This paper introduces a developed multi-sensor integrated system comprising a thermal infrared camera, an RGB camera, and a LiDAR sensor, mounted on a lightweight unmanned aerial vehicle (UAV). This system is applied to the inspection tasks of levee engineering, enabling the real-time, rapid, all-day, all-round, and non-contact acquisition of multi-source data for levee structures and their surrounding environments. Our aim is to address the inefficiencies, high costs, limited data diversity, and potential safety hazards associated with traditional methods, particularly concerning the structural safety of dam bodies. In the preprocessing stage of multi-source data, techniques such as thermal infrared data enhancement and multi-source data alignment are employed to enhance data quality and consistency. Subsequently, a multi-level approach to detecting and screening suspected risk areas is implemented, facilitating the rapid localization of potential hazard zones and assisting in assessing the urgency of addressing these concerns. The reliability of the developed multi-sensor equipment and the multi-level suspected hazard detection algorithm is validated through on-site levee engineering inspections conducted during flood disasters. The application reliably detects and locates suspected hazards, significantly reducing the time and resource costs associated with levee inspections. Moreover, it mitigates safety risks for personnel engaged in levee inspections. Therefore, this method provides reliable data support and technical services for levee inspection, hazard identification, flood control, and disaster reduction.

Emissivity information derived from thermal infrared (TIR) hyperspectral imagery has the advantages of both high spatial and spectral resolutions, which facilitate the detection and identification of the subtle spectral features of ground targets. Despite the emergence of several different TIR hyperspectral imagers, there are still no universal spectral emissivity measurement standards for TIR hyperspectral imagers in the field. In this paper, we address the problems encountered when measuring emissivity spectra in the field and propose a practical data acquisition and processing framework for a Fourier transform (FT) TIR hyperspectral imager—the Hyper-Cam LW—to obtain high-quality emissivity spectra in the field. This framework consists of three main parts. (1) The performance of the Hyper-Cam LW sensor was evaluated in terms of the radiometric calibration and measurement noise, and a data acquisition procedure was carried out to obtain the useful TIR hyperspectral imagery in the field. (2) The data quality of the original TIR hyperspectral imagery was improved through preprocessing operations, including band selection, denoising, and background radiance correction. A spatial denoising method was also introduced to preserve the atmospheric radiance features in the spectra. (3) Three representative temperature-emissivity separation (TES) algorithms were evaluated and compared based on the Hyper-Cam LW TIR hyperspectral imagery, and the optimal TES algorithm was adopted to determine the final spectral emissivity. These algorithms are the iterative spectrally smooth temperature and emissivity separation (ISSTES) algorithm, the improved Advanced Spaceborne Thermal Emission and Reflection Radiometer temperature and emissivity separation (ASTER-TES) algorithm, and the Fast Line-of-sight Atmospheric Analysis of Hypercubes-IR (FLAASH-IR) algorithm. The emissivity results from these different methods were compared to the reference spectra measured by a Model 102F spectrometer. The experimental results indicated that the retrieved emissivity spectra from the ISSTES algorithm were more accurate than the spectra retrieved by the other methods on the same Hyper-Cam LW field data and had close consistency with the reference spectra obtained from the Model 102F spectrometer. The root-mean-square error (RMSE) between the retrieved emissivity and the standard spectra was 0.0086, and the spectral angle error was 0.0093.

Although hyperspectral anomaly detection is commonly conducted in the visible, near-infrared, and shortwave infrared spectral regions, there has been less research on hyperspectral anomaly detection in the longwave infrared (LWIR) hyperspectral region. The radiance of thermal infrared hyperspectral imagery is determined by the temperature and emissivity. To avoid the detection uncertainty caused by the single factor of temperature, emissivity can be introduced to detect anomalies. However, in the emissivity domain, the spectral contrast and signal-to-noise ratio (SNR) are low, which makes it difficult to separate the anomalies from the background. In this paper, an anomaly detection method combining emissivity and a segmented low-rank prior (EaSLRP) is proposed for use with thermal infrared hyperspectral imagery. The EaSLRP method is divided into three parts—1) temperature/emissivity retrieval, 2) extraction of the thermal infrared hyperspectral background information, and 3) Mahalanobis distance detection. A homogeneous region generation method is also proposed to solve the problem of the complex global background leading to inaccurate background estimation. The GoDec method is used for matrix decomposition and background information extraction and to remove some of the noise. The proposed Mahalanobis distance detector then uses the background component and original image for anomaly detection, while highlighting the spectral difference between the anomalies and background. This method can also suppress the influence of noise, to some extent. The experimental results obtained with airborne Fourier transform thermal infrared spectrometer hyperspectral images demonstrate that the EaSLRP method is effective when compared with the Reed–Xiaoli detector (RXD), the segmented RX detector (SegRX), the low-rank and sparse representation-based detector (LRASR), the low-rank and sparse matrix decomposition (LRaSMD)-based Mahalanobis distance method (LSMAD), and the locally enhanced low-rank prior method (LELRP-AD).

Levees are critical for flood defence, but their integrity is threatened by hazards such as piping and seepage, especially during high-water-level periods. Traditional manual inspections for these hazards and associated emergency response elements, such as personnel and assets, are inefficient and often impractical. While UAV-based remote sensing offers a promising alternative, the effective fusion of multi-modal data and the scarcity of labelled data for supervised model training remain significant challenges. To overcome these limitations, this paper reframes levee monitoring as an unsupervised anomaly detection task. We propose a novel, fully automated framework that unifies geophysical hazards and emergency response elements into a single analytical category of “abnormal targets” for comprehensive situational awareness. The framework consists of three key modules: (1) a state-of-the-art registration algorithm to precisely align infrared and visible images; (2) a generative adversarial network to fuse the thermal information from IR images with the textural details from visible images; and (3) an adaptive, unsupervised segmentation module where a mean-shift clustering algorithm, with its hyperparameters automatically tuned by Bayesian optimization, delineates the targets. We validated our framework on a real-world dataset collected from a levee on the Pajiang River, China. The proposed method demonstrates superior performance over all baselines, achieving an Intersection over Union of 0.348 and a macro F1-Score of 0.479. This work provides a practical, training-free solution for comprehensive levee monitoring and demonstrates the synergistic potential of multi-modal fusion and automated machine learning for disaster management.

Hyperspectral remote sensing image (HSI) can record complete and continuous spectral curves of land features while obtaining the image information, which can achieve precise classification. However, HSIs have complex and nonlinear structures due to the high dimensionality and uncertainty of signals, resulting in redundant band information and difficulty in sample labeling. Although a series of band selection and unsupervised classification methods have been developed, they currently follow the research framework of “band selection first and then clustering”, resulting in transmission and accumulation errors. In this paper, based on the multiobjective evolutionary algorithm, an integrated method for HSI band selection and fuzzy clustering (IBSC) was proposed. The proposed IBSC method can achieve multitask encoding and modeling for band selection and fuzzy clustering, and the encoded individual solutions can generate new candidate solutions through information exchange between band selection and clustering. The effectiveness of IBSC was proved by experiments with three commonly used HSI clustering datasets, and the overall clustering accuracy is improved by about 1%. Thus, this integrated method can reduce the cumulative error between band selection and fuzzy clustering independent models.