: This report is a review of the publicly available literature on algorithms for detecting ships in Synthetic Aperture Radar (SAR) imagery, with the aim of recommending algorithms for inclusion in the Analysts' Detection Support System (ADSS). The ADSS is a software system being developed at DSTO for the automatic detection of targets in SAR imagery. We outline the motivations, theory and justifications of the various approaches so that educated comparisons and evaluations can be made. Most current research on ship detection is based on detecting the ship itself rather than its wake. Detection of ship wakes is not addressed in any depth. Ship detection systems generally consist of several stages: land masking; preprocessing; prescreening; and discrimination. We consider each of these stages in turn and discuss the various algorithms which have been used. A basic system for low to medium resolution single channel SAR imagery is recommended and suggestions for improvements and alternatives are made.

/pdf/the-state-of-the-art-in-ship-detection-in-synthetic-aperture-40c27vh09z.pdf

The State-of-the-Art in Ship Detection in Synthetic Aperture Radar Imagery

A building management system for one or more buildings, having a processor and a display for showing a model of a building being managed. The model may be shown as a three dimensional depiction or rendition, or a virtual building. A database may provide information regarding sensors, actuators and other items which may be viewed in conjunction with the displayed model. Information regarding the location and status of the sensors, control devices, and the like, which may be points of interest, may be mapped on the virtual depiction or model of the building. A user or operator may thus move through the building and view and affect rooms, sensing and control devices, and other items, including quick navigation to points of interest, in virtual reality. A recorder and play mechanism may be a significant portion of the system for recording structures, parameters, environment, events and other information of the system.

Building management system

In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task. The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with different emphases at each phase to handle the text in different sizes, orientations, color distributions and backgrounds. We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle. The procedure can significantly improve text detection rate and optical character recognition (OCR) accuracy. Instead of using binary information for OCR, we extract features from an intensity image directly. We propose a local intensity normalization method to effectively handle lighting variations, followed by a Gabor transform to obtain local features, and finally a linear discriminant analysis (LDA) method for feature selection. We have applied the approach in developing a Chinese sign translation system, which can automatically detect and recognize Chinese signs as input from a camera, and translate the recognized text into English.

Automatic detection and recognition of signs from natural scenes

With the rapid growth of Sentinel-1 synthetic aperture radar (SAR) data, how to exploit Sentinel-1 imagery and achieve effective and robust marine surveillance are crucial problems. In this paper, we present the OpenSARShip, a dataset dedicated to Sentinel-1 ship interpretation. The OpenSARShip, providing 11 346 SAR ship chips integrated with automatic identification system messages, owes five essential properties: specificality, large scale, diversity, reliability, and public availability. These properties make sure that the OpenSARShip achieves its objectives. The first is to provide researchers a benchmark dataset to develop applicable and adaptive ship interpretation algorithms and push the performance ceilings of data analysis. The other is to provide a dataset for performing application-oriented quality assessment for Sentinel-1 imagery, which can boost their applications in a targeting way. The construction and the organization of the OpenSARShip are discussed, which show the inside of the dataset and ensure the essential properties. The elaborate geometric and scattering analyses, the benchmark for classification, and the imagery applicability assessment by using the OpenSARShip all demonstrate the applicability and potential of the dataset.

OpenSARShip: A Dataset Dedicated to Sentinel-1 Ship Interpretation

Described herein are systems and methods for presenting building information. In overview, the technologies described herein provide relationships between Building Information Modeling (BIM) data (which includes building schematics defined in terms of standardized three dimensional models) and Building Management System (BMS) data (which includes data indicative of the operation of building components such as HVAC components and the like). Some embodiments use relationships between these forms of data thereby to assist technicians in identifying the physical location of particular pieces of equipment, for example in the context of performing inspections and/or maintenance. In some cases this includes the provision of 2D and/or 3D maps to portable devices, these maps including the location of equipment defined both in BIM and BMS data. In some cases, augmented reality technology is applied thereby to provide richer access to positional information.

