Search Results (147)

The increasing deployment of underwater vehicles demands accurate and energy-efficient target tracking in sensor networks. However, existing approaches have largely addressed tracking accuracy and energy efficiency in isolation, and a system-level framework that jointly optimizes both remains lacking. To address this gap, this paper proposes a joint optimization framework with two main contributions. First, to improve tracking accuracy under complex maneuvering conditions, we develop an Interactive Multi-Model using Long Short-Term Memory Classification (IMM-LSTM-C) algorithm, which integrates multi-step model likelihoods into an LSTM network for precise motion classification, achieving a 7.1% accuracy improvement over IMM-BP. Second, to reduce network energy consumption while maintaining tracking performance, we introduce an Improved Binary Prairie Dog Optimization (IBPDO) algorithm for node selection, enhanced with Cauchy mutation and opposition-based learning. Simulation results show that IBPDO achieves 6.1–8.2% higher accuracy than BWOA and reduces energy consumption by 12% compared to LNS. Furthermore, the complete joint framework demonstrates synergistic effects, reducing tracking error by 19.3% and energy consumption by 15.4% over the IMM + LNS baseline. The proposed framework provides an effective balance between tracking accuracy and energy efficiency in underwater acoustic sensor networks. Full article

To address the conflict between trajectory fragmentation and the trade-off between association efficiency and data integrity in underwater micro-scale multi-target sonar motion detection and tracking in video sequences, a multi-target motion detection and tracking algorithm based on a dual trajectory storage mechanism and adaptive trajectory association is proposed. The method first obtains target centroids through Gaussian mixture model foreground extraction, morphological post-processing, and connected region analysis. By employing a dual-storage structure consisting of real-time trajectories and complete trajectories, it dynamically adjusts association thresholds based on frame sampling rates to achieve adaptive distance calculation for trajectory tracking. Experimental results demonstrate that the proposed method achieves a completeness rate of 100% in recording valid trajectory point lengths. The adaptive threshold mechanism improves association accuracy to 96.07% while reducing trajectory fragmentation rate to 0.9%. The average association time is 0.28 ms per frame, enabling efficient real-time association while ensuring the integrity of motion trajectory tracking. This research contributes to enhancing real-time detection and tracking capabilities for micro-scale underwater targets and provides support for applications such as underwater security surveillance, marine resource exploration, and intelligent autonomous underwater vehicle navigation. Full article

We present PIRATE (Precision Imaging Real-time Autonomous Tracker and Explorer), a fully autonomous unmanned surface vehicle designed to enable self-operating data collection and persistent tracking of mobile underwater targets through the tight integration of acoustic localization, onboard visual perception, and closed-loop navigation. PIRATE employs a single mobile acoustic receiver to estimate target position using time-difference-of-arrival (TDoA) measurements acquired at different times and locations through planned autonomous motion and uses these estimates to drive adaptive vehicle behavior and activate fine-grained visual sensing in real time. This architecture enables sustained target-driven operation, in which navigation, acoustic monitoring, and visual processing are dynamically coordinated based on mission context and localization uncertainty. The system integrates real-time AI-based visual detection and tracking with automatic mission control, allowing visual perception to operate opportunistically within an acoustically guided tracking loop rather than as a standalone sensing modality. Field experiments in a shallow-water environment demonstrate reliable autonomous navigation, single-receiver acoustic localization with meter-scale accuracy, and stable onboard visual inference under sustained operation. By enabling coupled acoustic tracking and onboard visual perception in a fully autonomous surface platform free of external infrastructure, PIRATE provides a practical foundation for fine-scale behavioral observation, adaptive marine monitoring, and long-duration studies of mobile underwater organisms. We demonstrate this advantage with two possible applications. Full article

