Morphological Convolution and Attention Calibration Network for Hyperspectral and LiDAR Data Classification

Li, Zhongwei; Sui, Hao; Luo, Cai

doi:10.1109/jstars.2023.3284655

Cited by 14 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is important to note that this method is challenging to apply in datasets that lack LiDAR data. Li et al [48] introduce a method for improving the classification accuracy of remote sensing data by integrating multimodal information. The proposed approach combines a morphological convolution block and an attention calibration network to jointly classify HSI and LiDAR data.…”

Section: Introductionmentioning

confidence: 99%

ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers

Esmaeili,

Abbasi-Moghadam,

Sharifi

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hyperspectral imagery is widely used for analyzing substances and objects, specifically focusing on their classification. The advancement of processing capabilities and the emergence of cloud computing platforms have made deep learning (DL) models increasingly popular for accurately and efficiently hyperspectral images (HSI) classification. In addition, utilizing image-processing techniques that employ specific mathematical operations for feature extraction and noise reduction further improves the precision of HSI classification. This study introduces the ResMorCNN model, which utilizes 3-D convolutional layers and morphology mathematics to extract structural information, shapes, and interregional interactions from HSIs. These features are then incorporated into the model's layers using residual connections. This approach significantly enhances the classification accuracy of datasets with different characteristics. In fact, the proposed model achieves an average accuracy higher than the top-performing DL method in a competition. To evaluate the overall effectiveness of the proposed method, it was tested on four distinct and comprehensive datasets, Indian Pines, Pavia University, Houston University, and Salinas. These datasets were carefully selected, taking into account factors such as scale, dispersion, and sample size. The overall accuracy results obtained for each evaluated dataset were 97.81%, 99.33%, 98.67%, and 99.71%, respectively. This demonstrates an average improvement of 3.37% compared to the results of the best-performing method. The results demonstrate the effectiveness of the proposed ResMorCNN model for various applications that require accurate and efficient classification of HSI.

show abstract

Section: Introductionmentioning

confidence: 99%