Object-based image analysis approach for vessel detection on optical and radar images

Abstract. Commercial satellites for Earth observation can integrate conventional positioning and tracking systems for monitoring legal and illegal activities by sea, in order to effectively detect and prevent events threatening human life and environment. This study describes an object-oriented approach to detect vessels combining high- and medium-resolution optical and radar images. Once detected, the algorithm estimates their position, length, and heading and assigns a speed range. Tests are done using WorldView-2, QuickBird, GeoEye-1, Sentinel-2A, COSMO-SkyMed, and Sentinel-1 data imaged in several test sites including China, Australia, Italy, Hong Kong, and the western Mediterranean Sea. Validation of results with data from the automatic identification system shows that the estimates for length and heading have R2  =  0.85 and R2  =  0.92, respectively. Tests for evaluating speed from Sentinel-2 time-lag image displacement show encouraging results, with 70% of estimates’ residuals within ±2  m  /  s. Finally, our method is compared to the state-of-the-art search for unidentified maritime object (SUMO), provided by the European Commission’s Joint Research Centre. Finally, our method is compared to the state-of-the-art SUMO. Tests with Sentinel-1 data show similar results in terms of correct detections. Nevertheless, our method returns a smaller number of false alarms compared to SUMO.

[1]  M. Gianinetto,et al.  DETECTION OF MOVING VEHICLES WITH WORLDVIEW-2 SATELLITE DATA , 2012 .

[2]  Krištof Oštir,et al.  Vessel detection and classification from spaceborne optical images: A literature survey , 2018, Remote sensing of environment.

[3]  A. Kääb,et al.  Motion detection using near-simultaneous satellite acquisitions , 2014 .

[4]  M. Yeremy,et al.  Ocean Surveillance with Polarimetric SAR , 2001 .

[5]  G. Lemoine,et al.  Integrating remote sensing in fisheries control , 2005 .

[6]  Bjørn T. Narheim,et al.  Tracking ship traffic with Space-Based AIS: Experience gained in first months of operations , 2010, 2010 International WaterSide Security Conference.

[7]  Baojun Zhao,et al.  Compressed-Domain Ship Detection on Spaceborne Optical Image Using Deep Neural Network and Extreme Learning Machine , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Heng-Ming Tai,et al.  Inshore Ship Detection in Remote Sensing Images via Weighted Pose Voting , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Michael Teutsch,et al.  Detection and classification of man-made offshore objects in TerraSAR-X and RapidEye imagery: Selected results of the DeMarine-DEKO project , 2011, OCEANS 2011 IEEE - Spain.

[10]  Yuan Tian,et al.  Ship Detection Using Texture Statistics from Optical Satellite Images , 2011, 2011 International Conference on Digital Image Computing: Techniques and Applications.

[11]  Paris W. Vachon,et al.  Ship signatures in synthetic aperture radar imagery , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[12]  Hans C. Graber,et al.  Imaging Ships from Satellites , 2013 .

[13]  Naoki Suzuki,et al.  Benchmarking operational SAR ship detection , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[14]  Hui Zhou,et al.  A Novel Hierarchical Method of Ship Detection from Spaceborne Optical Image Based on Shape and Texture Features , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[15]  J. Campbell,et al.  Ocean surface feature detection with the CCRS along-track InSAR , 1997 .

[16]  M. Sciotti,et al.  Maritime multi-sensor data association based on geographic and navigational knowledge , 2008, 2008 IEEE Radar Conference.

[17]  Marco Gianinetto,et al.  Integration of COSMO-SkyMed and GeoEye-1 Data With Object-Based Image Analysis , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  Haigang Sui,et al.  Automatic ship detection for optical satellite images based on visual attention model and LBP , 2014, 2014 IEEE Workshop on Electronics, Computer and Applications.

[19]  Alexander Bauer,et al.  Object-oriented sensor data fusion for wide maritime surveillance , 2010, 2010 International WaterSide Security Conference.

[20]  Marco Gianinetto,et al.  A combined use of multispectral and SAR images for ship detection and characterization through object based image analysis , 2017, Remote Sensing.

[21]  Jian Yang,et al.  Ship Detection in SAR Imagery via Variational Bayesian Inference , 2016, IEEE Geoscience and Remote Sensing Letters.

[22]  A. Harati-Mokhtari,et al.  Automatic Identification System (AIS): Data Reliability and Human Error Implications , 2007, Journal of Navigation.

[23]  Vincent Pagé,et al.  Characterization of a Bayesian Ship Detection Method in Optical Satellite Images , 2010, IEEE Geoscience and Remote Sensing Letters.

[24]  Laurent Ferro-Famil,et al.  Polarimetric time-frequency analysis of vessels in Spotlight SAR images , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[25]  Jie Ma,et al.  Unsupervised Ship Detection Based on Saliency and S-HOG Descriptor From Optical Satellite Images , 2015, IEEE Geoscience and Remote Sensing Letters.

[26]  Van Wimersma Greidanus Herman.  Assessing the Operationality of Ship Detection from Space , 2005 .

[27]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[28]  Thomas Fritz,et al.  Ship Surveillance With TerraSAR-X , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Thomas Krauß,et al.  TRAFFIC FLOW ESTIMATION FROM SINGLE SATELLITE IMAGES , 2013 .

[30]  Nicolas Longépé,et al.  Ship detection in SAR medium resolution imagery for maritime surveillance: Algorithm validation using AIS data , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[31]  Henri Bouma,et al.  Segmentation and wake removal of seafaring vessels in optical satellite images , 2013, Optics/Photonics in Security and Defence.

[32]  Naouma Kourti,et al.  The SUMO Ship Detector Algorithm for Satellite Radar Images , 2017, Remote. Sens..

[33]  Pierre Soille,et al.  Mass Processing of Sentinel-1 Images for Maritime Surveillance , 2017, Remote. Sens..

[34]  Thomas Krauß.  Exploiting Satellite Focal Plane Geometry for automatic Extraction of Traffic Flow from single optical Satellite Imagery , 2014 .

[35]  Xinwei Zheng,et al.  A New Method on Inshore Ship Detection in High-Resolution Satellite Images Using Shape and Context Information , 2014, IEEE Geoscience and Remote Sensing Letters.

[36]  T.M. Padmaja,et al.  Majority filter-based minority prediction (MFMP): An approach for unbalanced datasets , 2008, TENCON 2008 - 2008 IEEE Region 10 Conference.

[37]  Guang Yang,et al.  Ship Detection From Optical Satellite Images Based on Sea Surface Analysis , 2014, IEEE Geoscience and Remote Sensing Letters.

[38]  Laurent Najman,et al.  A complete processing chain for ship detection using optical satellite imagery , 2010 .

[39]  Branka Cuca,et al.  Evaluation of registration accuracy between Sentinel-2 and Landsat 8 , 2016, International Conference on Remote Sensing and Geoinformation of Environment.

[40]  D. Crisp,et al.  The State-of-the-Art in Ship Detection in Synthetic Aperture Radar Imagery , 2004 .

[41]  Christian Hoffmann,et al.  OBJECT-ORIENTED SHIP DETECTION FROM VHR SATELLITE IMAGES , 2005 .

[42]  H. Greidanus,et al.  A Detailed Comparison between Radar and Optical Vessel Signatures , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[43]  Christoph H. Gierull,et al.  A Compound-Plus-Noise Model for Improved Vessel Detection in Non-Gaussian SAR Imagery , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[44]  Bo Zhang,et al.  Vessel detection and analysis combining SAR images and AIS information , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).