Semantic segmentation of airborne laser scanning (ALS) point clouds remains a challenging task due to the complexity and diversity of 3D scenes in the real world. Currently, most deep learning-based airborne LiDAR point cloud segmentation methods prioritize designing local feature extraction operators while overlooking the long-range dependencies among neighborhoods and the inherently diverse properties of point cloud data. To address these issues, this paper introduces a dual-attention and elevation-aware airborne LiDAR point cloud semantic segmentation network (DAEA-Net) built upon an encoding-decoding architecture. First, we develop a cross multiple anti-affine attention (CMAAA) module that effectively captures global contextual information across different neighborhoods through interactive learning of multiple features. Second, we introduce an elevation awareness (EA) module that uses normal vectors to establish a geometric similarity discriminant for each neighboring point. It incorporates an autoencoder architecture to fuse elevation information, enhancing the horizontal structural dissimilarity between objects of similar height while enriching the representation of elevation data. Additionally, to compensate for the potential information loss in the encoding-decoding hierarchical structure, we design a lightweight U-global attention (UGA) module to link decoding and encoding hierarchical levels. It merges features of different resolutions and levels during downsampling and upsampling through pooling while utilizing the self-attention mechanism to enhance the network’s global expression capability. The proposed DAEA-Net enhances ALS semantic segmentation performance by enabling interactive learning of multiple features and effectively representing elevation information. Extensive experiments conducted on two datasets demonstrate that our method delivers superior semantic segmentation performance compared to several existing advanced techniques.

Significant progress has been achieved by using deep learning technology for the semantic segmentation of airborne laser scanning (ALS) point clouds. However, there are still challenges in effectively capturing contextual information and fusing network multilevel features to improve ALS point cloud segmentation performance. In this letter, we propose a lightweight bidirectional feature aggregation and adaptive fusion network. First, we propose a novel adaptive bidirectional feature aggregation module to adaptively aggregate multi-scale local features, effectively expanding the receptive field. After that, we introduce a feature adaptive fusion module between up-sampling and down-sampling in the same layer to explore more comprehensive multilevel features and finer contextual information. Experiments on ISPRS 3D, GML, and LASDU datasets verify the superior segmentation performance of the proposed method with mF1 of 72.83% on ISPRS 3D, 76.12% on GML, and 78.95% on LASDU.

In this paper, we introduce a fast iterative adaptive approach for the reconstruction of 3D seismic data with randomly missing traces. Our method starts by transforming 3D seismic volume to 2D harmonic signal for each frequency slice, and then the power spectrum of the frequency slice is iteratively estimated by a weighted least square fitting criterion. The missing data can be recovered with the obtained spectral estimate using a linear minimum mean-squared error estimator. However, estimation of the power spectrum depends on matrix-vector multiplications for each iteration that leads to high computation complexity when the data are large scale and high dimension. To solve the associated spectrum estimation problem above, a fast iterative adaptive scheme is adopted by utilising 2D fast discrete Fourier transform, which makes use of the block-Vandermonde structure and the 2D Fourier property of the steering matrix. Simulation experiments on synthetic and field data verify the effectiveness of the proposed algorithm. Compared with other reconstruction methods based on frequency slice, such as minimum-weighted norm interpolation approach, multi-channel singular spectrum analysis, and Curvelet transform method, the proposed method achieves better reconstruction performance and low computational complexity.

Reconstruction of missing seismic data is a critical procedure for subsequent applications like multiple wave suppression, wave-equation migration imaging and so on. In this paper, a fast, hyperparameter-free and sparse iterative spectral estimation approach is proposed for the reconstruction of two-dimensional seismic data of randomly missing traces. The proposed approach is based on the harmonic structure of the frequency slice of seismic data and the weighted covariance fitting criterion. Specifically, the method first iteratively estimates the spectrum of the frequency slice by solving a weighted covariance fitting problem. Then, the missing data is reconstructed by using the estimated spectrum and a linear minimum mean-squared error estimator. However, the spectral estimation depends on matrix-vector multiplications for each iteration, which has a high computational cost when the data increase to a large size. To solve this problem, a fast iterative technology is proposed by using an inverse fast Fourier transform, which fully exploits the Hermitian–Toeplitz structure of the covariance matrix and the exponential form of the steering vector and it significantly reduces the computational complexity. The proposed algorithm is hyperparameter-free, can provide super spectral resolution, and thus obtain better reconstruction performance. The experimental results of synthetic and real seismic data show that the proposed algorithm has higher reconstruction accuracy and lower computational complexity compared to other commonly used reconstruction algorithms.

Parameter estimation of chirp signal model with time-varying amplitude and additive noise is a critical problem in statistical signal processing. A statistically efficient algorithm is proposed to estimate the nonlinear parameters of frequency rate (FR) and initial frequency (IF). Initial estimates are first deduced from the ambiguity function (AF) and then refined through a statistics-based iterative procedure that improves their convergence rates from $O_p(N^{-1})$ and $O_p(N^{-2})$ to $O_p(N^{-3/2})$ and $O_p(N^{-5/2}),$ respectively. It is worth noting that the convergence rates of FR and IF double while being controlled by each other at each iteration, causing the convergence rates of FR and IF to jump up and down before the algorithm converges. Four iterative processes are considered involving crossovers between two types of initial estimators and two types of iterative coefficients. The asymptotic distribution of the refined estimators is obtained and demonstrated to be bivariate normal, and the Cramér–Rao lower bound (CRLB) is derived for each. Monte Carlo simulations were performed to verify the effectiveness of the proposed algorithm.