scholarly journals A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television

2021 ◽  
Vol 9 (11) ◽  
pp. 1199
Author(s):  
Xinglong Liu ◽  
Yicheng Li ◽  
Yong Wu ◽  
Zhiyuan Wang ◽  
Wei He ◽  
...  
Keyword(s):  
Region Of Interest ◽  
Weather Conditions ◽  
Calibration Method ◽  
Closed Circuit ◽  
Automatic Identification ◽  
Identification System ◽  
Closed Circuit Television ◽  
Multi Scale ◽  
Marine Radar ◽  
Ship Recognition

Vessel recognition plays important role in ensuring navigation safety. However, existing methods are mainly based on a single sensor, such as automatic identification system (AIS), marine radar, closed-circuit television (CCTV), etc. To this end, this paper proposes a coarse-to-fine recognition method by fusing CCTV and marine radar, called multi-scale matching vessel recognition (MSM-VR). This method first proposes a novel calibration method that does not use any additional calibration target. The calibration is transformed to solve an N point registration model. Furthermore, marine radar image is used for coarse detection. A region of interest (ROI) area is computed for coarse detection results. Lastly, we design a novel convolutional neural network (CNN) called VesNet and transform the recognition into feature extraction. The VesNet is used to extract the vessel features. As a result, the MVM-VR method has been validated by using actual datasets collected along different waterways such as Nanjing waterway and Wuhan waterway, China, covering different times and weather conditions. Experimental results show that the MSM-VR method can adapt to different times, different weather conditions, and different waterways with good detection stability. The recognition accuracy is no less than 96%. Compared to other methods, the proposed method has high accuracy and great robustness.

Dental Image Segmentation Using Clustering Techniques and Level Set Methods

2019 ◽  
pp. 86-106
Author(s):  
Prabha Sathees
Keyword(s):  
Level Set ◽  
Dental Treatment ◽  
Level Set Methods ◽  
Region Of Interest ◽  
Automatic Identification ◽  
Identification System ◽  
Clustering Techniques ◽  
Enhanced Diffusion ◽  
Diffusion Filtering ◽  
Basic Level

Segmentation is necessary for dental images for finding the parts of the teeth, surrounding tissues, and bones. The human identification system in dental methodology is a tedious and time-consuming process. The automatic identification system is the best solution for dental diagnosis and dental treatment systems. Choosing an appropriate region of interest with high accuracy and success rate is a challenging one. This can be attained with the help of proper segmentation methodologies. The segmentation techniques proposed for the root canal treatment are analyzed and compared. Clustering techniques and level set methods with different edge maps are implemented for the proper analysis of segmentation in dental images. Finally, the integration of coherence-enhanced diffusion filtering in basic level set segmentation methodology seems to be effective in improving the segmentation performance of dental images.

scholarly journals Video-Based Detection Infrastructure Enhancement for Automated Ship Recognition and Behavior Analysis

2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Xinqiang Chen ◽  
Lei Qi ◽  
Yongsheng Yang ◽  
Qiang Luo ◽  
Octavian Postolache ◽  
...  
Keyword(s):  
Behavior Analysis ◽  
Detection System ◽  
Autonomous Vehicle ◽  
Network Capacity ◽  
Automatic Identification ◽  
Identification System ◽  
Maritime Surveillance ◽  
Bounding Boxes ◽  
Ship Recognition ◽  
Ship Behavior

Video-based detection infrastructure is crucial for promoting connected and autonomous shipping (CAS) development, which provides critical on-site traffic data for maritime participants. Ship behavior analysis, one of the fundamental tasks for fulfilling smart video-based detection infrastructure, has become an active topic in the CAS community. Previous studies focused on ship behavior analysis by exploring spatial-temporal information from automatic identification system (AIS) data, and less attention was paid to maritime surveillance videos. To bridge the gap, we proposed an ensemble you only look once (YOLO) framework for ship behavior analysis. First, we employed the convolutional neural network in the YOLO model to extract multi-scaled ship features from the input ship images. Second, the proposed framework generated many bounding boxes (i.e., potential ship positions) based on the object confidence level. Third, we suppressed the background bounding box interferences, and determined ship detection results with intersection over union (IOU) criterion, and thus obtained ship positions in each ship image. Fourth, we analyzed spatial-temporal ship behavior in consecutive maritime images based on kinematic ship information. The experimental results have shown that ships are accurately detected (i.e., both of the average recall and precision rate were higher than 90%) and the historical ship behaviors are successfully recognized. The proposed framework can be adaptively deployed in the connected and autonomous vehicle detection system in the automated terminal for the purpose of exploring the coupled interactions between traffic flow variation and heterogeneous detection infrastructures, and thus enhance terminal traffic network capacity and safety.

