Hyperspectral target detection aims to locate targets of interest in the scene, and deep learning-based detection methods have achieved the best results. However, black box network architectures are usually designed to directly learn the mapping between the original image and the discriminative features in a single data-driven manner, a choice that lacks sufficient interpretability. On the contrary, this article proposes a novel deep spatial-spectral joint-sparse prior encoding network (JSPEN), which reasonably embeds the domain knowledge of hyperspectral target detection into the neural network, and has explicit interpretability. In JSPEN, the sparse encoded prior information with spatial-spectral constraints is learned end-to-end from hyperspectral images (HSIs). Specifically, an adaptive joint spatial-spectral sparse model (AS JSM) is developed to mine the spatial-spectral correlation of HSIs and improves the accuracy of data representation. An optimization algorithm is designed for iteratively solving AS JSM, and JSPEN is proposed to simulate the iterative optimization process in the algorithm. Each basic module of JSPEN one-to-one corresponds to the operation in the optimization algorithm so that each intermediate result in the network has a clear explanation, which is convenient for intuitive analysis of the operation of the network. With end-to-end training, JSPEN can automatically capture the general sparse properties of HSIs and faithfully characterize the features of background and target. Experimental results verify the effectiveness and accuracy of the proposed method. Code is available at https://github.com/Jiahuiqu/JSPEN.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCYB.2024.3403729DOI Listing

Publication Analysis

Top Keywords

hyperspectral target
12
target detection
12
deep spatial-spectral
8
spatial-spectral joint-sparse
8
joint-sparse prior
8
prior encoding
8
encoding network
8
optimization algorithm
8
network
6
jspen
5

Similar Publications

Ultrastructural Remodeling of Cardiomyocytes in Postinfarction Myocardium of Rats in the Late Stages of the Disease.

Cytometry A

December 2024

Laboratory of Hyperspectral Imaging of Surgical Targets, Center of Excellence, L.A. Orbeli Institute of Physiology, National Academy of Sciences, Yerevan, Armenia.

Identifying factors that contribute to the transition to the dilated phase in cardiac ischemia is a critical challenge in heart failure treatment. Currently, no effective therapies exist for this ischemic complication, and the mechanisms driving left ventricular dilatation during chronic post-infarction remodeling remain poorly understood. One potential pathological process leading to ventricular dilatation involves specific compensatory rearrangements in the border zone adjacent to the infarct, which isolates the intact myocardium from inflammation at the scar edge.

View Article and Find Full Text PDF

As consumers increasingly prioritize food safety and nutritional value, the dairy industry faces a pressing need for rapid and accurate methods to detect essential nutritional components in milk, such as fat, protein, and lactose. Hyperspectral imaging (HSI) technology, known for its non-destructive, fast, and precise nature, shows great promise in food quality assessment. However, the high dimensionality of HSI data poses challenges for effective band selection and model optimization.

View Article and Find Full Text PDF

Exploring hyperspectral anomaly detection with human vision: A small target aware detector.

Neural Netw

December 2024

State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an, 710071, Shanxi, China.

Hyperspectral anomaly detection (HAD) aims to localize pixel points whose spectral features differ from the background. HAD is essential in scenarios of unknown or camouflaged target features, such as water quality monitoring, crop growth monitoring and camouflaged target detection, where prior information of targets is difficult to obtain. Existing HAD methods aim to objectively detect and distinguish background and anomalous spectra, which can be achieved almost effortlessly by human perception.

View Article and Find Full Text PDF

BSDR: A Data-Efficient Deep Learning-Based Hyperspectral Band Selection Algorithm Using Discrete Relaxation.

Sensors (Basel)

December 2024

Wimmera Catchment Management Authority, 24 Darlot St, Horsham, VIC 3400, Australia.

Hyperspectral band selection algorithms are crucial for processing high-dimensional data, which enables dimensionality reduction, improves data analysis, and enhances computational efficiency. Among these, attention-based algorithms have gained prominence by ranking bands based on their discriminative capability. However, they require a large number of model parameters, which increases the need for extensive training data.

View Article and Find Full Text PDF

Phenotyping cotton leaf chlorophyll via hyperspectral reflectance sensing, spectral vegetation indices, and machine learning.

Front Plant Sci

November 2024

United States Department of Agriculture (USDA), Agricultural Research Service (ARS), U.S. Arid-Land Agricultural Research Center, Maricopa, AZ, United States.

Cotton ( L.) leaf chlorophyll (Chl) has been targeted as a phenotype for breeding selection to improve cotton tolerance to environmental stress. However, high-throughput phenotyping methods based on hyperspectral reflectance sensing are needed to rapidly screen cultivars for chlorophyll in the field.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!