Sea horizon line (SHL) detection plays a pivotal role in the computational performance improvement of computer applications for the maritime environment by dividing the image into sea and sky regions. This division isolates the region of interest and reduces the computational cost of further processing. Testing and performance evaluation of SHL detection methods require a robust image dataset covering the maritime environment’s features at different geographical, seasonal, and maritime conditions. However, publicly available maritime image datasets are developed under a limited environment with slight-to-moderate variations in maritime features. This article proposes a novel sea image dataset that fills this gap by incorporating various geographical, seasonal, and maritime features. Across West Malaysia, one offshore and four geographically separated onshore locations were selected. On ten different occasions, field observations were recorded using a visual-range optical sensor and weather station. The data collection experiments were conducted between February 2020 until April 2021. The collected data were preprocessed and SHL images were selected based on their high feature diversity. Manual SHL annotation was applied on images, and a ground truth matrix was generated, which serves as a performance benchmark for SHL detection methods. As a result, the dataset presents 2673 high-definition (1920 × 1080 pixels) RGB images having a combination of 36 different geographical, seasonal, and maritime features to test and evaluate computer vision-based SHL detection methods.
Wind-waves exhibit variations both in shape and steepness, and their asymmetrical nature is a well-known feature. One of the important characteristics of the sea surface is the front-back asymmetry of wind-wave crests. The wind-wave conditions on the surface of the sea constitute a sea state, which is listed as an essential climate variable by the Global Climate Observing System and is considered a critical factor for structural safety and optimal operations of offshore oil and gas platforms. Methods such as statistical representations of sensor-based wave parameters observations and numerical modeling are used to classify sea states. However, for offshore structures such as oil and gas platforms, these methods induce high capital expenditures (CAPEX) and operating expenses (OPEX), along with extensive computational power and time requirements. To address this issue, in this paper, we propose a novel, low-cost deep learning-based sea state classification model using visual-range sea images. Firstly, a novel visual-range sea state image dataset was designed and developed for this purpose. The dataset consists of 100,800 images covering four sea states. The dataset was then benchmarked on state-of-the-art deep learning image classification models. The highest classification accuracy of 81.8% was yielded by NASNet-Mobile. Secondly, a novel sea state classification model was proposed. The model took design inspiration from GoogLeNet, which was identified as the optimal reference model for sea state classification. Systematic changes in GoogLeNet’s inception block were proposed, which resulted in an 8.5% overall classification accuracy improvement in comparison with NASNet-Mobile and a 7% improvement from the reference model (i.e., GoogLeNet). Additionally, the proposed model took 26% less training time, and its per-image classification time remains competitive.
Super-pixels represent perceptually similar visual feature vectors of the image. Super-pixels are the meaningful group of pixels of the image, bunched together based on the color and proximity of singular pixel. Computation of super-pixels is highly affected in terms of accuracy if the image has high pixel intensities, i.e., a semi-dark image is observed. For computation of super-pixels, a widely used method is SLIC (Simple Linear Iterative Clustering), due to its simplistic approach. The SLIC is considerably faster than other state-of-the-art methods. However, it lacks in functionality to retain the content-aware information of the image due to constrained underlying clustering technique. Moreover, the efficiency of SLIC on semi-dark images is lower than bright images. We extend the functionality of SLIC to several computational distance measures to identify potential substitutes resulting in regular and accurate image segments. We propose a novel SLIC extension, namely, SLIC++ based on hybrid distance measure to retain content-aware information (lacking in SLIC). This makes SLIC++ more efficient than SLIC. The proposed SLIC++ does not only hold efficiency for normal images but also for semi-dark images. The hybrid content-aware distance measure effectively integrates the Euclidean super-pixel calculation features with Geodesic distance calculations to retain the angular movements of the components present in the visual image exclusively targeting semi-dark images. The proposed method is quantitively and qualitatively analyzed using the Berkeley dataset. We not only visually illustrate the benchmarking results, but also report on the associated accuracies against the ground-truth image segments in terms of boundary precision. SLIC++ attains high accuracy and creates content-aware super-pixels even if the images are semi-dark in nature. Our findings show that SLIC++ achieves precision of 39.7%, outperforming the precision of SLIC by a substantial margin of up to 8.1%.
2 August 2026 in Journal of Atmospheric and Solar-Terrestrial Physics