Ship Recognition by Integration of SAR and AIS

2012 ◽  
Vol 65 (2) ◽  
pp. 323-337 ◽  
Author(s):  
Sudhir Kumar Chaturvedi ◽  
Chan-Su Yang ◽  
Kazuo Ouchi ◽  
Palanisamy Shanmugam
Keyword(s):  
Dead Reckoning ◽  
Warning System ◽  
Integrated System ◽  
Tokyo Bay ◽  
Automatic Identification ◽  
Identification System ◽  
Sar Image ◽  
Ship Recognition ◽  
Matching Criteria ◽  
Integrated System Design

A novel design of an integrated system using Synthetic Aperture Radar (SAR) image and Automatic Identification System (AIS) data is proposed in this paper for the purpose of identifying ships at sea. TerraSAR-X® (SpotLight mode) images and AIS data collected over Incheon Port (Korea) and Tokyo Bay (Japan) were used on different dates. Four main steps for integration of SAR and AIS based ships can be identified, namely: ‘Time Matching’ to retrieve the respective Dead Reckoning (DR) position of the ships at SAR image acquisition times; ‘Position Matching’ based on a nearest neighbourhood re-sampling method with compensation of position shift; ‘Size Matching’ and ‘Speed Matching’. Under each of the matching criteria, the measurement error in each of the matching criteria was found to be less than 20% and the SAR extracted ship's hull boundaries were presented on a screen to display the system results. The results of this study will contribute to the design a Near-Real-Time (NRT) operational system for ship detection, identification, and classification by SARs in different data acquisition modes over various geographical locations at different acquisition times. This novel integrated system design will provide a most important preliminary step towards integration based on ships' hull monitoring in order to recognize ‘friend’ and ‘foe’ ship targets over a huge oceanic region and would be useful for coast guards as an early warning system.

scholarly journals Real-World Marine Radar Datasets for Evaluating Target Tracking Methods

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4641
Author(s):  
Jaya Shradha Fowdur ◽  
Marcus Baum ◽  
Frank Heymann
Keyword(s):  
Target Tracking ◽  
Target Detection ◽  
Situation Awareness ◽  
Real World ◽  
Autonomous Navigation ◽  
Automatic Identification ◽  
Identification System ◽  
Initial Dataset ◽  
Marine Radar ◽  
German Aerospace

As autonomous navigation is being implemented in several areas including the maritime domain, the need for robust tracking is becoming more important for traffic situation awareness, assessment and monitoring. We present an online repository comprising three designated marine radar datasets from real-world measurement campaigns to be employed for target detection and tracking research purposes. The datasets have their respective reference positions on the basis of the Automatic Identification System (AIS). Together with the methods used for target detection and clustering, a novel baseline algorithm for an extended centroid-based multiple target tracking is introduced and explained. We compare the performance of our algorithm to its standard version on the datasets using the AIS references. The results obtained and some initial dataset specific analysis are presented. The datasets, under the German Aerospace Centre (DLR)’s terms and agreements, can be procured from the company website’s URL provided in the article.

