US20090002224A1 - SAR ATR tree line extended operating condition - Google Patents
SAR ATR tree line extended operating condition Download PDFInfo
- Publication number
- US20090002224A1 US20090002224A1 US11/232,807 US23280705A US2009002224A1 US 20090002224 A1 US20090002224 A1 US 20090002224A1 US 23280705 A US23280705 A US 23280705A US 2009002224 A1 US2009002224 A1 US 2009002224A1
- Authority
- US
- United States
- Prior art keywords
- image
- clutter
- synthetic aperture
- pixels
- radar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/414—Discriminating targets with respect to background clutter
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/9021—SAR image post-processing techniques
- G01S13/9027—Pattern recognition for feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/904—SAR modes
- G01S13/9052—Spotlight mode
Definitions
- This invention is in the field of target identification in the presence of clutter, said clutter generated by trees and associated tree lines.
- Radar target detection and identification have been proven necessary in military surveillance, reconnaissance, and combat missions. The detection and identification of targets provide real-time assessment of the number and the locations of targets of interest.
- One method of target detection and identification is to process the image acquired by the radar using, for example, Synthetic Aperture Radar (SAR) technology.
- SAR Synthetic Aperture Radar
- the general principle behind SAR is to obtain high resolution images by coherently combining the amplitude and phase information of separate radar returns from a plurality of sequentially transmitted pulses from a relatively small antenna on a moving platform.
- the returns from the plurality of pulses transmitted during a SAR image when coherently combined and processed, result in image quality comparable to a longer antenna, corresponding approximately to the synthetic “length” traveled by the antenna during the acquisition of the image.
- the false alarm rate and probability of misdetection also increases when a target of interest is in the vicinity of trees, typically near a tree line.
- the presence of the tree line adds clutter to the SAR image, changing the contour, obfuscating the rendition of a target in the SAR image and thereby significantly reducing the ability of automated processing techniques to detect and identify targets.
- a synthetic aperture radar acquires an image of one or more objects and identifies the one or more objects as targets.
- the one or more objects are located in the proximity of clutter within the image.
- the objects, i.e. possible target candidates, are located in the proximity of trees, or a tree line, and may be partially covered or obscured by the trees.
- the synthetic aperture radar comprises an analog to digital converter for converting a plurality of radar returns into a digital stream, the radar returns representing the clutter and the objects to be identified along with a computer for:
- an object identification (algorithm)
- the object identification utilizes one or more historically known target characteristic and one or more measured characteristic to obtain an output
- an object isolation such, for example, as a Watershed transform
- An example of a historically known target characteristic are bright pixels within the synthetic aperture image.
- An example of a measured target characteristic is a density image above a threshold extracted from the synthetic aperture image.
- An example of an output from the object identification (algorithm) is a density image extracted from the SAR image.
- the density image is composed of a concentration of image pixels having an amplitude above a threshold.
- object isolation is performed using a Watershed transform operating on the density image, or output.
- the one or more objects within the clutter reduced image are sorted in order of most likely to be a target using a criterion indicative of the target's characteristics, such as maximum density.
- FIG. 1 is a SAR radar of the prior art used in generating an image of a target to be identified using the present invention
- FIG. 2 shows the radar of the present invention
- FIG. 3 shows the steps used for object identification
- FIG. 4 shows part 1 of the object isolation—image segmentation portion of this invention
- FIG. 5 shows part 2 of the object isolation—image segmentation portion of this invention.
- FIG. 6 shows the object isolation and object suppression steps of this invention.
- the present invention describes an apparatus and method for separating clutter pixels from object pixels in a SAR image thereby facilitating identification of the object as a target.
- the target is identified by comparing object pixels with previously stored models of targets.
- the invention is suited for SAR Automatic Target Recognition (ATR) tree line Extended Operating Condition where objects, or potential targets, may be partially obscured because of the object location in the vicinity of clutter or clutter causing sources, such as trees, or trees forming tree lines.
- ATR Automatic Target Recognition
- the first step is to acquire a Synthetic Aperture (SAR) image of the scene containing the object to be identified as possible targets.
- FIG. 1 shows the typical prior art geometric relationship between a moving platform carrying a radar transmitter/receiver using Synthetic Aperture (SAR) spotlight methods and scene 107 containing an object (possible target) 101 to be imaged by said radar transmitter/receiver.
- the moving platform is initially at position 103 , travels with velocity V in the direction shown to position 105 .
- SAR spotlight mode the SAR antenna is actively oriented towards object 101 as the platform moves with respect to object 101 with velocity V.
- the moving platform moves from position 103 to position 105 , while adjusting the side looking angle from ⁇ to ⁇ + ⁇ for spotlight mode so that the antenna keeps illuminating scene 107 .
- Antenna illumination with radar energy covers scene 107 during the frame length, and includes object 101 .
- the antenna receive pattern covers scene 107 , and includes object 101 .
- Radar pulses are transmitted and corresponding returns received at many points during the frame length between position 103 and position 105 .
- SAR radar is well known in the art and, for example, is described by W. Carrara, et al, in Spotlight Synthetic Aperture Radar , Artech house, 1995, incorporated herein be reference in its entirety.
- the spotlight mode is used as a SAR example, however, the present invention will function with other SAR mapping/object acquisition methods.
- FIG. 2 shows a synthetic aperture radar 201 for acquiring an image of an object (a possible target) 101 in a scene 107 and computing a target identification for said object 101 .
- the object 101 is located in the proximity of a source of clutter, such as, for example, trees.
- the trees, or similar clutter are within the scene, and generating clutter within the image because of their proximity to the target.
- the target is located in the proximity of trees, or a tree line, and may be partially covered or blocked by the trees.
- the trees generate clutter within the image.
- Synthetic aperture radar 201 comprises analog to digital converter 202 for converting a plurality of radar returns from the scene 107 into a digital stream, said radar returns represent the clutter and the target.
- a computer 200 is provided for converting the digital stream from A/D converter 202 into a synthetic aperture image having clutter pixels descriptive of the clutter and object pixels descriptive of the object to be identified into a possible target.