Systems and methods for presenting building information

This paper describes, for the first time to the authors' knowledge, the phenomenon of nonuniform azimuth image shift of a rigid body observed in the Radarsat synthetic aperture radar (SAR) images of cruising ships. The effect is caused by the different slant-range velocities of coherent scatterers across the hull associated with the ship motions. The slant-range velocity is estimated from the SAR image of an identified ship, and it is compared with that computed from a numerical model using the ship's specification and meteorological data. The result indicates that the dominant contribution to the nonuniform image shift is the pitching motion of the ship. Further comparison is made with the wave orbital velocity, and the results are shown to be in good agreement. Comparisons are also made between the SAR-derived slant-range velocities of two unknown ships and wave orbital velocities, and reasonable agreement is obtained. One of the ships' images exhibits not only nonuniform shift but also image skew. The latter skewing effect may be caused by rolling of the ship.

Nonuniform azimuth image shift observed in the Radarsat images of ships in motion

One of the main problems in ship detection is the presence of sea clutter inherent to coherent imagery. A traditional approach to differentiate a target embedded in noise is to utilize the statistical property of the clutter with some success. In this paper, we propose a new technique of ship detection based on cross-correlating split-look SAR images. If the inter-look images consist of the correlated images of a ship and clutter, the degree of mutual correlation increases, and from the difference in correlation, the ship can be identified. Applying the present method to RADARSAT (Standard 1) images, we have found the minimum detectable size of ships is 62.6 m. The SAR data used in this application were acquired under fairly calm sea states, such that the ships can be identified by the naked eye. Thus, the method has not been tested in an extreme limit of high sea states, and remains as a further study.

Detection of ships using cross-correlation of split-look SAR images

Changes in electromagnetic properties during thermal aging of duplex stainless steel

This paper reports the development of a container identification mark or number recognition system designed for application to a container terminal. The recognition system recognizes the number or mark on the back surface of a container in an outdoor environment by photographing the mark by a camera system installed on the container gate. Containers in many cases differ in color as well as in layout depending on their owners; the layouts commonly contain one to four horizontal columns or rows of writing or more rarely vertical rows of writing. The container number recognition system is constructed from an illumination intensity sensor and illumination system for handling the outdoor illumination changes, a shutter speed control device, and devices such as filters for handling various container colors. In addition, the proposed system uses a character recognition scheme based on a dynamic design method for recognizing differing character string layouts in container marks or numbers. Field tests have been conducted to obtain a recognition rate of 92.8% for all data, a recognition rate of 97.9% for effective or appropriate data excluding data outside the field of vision, and an average recognition speed of less than 2 seconds. © 2004 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 87(12): 38–50, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.20134

Development of Container Identification Mark Recognition System

PROBLEM TO BE SOLVED: To provide an optimal maintenance plan decision method capable of making a maintenance plan in the whole depreciation period of a plant or a product by quantitatively considering the point of view of costs. SOLUTION: Data related with damage probability and maintenance costs related with a unit or components constituting a plant or a product are stored, and the depreciation period of the plant or components is divided into short maintenance periods with specific intervals, and the states of the unit or components constituting the plant or product when each short maintenance period ends are calculated based on the damage probability, and the unit or components to be inspected or repaired when the short maintenance period starts are selected based on the calculated result, and the inspection and repair costs are calculated by an arithmetic means, and by repeating the calculation until the depreciation fiscal year, the units or components to be maintained can be selected, and the maintenance costs can be calculated.

Kumano Shintaro

Papers

Nonuniform azimuth image shift observed in the Radarsat images of ships in motion

Detection of ships using cross-correlation of split-look SAR images

Changes in electromagnetic properties during thermal aging of duplex stainless steel

Development of Container Identification Mark Recognition System

Optimal maintenance plan decision method