In recent years, unmanned aerial vehicle (UAV) technology has shown great potential for application in hyperspectral image (HSI) classification tasks due to its advantages of flexible scheduling and fast response. However, existing deep learning-based classification algorithms have not thoroughly studied the problems caused by the higher spatial resolution of UAV HSIs. Such as more severe intra-class variation and higher computational resource consumption. These issues limit classification performance. To address these challenges, this paper proposes a lightweight spatial-spectral deformable convolutional neural network (LS2DCNet) for UAV HSI classification. This network reduces computational resource usage and data processing time, meeting the fast-response application requirements while ensuring classification performance. First, spatial-spectral deformable convolution (S2DConv) is designed to construct a lightweight feature extraction network. This not only enhances the adaptive extraction of fine features but also reduces computational resource consumption, and improves response speed. Second, a dynamic labeling-based joint loss (DL-JLoss) is designed to dynamically learn the distribution relationship between data classes. This improves the network’s generalization performance. A more realistic experimental validation was conducted on three UAV HSI datasets using regionally divided training samples, and inference comparisons were performed on embedded devices. The results show that the proposed LS2DCNet exhibits a better overall performance in terms of classification accuracy and inference speed.The relevant code can be found at https://github.com/niuroushu/A-Lightweight-Spatial-Spectral-Deformable-CNN-for-UAV-Hyperspectral-Image-Classification.

Convolutional neural network (CNN)-based hyperspectral image (HSI) classification models often exhibit high volume and complexity. This not only poses challenges in deploying them on mobile and embedded devices due to storage and power constraints but also introduces a dilemma between the growing demand for labeled samples and the high cost associated with manual labeling. To address these challenges, we propose an ultra-lightweight hybrid CNN based on redundancy removal (ULite-R2HCN), specifically designed for HSI classification in scenarios with limited samples. To reduce computational costs and enhance feature extraction effectiveness, we focus on optimizing the widely used depthwise convolution (DW-Conv) and pointwise convolution (PW-Conv) in the lightweight HSI classification model. For DW-Conv, we design a spatial convolution with redundancy removal (R2Spatial-Conv). This involves the design of multi-scale 3D convolution kernels with specific structures instead of 2D convolution kernels, aiming to reduce redundant convolution kernels and extract multi-scale spatial features. Simultaneously, for PW-Conv, we design a spectral convolution with redundancy removal (R2Spectral-Conv). This utilizes a “copy-splicing-grouping” structure to extract spectral features within arbitrary range intervals, effectively reducing redundant spectral extractions and capturing long-range spectral relationships. Numerous experiments have shown that the proposed ULite-R2HCN achieves higher classification accuracy with an ultra-light volume for a few training samples. In addition, sufficient ablation experiments also verified the advanced performance of the designed R2Spatial-Conv and R2Spectral-Conv.

Recent studies have demonstrated the potential of hybrid convolutional models that combine 3D and 2D convolutional neural networks (CNNs) for hyperspectral image (HSI) classification. However, these models do not fully utilize the benefits of hybrid convolution due to inefficient connections between the two types of CNNs. Moreover, most CNNs, including hybrid models, require a significant number of parameters and computational resources for accurate classification, which increases the need for labeled samples and computational cost. Although the common lightweight strategies like depthwise separable convolution (DSC) can reduce parameters and computation compared to normal convolution (NC), they often compromise accuracy. To address these challenges, we propose a lightweight hybrid convolutional neural network (Lite-HCNet) for HSI classification with minimal model parameters and computational effort. Firstly, we design a novel channel attention module (NCAM) and combine it with a convolutional kernel decomposition (CKD) strategy to propose a lightweight and efficient DSC (LE-DSC) deployed in Lite-HCNet. The LE-DSC not only reduces the DSC volume further but also enhances its performance. Secondly, a lightweight and efficient hybrid convolutional layer (LE-HCL) is designed in Lite-HCNet to explore the efficient connection structure between 3D CNNs and 2D CNNs. Experiments show that the Lite-HCNet reduces the required computational cost and practical deployment difficulty while offering advanced performance with a small number of training samples. Furthermore, abundant ablation experiments confirm the superior performance of the designed LE-DSC.

In recent years, convolutional neural networks (CNNs) have been widely used in hyperspectral images (HSIs) classification. However, 2-D CNN, 3-D CNN, and even the newly emerged hybrid CNN (HCNN) all require multiple or deep CNN layers to obtain excellent classification performance, which inevitably results in the high complexity and the need for a large number of training samples. Moreover, as a local operator, convolution is challenging to fully use global information. To solve the above two issues, we design a HCNN based on global reasoning (GloRe-HCNN) for HSI classification. On the one hand, the GloRe-HCNN uses only one layer of 3-D CNN and one layer of 2-D CNN to jointly extract the spatial–spectral features of HSI. On the other hand, we contrive a spatial–spectral global reasoning unit (SS-GloRe-Unit) to take the place of stacked multilayer 3-D CNN for extracting global features fully. We select small training samples in three standard datasets and compare them with state-of-the-art CNN methods. Numerous experiments show that our GloRe-HCNN performs advanced performance.

In this paper, a very low bitrate video coding scheme using the generalized finite automata (GFA) representation of the bitplane model of video sequences is proposed. Unlike the traditional motion estimate based MPEG scheme, where a group of pictures (GOP) in a video sequence is arranged into I, P and B frames, in the proposed scheme, all the frames in a GOP are first transformed into the wavelet coefficients and the coefficients in subbands are then modeled by the significant bitplanes. Finally, the bitplane model is represented by the genealogy tree structured GFA. The state indices and their transitions in the GFA representation are then entropy coded using the arithmetic code. Since the fractal similarities between the frames, wavelet levels and bit-planes are optimally explored by the GFA, the GFA model of the GOP is minimized, leading to a super low bitrate video coding scheme which can facilitate applications such as video streaming over low bandwidth networks, video streaming to mobile clients (PDA and cellular telephones), mobile-conferencing, video gaming, etc

This paper presents a new approach for fitting a subdivision surface from an irregular and dense triangle mesh of arbitrary topological type. All feature edges and feature vertices of the original mesh model are first identified. A topology- and feature-preserving mesh simplification algorithm is developed to further simplify the dense triangle mesh into a coarse mesh. A subdivision surface with exactly the same topology and sharp features as that of the simplified mesh is finally fitted from a subset of the vertices of the original dense mesh. During the fitting process, both the position masks and subdivision rules are used for setting up the fitting equation. Examples are provided to demonstrate the proposed approach.