YOLOv5 is a one-stage detector that achieves appealing performance in real-time object detection. When it comes to remote sensing object detection, there are many small objects in the scene, and the number of objects in different categories varies significantly. Directly applying YOLOv5 for remote sensing object detection usually ignores these small objects. Furthermore, imbalance among different categories also makes the model prone to some majority categories. In this way, we propose a smallness and imbalance-aware head and apply it to YOLOv5. The improved model is named SIA-YOLOv5. To be specific, a normalized Gaussian Wasserstein distance is designed to replace the commonly used intersection over union in the regression process, which substantially improves the localization accuracy for small objects. Meanwhile, an adaptive weighting strategy is designed to make a flexible emphasis on the classification accuracy among different categories, which relieves the unstable performance caused by imbalanced data. In addition, BiFPN and coordinate attention are utilized for better feature extraction. Experimental data and analysis have demonstrated the effectiveness of the proposed method.
Hyperspectral anomaly detection (HAD) does not require a priori information, and accurate discrimination is made by analyzing the difference between the anomalies and the background pixels. However, the bands of hyperspectral images are highly correlated with each other. There is a lot of redundant information between them, which causes the band selection to be difficult to accurately distinguish between background and anomalies. This paper introduces background purification and feature extraction strategies to increase the distinction between anomalies and background pixels. To be specific, the domain transformation extracts discriminative sample features. The row-constrained low-rank sparse matrix decomposition is utilised to obtain low-rank background matrices to construct purer background to highlight the anomalies. The sliding window strategy is adopted to divide the subspace to reduce the spatial correlation. Highly representative and low redundancy bands are selected for band selection in the local region. Finally, the local region is detected by RX and the map is obtained by domain-valued normalisation of the local results. Experiments on several HSI data sets show that the proposed method can suppress the background well. It can also make full use of the spectral information and achieves acceptable detection accuracy.
Hyperspectral image (HSI) super-resolution attracts the great interest in remote sensing, since its effectiveness in obtaining the HSI with rich spatial information while preserving the high spectral discriminative ability, without modifying the imagery equipment. This paper proposes a novel HSI super-resolution method via gradient guided residual dense network (G-RDN), in which the spatial gradient is utilized to guide the super-resolution process. Specifically, there are three modules in the super-resolving process. Firstly, the spatial mapping between the low-resolution HSI and the desired high resolution HSI is learnt via a residual dense network. The residual dense network (RDN) is exploited to fully exploit the hierarchical features learnt from all the convolutional layers. Meanwhile, the gradient detail is extracted via a residual net (ResNet), which is further utilized to guide the super-resolution process. Finally, the fully obtained global hierarchical features is merged with the gradient details via an empirical weight. Experimental results and data analysis on three benchmark datasets show that our method achieves favorable performance.
Limited by the imagery sensors, hyperspectral images (HSIs) are characterized by their rich spectral information but poor spatial information. With the guidance of the panchromatic (PAN) images, hyperspectral pansharpening aims at achieving a HSI with both the fine spatial detail and the high spectral discrimination ability. Although many deep learning-based methods have gained great attention in recent years, it is still challenging for obtaining an appealing performance. In this paper, we propose a novel detail injection network for the hyperspectral pansharpening, which fully exploits the hierarchical features in both the low resolution HSI and the high-resolution PAN. Specifically, the lowresolution HSIs are firstly upsampled to the desired size, and make a concatenation with the PAN image to formulate a new HSI. The new HSI is sent into a residual dense network, in which residual dense block are designed to extract the abundant local features. Finally, details are injected in hierarchical levels for achieving the acceptable performance. Experimental results and data analysis on two datasets which include both indoor and outdoor scenarios have demonstrated the effectiveness of the proposed method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.