- Computer 200 also identifies one or more target regions within scene 107 having object pixels within said synthetic aperture image using an object identification 206 .
- Object identification 206 utilizes one or more historically known target characteristic, such as looking for the brightest pixels within the SAR image. Also, Object identification 206 uses measured image characteristics, such as a density of the bright pixels (density image) above a threshold.
- Computer 200 may be remotely located. In this case, the data can be processed in batch mode.
- Computer 200 identifies the boundaries of one or more objects in the synthetic aperture image using image segmentation 204 .
- Segmentation 204 uses a threshold of the density image and application of a watershed algorithm to identify the boundaries of said one or more objects.
- computer 200 deletes associated clutter pixels (or suppresses them from further target identification calculations) from the synthetic aperture image thereby generating a clutter reduced image.
- the clutter reduced image contains the objects (targets), but little, if any, of the clutter.
- Computer 200 compares the clutter reduced image (containing the object pixels) with known images of a probable target until a match is found, said match representing said target identification.
- FIG. 3 Further details explaining the concepts of the invention with an exemplary embodiment is further detailed in FIG. 3 .
- a raw SAR image, or SAR image chip is examined in Identify Brightest Pixels 301 , where the brightest pixels in the image are identified. Typically 2 percent of the top brightest points are identified.
- the distribution of these brightest points is analyzed using a density window of, for example 13 pixels, in Compute Density Image 303 .
- the 13 pixels correspond to a window size approximating that of a typical target in a 1 foot resolution system. For other resolutions, a different number of pixels are applicable, as the window is resolution dependent.
- the result from Compute Density Image 303 is Gaussian Smoothed in compute Gaussian Smoothing 305 using a Gaussian filter size of, for example, 15 pixels and a Gaussian Scaling factor for the filter of 5 pixels, 1 ⁇ 3 the size of the smoothing filter.
- the exemplary Gaussian filter size of 15 pixels is slightly larger than the 13 pixels used in Compute Density Image 303 .
- the Gaussian smoothing facilitates finding the density maxima in Find Density Maxima 307 .
- the density maxima typically corresponds to the object(s) being imaged.
- the density maxima is tested by using Test Using Filters 309 . While many tests are possible, the following examples have been found useful for a best mode implementation:
- Threshold of linear distance from object in pixels use 5 pixels, equating to 5 feet.
- test 309 the maxima is declared to be an object. If test 309 is not met, the maxima in NOT an object and removed from the SAR image by Remove Maxima 311 .
- ELSE 319 redirects the object (SAR image, image chip, portion of SAR image, density image) being analyzed to FIG. 4 .
- FIG. 4 is part of the object isolation/image segmentation portion. If density peaks being examined in FIG. 3 are determined to be an object, the density image is further analyzed to determine the extent of the object. The density image is subjected to a density threshold 402 . That is, every pixel is compared to a threshold. Typically, a threshold 0.10 of maximum amplitude is used. Some portions of the SAR image will pass the threshold, some will not. The points passing the threshold are grouped together into regions L i in Identify Regions L i Within Image 404 . In Number of Objects per Region N/L i , the number of objects N within each identified region are counted. In Test N 408 , there are three outcomes for N:
- N ⁇ 2 it means two or more objects have been found within the region. Thus, it is likely two objects are closely spaced.
- N ⁇ 2 GO TO FIG. 5 , 414 sends the information contained in the respective region to FIG. 5 , to Find Saddle Points 501 for further analysis.
- the density image is presented to Watershed transformation Identify Watersheds W i 515 .
- a Watershed transformation containing one or more objects from 519 is sent to Split L i Using Adjacent W i , 523 . From there, the information is sent to the start of a loop, Find Saddle Points, 501 . After identifying saddle points, adjacent watershed is found in Identify Adjacent Watershed 503 .
- the peak to valley ratio PKSDL is computed in Form Peak/Valley Ratio PKSDL, 505 .
- PKSDL is tested in Test PKSDL 507 .
- the peak is tested with respect to a limit PVT, typically to be 10 percent higher than the neighboring valley.
- the output from 523 is a masked array in Mask Array, 525 containing objects of interest to be sorted by Sort Mask by Maximum Density 602 in W i FIG. 6 .
- masks collected during the process are sorted based on the maximum density present within the mask itself in sort Mask By Maximum Density, 602 .
- the sorted masks are examined in turn to find if they contain a target in Target Mask, 604 . If a target is contained within the mask, then that mask and contents thereof are a SAR image ready for automatic target recognition. If a target is not within the mask, then CDF (Cumulative Density Function) of Non Target Region, 606 computes the CDF. Pixels above the computed CDF are masked in Mask Pixels above CDF, 608 . The pixels found in 608 are replaced with average values of random noise from random noise 612 by Replace with Average, 610 .
- CDF Cumulative Density Function
- a SAR radar is used as an example to acquire images of a target object to be identified
- other imaging means using the same principles are contemplated.
- Sonar generated images are one example of good candidates for this method.
- a SAR radar system is used to exemplify the use of the algorithm for target detection/identification
- a sonar system could be used instead, or any other device that generates a SAR like image/data.
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Analysis (AREA)
Abstract
A synthetic aperture radar acquires an image of one or more objects and identifies them as targets. The objects are located in the proximity of clutter within the image such of trees, or a tree line. The radar acquires a SAR image having pixels descriptive of the clutter and the object(s). Regions having object pixels are identified within the synthetic aperture image using an object identification (algorithm), where the object identification (algorithm) utilizes one or more historically known target characteristics and one or more measured characteristic to obtain an output. Boundaries are identified for the one or more objects within the output using an object isolation, such as, for example, a Watershed transform. Clutter pixels are identified external to the one or more objects. The clutter pixels are suppressed from the synthetic aperture image thereby generating a clutter reduced image containing the one or more objects. The objects are compared with known images of a probable target until a match is found, the match representing the target identification.
Description
- 1. Field of Invention
- This invention is in the field of target identification in the presence of clutter, said clutter generated by trees and associated tree lines.
