High-dimensional feature extraction of sea clutter and target signal for intelligent maritime monitoring network

Liu, Ningbo; Xu, Yong; Ding, Hao; Yang, Xue; Guan, Jian

doi:10.1016/j.comcom.2019.08.016

Cited by 16 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the developed approach did not satisfy the instances of jamming in the main lobe. Ningbo et al 18 developed a time-frequency domain processing method with the residual neural network (NN). This method had a high capability to recognize weak targets even in the background of heavy sea clutter and achieved higher classification accuracy.…”

Section: Literature Surveymentioning

confidence: 99%

“…37 One of the recently developed metaheuristic optimization algorithms is MLO, which is inspired from the basic principles of electromagnetic field theory. 18 However, this algorithm provides promising results while solving the optimization problems. In this heuristic algorithm, the search is done by magnetic particles, which is considered as search agents.…”

Section: Training Of Dmon Using Proposed Malo Algorithmmentioning

confidence: 99%

“…On the other side, the feature detector transforms a binary classification issue of target from the problem of target detection and creates a constant and distinguishable judgment area in feature space to examine whether the detected echo includes the background type or target type. 18 Recently, the theory of sparse signal processing technology renders a latest solution for radar detection. 19 However, the moving target detection issue can be transformed into the sparse decomposition domain.…”

Section: Introductionmentioning

confidence: 99%

“…Hence, the deep-learning method has powerful viability to the complex and variable detection background and satisfies the target detection need even in the complicated environmental conditions. 18 This study is developed by employing the proposed Magnetic Ant Lion Optimization (MALO) algorithm for moving target detection based on visual features and deep learning. The proposed approach consists of various stages, such as image reconstruction, gridding, feature extraction, classification of targets, and location detection for the recognition for moving targets.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Visual features and Deep Maxout Network‐based moving target detection using radar signals under sea clutter

Battula

Jaya

2021

Int J Intell Syst

View full text Add to dashboard Cite

Radar echoes have emerged as a rapid technology that is utilized in a wide range of applications especially in target identification under sea-clutter background. The detection of moving targets under a sea-clutter background is still a complex task because of the entering and evacuating of targets, which is highly unpredictable and unexpectable. Because of the lack of essential information, target detection and parameter estimations have become key constraints. Besides, it is very difficult to differentiate directly the small targets from the clutter background. However, the accurate location of the target cannot be determined exactly by the existing approaches.To address such limitations, an efficient strategy is proposed in this study for recognizing the moving targets under sea-clutter background using the proposed Magnetic Ant Lion Optimization algorithm, which is derived by the integration of Magnetic Optimization and Ant Lion Optimization. However, the proposed method achieves effective performance in terms of detection rate, mean-squared error, and the missed target rate with the values of 0.988, 0.012, and 0.224 for vertical-horizontal polarity.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Section: Training Of Dmon Using Proposed Malo Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Visual features and Deep Maxout Network‐based moving target detection using radar signals under sea clutter

Battula

Jaya

2021

Int J Intell Syst

View full text Add to dashboard Cite

show abstract

“…Extracting the high-dimensional time-frequency features of clutter is beneficial to the formation of the high-dimensional feature space which is nonlinear separable between clutter and target [ 22 ]. The autocorrelation matrix of the radar clutter element is selected as the critical feature of clutter classification and recognition.…”

Section: Introductionmentioning

confidence: 99%

Classification Method of Uniform Circular Array Radar Ground Clutter Data Based on Chaotic Genetic Algorithm

Yang

Huang

Xie

et al. 2021

Sensors

View full text Add to dashboard Cite

The classification and recognition of radar clutter is helpful to improve the efficiency of radar signal processing and target detection. In order to realize the effective classification of uniform circular array (UCA) radar clutter data, a classification method of ground clutter data based on the chaotic genetic algorithm is proposed. In this paper, the characteristics of UCA radar ground clutter data are studied, and then the statistical characteristic factors of correlation, non-stationery and range-Doppler maps are extracted, which can be used to classify ground clutter data. Based on the clustering analysis, results of characteristic factors of radar clutter data under different wave-controlled modes in multiple scenarios, we can see: in radar clutter clustering of different scenes, the chaotic genetic algorithm can save 34.61% of clustering time and improve the classification accuracy by 42.82% compared with the standard genetic algorithm. In radar clutter clustering of different wave-controlled modes, the timeliness and accuracy of the chaotic genetic algorithm are improved by 42.69% and 20.79%, respectively, compared to standard genetic algorithm clustering. The clustering experiment results show that the chaotic genetic algorithm can effectively classify UCA radar’s ground clutter data.

show abstract

CNN-Based Sea-Surface Target Detection Using Continuous Wavelet Transform

Ni,

Li,

et al. 2024

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

High-dimensional feature extraction of sea clutter and target signal for intelligent maritime monitoring network

Cited by 16 publications

References 12 publications

Visual features and Deep Maxout Network‐based moving target detection using radar signals under sea clutter

Visual features and Deep Maxout Network‐based moving target detection using radar signals under sea clutter

Classification Method of Uniform Circular Array Radar Ground Clutter Data Based on Chaotic Genetic Algorithm

CNN-Based Sea-Surface Target Detection Using Continuous Wavelet Transform

Contact Info

Product

Resources

About