Classification of the Land Cover of a Megacity in ASEAN Using Two Band Combinations and Three Machine Learning Algorithms: A Case Study in Ho Chi Minh City

Huang, Chaoqing; He, Chao; Wu, Qian; Nguyen, MinhThu; Hong, Song

doi:10.3390/su15086798

Cited by 2 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [23] proposed a new point cloud classification algorithm of the mixed kernel function support vector machine (SVM) to distinguish different types of ground objects. Many other scholars compared these algorithms; for example, Huang et al [24] classified the land cover in Ho Chi Minh City by comparing three classification algorithms, i.e., the back propagation neural network, SVM, and RF. However, the performance of a single method in confusing areas, such as boundaries and covered by thin point clouds, is often degraded due to the potential interclass similarity and intraclass inconsistency of objects, which prompted researchers to explore more accurate point cloud classification models [25].…”

Section: Introductionmentioning

confidence: 99%

Land Cover Classification Based on Airborne Lidar Point Cloud with Possibility Method and Multi-Classifier

Zhao,

Ji,

Yang

2023

Sensors

View full text Add to dashboard Cite

As important geospatial data, point cloud collected from an aerial laser scanner (ALS) provides three-dimensional (3D) information for the study of the distribution of typical urban land cover, which is critical in the construction of a “digital city”. However, existing point cloud classification methods usually use a single machine learning classifier that experiences uncertainty in making decisions for fuzzy samples in confusing areas. This limits the improvement of classification accuracy. To take full advantage of different classifiers and reduce uncertainty, we propose a classification method based on possibility theory and multi-classifier fusion. Firstly, the feature importance measure was performed by the XGBoost algorithm to construct a feature space, and two commonly used support vector machines (SVMs) were the chosen base classifiers. Then, classification results from the two base classifiers were quantitatively evaluated to define the confusing areas in classification. Finally, the confidence degree of each classifier for different categories was calculated by the confusion matrix and normalized to obtain the weights. Then, we synthesize different classifiers based on possibility theory to achieve more accurate classification in the confusion areas. DALES datasets were utilized to assess the proposed method. The results reveal that the proposed method can significantly improve classification accuracy in confusing areas.

show abstract

Section: Introductionmentioning

confidence: 99%