- 2. Description of the Related Art
- An important function of a radar system, whether a Real Beam type, Synthetic Aperture (SAR) or Interferometric SAR is to detect a target as well as identify it. Radar target detection and identification have been proven necessary in military surveillance, reconnaissance, and combat missions. The detection and identification of targets provide real-time assessment of the number and the locations of targets of interest.
- One method of target detection and identification is to process the image acquired by the radar using, for example, Synthetic Aperture Radar (SAR) technology. By processing a SAR generated image, the features of a target can be extracted and matched to a database for identification.
- The general principle behind SAR is to obtain high resolution images by coherently combining the amplitude and phase information of separate radar returns from a plurality of sequentially transmitted pulses from a relatively small antenna on a moving platform. The returns from the plurality of pulses transmitted during a SAR image, when coherently combined and processed, result in image quality comparable to a longer antenna, corresponding approximately to the synthetic “length” traveled by the antenna during the acquisition of the image.
- Attempts have been made towards target identification extracted from SAR radar images. For example, J. Wissinger, et. al., in MSTAR's Extensible Search Engine and Model-Based Inferencing Toolkit, SPIE 13th Annual International Symposium on AeroSene, Algorithms for SAR Imagery VI, rely on models to implement an algorithm for target identification. During operation, all targets under consideration are forced into one of the known target classes. There is no mechanism to adapt for an unknown target. Thus a high false alarm rate is encountered.
- Similarly, J. De Bonet, P. Viola, and J. Fisher, in Flexible Histograms: A Multiresolution Target Discrimination Model, SPIE Proceedings, 1998, rely only on multiscale features of targets. Again, this yields a relatively high false alarm rate.
- The false alarm rate and probability of misdetection also increases when a target of interest is in the vicinity of trees, typically near a tree line. The presence of the tree line adds clutter to the SAR image, changing the contour, obfuscating the rendition of a target in the SAR image and thereby significantly reducing the ability of automated processing techniques to detect and identify targets.
- Because of above limitations of the prior art, high false alarm rates are encountered, along with inaccurate target detection and target mis-identification, thereby limiting the utility of an imaging and target detection radar.
- A synthetic aperture radar acquires an image of one or more objects and identifies the one or more objects as targets. The one or more objects are located in the proximity of clutter within the image. The objects, i.e. possible target candidates, are located in the proximity of trees, or a tree line, and may be partially covered or obscured by the trees.
- The synthetic aperture radar comprises an analog to digital converter for converting a plurality of radar returns into a digital stream, the radar returns representing the clutter and the objects to be identified along with a computer for:
- converting the digital stream into a synthetic aperture image having clutter pixels descriptive of the clutter and object pixels descriptive of the one or more objects;
- identifying one or more regions having object pixels within the synthetic aperture image using an object identification (algorithm), where the object identification (algorithm) utilizes one or more historically known target characteristic and one or more measured characteristic to obtain an output;
- identifying boundaries for the one or more of objects within the output using an object isolation, such, for example, as a Watershed transform;
- identifying clutter pixels external to the one or more objects;
- suppressing the clutter pixels from the synthetic aperture image thereby generating a clutter reduced image containing the one or more objects;
- comparing each of the one or more objects within the clutter reduced image with known images of a probable target until a match is found, the match representing the target identification.
- An example of a historically known target characteristic are bright pixels within the synthetic aperture image.
- An example of a measured target characteristic is a density image above a threshold extracted from the synthetic aperture image.
- An example of an output from the object identification (algorithm) is a density image extracted from the SAR image. In a typical embodiment, the density image is composed of a concentration of image pixels having an amplitude above a threshold.
- In another typical embodiment, object isolation is performed using a Watershed transform operating on the density image, or output.
- Where faster target identification is desired, the one or more objects within the clutter reduced image are sorted in order of most likely to be a target using a criterion indicative of the target's characteristics, such as maximum density.
- Further target identification speed improvements are gained by having the synthetic aperture image masked to generate one or more masks and then sorted by maximum density of each of said masks.
- In the Drawing:
-
FIG. 1 is a SAR radar of the prior art used in generating an image of a target to be identified using the present invention; -
FIG. 2 shows the radar of the present invention; -
FIG. 3 shows the steps used for object identification; -
FIG. 4 showspart 1 of the object isolation—image segmentation portion of this invention; -
FIG. 5 shows part 2 of the object isolation—image segmentation portion of this invention; and -
FIG. 6 shows the object isolation and object suppression steps of this invention. - The present invention describes an apparatus and method for separating clutter pixels from object pixels in a SAR image thereby facilitating identification of the object as a target. The target is identified by comparing object pixels with previously stored models of targets. The invention is suited for SAR Automatic Target Recognition (ATR) tree line Extended Operating Condition where objects, or potential targets, may be partially obscured because of the object location in the vicinity of clutter or clutter causing sources, such as trees, or trees forming tree lines.
- The first step is to acquire a Synthetic Aperture (SAR) image of the scene containing the object to be identified as possible targets.
