To address the issue of low matching accuracy between the prior spectral library obtained through vertical nadir acquisition and the measured spectra acquired through tilted acquisition, a spectral curve inversion algorithm based on a kernel-driven BRDF model is proposed in this paper. This algorithm is capable of inverting spectral curves at specified angles, thereby enhancing the matching accuracy with spectra obtained through tilted acquisition. Through a field multi-angle spectral measurement system, we collected multi-angle spectral information of common features used in military target recognition, such as dry grasslands and desert camouflage nets. Subsequently, spectral feature analysis was conducted, and the performance of various inversion algorithms was compared. The results indicate: (1) The reflectance of both types of features changes individually in a similar trend with variations in detection angles. (2) Curve inversion algorithms demonstrate favorable results for tilted curves, with coefficients of determination above 0.83 between inverted and measured spectra at tilted angles. (3) According to Spectral Angle Mapping (SAM), the inversion algorithm reduces spectral angles between inverted spectra and measured spectra at tilted angles, thereby enhancing spectral matching accuracy. This study enriches the relevant field of multi-angle remote sensing and holds theoretical and practical significance for high-spectral target matching detection.
Recently, transformer self-attention mechanisms have had significant advantages in the deep learning field, and it has been extensively used for natural language processing and video tracking. Furthermore, self-attention mechanisms have also been applied in hyperspectral unmixing. Although self-attention mechanisms are usually efficient and flexible tools, the original transformer might break the inner structure of data during learning, causing negative effects to unmixing. In this work, we employ transformer self-attention mechanisms to achieve a deep self-embedded transformer network(DSET-Net) for hyperspectral unmixing. The proposed DSET-Net adopts an autoencoder framework and achieves local and overall feature parameter sharing in the encoder through a 'Transformer in Transformer (TNT)' strategy. The DSET-Net preserves the spatial details of hyperspectral images and involves only one convolution operation in the encoder, substantially improving the learning performance. The effectiveness of the proposed method is evaluated by using real hyperspectral datasets. Our experimental results indicate that the newly proposed DSET-Net is very competitive compared with other state-of-the-art approaches.
Most existing depth networks that perform hyperspectral anomaly detection (HAD) using reconstruction errors tend to fit anomalous pixels, resulting in small reconstruction errors for anomalies, which are not favorable for separating targets from hyperspectral images (HSIs). To achieve a superior background reconstruction network for HAD purposes, a self-supervised blind-block reconstruction network (termed BockNet) with a guard window is proposed. BockNet creates a blind-block (guard window) at the center of the network's receptive field, making it unable to see the information inside the guard window when reconstructing the central pixel. This process seamlessly embeds a sliding dual-window model into our BockNet, where the inner window is the guard window, and the outer window is the receptive field outside the guard window. Naturally, BockNet uses only the outer window information to predict/reconstruct the central pixel of the perceptive field. During the reconstruction of pixels inside anomalous targets of different sizes, the targets typically fall into the guard window, weakening the contribution of anomalies to the reconstruction results and allowing these reconstructed pixels to converge to the background distribution of the outer window region. Accordingly, the reconstructed HSI can be regarded as a pure background HSI, and the reconstruction error of anomalous pixels will be further enlarged, thus improving the discrimination ability of the proposed network for anomalies. Extensive experiments on two datasets show the competitive performance of our BockNet compared to state-of-the-art detectors.
Hyperspectral imaging technology has undergone rapid development in recent years. However, with the exponential growth of data volume, the difficulty of data processing is also increasing rapidly. In such an environment, various target detection algorithms are constantly emerging according to different application environments. In view of this, this paper constructs a Knowledge graph based on hyperspectral anomaly detection algorithm on the neo4j platform, and simply summarizes and sorts out the scattered algorithms. Based on the construction method, we believe that the graph we have constructed has great development prospects in recommending hyperspectral target detection algorithms.
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.