Accurate detection of underwater bubble plumes is essential for stable target tracking and quantitative analysis in marine engineering safety monitoring, gas leakage assessment, and environmental studies. However, challenging optical conditions in controlled underwater experiments cause bubble targets to exhibit low contrast, weak boundaries, and large-scale variations, which significantly hinder detection accuracy. To address these challenges, this paper proposes an integrated detection and tracking-based quantitative analysis framework for underwater bubble plumes, termed BubbleQuantTrack, and develops an improved bubble detection model named BubbleDet Y11 based on the YOLOv11 framework. BubbleDet Y11 employs a lightweight reparameterized backbone network, RepViT, to enhance feature representation while maintaining high inference efficiency. In addition, an attentional scale fusion (ASF) module is introduced to fuse multiscale features and apply attention-based reweighting, thereby improving the detection of small-scale bubbles and weak boundary targets and reducing missed detections in complex scenes. Furthermore, a two-stage association tracking strategy based on ByteTrack is used for cross-frame target association, enabling trajectory-level quantitative analysis of bubble motion characteristics. Experimental results show that BubbleDet Y11 achieves 90.8% mAP at IoU 0.5, outperforming the baseline YOLOv11 model while preserving real-time performance, which demonstrates the effectiveness and practical applicability of the proposed method. Full article

In recent years, autonomous underwater vehicles (AUVs) have been increasingly employed for target surveillance and tracking. However, the limited performance and information-processing capability of a single AUV make it difficult to achieve high-precision tracking in practice. To address these challenges, this paper proposes an online-to-offline multi-agent reinforcement learning (MARL) framework that employs offline training on historical data to obtain the expert policy. Then, the optimal policy is generated by online fine-tuning technology, which enhances the training efficiency of reinforcement learning in new scenarios. To expand the surveillance range of AUV swarms, a distributed cooperative strategy based on area information entropy (AIE) is introduced. To reduce energy consumption in complex marine environments containing obstacles and vortices, ocean current and energy consumption models are introduced, together with an energy-efficiency optimization strategy. Furthermore, a long short-term memory (LSTM) network is integrated into the offline-to-online MARL framework to predict time-varying environmental states, thereby improving tracking accuracy and energy efficiency. Experimental results show that the proposed scheme is superior to the baseline schemes in terms of energy consumption, task success rate, and distance between AUVs. In addition, various performance indicators of the extended AUV swarm are also superior to the baseline schemes, demonstrating that the proposed scheme has excellent performance and scalability. Full article

The paper presents the development and preliminary evaluation of a two-dimensional (2-D) network of magnetometers for magnetic anomaly detection. The configuration significantly improves over the existing one-dimensional (1-D) architecture, as it enhances the spatial characterization of magnetic anomalies through the simultaneous acquisition of data over an extended area. This leads to a reliable estimation of the target motion parameters. Each sensor node in the network includes a custom-designed electronic system, integrating a biaxial fluxgate magnetometer that operates in null mode. Deep learning models process the raw measurements collected by the magnetometers and extract structured information that enables both automated detection and preliminary target tracking. In the experimental evaluation, a $5\times 5$ array of nodes was deployed over a $12\times 12$ m² area for terrestrial tests, using moving ferromagnetic cylinders as targets. The results confirmed the feasibility of the 2-D configuration and supported its integration into intelligent, real-time surveillance systems for security and underwater monitoring applications. Full article

Aiming at the robust path-following control problem of underwater snake robot (USR) systems subject to modeling uncertainties and time-varying external disturbances, this paper proposes a robust path-following control algorithm based on a fast fixed-time extended state observer (FTESO). First, a fixed-time stability framework with a shorter settling time than existing systems is introduced, and a novel extended state observation system based on the fixed-time stability framework is constructed. Subsequently, by combining the disturbance estimates from the proposed observer with a nonsingular fast fixed-time path-following controller, a robust fixed-time path-following controller is developed. This control strategy incorporates a dynamic event-triggering mechanism, which accomplishes the path-following task while conserving computational resources. The fixed-time convergence of the closed-loop control system is rigorously proved using Lyapunov stability theory. Furthermore, a novel head joint suppression function is designed to reduce the probability of losing the tracking target. Simulation results demonstrate that, compared with conventional control methods, the proposed approach exhibits superior tracking performance and enhanced disturbance rejection capability in complex underwater environments. Full article