FIG. 1 shows the typical prior art geometric relationship between a moving platform carrying a radar transmitter/receiver using Synthetic Aperture (SAR) spotlight methods andscene 107 containing an object (possible target) 101 to be imaged by said radar transmitter/receiver. The moving platform is initially atposition 103, travels with velocity V in the direction shown to position 105. In SAR spotlight mode, the SAR antenna is actively oriented towardsobject 101 as the platform moves with respect toobject 101 with velocity V. The moving platform moves fromposition 103 toposition 105, while adjusting the side looking angle from φ to φ+Δφ for spotlight mode so that the antenna keepsilluminating scene 107. Antenna illumination with radar energy coversscene 107 during the frame length, and includesobject 101. Similarly, the antenna receive pattern coversscene 107, and includesobject 101. Radar pulses are transmitted and corresponding returns received at many points during the frame length betweenposition 103 andposition 105. SAR radar is well known in the art and, for example, is described by W. Carrara, et al, in Spotlight Synthetic Aperture Radar, Artech house, 1995, incorporated herein be reference in its entirety. The spotlight mode is used as a SAR example, however, the present invention will function with other SAR mapping/object acquisition methods. -
FIG. 2 shows asynthetic aperture radar 201 for acquiring an image of an object (a possible target) 101 in ascene 107 and computing a target identification for saidobject 101. Theobject 101 is located in the proximity of a source of clutter, such as, for example, trees. The trees, or similar clutter, are within the scene, and generating clutter within the image because of their proximity to the target. The target is located in the proximity of trees, or a tree line, and may be partially covered or blocked by the trees. The trees generate clutter within the image. -
Synthetic aperture radar 201 comprises analog todigital converter 202 for converting a plurality of radar returns from thescene 107 into a digital stream, said radar returns represent the clutter and the target. - A
computer 200 is provided for converting the digital stream from A/D converter 202 into a synthetic aperture image having clutter pixels descriptive of the clutter and object pixels descriptive of the object to be identified into a possible target. -
Computer 200 also identifies one or more target regions withinscene 107 having object pixels within said synthetic aperture image using anobject identification 206.Object identification 206 utilizes one or more historically known target characteristic, such as looking for the brightest pixels within the SAR image. Also,Object identification 206 uses measured image characteristics, such as a density of the bright pixels (density image) above a threshold. -
Computer 200 may be remotely located. In this case, the data can be processed in batch mode. -
Computer 200 identifies the boundaries of one or more objects in the synthetic aperture image usingimage segmentation 204.Segmentation 204 uses a threshold of the density image and application of a watershed algorithm to identify the boundaries of said one or more objects. - Once the objects have been identified,
computer 200 deletes associated clutter pixels (or suppresses them from further target identification calculations) from the synthetic aperture image thereby generating a clutter reduced image. Now, the clutter reduced image contains the objects (targets), but little, if any, of the clutter. -
Computer 200 compares the clutter reduced image (containing the object pixels) with known images of a probable target until a match is found, said match representing said target identification. - Further details explaining the concepts of the invention with an exemplary embodiment is further detailed in
FIG. 3 . Here, a raw SAR image, or SAR image chip, is examined in IdentifyBrightest Pixels 301, where the brightest pixels in the image are identified. Typically 2 percent of the top brightest points are identified. The distribution of these brightest points is analyzed using a density window of, for example 13 pixels, inCompute Density Image 303. The 13 pixels correspond to a window size approximating that of a typical target in a 1 foot resolution system. For other resolutions, a different number of pixels are applicable, as the window is resolution dependent. The result fromCompute Density Image 303 is Gaussian Smoothed incompute Gaussian Smoothing 305 using a Gaussian filter size of, for example, 15 pixels and a Gaussian Scaling factor for the filter of 5 pixels, ⅓ the size of the smoothing filter. The exemplary Gaussian filter size of 15 pixels is slightly larger than the 13 pixels used inCompute Density Image 303. The Gaussian smoothing facilitates finding the density maxima inFind Density Maxima 307. The density maxima typically corresponds to the object(s) being imaged. The density maxima is tested by usingTest Using Filters 309. While many tests are possible, the following examples have been found useful for a best mode implementation: - a) Relative threshold on density peaks relative to the maximum density peak in the image (chip).
- b) Percentage of top points the peak must have, 5 percent.
- c) Minimum number of pixels the peak must have (minimum target/object size), typical 2 percent of density window.
- d) Threshold of linear distance from object in pixels, use 5 pixels, equating to 5 feet.
- If
test 309 is met, the maxima is declared to be an object. Iftest 309 is not met, the maxima in NOT an object and removed from the SAR image byRemove Maxima 311. - ELSE 319 redirects the object (SAR image, image chip, portion of SAR image, density image) being analyzed to
FIG. 4 . -
FIG. 4 is part of the object isolation/image segmentation portion. If density peaks being examined inFIG. 3 are determined to be an object, the density image is further analyzed to determine the extent of the object. The density image is subjected to adensity threshold 402. That is, every pixel is compared to a threshold. Typically, a threshold 0.10 of maximum amplitude is used. Some portions of the SAR image will pass the threshold, some will not. The points passing the threshold are grouped together into regions Li in Identify Regions Li WithinImage 404. In Number of Objects per Region N/Li, the number of objects N within each identified region are counted. InTest N 408, there are three outcomes for N: - N=0,
- N=1 or
- N≧2.
- For N=0, it means no objects have been found within that particular region Li, thus the region is removed from further consideration in N=0 Remove Li, 410.
