Ship detection and classification from overhead imagery

Buck, Heidi; Sharghi, Elan; Bromley, Keith; Guilas, Chessa; Chheng, Tommy

doi:10.1117/12.754019

Cited by 13 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, radar images can be interpreted independent from clouds or illumination. According to [9], this is one of the reasons why considerably fewer examinations are available for the detection and classification of ships in optical data in contrast to radar data. However, optical data also has its advantages: a comparison of methods for radar and optical data in [10] led to the result that the estimation of ship sizes was more precise in optical data.…”

Section: Development Of Ship Detection For Rapideyementioning

confidence: 96%

“…For example, in [13] a method is described that combines images from different spectral regions which may not always be available. In [9] and [11] images are first characterized into "grey" or "black" images, and the detection is implemented based on image processing methods like thresholding, edge detection and dilation. The application of Genetic Algorithms and Neural Networks for ship characterization showed dissatisfactory results in [14].…”

Section: Development Of Ship Detection For Rapideyementioning

confidence: 99%

“…In [12] wavelet analysis and Radon transform are used for classification of objects. Edge detection and Hough transform are used in [9] to find parallel and perpendicular lines as well as circles. Interesting approaches are described in the literature but a fully mature method is not available yet.…”

Section: Development Of Ship Detection For Rapideyementioning

confidence: 99%

“…For preprocessing some preparatory techniques are described in the literature like land masking and dividing images into smaller parts to gain advantages regarding processing time and local application of operators [9,11,12]. Preprocessing may also include filtering in order to smooth background [13] or histogram stretching for contrast improvement [12].…”

Section: Development Of Ship Detection For Rapideyementioning

confidence: 99%

See 3 more Smart Citations

Detection and classification of man-made offshore objects in TerraSAR-X and RapidEye imagery: Selected results of the DeMarine-DEKO project

Saur

Estable

Zielinski

et al. 2011

OCEANS 2011 IEEE - Spain

View full text Add to dashboard Cite

The project DEKO (Detection of artificial objects in sea areas) is integrated in the German DeMarine-Security project and focuses on the detection and classification of ships and offshore artificial objects relying on TerraSAR-X as well as on RapidEye multispectral optical images. The objectives are 1/ the development of reliable detection algorithms and 2/ the definition of effective, customized service concepts. In addition to an earlier publication, we describe in the following paper some selected results of our work. The algorithms for TerraSAR-X have been extended to a processing chain including all needed steps for ship detection and ship signature analysis, with an emphasis on object segmentation. For Rapid Eye imagery, a ship detection algorithm has been developed. Finally, some applications are described: Ship monitoring in the Strait of Dover based on TerraSAR-X StripMap using AIS information for verification, analyzing TerraSAR-X HighResolution scenes of an industrial harbor and finally an example of surveying a wind farm using change detection

show abstract

Section: Development Of Ship Detection For Rapideyementioning

confidence: 96%

Section: Development Of Ship Detection For Rapideyementioning

confidence: 99%

Section: Development Of Ship Detection For Rapideyementioning

confidence: 99%

Section: Development Of Ship Detection For Rapideyementioning

confidence: 99%

See 2 more Smart Citations

Detection and classification of man-made offshore objects in TerraSAR-X and RapidEye imagery: Selected results of the DeMarine-DEKO project

Saur

Estable

Zielinski

et al. 2011

OCEANS 2011 IEEE - Spain

View full text Add to dashboard Cite

show abstract

“…[1][2][3] The FMV capability focuses on automatically detecting and tracking maritime targets (against a maritime background) in full-motion video; it is intended to be a video analysis tool for extracting meaningful data from FMV with minimal human supervision.…”

Section: Introductionmentioning

confidence: 99%

Marine object detection in UAV full-motion video

Parameswaran¹,

Lane²,

Bagnall³

et al. 2014

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Recent years have seen an increased use of Unmanned Aerial Vehicles (UAV) with video-recording capability for Maritime Domain Awareness (MDA) and other surveillance operations. In order for these efforts to be effective, there is a need to develop automated algorithms to process the full-motion videos (FMV) captured by UAVs in an efficient and timely manner to extract meaningful information that can assist human analysts and decision makers. This paper presents a generalizeable marine object detection system that is specifically designed to process raw video footage streaming from UAVs in real-time. Our approach does not make any assumptions about the object and/or background characteristics because, in the MDA domain, we encounter varying background and foreground characteristics such as boats, bouys and ships of varying sizes and shapes, wakes, white caps on water, glint from the sun, to name but a few. Our efforts rely on basic signal processing and machine learning approaches to develop a generic object detection system that maintains a high level of performance without making prior assumptions about foreground-background characteristics and does not experience abrupt performance degradation when subjected to variations in lighting, background characteristics, video quality, abrupt changes in video perspective, size, appearance and number of the targets. In the following report, in addition to our marine object detection system, we present representative object detection results on some real-world UAV full-motion video data.

show abstract