A novel marine radar targets extraction approach based on sequential images and Bayesian Network

Ma, Feng; Chen, Yu‐Wang; Yan, Xinping; Chu, Xiumin; Wang, Jin

doi:10.1016/j.oceaneng.2016.04.030

Cited by 31 publications

(15 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al (2013) estimated navigational risks on the Yangtze River using a BN technique; the preliminary structure of the BN was obtained from data via the necessary path condition algorithm, and additional domain knowledge was referenced to further consolidate the structure. Ma et al (2016) presented a BNbased target-extraction method to extract moving vessels from numerous blips captured in frameby-frame radar images; at the beginning, an initial BN structure was established based on expert judgment and was then improved with the help of a K2 scoring algorithm. Akhtar and Utne (2014) developed a Bayesian causal network to analyse maritime accidents using the qualitative model (HFACS) and its taxonomy for structuring fatigue-related factors into levels, which decreased the number of links (correlations) in need.…”

Section: Use Of Bn In Maritime Accident Analysismentioning

confidence: 99%

Bayesian network modelling and analysis of accident severity in waterborne transportation: A case study in China

Wang

Yang

2018

Reliability Engineering & System Safety

140

View full text Add to dashboard Cite

The rapid development of the shipping industry requires the use of large vessels carrying highvolume cargoes. Accidents incurred by these vessels can lead to a heavy loss of life and damage to the environment and property. As a leading country in international trade, China has developed its waterway transport systems, including inland waterways and coastal shipping, in the past decades. A few catastrophic shipping accidents have occurred during this period. This paper aims to develop a new risk analysis approach based on Bayesian networks (BNs) to enable the analysis of accident severity in waterborne transportation. Although the risk data are derived from accidents that occurred in China's waters, the risk factors influencing accident severity and the risk modelling methodology are generic and capable of generating useful insights on waterway risk analysis in a broad sense. To develop the BN-based risk model, waterway accident data are first collected from all accident investigation reports by China's Maritime Safety Administration (MSA) from 1979 to 2015. Based on the derived quantitative data, we identify the factors related to the severity of waterway accidents and use them as nodes of the risk model. Second, based on a receiver operating characteristic (ROC) curve, an augmented naïve BN (ABN) model is selected through a comparative study with a naïve BN (NBN) model to analyse the key risk factors influencing waterway accident severity. The results show that the key factors influencing waterway safety include the type and location of the accident and the type and age of the ship. Moreover, a novel scenario analysis is conducted to predict accident severity in various situations by combining different states (e.g., high risk) of the key factors to generate useful insights for accident prevention. More specifically, the findings can aid transport authorities, ship owners and other stakeholders in improving waterborne transportation safety under uncertainty.

show abstract

Section: Use Of Bn In Maritime Accident Analysismentioning

confidence: 99%

Bayesian network modelling and analysis of accident severity in waterborne transportation: A case study in China

Wang

Yang

2018

Reliability Engineering & System Safety

140

View full text Add to dashboard Cite

show abstract

“…The maritime administrators make their inferences on featured data according to their experience, which comes from the daily observation of massive vessels. The artificial intelligence is typically a kind of probabilistic inference [16].…”

Section: A Proposed Approachmentioning

confidence: 99%

“…Bayesian Inference is one of the most classical methodologies in the probabilistic inference domain, and it is capable of handling the noise data of moving targets [16]. However, the limitation of Bayesian Inference is that it requires the frame of discernment being mutually exclusive and independent.…”

Section: A Proposed Approachmentioning

confidence: 99%

“…Referring to the procedure of vessel classification of maritime administrators, it is feasible to simulate the experiences of administrators based on artificial intelligence that should be able to make conjunctive inference with the SOG, COG, and position. Focused on the extraction of vessel targets in radar images, Ma et al [16] given the similar cognition of building an artificial intelligence base on Bayesian Network. Therefore, building an artificial intelligence for extracting featured AIS data is a typical probabilistic inference issue applied in vessels' spatial-temporal data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

An Internet of Things Approach for Extracting Featured Data Using AIS Database: An Application Based on the Viewpoint of Connected Ships

Malekian

et al. 2017

Symmetry

View full text Add to dashboard Cite

Automatic Identification System (AIS), as a major data source of navigational data, is widely used in the application of connected ships for the purpose of implementing maritime situation awareness and evaluating maritime transportation. Efficiently extracting featured data from AIS database is always a challenge and time-consuming work for maritime administrators and researchers. In this paper, a novel approach was proposed to extract massive featured data from the AIS database. An Evidential Reasoning rule based methodology was proposed to simulate the procedure of extracting routes from AIS database artificially. First, the frequency distributions of ship dynamic attributes, such as the mean and variance of Speed over Ground, Course over Ground, are obtained, respectively, according to the verified AIS data samples. Subsequently, the correlations between the attributes and belief degrees of the categories are established based on likelihood modeling. In this case, the attributes were characterized into several pieces of evidence, and the evidence can be combined with the Evidential Reasoning rule. In addition, the weight coefficients were trained in a nonlinear optimization model to extract the AIS data more accurately. A real life case study was conducted at an intersection waterway, Yangtze River, Wuhan, China. The results show that the proposed methodology is able to extract data very precisely.

show abstract

“…In fact, a considerable proportion of radar blips or objects are caused by noises or stationary objects. In inland waterways or ports, such false or stationary objects are even more than real moving vessels (Ma et al, 2015b). Therefore, radar operators have to identify moving vessels from a plethora of blips manually.…”

Section: Introductionmentioning

confidence: 99%

A novel approach of collision assessment for coastal radar surveillance

Chen

Huang

et al. 2016

Reliability Engineering & System Safety

Self Cite

View full text Add to dashboard Cite

For coastal radar surveillance, this paper proposes a data-driven approach to estimate a blip's collision probability preliminarily based on two factors: the probability of it being a moving vessel and the collision potential of its position. The first factor is determined by a Directed Acyclic Graph (DAG), whose nodes represent the blip's characteristics, including the velocity, direction and size. Additionally, the structure and conditional probability tables of the DAG can be learned from verified samples. Subsequently, obstacles in a waterway can be described as collision potential fields using an Artificial Potential Field model, and the corresponding coefficients can be trained in accordance with the historical vessel distribution. Then, the other factor, the positional collision potential of any position is obtained through overlapping all the collision potential fields. For simplicity, only static obstacles have been considered. Eventually, the two factors are characterised as evidence, and the collision probability of a blip is estimated by combining them with Dempster's rule. Through ranking blips on collision probabilities, those that pose high threat to safety can be picked up in advance to remind radar operators. Particularly, a good agreement between the proposed approach and the manual operation was found in a preliminary test.

show abstract

A novel marine radar targets extraction approach based on sequential images and Bayesian Network

Cited by 31 publications

References 40 publications

Bayesian network modelling and analysis of accident severity in waterborne transportation: A case study in China

Bayesian network modelling and analysis of accident severity in waterborne transportation: A case study in China

An Internet of Things Approach for Extracting Featured Data Using AIS Database: An Application Based on the Viewpoint of Connected Ships

A novel approach of collision assessment for coastal radar surveillance

Contact Info

Product

Resources

About