Multi-object tracking (MOT) is a critical task in computer vision, with widespread applications in intelligent surveillance, behavior analysis, autonomous navigation, and marine ecological monitoring. In particular, accurate tracking of underwater fish plays a significant role in scientific fishery management, biodiversity assessment, and behavioral analysis of marine species. However, MOT remains particularly challenging due to low visibility, frequent occlusions, and the highly non-linear, burst-like motion of fish. To address these challenges, this paper proposes an improved tracking framework that integrates Interacting Multiple Model Kalman Filtering (IMM-KF) into DeepSORT, forming a self-adaptive multi-object tracking algorithm tailored for underwater fish tracking. First, a lightweight YOLOv8n (You Only Look Once v8 nano) detector is employed for target localization, chosen for its balance between detection accuracy and real-time efficiency in resource-constrained underwater scenarios. The tracking stage incorporates two complementary motion models—Constant Velocity (CV) for regular cruising and Constant Acceleration (CA) for rapid burst swimming. The IMM mechanism dynamically evaluates the posterior probability of each model given the observations, adaptively selecting and fusing predictions to maintain both responsiveness and stability. The proposed method is evaluated on a real-world underwater fish dataset collected from the East China Sea, comprising 19 species of marine fish annotated in YOLO format. Experimental results show that the IMM-DeepSORT framework outperforms the original DeepSORT in terms of MOTA, MOTP, and IDF1. In particular, it significantly reduces false matches and improves tracking continuity, demonstrating the method’s effectiveness and reliability in complex underwater multi-target tracking scenarios. Full article

Underwater sonar target detection and tracking face persistent challenges due to the complex and variable aquatic environment, resulting in low signal-to-noise ratios and fluctuating intensity levels. These challenges are further exacerbated when detecting small, weakly scattering targets, making effective and stable detection crucial. This paper introduces a nested multi-scale sonar target detection method leveraging random walk principles, based on the local contrast of information entropy and target intensity. The method unfolds in four stages: Initially, target intensity and information entropy are calculated to estimate the potential target range. Subsequently, a multi-scale local contrast descriptor suppresses background noise. The random walk fine local contrast descriptor then distinguishes the target from the background, precisely locating and enhancing the target. Finally, these descriptors are integrated using the nesting principle to enhance targets while suppressing the background. This method has been validated through real lake experiments. Both qualitative and quantitative analyses, along with sequence data analysis, demonstrate superior target detection accuracy compared to traditional baseline methods. Full article

Autonomous underwater vehicles (AUVs) play a critical role in underwater remote sensing and monitoring applications. This paper addresses the problem of navigating multiple AUVs to perform sweep video sensing of unknown underwater regions over uneven seafloors, where visibility is limited by the conical field of view (FoV) of the onboard cameras and by occlusions caused by terrain. Coverage is formulated as a feasibility objective of achieving a prescribed target fraction while respecting vehicle kinematics, actuation limits, terrain clearance, and inter-vehicle spacing constraints. We propose an online, occlusion-aware trajectory planning algorithm that integrates frontier-based goal selection, safe viewing depth estimation with clearance constraints, and model predictive control (MPC) for trajectory tracking. The algorithm adaptively guides a team of AUVs to preserve line of sight (LoS) visibility, maintain safe separation, and ensure sufficient clearance while progressively expanding coverage. The approach is validated through MATLAB simulations on randomly generated 2.5D seafloor surfaces with varying elevation characteristics. Benchmarking against classical lawnmower baselines demonstrates the effectiveness of the proposed method in achieving occlusion-aware coverage in scenarios where fixed-pattern strategies are insufficient. Full article

The aim of the study was to determine correlations between performance of vertical jumps and dolphin kick sprints, and between the results of a dry-land butterfly arm pull test and butterfly arms-only swimming. The study recruited competitive junior male swimmers (15.9 (0.7) years, 179.3 (5.3) cm body height, 64.6 (4.3) kg body mass). On dry land, we measured jump height, lower-limb work and power, as well as peak velocity, power, and force in the butterfly arm pull test. In swimming tests, time, velocity, power, force, and work were assessed during the dolphin kick and butterfly arms-only trials. Pearson’s correlation coefficients and the coefficients of determination were calculated between measurements. The findings showed correlations between swimming velocity and power recorded during the dolphin kick test with jump height, work and power measured in the jump tests (maximum r = 0.90, r² = 0,81, p < 0.05). The best correlations between the results of the jump tests and swim variables were determined for the CJ30s test. The butterfly arm pull test was not associated with all parameters measured by the butterfly arms-only test. Our study demonstrates that targeted dry-land training programmes using exercises like vertical jumps can enhance competitive swimmers’ performance and offer coaches an accessible means of tracking athlete progress. Moreover, such simple drills may serve as a cost-effective approach for early evaluation of strength and power potential and for preventing musculoskeletal injuries, all without requiring pool access or specialized underwater equipment. However, the small and homogeneous sample (n = 12, junior males only) and the absence of reliability analyses limit the generalizability of the results. Full article