- If N=1, it means exactly one object has been found in region Li. Thus the particular Li region where N=1 has been identified as containing an object, and the object is possibly a target. In N=1 MASK ARRAY GO TO
FIG. 6 , 412 a mask is created identifying the region Li in the SAR image that contains the object corresponding to N=1. - If N≧2 it means two or more objects have been found within the region. Thus, it is likely two objects are closely spaced. In this case, N≧2 GO TO
FIG. 5 , 414 sends the information contained in the respective region toFIG. 5 , to FindSaddle Points 501 for further analysis. - As shown in
FIG. 5 , the density image is presented to Watershed transformationIdentify Watersheds W i 515. Number of Objects M per Wi, Test M, 517 finds the spatial extent of a masked region and determines if the detected region has a number of objects (possible targets) found by the Watershed transformation, and tests M. If M>0, 519 will direct a particular Wi for M greater than zero for further consideration. If M=0, Remove Respective Wi, 521 will remove a particular Watershed transformation Wi from consideration, as no objects can be found within. - A Watershed transformation containing one or more objects from 519 is sent to Split Li Using Adjacent Wi, 523. From there, the information is sent to the start of a loop, Find Saddle Points, 501. After identifying saddle points, adjacent watershed is found in Identify
Adjacent Watershed 503. The peak to valley ratio PKSDL is computed in Form Peak/Valley Ratio PKSDL, 505. PKSDL is tested inTest PKSDL 507. Typically PKSDL, the peak is tested with respect to a limit PVT, typically to be 10 percent higher than the neighboring valley. In IFPVT≧PKSDL 509, if PVT is found larger than PKSDL (10 percent), adjacent watershed(s) found in 503 are combined in Combine Adjacent Wi, 511, and sent to 523. Conversely, IF PKSDL≧PVT, 513 is met, there is adequate peak to valley distinction and further saddle points are sought in Split Li Using Adjacent 523. - The output from 523 is a masked array in Mask Array, 525 containing objects of interest to be sorted by Sort Mask by
Maximum Density 602 in WiFIG. 6 . - Continuing with
FIG. 6 , masks collected during the process are sorted based on the maximum density present within the mask itself in sort Mask By Maximum Density, 602. The sorted masks are examined in turn to find if they contain a target in Target Mask, 604. If a target is contained within the mask, then that mask and contents thereof are a SAR image ready for automatic target recognition. If a target is not within the mask, then CDF (Cumulative Density Function) of Non Target Region, 606 computes the CDF. Pixels above the computed CDF are masked in Mask Pixels above CDF, 608. The pixels found in 608 are replaced with average values of random noise fromrandom noise 612 by Replace with Average, 610. - The details of the Watershed transformation as applicable to this disclosure are detailed in The Morphological Approach to Segmentation: The Watershed Transformation Mathematical Morphology in Image Processing, E. R. Dougherty, ed. Optical Engineering, pp 433-482, New York, Basel, Hong Kong, Marcel Dekker, 1993 and in Topographic Distance and Watershed Lines, by F. Meyer, Signal Processing, special issue on mathematical morphology, vol 38, no 1, pp 113-126, July 1996, incorporated herein in their entirety by reference.
- All references cited in this document are incorporated herein in their entirety by reference.
- Although presented in exemplary fashion employing specific embodiments, the disclosed structures are not intended to be so limited. For example, while a SAR radar is used as an example to acquire images of a target object to be identified, other imaging means using the same principles are contemplated. Sonar generated images are one example of good candidates for this method. Furthermore, although a SAR radar system is used to exemplify the use of the algorithm for target detection/identification, a sonar system could be used instead, or any other device that generates a SAR like image/data.
- Those skilled in the art will also appreciate that numerous changes and modifications could be made to the embodiment described herein without departing in any way from the invention.
Claims (14)
1. A side looking synthetic aperture radar for acquiring an image of one or more stationary objects and identifying said one or more stationary objects, said one or more stationary objects located in the proximity of tree clutter within said image, said side looking synthetic aperture radar comprising:
analog to digital converter for converting a plurality of radar returns into a digital stream, said radar returns representing said tree clutter and said stationary objects;
a computer for:
converting said digital stream into a synthetic aperture image having clutter pixels descriptive of said tree clutter and object pixels descriptive of said one or more stationary objects;
identifying one or more regions having object pixels within said synthetic aperture image using a stationary object identification, said stationary object identification utilizing one or more historically known target characteristic and one or more measured characteristic to obtain an output;
identifying boundaries for said one or more stationary objects within said output using an object isolation;
identifying tree clutter pixels external to said one or more stationary objects;
suppressing said tree clutter pixels from said synthetic aperture image thereby generating a clutter reduced image containing said one or more stationary objects;
comparing each of said one or more stationary objects within said clutter reduced image with known images of a probable target until a match is found, said match representing said target identification.
2. A radar as described in claim 1 wherein said historically known target characteristic are bright pixels within said synthetic aperture image.
3. A radar as described in claim 2 wherein said measured target characteristic is a density image above a threshold extracted from said synthetic aperture image.
4. A radar as described in claim 3 wherein said output is said density image above a threshold.
5. A radar as described in claim 4 wherein said object isolation is performed using a Watershed transform operating on said output.
6. A radar as described in claim 5 wherein said one or more objects within said clutter reduced image are sorted in order of most likely to be a target using a criterion.
7. A radar as described in claim 6 wherein portions of said synthetic aperture image are masked to generate one or more masks and then sorted by maximum density of each of said masks.
8. A method for using a side looking synthetic aperture radar for acquiring an image of one or more stationary objects and identifying said one or more stationary objects, said one or more stationary objects located in the proximity of tree clutter within said image, said method comprising the steps of:
converting a plurality of radar returns into a digital stream, said radar returns representing said tree clutter and said stationary objects;
converting said digital stream into a synthetic aperture image having clutter pixels descriptive of said tree clutter and object pixels descriptive of said one or more stationary objects;
identifying one or more regions having object pixels within said synthetic aperture image using a stationary object identification, said stationary object identification utilizing one or more historically known target characteristic and one or more measured characteristic to obtain an output;
identifying boundaries for said one or more stationary objects within said output using an object isolation;
identifying tree clutter pixels external to said one or more stationary objects;
suppressing said tree clutter pixels from said synthetic aperture image thereby generating a clutter reduced image containing said one or more stationary objects;
comparing each of said one or more stationary objects within said clutter reduced image with known images of a probable target until a match is found, said match representing said target identification.
9. A method as described in claim 8 wherein said historically known target characteristic are bright pixels within said synthetic aperture image.
10. A method as described in claim 9 wherein said measured target characteristic is a density image above a threshold extracted from said synthetic aperture image.
11. A method as described in claim 10 wherein said out-put is said density image above a threshold.
12. A method as described in claim 11 wherein said object isolation is performed using a Watershed transform operating on said output.
13. A method as described in claim 12 wherein said one or more objects within said clutter reduced image are sorted in order of most likely to be a target using a criterion.
