Skip to content
Open access

Shape-Based Maritime Man-Made Object Detection Using Deep Learning Fusion-Based Neural Network and Region-Based Methods

Nov 2026 · Machines · Vol 14, pp. 1300 · 0 citations · 37 references

TL;DR

The findings demonstrate that emphasizing shape primitives significantly enhances classification robustness against wave textures and solar reflections for large maritime structures and their structural segments, while highlighting the need for future multi-scale extensions to address small SAR targets.

Abstract

Maritime search-and-rescue (SAR) operations typically involve scanning vast sea areas for sparse targets with often unknown appearances, making the process highly labour- and capital-intensive. Automating this task using reconnaissance drones and computer vision offers a significant operational advantage. This study investigates the detection of man-made objects in marine backgrounds without prior knowledge of their specific appearance, relying instead on characteristic visual patterns and shape primitives. To achieve this, two distinct algorithms were developed: a deep learning fusion-based neural network (integrating a convolutional edge filter, an autoencoder, and an artificial neural network) and a classical region-based detector utilizing Canny edge detection and geometric trimming. Both methods were trained and evaluated for binary object presence detection (patch-level classification) using six-fold grouped cross-validation on a custom, balanced dataset of 37,032, 128 × 128 image patches featuring ships, offshore platforms, and wind turbines. Performance was assessed using standard confusion matrix metrics. The fusion-based neural network achieved an exceptional mean F1 score of 0.985 (minimum 0.973 across folds), outperforming baseline networks lacking edge and autoencoder layers. Conversely, while the classical region-based method yielded a lower mean F1 score of 0.686, it demonstrated an outstanding real-time processing speed of 143 frames per second (FPS). To leverage the complementary speed and accuracy of both detectors for future drone-based SAR missions, a conceptual hybrid integration framework combining both methods is outlined. The findings demonstrate that emphasizing shape primitives significantly enhances classification robustness against wave textures and solar reflections for large maritime structures and their structural segments, while highlighting the need for future multi-scale extensions to address small SAR targets and noting that generalization to independent external datasets has not yet been empirically tested.

Read PDF

Similar papers

Open access Sep 2026

Deep Learning-Based Classification of Military Aircraft Types from Satellite Imagery

Automatic classification of military aircraft in satellite imagery is a challenging problem with a high risk of error due to the limited pixel area of targets, variations in image resolution and illumination conditions, background complexity, and strong visual similarity among classes. In this study, a deep learning ap...

Fahrettin Varlik, Cüneyt Özdemir · 0 citations
Sep 2026

SMDS-Net: aerial object detection method based on adaptive multi-scale feature fusion and semantically guided detail preservation

Experimental results on public benchmark datasets demonstrate that the proposed SMDS-Net achieves highly competitive detection accuracy while significantly reducing the number of model parameters and theoretical computational complexity.

Ke-Lei Sun, Jia-Li Xia, Hua-Ping Zhou et al. · 0 citations
Open access Oct 2026

Automated detection of meteor trails in all sky images using Radon transformation and convolutional neural network

We present an automated pipeline for detecting meteor trails in single-frame, half-minute-cadence all-sky images acquired by the Digital Autonomous Fireball Observatories (DAFO) network. Unlike existing approaches that rely either on handcrafted feature extraction or purely data-driven methods, the proposed system comb...

T. Suk, S. Simberová · 0 citations
Open access Sep 2026

Road Rockfall Detection by Integrating Feature Engineering with YOLO and Cascade Decision Fusion

A serial cascaded detection method that integrates an improved YOLO detector with machine-learning-based secondary verification is proposed, demonstrating that interpretable local features can effectively filter out false-positive YOLO candidates, thereby suppressing false alarms and improving overall discrimination pe...

Zhi-Qing Qin, Tao Niu, Cai-Jin Lu et al. · 0 citations
Open access Sep 2026

FPGA-Based Acceleration of a Multiscale Decision Fusion CNN for Radar-Based Object Classification

This paper presents the deployment and system-level characterization of an adopted multiscale decision fusion convolutional neural network (MDF-CNN) for radar-based object classification on the Xilinx Kria KR260 platform and compares two deployment configurations that differ in hardware, numerical precision, software r...

Turki Aldosari, A. Alghaihab, Saleh A. Alshebeili · 0 citations
Review Open access Oct 2026

Comparative Evaluation of Deep Object Detection Architectures for Automatic Target Recognition in Real-World AUV-Acquired Side-Scan Sonar Imagery

Reliable detection of underwater objects is important for mine countermeasures, unexploded-ordnance surveys, navigational-hazard assessment, and subsea infrastructure inspection. Interpretation of side-scan sonar (SSS) imagery is still largely performed by trained human operators, making post-mission analysis time-cons...

Daniel Powarzyński, Norbert Sigiel, Aleksander Cirocki et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.