The detection of oil spills in water is a frequently researched area, but most of the research has been based on very large patches of crude oil on offshore areas. We present a novel framework for detecting oil spills inside a port environment, while using unmanned areal vehicles (UAV) and a thermal infrared (IR) camera. This framework is split into a training part and an operational part. In the training part, we present a process for automatically annotating RGB images and matching them with the IR images in order to create a dataset. The infrared imaging camera is crucial to be able to detect oil spills during nighttime. This dataset is then used to train on a convolutional neural network (CNN). Seven different CNN segmentation architectures and eight different feature extractors are tested in order to find the best suited combination for this task. In the operational part, we propose a method to have a real-time, onboard UAV oil spill detection using the pre-trained network and a low power interference device. A controlled experiment in the port of Antwerp showed that we are able to achieve an accuracy of 89% while only using the IR camera.

In this study, we propose a new method to identify corrosion minerals in carbon steel using hyperspectral imaging (HSI) in the shortwave infrared range (900–1700 nm). Seven samples were artificially corroded using a neutral salt spray test and examined using a hyperspectral camera. A normalized cross-correlation algorithm is used to identify four different corrosion minerals (goethite, magnetite, lepidocrocite and hematite), using reference spectra. A Fourier Transform Infrared spectrometer (FTIR) analysis of the scraped corrosion powders was used as a ground truth to validate the results obtained by the hyperspectral camera. This comparison shows that the HSI technique effectively detects the dominant mineral present in the samples. In addition, HSI can also accurately predict the changes in mineral composition that occur over time.

The high incidence of oil spills in port areas poses a serious threat to the environment, prompting the need for efficient detection mechanisms. Utilizing automated drones for this purpose can significantly improve the speed and accuracy of oil spill detection. Such advancements not only expedite cleanup operations, reducing environmental harm but also enhance polluter accountability, potentially deterring future incidents. Currently, there’s a scarcity of datasets employing RGB images for oil spill detection in maritime settings. This paper presents a unique, annotated dataset aimed at addressing this gap, leveraging a neural network for analysis on both desktop and edge computing platforms. The dataset, captured via drone, comprises 1268 images categorized into oil, water, and other, with a convolutional neural network trained using an Unet model architecture achieving an F1 score of 0.71 for oil detection. This underscores the dataset’s practicality for real-world applications, offering crucial resources for environmental conservation in port environments.

This study presents a novel method for the detection and quantification of atmospheric corrosion products on carbon steel. Using hyperspectral imaging (HSI) in the short-wave infrared range (SWIR) (900–1700 nm), we are able to identify the most common corrosion minerals such as: α-FeO(OH) (goethite), γ-FeO(OH) (lepidocrocite), and γ-Fe₂O₃ (maghemite). Six carbon steel samples were artificially corroded in a salt spray chamber, each sample with a different duration (between 1 h and 120 hours). These samples were analysed by scanning X-ray diffraction (XRD) and also using a SWIR HSI system. The XRD data is used as baseline data. A random forest regression algorithm is used for training on the combined XRD and HSI data set. Using the trained model, we can predict the abundance map based on the HSI images alone. Several image correlation metrics are used to assess the similarity between the original XRD images and the HSI images. The overall abundance is also calculated and compared for XRD and HSI images. The analysis results show that we are able to obtain visually similar images, with error rates ranging from 3.27 to 13.37%. This suggests that hyperspectral imaging could be a viable tool for the study of corrosion minerals.

Optical hyperspectral cameras capture the spectral reflectance of materials. Since many materials behave as heterogeneous intimate mixtures with which each photon interacts differently, the relationship between spectral reflectance and material composition is very complex. Quantitative validation of spectral unmixing algorithms requires high-quality ground truth fractional abundance data, which are very difficult to obtain. In this work, we generated a comprehensive laboratory ground truth dataset of intimately mixed mineral powders. For this, five clay powders (Kaolin, Roof clay, Red clay, mixed clay, and Calcium hydroxide) were mixed homogeneously to prepare 325 samples of 60 binary, 150 ternary, 100 quaternary, and 15 quinary mixtures. Thirteen different hyperspectral sensors have been used to acquire the reflectance spectra of these mixtures in the visible, near, short, mid, and long-wavelength infrared regions (350-15385) nm. Overlaps in wavelength regions due to the operational ranges of each sensor and variations in acquisition conditions resulted in a large amount of spectral variability. Ground truth composition is given by construction, but to verify that the generated samples are sufficiently homogeneous, XRD and XRF elemental analysis is performed. We believe these data will be beneficial for validating advanced methods for nonlinear unmixing and material composition estimation, including studying spectral variability and training supervised unmixing approaches. The datasets can be downloaded from the following link: https://github.com/VisionlabHyperspectral/Multisensor_datasets.