Active sonar target tracking for anti-submarine warfare applications

Wang, J.; Trojan, A. von; Lourey, S.

doi:10.1109/oceanssyd.2010.5603790

Cited by 3 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tracking over the TD matrix is possible through filtering, for example by exploiting variants of the Kalman filter [10] or using blind tracking to handle non-Gaussian clutter [21]. Alternatively, clutter could be classified using a mixture of distributions [25], such that detection is matched to local clutter patterns within the reflected pattern.…”

Section: Related Workmentioning

confidence: 99%

“…The method applies tracking by maximum-likelihood probabilistic data association (ML-PDA) [6], filtering [7], dynamic programming tracking by Markov chain representation [8] and probabilistic multi-hypothesis tracking [9]. Yet, tracking assumes an underline dynamics for the tracked target [10], which may be hard to model for the case of marine animals whose motion tends to be of rapid orientation changes. Considering this, we have recently introduced a probabilistic approach for the case of tracking a single target [11], which allows to detect the target's reflections within the clutter by using the Viterbi algorithm to identify structured patterns within a time-distance (TD) matrix formed by concatenating matched filter's outputs sequentially.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Denoising Autoencoders and Dynamic Programming for Acoustic Detection and Tracking of Underwater Moving Targets

Testolin

Diamant

2020

Sensors

View full text Add to dashboard Cite

Accurate detection and tracking of moving targets in underwater environments pose significant challenges, because noise in acoustic measurements (e.g., SONAR) makes the signal highly stochastic. In continuous marine monitoring a further challenge is related to the computational complexity of the signal processing pipeline—due to energy constraints, in off-shore monitoring platforms algorithms should operate in real time with limited power consumption. In this paper, we present an innovative method that allows to accurately detect and track underwater moving targets from the reflections of an active acoustic emitter. Our system is based on a computationally- and energy-efficient pre-processing stage carried out using a deep convolutional denoising autoencoder (CDA), whose output is then fed to a probabilistic tracking method based on the Viterbi algorithm. The CDA is trained on a large database of more than 20,000 reflection patterns collected during 50 designated sea experiments. System performance is then evaluated on a controlled dataset, for which ground truth information is known, as well as on recordings collected during different sea experiments. Results show that, compared to the benchmark, our method achieves a favorable trade-off between detection and false alarm rate, as well as improved tracking accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Combining Denoising Autoencoders and Dynamic Programming for Acoustic Detection and Tracking of Underwater Moving Targets

Testolin

Diamant

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Alternatively, to manage non-Gaussian noise, various noise density functions has been used [17] with an application for magnetic resonance imaging (MRI) curve evaluation [22]. To deal with non-linearity of measurements, tracking can be achieved using variants of the extended Kalman filter [10], that track radial range and velocity measurements [23], [10]. In [24], solutions to variant tracking applications are compared.…”

Section: Related Workmentioning

confidence: 99%

“…. + M (i, min[j + τ 2 , K]) , (10) where τ 2 corresponds to the maximum drift of the deploying vessel. This way, each column of M takes into account all measurements in a window of length τ 2 .…”

Section: Ignoring Stationary Targetsmentioning

confidence: 99%

“…However, template matching requires prior knowledge about either the environment or the target, which are both considered unknown in the herein provided case. Detection of a moving target is also viewed as a tracking problem and solutions are traditionally obtained through the use of tracking filters; based on an assumed motion model, the filter is set to track multiple possible paths [10], [11]. A different approach is to track the distance-velocity matrix where, for each signal, non-zero velocity components are searched by estimating Doppler shift content in the reverberant signal [12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Active Acoustic Track-Before-Detect Approach for Finding Underwater Mobile Targets

Diamant

Kipnis

Bigal

et al. 2019

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

We consider the challenge of tracking and estimating the size of a single submerged target in a high reverberant underwater environment using a single active acoustic transceiver. This problem is common for a multitude of applications, ranging from the security and safety needs of tracking submerged vehicles and scuba divers, to environmental research and management implications such as the monitoring of pelagic fauna. Considering that the target can be either slow (e.g., a scuba diver) or fastmoving (e.g., a shark), we avoid continuous signalling, and rely on the emission of wideband pulses whose reflection pattern are evaluated and reshaped in a time-distance matrix. As opposed to common approaches that track targets through template matching or by using tracking filters, we avoid making difficult assumptions about the target's reflection patterns or motion type, and instead perform probabilistic tracking using a constraint Viterbi algorithm, whereby detection is determined based on maximum likelihood criterion. In this process, we use the expectation-maximization (EM) approach to manage stationary reflections through distribution analysis, which otherwise may be misidentified as targets. Based on the tracked path, we then evaluate the target's size. To test our approach, we performed extensive simulations as well as eight sea experiments in different environmental settings to track both a scuba diver and a sandbar shark (Carcharhinus plumbeus). The simulation results show a tracking performance that is close to the Cramér-Rao lower bound, and the experiment results show a good trade-off between detection rate and false alarm rate for a low signal-to-clutter ratio of 5 [dB], and average tracking error of 1.5 [m] and 6.5 [m] in the detections of a scuba diver and sandbar shark, respectively. For reproducibility, we share our sea experiment data.

show abstract

Tracking Multiple Underwater Targets Using Adaptive Gaussian Mixture Probability Hypothesis Density Filter With Unknown Clutter Rate

Kim

2024

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

Active sonar target tracking for anti-submarine warfare applications

Cited by 3 publications

References 7 publications

Combining Denoising Autoencoders and Dynamic Programming for Acoustic Detection and Tracking of Underwater Moving Targets

Combining Denoising Autoencoders and Dynamic Programming for Acoustic Detection and Tracking of Underwater Moving Targets

An Active Acoustic Track-Before-Detect Approach for Finding Underwater Mobile Targets

Tracking Multiple Underwater Targets Using Adaptive Gaussian Mixture Probability Hypothesis Density Filter With Unknown Clutter Rate

Contact Info

Product

Resources

About