14. A method as described in claim 13 wherein portions of said synthetic aperture image are masked to generate one or more masks and then sorted by maximum density of each of said masks.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/232,807 US20090002224A1 (en) | 2005-09-22 | 2005-09-22 | SAR ATR tree line extended operating condition |
US12/381,249 US7787657B2 (en) | 2005-09-22 | 2009-03-09 | SAR ATR treeline extended operating condition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/232,807 US20090002224A1 (en) | 2005-09-22 | 2005-09-22 | SAR ATR tree line extended operating condition |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/381,249 Division US7787657B2 (en) | 2005-09-22 | 2009-03-09 | SAR ATR treeline extended operating condition |
Publications (1)
Publication Number | Publication Date |
---|---|
US20090002224A1 true US20090002224A1 (en) | 2009-01-01 |
Family
ID=40159748
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/232,807 Abandoned US20090002224A1 (en) | 2005-09-22 | 2005-09-22 | SAR ATR tree line extended operating condition |
US12/381,249 Active US7787657B2 (en) | 2005-09-22 | 2009-03-09 | SAR ATR treeline extended operating condition |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/381,249 Active US7787657B2 (en) | 2005-09-22 | 2009-03-09 | SAR ATR treeline extended operating condition |
Country Status (1)
Country | Link |
---|---|
US (2) | US20090002224A1 (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101908138A (en) * | 2010-06-30 | 2010-12-08 | 北京航空航天大学 | Identification method of image target of synthetic aperture radar based on noise independent component analysis |
CN102054268A (en) * | 2011-01-06 | 2011-05-11 | 西安电子科技大学 | Adaptive segmentation method of SAR (Stop and Reveres) image water area |
US8350749B1 (en) * | 2009-04-29 | 2013-01-08 | The United States Of America As Represented By The Secretary Of The Air Force | Radar signature database validation for automatic target recognition |
CN103218623A (en) * | 2013-04-24 | 2013-07-24 | 南京理工大学 | Radar target feature extraction method based on self-adaption neighborhood preserving identification projection |
US8872693B1 (en) | 2009-04-29 | 2014-10-28 | The United States of America as respresented by the Secretary of the Air Force | Radar signature database validation for automatic target recognition |
US20160180198A1 (en) * | 2014-12-22 | 2016-06-23 | Cognex Corporation | System and method for determining clutter in an acquired image |
WO2016106216A3 (en) * | 2014-12-22 | 2016-08-25 | Ebay Inc. | Systems and methods for generating virtual contexts |
WO2017052422A1 (en) * | 2015-09-21 | 2017-03-30 | Saab Ab | Detecting objects in images |
US10068371B2 (en) | 2013-11-14 | 2018-09-04 | Ebay Inc. | Extraction of body dimensions from planar garment photographs of fitting garments |
US10204375B2 (en) | 2014-12-01 | 2019-02-12 | Ebay Inc. | Digital wardrobe using simulated forces on garment models |
US10310616B2 (en) | 2015-03-31 | 2019-06-04 | Ebay Inc. | Modification of three-dimensional garments using gestures |
US10366439B2 (en) | 2013-12-27 | 2019-07-30 | Ebay Inc. | Regional item reccomendations |
US10475113B2 (en) | 2014-12-23 | 2019-11-12 | Ebay Inc. | Method system and medium for generating virtual contexts from three dimensional models |
US20210132214A1 (en) * | 2018-05-08 | 2021-05-06 | Nec Corporation | Synthetic aperture radar image analysis system, synthetic aperture radar image analysis method, and synthetic aperture radar image analysis program |
US11055758B2 (en) | 2014-09-30 | 2021-07-06 | Ebay Inc. | Garment size mapping |
US11100054B2 (en) | 2018-10-09 | 2021-08-24 | Ebay Inc. | Digital image suitability determination to generate AR/VR digital content |
US11562505B2 (en) | 2018-03-25 | 2023-01-24 | Cognex Corporation | System and method for representing and displaying color accuracy in pattern matching by a vision system |
CN116908791A (en) * | 2023-09-14 | 2023-10-20 | 中国科学院空天信息创新研究院 | Method for inhibiting strong clutter of down-track SAR by combining space and signal similarity |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9035774B2 (en) * | 2011-04-11 | 2015-05-19 | Lone Star Ip Holdings, Lp | Interrogator and system employing the same |
US8977062B2 (en) | 2013-02-25 | 2015-03-10 | Raytheon Company | Reduction of CFAR false alarms via classification and segmentation of SAR image clutter |
CN103366371B (en) * | 2013-06-25 | 2016-08-10 | 西安电子科技大学 | Based on K distribution and the SAR image segmentation method of textural characteristics |
CN103440490B (en) * | 2013-09-16 | 2016-10-19 | 南京大学 | City impervious surface extracting method under SAR image space-time similarity analysis |
CN103824088B (en) * | 2014-01-23 | 2017-04-19 | 西安电子科技大学 | SAR target variant recognition method based on multi-information joint dynamic sparse representation |
US10088555B2 (en) | 2014-12-15 | 2018-10-02 | Airbus Singapore Private Limited | Automated method for selecting training areas of sea clutter and detecting ship targets in polarimetric synthetic aperture radar imagery |
CN104778717A (en) * | 2015-05-05 | 2015-07-15 | 西安电子科技大学 | SAR image change detection method based on oriented difference chart |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4739401A (en) * | 1985-01-25 | 1988-04-19 | Hughes Aircraft Company | Target acquisition system and method |
US5245347A (en) * | 1980-12-29 | 1993-09-14 | Raytheon Company | All weather tactical strike system (AWTSS) and method of operation |
US5345242A (en) * | 1990-09-27 | 1994-09-06 | Loral Aerospace Corp. | Clutter rejection using connectivity |
US5561431A (en) * | 1994-10-24 | 1996-10-01 | Martin Marietta Corporation | Wavelet transform implemented classification of sensor data |
US5754694A (en) * | 1992-06-30 | 1998-05-19 | Texas Instruments Incorporated | System and method for distinguishing objects |
