16 May 2023 in IEEE Transactions on Geoscience and Remote Sensing
As a fundamental task in remote sensing observation of the earth, change detection using hyperspectral images (HSI) features high accuracy due to the combination of the rich spectral and spatial information, especially for identifying land-cover variations in bi-temporal HSIs. Relying on the image difference, existing HSI change detection methods fail to preserve the spectral characteristics and suffer from high data dimensionality, making them extremely challenging to deal with changing areas of various sizes. To tackle these challenges, we propose a cross-band 2-D self-attention Network (CBANet) for end-to-end HSI change detection. By embedding a cross-band feature extraction module into a 2-D spatial-spectral self-attention module, CBANet is highly capable of extracting the spectral difference of matching pixels by considering the correlation between adjacent pixels. The CBANet has shown three key advantages: 1) less parameters and high efficiency; 2) high efficacy of extracting representative spectral information from bi-temporal images; and 3) high stability and accuracy for identifying both sparse sporadic changing pixels and large changing areas whilst preserving the edges. Comprehensive experiments on three publicly available datasets have fully validated the efficacy and efficiency of the proposed methodology.
19 October 2021 in IEEE Geoscience and Remote Sensing Letters
The principal component analysis (PCA) and 2-D singular spectral analysis (2DSSA) are widely used for spectral domain and spatial domain feature extraction in hyperspectral images (HSI). However, PCA itself suffers from low efficacy if no spatial information is combined, whilst 2DSSA can extract the spatial information yet has a high computing complexity. As a result, we propose in this paper a PCA domain 2DSSA approach for spectral-spatial feature mining in HSI. Specifically, PCA and its variation, folded-PCA are utilized to fuse with the 2DSSA, as folded-PCA can extract both global and local spectral features. By applying 2DSSA only on a small number of PCA components, the overall computational complexity has been significantly reduced whilst preserving the discrimination ability of the features. In addition, with the effective fusion of spectral and spatial features, the proposed approach can work well on the uncorrected dataset without removing the noisy and water absorption bands, even under a small number of training samples. Experiments on two publicly available datasets have fully demonstrated the superiority of the proposed approach, in comparison to several state-of-the-art HSI classification methods and deep-learning models.
13 August 2021 in IEEE Access
Monocular depth estimation is an undirected problem, so constructing a network to predict better image depth information is an important research topic. This paper proposes a mixed-scale Unet network (MAPUnet) with a dense atrous pyramid based on the coder-decoder structure widely used in computer vision. We innovatively introduce the Unet++ structure of the image segmentation network for depth estimation. We reset the number of convolutional layers of the network under the framework of the Unet++ network and innovatively connect the decoders densely. Moreover, by choosing the appropriate size of the atrous radius, we form a dense atrous pyramid based on different feature layers to better connect the features in the deep and shallow layers of the network. To verify the effectiveness of the proposed algorithm, we test the network on the KITTI dataset and the NYU Depth V2 dataset. We compare the network with the current state-of-the-art methods. The proposed method has higher accuracy and has steadily improved relative to the threshold of accuracy and root-mean-square error. We also conduct ablation studies, studies targeting the effectiveness of the network framework, and discussions on the convergence time and parameter complexity of the network. We will open-source the code at https://github.com/yang-yi-fan/MAPUnet .
15 January 2024 in IEEE Access
In this paper, we propose an unstructured road-free space detection method that integrates distance imaging information in the Transformer framework. The proposed network is FNS-Swin, which innovatively supplements features through data fusion to reduce the dependence of Transformer networks applied to computer vision on RGB image data volume while improving the accuracy of segmentation algorithms. Regarding the network framework, we adopted Swin Transformer’s sliding window structure. We reset the number of layers of the network model to better adapt to learning fused features. It dynamically fuses distance and image geometric features by adding a cross-attention mechanism, enhancing the data correlation between the two representations. In the depth information extraction section, we used the SNE model to extract the depth features of depth images and convert them into surface normal vector maps, enhancing the correlation between depth information and road plane prediction. To verify the effectiveness of the proposed algorithm, we conducted testing experiments on unstructured ORFD datasets and KITTI-Road datasets, respectively. The experimental results show that our algorithm outperforms others in multiple metrics, achieving the best overall performance.