Big Data Insights into Container Vessel Dwell Times

2021 ◽  
pp. 036119812110152
Author(s):  
Daniel Smith
Keyword(s):  
New York ◽  
Los Angeles ◽  
Dwell Time ◽  
Weather Conditions ◽  
Turnaround Time ◽  
Future Research ◽  
Automatic Identification ◽  
Identification System ◽  
Data Sets ◽  
Schedule Adherence

Analysis of automatic identification system (AIS) vessel call records can greatly improve our understanding of container vessel dwell times when coupled with information on port volumes and vessel schedules. Port productivity discussions often use vessel time in port—referred to as dwell time, turnaround time, or berth time—as a primary metric. This emphasis implies a need to understand the factors that determine dwell time, especially in port comparisons. Previous dwell time analyses have been handicapped by limited data. This analysis differs in that it uses a multiyear, multiport database covering all relevant vessel calls at major continental U.S. container ports (Baltimore, Boston, Charleston, Houston, Jacksonville, Long Beach, Los Angeles, Miami, Mobile, New Orleans, Northwest Seaport Alliance, New York–New Jersey, Oakland, Palm Beach, Philadelphia, Port Everglades, Savannah, Virginia, and Wilmington, NC), and by including vessel schedules and seasonality. The analysis indicated a much stronger association of dwell time with expected cargo volume at each call than with vessel capacity, and expected cargo volumes helped explain port dwell time differences. The analysis also found that vessel schedules may be the primary determinants of dwell time, and that schedule adherence may thus be equally important as dwell time per se. Seasonality also affected container vessel dwell time, but that influence may be complex as both weather conditions and seasonal cargo peaks probably affect the outcomes. Promising avenues for future research lie in merging AIS vessel call records with other data sets that, unfortunately, may not yet exist or be accessible.

Capacity Analysis for Bifurcated Estuaries Based on Ship Domain Theory and its Applications

2017 ◽  
Vol 2611 (1) ◽  
pp. 56-64 ◽  
Author(s):  
Xingjian Zhang ◽  
Junmin Mou ◽  
Jianfeng Zhu ◽  
Pengfei Chen ◽  
Rongfang (Rachel) Liu
Keyword(s):  
Traffic Management ◽  
River Estuary ◽  
Weather Conditions ◽  
Transportation Systems ◽  
Water Levels ◽  
Domain Theory ◽  
Yangtze River Estuary ◽  
Automatic Identification ◽  
Identification System ◽  
Estimation Model

The bifurcated estuary is an important segment of marine transportation systems that are themselves becoming increasingly important. Because of branching channels, the cyclical change of water levels, and sophisticated operating rules in many large bifurcated estuaries, it is often difficult to estimate the traffic capacity and simulate ships’ motions, even though it is critically important for traffic management and efficiency. In recent years, the increasing number of ships that collect and contribute to the Automatic Identification System (AIS) have made it possible to monitor traffic flow along waterways, including bifurcated estuaries. This study developed a typical capacity estimation model based on ship domain theory. By using AIS data collected in the Yangtze River estuary, a typical bifurcated estuary system, the study analyzed various physical characteristics, weather conditions, and vessel characteristics to derive related impacts of each on overall capacity of the bifurcated estuary. Validated with practical observations, the method can be applied to similar estuary channel systems to improve waterway operations and management.

scholarly journals Near Real Time Applications for Maritime Situational Awareness

2015 ◽  
Vol XL-7/W3 ◽  
pp. 999-1003 ◽  
Author(s):  
E. Schwarz ◽  
D. Krause ◽  
M. Berg ◽  
H. Daedelow ◽  
H. Maass
Keyword(s):  
Remote Sensing ◽  
Situational Awareness ◽  
Value Added ◽  
Remote Sensing Data ◽  
Image Data ◽  
Weather Conditions ◽  
Automatic Identification ◽  
Identification System ◽  
Product Portfolio ◽  
Other Information

Applications to derive maritime value added products like oil spill and ship detection based on remote sensing SAR image data are being developed and integrated at the Ground Station Neustrelitz, part of the German Remote Sensing Data Center. Products of meteo-marine parameters like wind and wave will complement the product portfolio. Research and development aim at the implementation of highly automated services for operational use. SAR images are being used because of the possibility to provide maritime products with high spatial resolution over wide swaths and under all weather conditions. In combination with other information like Automatic Identification System (AIS) data fusion products are available to support the Maritime Situational Awareness.

Sign in / Sign up

Export Citation Format

Share Document