improves classification accuracy. In this regard, using spatial features based on morphological profiles (MPs) has significantly increased classification accuracy. Despite MPs' efficiency in increasing the DSM's classification accuracy, the classification accuracy results under the situation of limited training samples are not still at satisfactory levels. The main novelty of this paper is to propose a new feature space based on local kernel descriptors obtained from MP for addressing the mentioned challenge of MP-based DSM classification. These innovative feature vectors consider local nonlinear dependencies and higher-order statistics between the morphological features. The experiments of this study are conducted on two well-known DSM datasets of Houston and Trento. Our results show that support vector machine (SVM)-based DSM classification with the new local kernel features achieved an average accuracy of 93.75%, which is much better than conventional SVM classification with single-band DSM and MP features (by about 57% and 11.5% on average, respectively). Additionally, our proposed method outperformed two other DSM classification methods by an average of 4.7%.

Keywords

Main Subjects

References

  1. Sharma, M., Garg, R.D., Badenko, V., Fedotov, A., Min, L. and Yao, A., "Potential of airborne lidar data for terrain parameters extraction", Quaternary International, Vol. 575, (2021), 317-327. https://doi.org/10.1016/j.quaint.2020.07.039
  2. Li, X., Chen, W.Y., Sanesi, G. and Lafortezza, R., "Remote sensing in urban forestry: Recent applications and future directions", Remote Sensing, Vol. 11, No. 10, (2019), 1144. https://doi.org/10.3390/rs11101144
  3. Muhadi, N.A., Abdullah, A.F., Bejo, S.K., Mahadi, M.R. and Mijic, A., "The use of lidar-derived dem in flood applications: A review", Remote Sensing, Vol. 12, No. 14, (2020), 2308. https://doi.org/10.3390/rs12142308
  4. Wang, A., He, X., Ghamisi, P. and Chen, Y., "Lidar data classification using morphological profiles and convolutional neural networks", IEEE Geoscience and Remote Sensing Letters, Vol. 15, No. 5, (2018), 774-778. https://doi.org/10.1109/LGRS.2018.2810276
  5. Wang, A., Xue, D., Wu, H. and Gu, Y., "Efficient convolutional neural architecture search for lidar dsm classification", IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, (2022), 1-17.. https://doi.org/10.1109/TGRS.2022.3171520
  6. Zhang, M., Ghamisi, P. and Li, W., "Classification of hyperspectral and lidar data using extinction profiles with feature fusion", Remote Sensing Letters, Vol. 8, No. 10, (2017), 957-966. https://doi.org/10.1080/2150704X.2017.1335902
  7. Singh, M.K., Mohan, S. and Kumar, B., "Fusion of hyperspectral and lidar data using sparse stacked autoencoder for land cover classification with 3d-2d convolutional neural network", Journal of Applied Remote Sensing, Vol. 16, No. 3, (2022), 034523-034523. https://doi.org/10.1117/1.JRS.16.034523
  8. Ghamisi, P. and Hoefle, B., "Lidar data classification using extinction profiles and a composite kernel support vector machine", IEEE Geoscience and Remote Sensing Letters, Vol. 14, No. 5, (2017), 659-663. https://doi.org/10.1109/LGRS.2017.2669304
  9. He, X., Wang, A., Ghamisi, P., Li, G. and Chen, Y., "Lidar data classification using spatial transformation and cnn", IEEE Geoscience and Remote Sensing Letters, Vol. 16, No. 1, (2018), 125-129. https://doi.org/10.1109/LGRS.2018.2868378.
  10. Wang, A., Wang, M., Jiang, K., Zhao, L. and Iwahori, Y., "A novel lidar data classification algorithm combined densenet with stn", in IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, IEEE. (2019), 2483-2486.
  11. Asghari Beirami, B. and Mokhtarzade, M., "Ensemble of log-euclidean kernel svm based on covariance descriptors of multiscale gabor features for face recognition", International Journal of Engineering, Transactions B: Applications, Vol. 35, No. 11, (2022), 2065-2071. https://doi.org/10.5829/IJE.2022.35.11B.01
  12. Wang, L., Zhang, J., Zhou, L., Tang, C. and Li, W., "Beyond covariance: Feature representation with nonlinear kernel matrices", in Proceedings of the IEEE international conference on computer vision. (2015), 4570-4578.
  13. Zhang, J., Wang, L., Zhou, L. and Li, W., "Beyond covariance: Sice and kernel based visual feature representation", International Journal of Computer Vision, Vol. 129, (2021), 300-320. https://doi.org/10.1007/s11263-020-01376-1
  14. Beirami, B.A. and Mokhtarzade, M., "Optimized weighted local kernel features for hyperspectral image classification", Multimedia Tools and Applications, Vol. 81, No. 15, (2022), 21859-21885. https://doi.org/10.1007/s11042-022-12452-8.
  15. Asghari Beirami, B. and Mokhtarzade, M., "Spatial-spectral classification of hyperspectral images based on extended morphological profiles and guided filter", Computer and Knowledge Engineering, Vol. 2, No. 2, (2020), 2-8. https://doi.org/10.22067/CKE.V2I2.81519
  16. Fang, L., He, N., Li, S., Plaza, A.J. and Plaza, J., "A new spatial–spectral feature extraction method for hyperspectral images using local covariance matrix representation", IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, No. 6, (2018), 3534-3546. https://doi.org/10.1109/TGRS.2018.2801387
  17. Mirzapour, F. and Ghassemian, H., "Moment-based feature extraction from high spatial resolution hyperspectral images", International Journal of Remote Sensing, Vol. 37, No. 6, (2016), 1349-1361. https://doi.org/10.1080/2150704X.2016.1151568
International Journal of Engineering
Volume 36, Issue 9
TRANSACTIONS C: Aspects
September 2023
Pages 1611-1617

Files

Share

How to cite

Statistics