US5937078A (en) * | 1996-04-10 | 1999-08-10 | The United States Of America As Represented By The Secretary Of The Navy | Target detection method from partial image of target |
US6333986B1 (en) * | 1998-05-08 | 2001-12-25 | Lockheed Martin Corporation | Cepstral method and system for detecting/classifying objects from air-based or space-based images |
US6337654B1 (en) * | 1999-11-05 | 2002-01-08 | Lockheed Martin Corporation | A-scan ISAR classification system and method therefor |
US6426718B1 (en) * | 2000-03-14 | 2002-07-30 | The Boeing Company | Subaperture processing for clutter reduction in synthetic aperture radar images of ground moving targets |
US20030072470A1 (en) * | 2001-10-15 | 2003-04-17 | Lee Henry C. | Two dimensional autonomous isotropic detection technique |
US20030164792A1 (en) * | 2000-07-24 | 2003-09-04 | Mohammed Jahangir | Method and apparatus for recognising a radar target |
US20040267682A1 (en) * | 2001-09-15 | 2004-12-30 | Henrik Baur | Model-based object classification and target recognition |
US20060109161A1 (en) * | 2004-11-23 | 2006-05-25 | Krikorian Kapriel V | Technique for cancellation of elevated clutter for the detection of fixed and ground moving targets under trees |
US7106243B2 (en) * | 2004-11-23 | 2006-09-12 | Raytheon Company | Technique for enhanced quality high resolution 2D imaging of ground moving targets |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6400831B2 (en) * | 1998-04-02 | 2002-06-04 | Microsoft Corporation | Semantic video object segmentation and tracking |
US6956961B2 (en) * | 2001-02-20 | 2005-10-18 | Cytokinetics, Inc. | Extracting shape information contained in cell images |
US20050058322A1 (en) * | 2003-09-16 | 2005-03-17 | Farmer Michael E. | System or method for identifying a region-of-interest in an image |
US20030076980A1 (en) * | 2001-10-04 | 2003-04-24 | Siemens Corporate Research, Inc.. | Coded visual markers for tracking and camera calibration in mobile computing systems |
-
2005
- 2005-09-22 US US11/232,807 patent/US20090002224A1/en not_active Abandoned
-
2009
- 2009-03-09 US US12/381,249 patent/US7787657B2/en active Active
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5245347A (en) * | 1980-12-29 | 1993-09-14 | Raytheon Company | All weather tactical strike system (AWTSS) and method of operation |
US4739401A (en) * | 1985-01-25 | 1988-04-19 | Hughes Aircraft Company | Target acquisition system and method |
US5345242A (en) * | 1990-09-27 | 1994-09-06 | Loral Aerospace Corp. | Clutter rejection using connectivity |
US5754694A (en) * | 1992-06-30 | 1998-05-19 | Texas Instruments Incorporated | System and method for distinguishing objects |
US5982934A (en) * | 1992-06-30 | 1999-11-09 | Texas Instruments Incorporated | System and method for distinguishing objects |
US5561431A (en) * | 1994-10-24 | 1996-10-01 | Martin Marietta Corporation | Wavelet transform implemented classification of sensor data |
US5937078A (en) * | 1996-04-10 | 1999-08-10 | The United States Of America As Represented By The Secretary Of The Navy | Target detection method from partial image of target |
US6333986B1 (en) * | 1998-05-08 | 2001-12-25 | Lockheed Martin Corporation | Cepstral method and system for detecting/classifying objects from air-based or space-based images |
US6337654B1 (en) * | 1999-11-05 | 2002-01-08 | Lockheed Martin Corporation | A-scan ISAR classification system and method therefor |
US20020057216A1 (en) * | 1999-11-05 | 2002-05-16 | Richardson Dennis W. | A-Scan ISAR classification system and method therefor |
US6437728B1 (en) * | 1999-11-05 | 2002-08-20 | Lockheed Martin Corporation | A-scan ISAR target recognition system and method |
US6426718B1 (en) * | 2000-03-14 | 2002-07-30 | The Boeing Company | Subaperture processing for clutter reduction in synthetic aperture radar images of ground moving targets |
US20030164792A1 (en) * | 2000-07-24 | 2003-09-04 | Mohammed Jahangir | Method and apparatus for recognising a radar target |
US20040267682A1 (en) * | 2001-09-15 | 2004-12-30 | Henrik Baur | Model-based object classification and target recognition |
US20030072470A1 (en) * | 2001-10-15 | 2003-04-17 | Lee Henry C. | Two dimensional autonomous isotropic detection technique |
US20060109161A1 (en) * | 2004-11-23 | 2006-05-25 | Krikorian Kapriel V | Technique for cancellation of elevated clutter for the detection of fixed and ground moving targets under trees |
US7095358B2 (en) * | 2004-11-23 | 2006-08-22 | Raytheon Company | Technique for cancellation of elevated clutter for the detection of fixed and ground moving targets under trees |
US7106243B2 (en) * | 2004-11-23 | 2006-09-12 | Raytheon Company | Technique for enhanced quality high resolution 2D imaging of ground moving targets |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8350749B1 (en) * | 2009-04-29 | 2013-01-08 | The United States Of America As Represented By The Secretary Of The Air Force | Radar signature database validation for automatic target recognition |
US8872693B1 (en) | 2009-04-29 | 2014-10-28 | The United States of America as respresented by the Secretary of the Air Force | Radar signature database validation for automatic target recognition |
CN101908138A (en) * | 2010-06-30 | 2010-12-08 | 北京航空航天大学 | Identification method of image target of synthetic aperture radar based on noise independent component analysis |
CN102054268A (en) * | 2011-01-06 | 2011-05-11 | 西安电子科技大学 | Adaptive segmentation method of SAR (Stop and Reveres) image water area |
CN103218623A (en) * | 2013-04-24 | 2013-07-24 | 南京理工大学 | Radar target feature extraction method based on self-adaption neighborhood preserving identification projection |
US10068371B2 (en) | 2013-11-14 | 2018-09-04 | Ebay Inc. | Extraction of body dimensions from planar garment photographs of fitting garments |
US11145118B2 (en) | 2013-11-14 | 2021-10-12 | Ebay Inc. | Extraction of body dimensions from planar garment photographs of fitting garments |