This study proposes a novel method to address the instability issues in multi-target bearing-only tracking for passive sonar systems. Utilizing a particle filter-guided on-site training mechanism, the complex multi-classification task is simplified into binary classification (target vs. non-target) by assigning an independent tracker to each target. This enables simultaneous on-site training and deployment of the neural network for tracking. A hybrid CNN-BiLSTM network is constructed: the Convolutional Neural Network (CNN) enhances target feature extraction and non-target discrimination, while the Bidirectional Long Short-Term Memory (BiLSTM) models spatiotemporal dependencies. Their synergy improves trajectory continuity and smoothness. Under simulated conditions, the proposed method reduces the minimum required SNR for stable tracking to −31.78 dB, a significant improvement over the −29.69 dB required by pure particle filtering methods. The average tracking error is also reduced from 0.61° to 0.34°. Both simulations and sea trial data demonstrate that the method maintains stable tracking even during target trajectory crossings, significantly enhancing multi-target tracking accuracy in complex underwater acoustic environments. Full article

This paper is based on the fish lateral line sensing mechanism and aims to determine the coupling relationship between the flow field sensing signal and target source position information. Firstly, according to the flow field distribution characteristics of the target source, the equivalent multipole model of the flow field disturbance during the underwater motion of the SUBOFF model is constructed, and then the target localization function based on the least squares method is established according to the theory of potential flow, and the residual function of the target localization is solved optimally using the quasi-Newton method (QN) to obtain the estimated position of the target source. On this basis, a curved bionic lateral line sensing array is constructed on the surface of a robotic fish, and the estimated location of the target source is obtained. The curvilinear bionic lateral line sensing array is constructed on the surface of the robotic fish, and the effectiveness and robustness of the above localization methods are analysed to validate whether the fish lateral line uses the pressure change to sense the underwater target. Full article

In order to solve problems such as recognition of blind areas which exist in traditional technology in underwater near-field target sensing, this paper constructs an underwater robot target sensing model based on the fish lateral line sensing mechanism and adopts CFD simulation technology to analyze the perturbation characteristic law of the pressure signal in the flow field around the underwater robot. By extracting the pressure signal following the bionic lateral line on the surface of the underwater robot as the target recognition information, the SVM multi-target recognition model is trained and built to realize the perception and recognition of the structural features and attitude features of the underwater robot. The results show that the structural features and attitude features of the underwater robot can be recognized by using the time-domain waveform structural features and spatially symmetric distribution features of the pressure coefficients, and the recognition accuracy can reach over 90%, which reveals the principle of target feature resolution based on the sideline perception signals of the fish nerve center. Full article

Bistatic active sonar enables robust and precise target position and tracking, making it a key technology for autonomous underwater vehicles (AUVs) in underwater surveillance. This paper proposes a multi-information-assisted target tracking algorithm for bistatic active sonar, leveraging spatial and temporal echo signal structures to address the challenges of AUVs in shallow water. First, broadened cluster formations in sonar echoes are analyzed, leading to the integration of a spatial clustering-based data association. This paper departs from conventional methods by fusing target position, echo amplitude, and Doppler information during the movement of AUVs, which can improve the efficiency of association probability computation. The re-derived multi-information-assisted association probability calculation method and algorithmic workflow are explicitly designed for real-time implementation in AUV systems. Simulation experiments verify the feasibility of integrating Doppler and amplitude information. The sea trial data from simulated AUV-deployed bistatic sonar contained only amplitude information due to experimental limitations. By utilizing this amplitude information, the algorithm proposed in this paper demonstrates a 23.95% performance improvement over the traditional probabilistic data association algorithm. The proposed algorithm provides AUVs with enhanced tracking autonomy, significantly advancing their capability in ocean engineering applications. Full article