From unsupervised to semi-supervised anomaly detection methods for HRRP targets

Bauw, Martin; Velasco-Forero, Santiago; Angulo, Jesús; Adnet, Claude; Airiau, Olivier

doi:10.1109/radarconf2043947.2020.9266497

Cited by 9 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is very striking, due to the availability of other communication and sensor technologies. The approaches from Bauw et al [77] and Van Loi et al [78] are both tested on real coastal-surveillance radar datasets. Bauw et al further specifies that one-dimensional high-resolution range profiles are used in their study.…”

Section: Data Sourcesmentioning

confidence: 99%

“…Patroumpas et al formalize scenarios such as fast or close approaches to detect suspicious interactions such as package picking [54]. Based on radar-range profiles, Bauw et al demonstrate, in [77], the detection of the visit of unusual ship types, e.g., fishing vessels, in areas where, normally, tankers and container and cargo vessels operate. This is the only publication which covers the anomaly type of zone entry in our review.…”

Section: Anomaly Typesmentioning

confidence: 99%

See 1 more Smart Citation

Maritime Anomaly Detection for Vessel Traffic Services: A Survey

Stach

Kinkel

Constapel

et al. 2023

JMSE

View full text Add to dashboard Cite

A Vessel Traffic Service (VTS) plays a central role in maritime traffic safety. Regulations are given by the International Maritime Organization (IMO) and Guidelines by the International Association of Marine Aids to Navigation and Lighthouse Authorities (IALA). Accordingly, VTS facilities utilize communication and sensor technologies such as an Automatic Identification System (AIS), radar, radio communication and others. Furthermore, VTS operators are motivated to apply Decision Support Tools (DST), since these can reduce workloads and increase safety. A promising type of DST is anomaly detection. This survey presents an overview of state-of-the-art approaches of anomaly detection for the surveillance of maritime traffic. The approaches are characterized in the context of VTS and, thus, most notably, sorted according to utilized communication and sensor technologies, addressed anomaly types and underlying detection techniques. On this basis, current trends as well as open research questions are deduced.

show abstract

Section: Data Sourcesmentioning

confidence: 99%

Section: Anomaly Typesmentioning

confidence: 99%

Maritime Anomaly Detection for Vessel Traffic Services: A Survey

Stach

Kinkel

Constapel

et al. 2023

JMSE

View full text Add to dashboard Cite

show abstract

“…In the area of target identification and detection domain. Bauw et al addressed the challenges of detecting unusual radar targets using semi-supervised anomaly detection methods (SAD) [85]. High resolution range profiles targets identification by ML has recently received a lot of traction in the radar research community.…”

Section: Target Identification and Trackingmentioning

confidence: 99%

Artificial intelligence meets radar resource management: A comprehensive background and literature review

Hashmi

Akbar

Adve

et al. 2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

A multi‐function radar is designed to perform disparate functions, such as surveillance, tracking, fire control, amongst others, within a limited resource (time, frequency, and energy) budget. A radar resource management (RRM) module within a radar system makes decisions on prioritisation, parameter selection, and scheduling of associated tasks. However, optimal RRM algorithms are generally computationally complex and operational radars resort to heuristics. On the other hand, algorithms based on artificial intelligence (AI) have been shown to yield near‐optimal radar resource allocation results at manageable computational complexity. This survey study aims at enabling researchers and practitioners better understand the application of AI in RRM‐related problems by providing a thorough literature review of AI‐based RRM techniques. We first provide background concepts in RRM followed by a brief review of Symbolic‐AI techniques for RRM. We mainly focus on the applications of state‐of‐the‐art machine learning techniques to RRM. We emphasise on the recent findings and their potential within practical RRM scenarios for real‐time resource allocation optimisation. The study concludes with a discussion of open research problems and future research directions in the light of the presented survey.

show abstract

“…However, these methods need to manually extract the features of the HRRP signal. To learn the feature extraction method, the Deep Support Vector Data Description (DeepSVDD) project is proposed which includes a normality hypersphere using a neural network [6]. In these years, a convolutional neural network (CNN) is widely developed in target detection [7].…”

Section: Introductionmentioning

confidence: 99%

HDT network: A high‐resolution range profile multi‐target detection and tracking method based on neural network

Sun

Liu

Wang

et al. 2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

In radar target detection and tracking tasks, the detection algorithm and data association algorithm are the primary technologies. The accuracy of detection, stability of tracking and processing speed are the key points to accomplishing effective high‐resolution range profile (HRRP) multi‐target tracking (MTT). Classic HRRP target tracking algorithms conduct the detection by extracting handcraft features and conduct tracking based on the data association algorithm. With the development of neural network methods, deep learning methods have been widely applied in target detection and tracking. An HRRP detection and tracking (HDT) network based on neural networks is proposed, which includes three steps: Firstly, the HRRP signal is processed by a convolutional neural network detector to extract the feature of the origin signal and generate the detection measurement. Secondly, a predicted measurement is generated by a Kalman filter, which estimates the current state of the target based on its previous states and the detection measurement. Finally, the ReID network calculates the cosine similarity between the tracks and measurements to associate them and a linear sum assignment operation is used to match the tracks and measurements. By using the proposed algorithm, the HDT network is capable of detecting and tracking multiple targets in complex cluttered environments with high accuracy. Experimental results on an HRRP dataset collected by a moving radar platform show the outstanding performance of the HDT network, including detection accuracy, track integrity and real‐time MTT.

show abstract

From unsupervised to semi-supervised anomaly detection methods for HRRP targets

Cited by 9 publications

References 14 publications

Maritime Anomaly Detection for Vessel Traffic Services: A Survey

Maritime Anomaly Detection for Vessel Traffic Services: A Survey

Artificial intelligence meets radar resource management: A comprehensive background and literature review

HDT network: A high‐resolution range profile multi‐target detection and tracking method based on neural network

Contact Info

Product

Resources

About