US10410414B2 (en) | 2013-11-14 | 2019-09-10 | Ebay Inc. | Extraction of body dimensions from planar garment photographs of fitting garments |
US11100564B2 (en) | 2013-12-27 | 2021-08-24 | Ebay Inc. | Regional item recommendations |
US10366439B2 (en) | 2013-12-27 | 2019-07-30 | Ebay Inc. | Regional item reccomendations |
US11734740B2 (en) | 2014-09-30 | 2023-08-22 | Ebay Inc. | Garment size mapping |
US11055758B2 (en) | 2014-09-30 | 2021-07-06 | Ebay Inc. | Garment size mapping |
US11599937B2 (en) | 2014-12-01 | 2023-03-07 | Ebay Inc. | Digital wardrobe |
US10204375B2 (en) | 2014-12-01 | 2019-02-12 | Ebay Inc. | Digital wardrobe using simulated forces on garment models |
US10977721B2 (en) | 2014-12-01 | 2021-04-13 | Ebay Inc. | Digital wardrobe |
US9984409B2 (en) | 2014-12-22 | 2018-05-29 | Ebay Inc. | Systems and methods for generating virtual contexts |
US20160180198A1 (en) * | 2014-12-22 | 2016-06-23 | Cognex Corporation | System and method for determining clutter in an acquired image |
US10192283B2 (en) * | 2014-12-22 | 2019-01-29 | Cognex Corporation | System and method for determining clutter in an acquired image |
WO2016106216A3 (en) * | 2014-12-22 | 2016-08-25 | Ebay Inc. | Systems and methods for generating virtual contexts |
US11270373B2 (en) | 2014-12-23 | 2022-03-08 | Ebay Inc. | Method system and medium for generating virtual contexts from three dimensional models |
US10475113B2 (en) | 2014-12-23 | 2019-11-12 | Ebay Inc. | Method system and medium for generating virtual contexts from three dimensional models |
US10310616B2 (en) | 2015-03-31 | 2019-06-04 | Ebay Inc. | Modification of three-dimensional garments using gestures |
US11662829B2 (en) | 2015-03-31 | 2023-05-30 | Ebay Inc. | Modification of three-dimensional garments using gestures |
US11073915B2 (en) | 2015-03-31 | 2021-07-27 | Ebay Inc. | Modification of three-dimensional garments using gestures |
EP3353567A4 (en) * | 2015-09-21 | 2019-04-17 | Saab AB | Detecting objects in images |
WO2017052422A1 (en) * | 2015-09-21 | 2017-03-30 | Saab Ab | Detecting objects in images |
US10571560B2 (en) | 2015-09-21 | 2020-02-25 | Saab Ab | Detecting objects in images |
US11562505B2 (en) | 2018-03-25 | 2023-01-24 | Cognex Corporation | System and method for representing and displaying color accuracy in pattern matching by a vision system |
US20210132214A1 (en) * | 2018-05-08 | 2021-05-06 | Nec Corporation | Synthetic aperture radar image analysis system, synthetic aperture radar image analysis method, and synthetic aperture radar image analysis program |
US11841421B2 (en) * | 2018-05-08 | 2023-12-12 | Nec Corporation | Synthetic aperture radar image analysis system, synthetic aperture radar image analysis method, and synthetic aperture radar image analysis program |
US11487712B2 (en) | 2018-10-09 | 2022-11-01 | Ebay Inc. | Digital image suitability determination to generate AR/VR digital content |
US11100054B2 (en) | 2018-10-09 | 2021-08-24 | Ebay Inc. | Digital image suitability determination to generate AR/VR digital content |
CN116908791A (en) * | 2023-09-14 | 2023-10-20 | 中国科学院空天信息创新研究院 | Method for inhibiting strong clutter of down-track SAR by combining space and signal similarity |
Also Published As
Publication number | Publication date |
---|---|
US20090174595A1 (en) | 2009-07-09 |
US7787657B2 (en) | 2010-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7787657B2 (en) | SAR ATR treeline extended operating condition | |
US7116265B2 (en) | Recognition algorithm for the unknown target rejection based on shape statistics obtained from orthogonal distance function | |
US6897802B1 (en) | Fusion of shape and multiscale features for unknown target rejection | |
Musman et al. | Automatic recognition of ISAR ship images | |
EP0389968B1 (en) | Apparatus and method for extracting edges and lines | |
US6437728B1 (en) | A-scan ISAR target recognition system and method | |
US20050201612A1 (en) | Method and apparatus for detecting people using stereo camera | |
US8422738B1 (en) | Adaptive automated synthetic aperture radar vessel detection method with false alarm mitigation | |
CN103971127B (en) | Forward-looking radar imaging sea-surface target key point detection and recognition method | |
CN111665517B (en) | Density statistics-based single photon laser height finding data denoising method and device | |
KR101891410B1 (en) | Apparatus for classifying target of inverse synthetic aperture radar image using trace transform and method thereof | |
US9098772B2 (en) | Rapid detection | |
Tabatabaei et al. | Automatic detection of the cracks on the concrete railway sleepers | |
Zhang et al. | Moving target shadow detection based on deep learning in video SAR | |
US6756934B1 (en) | Target shadow detector for synthetic aperture radar | |
Petković et al. | An overview on horizon detection methods in maritime video surveillance | |
Al-Saad et al. | Airbus ship detection from satellite imagery using frequency domain learning | |
Arshad et al. | An adaptive moving ship detection and tracking based on edge information and morphological operations | |
Buck et al. | Enhanced ship detection from overhead imagery | |
Liu et al. | An automatic ship detection system using ERS SAR images | |
Wu et al. | Motion detection based on two-piece linear approximation for cumulative histograms of ratio images in intelligent transportation systems | |
Arshad et al. | Adaptive real-time ship detection and tracking using morphological operations | |
Wang et al. | Object detection in side scan sonar | |
Ji et al. | Adaptive underwater sonar image target detection | |
He et al. | An adaptive ship detection algorithm for HRWS SAR images under complex background: Application to sentinel1a data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: RAYTHEON COMPANY, MASSACHUSETTS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:KHATIB, NADER;EZEKIEL, ALBERT;REEL/FRAME:017420/0960 Effective date: 20051121 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |