CN113064162A - Detection method and device applied to radar system for detecting foreign matters on airfield runway - Google Patents
Detection method and device applied to radar system for detecting foreign matters on airfield runway Download PDFInfo
- Publication number
- CN113064162A CN113064162A CN202110364726.3A CN202110364726A CN113064162A CN 113064162 A CN113064162 A CN 113064162A CN 202110364726 A CN202110364726 A CN 202110364726A CN 113064162 A CN113064162 A CN 113064162A
- Authority
- CN
- China
- Prior art keywords
- detection
- data
- target area
- real
- target
- 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.)
- Granted
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
- 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
- G01S13/885—Radar or analogous systems specially adapted for specific applications for ground probing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a detection method and a device applied to a radar system for detecting foreign matters on an airport runway, wherein the method comprises the following steps: continuously scanning a target area without foreign matters to obtain initial background data; carrying out azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image; removing other edge lines except the maximum edge line of the target area in the two-dimensional radar image by using the non-continuity characteristic of the edge of the target area and the layout geometric relationship of the radar equipment in the target area; extracting a target area in the two-dimensional radar image according to the maximum edge line of the target area to obtain an interested area; scanning the region of interest in real time to obtain real-time data; and establishing a clutter map according to the initial background data, and performing constant false alarm detection on the real-time data by using the clutter map to obtain foreign matter detection information. The method improves the detection probability in a multi-target and long-distance environment, and ensures the real-time and continuous requirements of the airport on the detection of foreign matters on the runway.
Description
Technical Field
The invention relates to the technical field of radar detection, in particular to a detection method and device applied to a radar system for detecting foreign matters on an airport runway and electronic equipment.
Background
Airport runway Foreign Objects (FOD) generally refer to Debris or objects that present on the airport runway and are harmful to aircraft and humans, such as aircraft spilled devices, cement blocks, birds, and the like.
The civil aviation administration stipulates that at least four times of closed manual inspection is carried out on the road surface every day to clean FOD foreign matters, but the conventional manual inspection mode has the defects of low efficiency, poor reliability, reduced navigation efficiency and the like.
In addition, there are methods of optical video detection and radar detection, where the optical video detection is through optical image recognition, and the recognition of the foreign object is affected by the resolution of the optical image, and the recognition efficiency is not high. When radar is used for detection, foreign object targets with weak backscattering are easy to miss detection, false alarms are easy to be caused by strong ground clutter and runway edge clutter, and effective detection under the conditions of end-to-end automation, multiple targets and long distance cannot be achieved. How to effectively improve the remote detection capability of the runway foreign object detection radar system becomes one of the problems to be solved urgently in application.
Disclosure of Invention
Technical problem to be solved
Aiming at the technical problems in the prior art, the invention provides a detection method, a detection device and electronic equipment applied to a radar system for detecting foreign matters on an airport runway, wherein the radar system for detecting foreign matters on the runway is used for solving the problems of end-to-end automatic processing, detection in a multi-target environment and effective detection under a long-distance condition. The invention provides a method for automatically extracting a runway interesting region by combining discontinuous characteristics, a time domain clutter map detection method and quantitative indexes of a confusion matrix combining detection results and reference truth values, which can overcome the occurrence of false alarms of clutter in spatial distribution, have better detection capability under the condition of multi-target and remote detection, and can objectively and comprehensively evaluate the performance condition of a target detection system by clear and complete quantitative evaluation indexes, so as to at least partially solve the technical problems.
(II) technical scheme
The invention provides a detection method applied to a radar system for detecting foreign matters on an airport runway, which comprises the following steps: continuously scanning a target area without foreign matters to obtain initial background data; carrying out azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image; removing other edge lines except the maximum edge line of the target area in the two-dimensional radar image by using the non-continuity characteristic of the edge of the target area and the layout geometric relationship of the radar equipment in the target area; extracting a target area in the two-dimensional radar image according to the maximum edge line of the target area to obtain an interested area; scanning the region of interest in real time to obtain real-time data; and establishing a clutter map according to the initial background data, and performing constant false alarm detection on the real-time data by using the clutter map to obtain foreign matter detection information.
Optionally, removing other edge lines in the two-dimensional radar image except the maximum edge line of the target area by using the non-continuity feature of the edge of the target area and the layout geometric relationship of the radar device in the target area includes: bilateral filtering preprocessing is carried out on the discontinuous characteristics of the edge of the target area, and the gradient size and the gradient direction of the edge of the preprocessed area corresponding to the layout geometric relationship of the radar equipment in the target area are calculated; and removing other edge lines except the maximum edge line of the target area in the two-dimensional radar image according to the gradient size and the gradient direction.
Optionally, a clutter map is established according to the initial background data, and the clutter map is used to perform constant false alarm detection on the real-time data, and the obtaining of the foreign object detection information includes: by the formula:
Al(m，n)＝(1-v)Al-1(m，n)+vXl(p，q)
performing iterative computation on the clutter map data; where l is the number of iterations, AlIs the data of the clutter map after the update, Al-1Is data, X, of a previous update of the clutter maplData obtained by scanning an interested region in real time, (m, n) are pixel point coordinates in a clutter map, and (p, q) are data obtained by scanning the interested region in real timeCoordinates of pixel points in the radar image obtained by the domain, wherein (m, n) and (p, q) correspond to coordinates of the same point in a target area, v is a weighting coefficient, and the value of v is based on the number of times l of iterative computation and the constant false alarm probability value of target detection; registering the real-time data according to the azimuth angle for registering the initial background data; comparing the ratio of the registered real-time data and clutter map data subjected to iterative computation with the threshold value, and marking the point corresponding to the real-time data which is greater than or equal to the threshold value as a target point; and processing the connected domain of the target point, and taking the center of mass of the connected domain as the position of the target foreign matter to obtain the foreign matter detection information.
Optionally, the processing the connected domain of the marked point to obtain the foreign object detection information includes: and carrying out connected domain processing on the marked points by any one of methods of a 4-connected domain, an 8-connected domain, a D-connected domain, Two-Pass and Seed Filling to obtain foreign matter detection information.
Optionally, the detection method applied to the radar system for detecting foreign matters on airfield runways further comprises the following steps: and establishing a confusion matrix according to the foreign matter detection information and the foreign matter number in the reference true value, and calculating the detection probability, the false alarm probability, the missed detection probability and the Kappa coefficient by using the confusion matrix.
Optionally, the performing azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image includes: taking the azimuth angle of the first scanning data as a main value, and registering the data obtained by subsequent scanning to the angle same as the main value through any one algorithm of linear interpolation, polynomial interpolation or sinc interpolation; and performing pulse compression and relative amplitude correction on the registered data in the distance direction to obtain a two-dimensional radar image.
Optionally, establishing a clutter map according to the initial background data, and performing constant false alarm detection on the real-time data by using the clutter map to obtain the foreign object detection information further includes: marking points corresponding to the real-time data smaller than the threshold value as non-target points; and iteratively updating the clutter map by using the non-target point.
Optionally, performing at least 10 iterative calculations on the clutter map data according to a formula; wherein the value range of w corresponding to at least 10 times of iterative computation is less than 0.5.
Another aspect of the present invention provides a foreign object detection apparatus including: the data acquisition module is used for continuously scanning a target area without foreign matters to obtain initial background data and scanning an interested area in real time to obtain real-time data; the interesting region acquisition module is used for carrying out azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image, removing other edge lines except the maximum edge line of the target region in the two-dimensional radar image by utilizing the discontinuous characteristics of the edge of the target region and the layout geometric relationship of radar equipment in the target region, and extracting the target region in the two-dimensional radar image according to the maximum edge line of the target region to obtain an interesting region; and the foreign matter information acquisition module is used for establishing a clutter map according to the initial background data and performing constant false alarm detection on the real-time data in a time domain by using the clutter map to obtain foreign matter detection information.
Another aspect of the present invention provides an electronic device, including: one or more processors; a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the detection method of any one of the embodiments of the present invention as applied to an airport runway foreign object detection radar system.
(III) advantageous effects
The invention provides a detection method applied to a radar system for detecting foreign matters on an airport runway, which removes other edge lines except the maximum edge line of a target area in a two-dimensional radar image by utilizing the non-continuity characteristic of the edge of the target area and the layout geometric relationship of radar equipment in the target area, reduces the complexity of the edge characteristic of the target area, can improve the automation degree of the system and further improves the detection efficiency.
Based on initial background data obtained by continuously scanning a target area, a clutter map is established by the initial background data, constant false alarm detection can be carried out on real-time scanned data from a time domain, the influence of severe change on a clutter space position and the influence of false alarm caused by clutter edges are overcome, and the detection efficiency in a long-distance and multi-target scene is improved.
Through calculation of the confusion matrix, a set of quantitative evaluation indexes is established, the single and overall performance of the detection system can be evaluated completely and definitely, and compared with the traditional method for calculating the proportion of correct number in the detection result of the placed target, the method is more comprehensive and objective, and provides reference for evaluation of the performance of the detection system.
The detection method applied to the radar system for detecting foreign matters on the airfield runway replaces manual inspection and cleaning, the navigation efficiency of the airfield is not influenced, and the requirements of the airfield on the real-time property and the continuity of the detection of the foreign matters on the runway are met.
The method has the advantages that the detection probability is improved under the detection environment of multiple targets and long-distance targets while the stable false alarm probability is maintained, and the method is particularly suitable for automatic runway foreign matter detection scenes of a support radar real-time monitoring runway area.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram showing an application scenario of a detection method applied to a radar system for detecting foreign matters on an airport runway according to an embodiment of the invention;
FIG. 2 schematically illustrates a flow chart of a detection method applied to an airport runway foreign object detection radar system, in accordance with an embodiment of the present invention;
FIG. 3 schematically illustrates a flow chart of a two-dimensional radar image acquisition method according to an embodiment of the invention;
FIG. 4 schematically illustrates a radar two-dimensional image under a rectangular coordinate system detected in real time according to an embodiment of the invention;
FIG. 5 schematically illustrates a flow chart of a target area edge processing method according to an embodiment of the invention;
FIG. 6 schematically illustrates an automatically extracted runway area of interest radar two-dimensional image, according to an embodiment of the invention;
FIG. 7 schematically illustrates a flow diagram of a constant false alarm detection method according to an embodiment of the invention;
FIG. 8 schematically illustrates a foreign object target marking result graph according to an embodiment of the present invention;
FIG. 9 schematically illustrates a flow chart of a detection method applied to an airport runway foreign object detection radar system, in accordance with another embodiment of the present invention;
fig. 10 schematically shows a block diagram of a foreign object detection apparatus according to an embodiment of the present invention;
FIG. 11 schematically shows a block diagram of an electronic device according to an embodiment of the invention.
[ description of reference ]
1-airport runway
2-radar positioning device
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It should be noted that in the drawings or description, the same drawing reference numerals are used for similar or identical parts. Features of the embodiments illustrated in the description may be freely combined to form new embodiments without conflict, and each claim may be individually referred to as an embodiment or features of the claims may be combined to form a new embodiment, and in the drawings, the shape or thickness of the embodiment may be enlarged and simplified or conveniently indicated. Further, elements or implementations not shown or described in the drawings are of a form known to those of ordinary skill in the art. Additionally, while exemplifications of parameters including particular values may be provided herein, it is to be understood that the parameters need not be exactly equal to the respective values, but may be approximated to the respective values within acceptable error margins or design constraints.
Unless a technical obstacle or contradiction exists, the above-described various embodiments of the present invention may be freely combined to form further embodiments, which are within the scope of the present invention.
Although the present invention has been described in connection with the accompanying drawings, the embodiments disclosed in the drawings are intended to be illustrative of preferred embodiments of the present invention and should not be construed as limiting the invention. The dimensional proportions in the figures are merely schematic and are not to be understood as limiting the invention.
Although a few embodiments of the present general inventive concept have been shown and described, it would be appreciated by those skilled in the art that changes may be made in these embodiments without departing from the principles and spirit of the general inventive concept, the scope of which is defined in the claims and their equivalents.
Fig. 1 is a schematic diagram showing an application scenario of a detection method applied to an airport runway foreign matter detection radar system according to an embodiment of the invention. It should be noted that fig. 1 is only an example of an application scenario in which the embodiment of the present invention may be applied to help those skilled in the art understand the technical content of the present invention, and does not mean that the embodiment of the present invention may not be applied to other devices, systems, environments or scenarios.
According to an embodiment of the present invention, as shown in fig. 1, the detection method applied to the radar system for detecting foreign objects on the airfield runway according to an embodiment of the present invention may be applied to, for example, automatic detection of the radar system for detecting foreign objects on the airfield runway. By arranging, for example, 4 radar locating devices in the vicinity of the airport runway 1, a radar scanning area covering the airport runway 1 can be constructed as indicated by the dashed box in fig. 1. By continuously scanning the radar scanning area without foreign matters, initial background data can be obtained, and then two-dimensional radar images are obtained through registration and compression. In the dashed line frame, the portion outside the airport runway 1 may be, for example, a non-runway area such as a grass land, a disordered irregular boundary line is provided between the airport runway 1 and the non-runway area, an area of interest closest to the airport runway 1 may be extracted from the two-dimensional radar image by processing the obtained maximum edge line, and further, the foreign matter information on the airport runway 1 may be monitored by processing image data obtained by scanning the area of interest in real time.
In order to achieve the acquisition of the foreign matter information in the application scenario, a radar scanning area needs to be constructed to acquire an area of interest to be monitored, and one embodiment is shown in fig. 2.
Fig. 2 is a flow chart schematically illustrating a detection method applied to an airport runway foreign matter detection radar system according to an embodiment of the present invention.
According to an embodiment of the present invention, as shown in fig. 2, the detection method applied to the radar system for detecting the foreign matter on the runway includes:
s201, continuously scanning the target area without the foreign matters to obtain initial background data.
S202, carrying out azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image.
S203, removing other edge lines except the maximum edge line of the target area in the two-dimensional radar image by using the non-continuity characteristics of the edge of the target area and the layout geometric relationship of the radar equipment in the target area.
And S204, extracting a target area in the two-dimensional radar image according to the maximum edge line of the target area to obtain an interested area.
And S205, scanning the region of interest in real time to obtain real-time data.
And S206, establishing a clutter map according to the initial background data, and performing constant false alarm detection on the real-time data by using the clutter map to obtain foreign matter detection information.
According to the embodiment of the invention, for example, FOD radar can be used for carrying out multi-time phase scanning on the scene of the runway of the airport, so that initial background data without foreign matters and radar echo data obtained by real-time detection of the foreign matters, namely data to be detected, are obtained. The initial background data is used as a sample for comparison with the data detected in real time, so that the airport runway to be monitored needs to be checked and cleaned manually, for example, to ensure that no foreign matter exists on the airport runway used for obtaining the initial background data. The target area without the foreign matter needs to be continuously scanned, namely, the continuity in time is ensured, and the clutter map is conveniently and subsequently utilized to carry out constant false alarm detection on the real-time data in the time domain.
The FOD radar is selected in the embodiment because the FOD radar is a frequency modulation continuous wave system radar working in millimeter wave band, the system has low transmitting power and high frequency band, the influence on the used working frequency band of the airport is small, and meanwhile, the system has scanning rotation capability and can scan and irradiate the scene of the runway of the airport to obtain radar echo signal data. However, the application of the FOD radar is only an example of a specific application, the detection method of the present invention is not limited to the FOD radar, and all radars which can implement the detection method of the present invention can be selected according to different use environments.
FIG. 3 schematically shows a two-dimensional radar image acquisition flow diagram according to an embodiment of the invention.
According to the embodiment of the present invention, as shown in fig. 3, the initial background data may be subjected to azimuth angle registration and range pulse compression through operations S301 to S302, so as to obtain a two-dimensional radar image.
S301, by taking the azimuth angle of the first scanning data as a main value, registering the data obtained by subsequent scanning to the angle same as the main value through any algorithm of linear interpolation, polynomial interpolation or sinc interpolation.
According to the embodiment of the invention, data of multiple scans which are continuous in time are selected as initial background data, and since data obtained by each scan may have a certain deviation, the initial background data needs to be registered, for example, an azimuth angle of first scan data in the data of multiple scans may be used as a main value, specifically, the registration may be performed, for example, by using an interpolation algorithm to register each scan data after the first scan to the same angle as the main value, the interpolation algorithm includes, for example, linear interpolation, polynomial interpolation, sinc interpolation, and the like, which have less influence on the detection algorithm.
And S302, performing pulse compression and relative amplitude correction on the registered data in the distance direction to obtain a two-dimensional radar image.
According to the embodiment of the invention, after the initial background data after registration is obtained, pulse compression processing needs to be carried out on the initial background data in the distance direction, and relative amplitude correction is carried out along the distance direction, so that a corresponding angle-distance two-dimensional radar image is obtained.
Fig. 4 schematically shows a radar two-dimensional image in a rectangular coordinate system detected in real time according to an embodiment of the present invention.
According to the embodiment of the invention, as shown in fig. 4, the black area (the dashed area) in the figure is the airport runway 1, and the gray area beside the runway is the grass, it can be seen that the boundary between the airport runway 1 and the grass land is uneven and fuzzy, which is easy to generate a false alarm in real-time detection, and the edge of the area to be detected of the airport runway is not clear, so that the target area obtained by each scanning is not definite, which is not beneficial to the automatic detection of the system.
Fig. 5 schematically shows a flowchart of a target area edge processing method according to an embodiment of the present invention.
According to the embodiment of the invention, as shown in fig. 5, for example, through operations S501 to S502, the edge lines other than the maximum edge line of the target area in the two-dimensional radar image may be removed by using the non-continuity characteristic of the edge of the target area and the layout geometric relationship of the radar device in the target area.
S501, bilateral filtering preprocessing is conducted on the non-continuity characteristics of the edge of the target area, and the size and the gradient direction of the edge of the preprocessed area corresponding to the layout geometric relationship of the radar equipment in the target area are calculated.
According to the embodiment of the invention, the runway area can be automatically extracted according to the non-continuous characteristics of the connecting part of the runway and the grassland and the layout geometric relationship of the radar equipment, and the runway area of interest is obtained. As shown in fig. 1, the airport runway 1 has a discontinuity characteristic with its surrounding grass-connecting portion, and the geometric relationship between the scanning range (the range of the dotted frame in fig. 1) and the airport runway 1 in the rectangular coordinate system determined by the deployed radar device is also determined. Thus, for example, the target region edge may be preprocessed by a bilateral filtering preprocessing operation capable of preserving the edge capability while smoothing denoising, referring to the formula:
wherein, (x, y), (i, j) are coordinates of pixel points in the two-dimensional radar image, g (i, j) is scattering intensity of the pixel points before bilateral filtering preprocessing, f (x, y) is scattering intensity of the pixel points after bilateral filtering preprocessing, S is a value range of the coordinate of the pixel points in the two-dimensional radar image, and w (i, j) is a spatial domain kernel, for example, an expression form of a gaussian function can be adopted as a template weight.
According to the embodiment of the invention, the edge extraction based on the gradient features is implemented according to the fact that the scattering intensity of the runway area has obvious discontinuity compared with the grassland and is reflected in obvious change of the gradient value, x and y represent the azimuth direction and the distance direction, the angle direction is an included angle with one axis, after the system installation and layout positions are determined, the actual edge of the runway has a determined angle direction relation relative to the scanning range, redundant edge lines can be removed according to the determined angle direction relation under a Cartesian coordinate system, only the maximum edge of the runway is reserved, the subsequent detection processing is carried out on the obtained runway interesting area, and the overall efficiency can be improved. In order to further derive the precise boundary from the blurred boundary obtained after the bilateral filtering preprocessing, for example, the gradient magnitude and gradient direction may be calculated from the pixel difference of the radar image. The gradient size may be expressed, for example, as:
wherein G is the gradient size, x and y are coordinate values of pixel points in the two-dimensional radar image, and Gx、GyThe gradient magnitude components in the horizontal and vertical directions of the gradient magnitude in the rectangular coordinate system are respectively, and the gradient direction can be expressed as:
θ＝arc tan(Gy/Gx) (3)
wherein theta is the gradient direction, G is the gradient size, x and y are coordinate values of the midpoint of the two-dimensional radar image, Gx、GyThe gradient components of the gradient magnitude in the horizontal and vertical directions in the rectangular coordinate system are respectively.
Fig. 6 schematically shows an automatically extracted radar two-dimensional image of a runway area of interest according to an embodiment of the invention.
According to the embodiment of the invention, as shown in fig. 6, after the bilateral filtering preprocessing, the black area in the figure is the airport runway, and the white area is the area outside the runway. The boundary between the airport runway and the periphery of the runway is very clear, and only the unique maximum edge line is reserved, so that the same region of interest can be obtained by each real-time scanning, and the automatic detection performance and the detection efficiency of the system are improved.
And S502, removing other edge lines except the maximum edge line of the target area in the two-dimensional radar image according to the gradient size and the gradient direction.
According to the embodiment of the invention, after the gradient size and the gradient direction are calculated, because the determined relation exists between the gradient directions of the four outer sides of the independent runway and the arrangement position of the radar system under the rectangular coordinate system, redundant edges can be removed in the extraction result and only the maximum edge is left, so that the runway interesting area is determined, after the runway interesting area is determined, the registered data can be scanned by using the same interesting area extraction range, and the detection efficiency is improved.
Fig. 7 schematically shows a flow chart of a constant false alarm detection method according to an embodiment of the present invention.
According to an embodiment of the present invention, as shown in fig. 7, for example, a Clutter Map (CM) may be created through operations S701 to S704, and clutter map constant false alarm detection (CM CFAR) may be performed on real-time data in a time domain using the clutter map, so as to obtain the foreign object detection information.
S701, establishing a clutter map according to the initial background data, and performing iterative computation on the clutter map, for example, by using a formula:
Al(m，n)＝(1-v)Al-1(m，n)+vXl(p，q) (4)
and carrying out constant false alarm detection on the time domain on the data obtained by scanning the region of interest in real time. Where l is the number of iterations, and also the number of consecutive scans of the target area that does not contain foreign objects, AlIs the data of the clutter map after the update, Al-1Is data, X, of a previous update of the clutter maplIs a fruitData obtained by automatically extracting and scanning the interested region, (m, n) is the coordinates of pixel points in a clutter map, (p, q) is the coordinates of pixel points in a radar image obtained by scanning the interested region in real time, (m, n) and (p, q) are the coordinates of the same corresponding point on an airport runway, v is a weighting coefficient, the value of v is based on the number of times of continuous scanning l and the constant false alarm probability value of target detection, and the value range of the constant false alarm probability value is 10 for example-7～10-5。
Preferably, according to the embodiment of the present invention, the number of times l of iterative computation is, for example, 10, and the value range of the corresponding v is less than 0.5.
S702, registering the real-time data according to the azimuth angle for registering the initial background data.
According to the embodiment of the invention, after the region of interest is scanned for multiple times in real time, the obtained real-time data also needs to be subjected to azimuth angle registration, and the registration method refers to the registration of the initial background data, wherein the registration angle is based on the main value azimuth angle of the first scanning when the initial background data is obtained, for example.
S703, comparing the ratio of the registered real-time data and the clutter map data subjected to iterative computation with the threshold value, and marking the point corresponding to the real-time data larger than or equal to the threshold value as a target point.
According to the embodiment of the invention, after real-time data is registered, detection is completed according to the self-adaptive decision threshold, and a detection result is subjected to binary marking, and the target decision comparator is, for example, according to a formula:
and comparing the ratio of the scattering intensity of the real-time data and the corresponding position in the clutter map data subjected to iterative computation with the judgment threshold value. Wherein c is the scattering intensity of a certain position in the real-time data scanning radar map to be detected, d is the scattering intensity of the corresponding position in the clutter map, e is the number of times of radar scanning, and T is a threshold value. When the scattering intensity ratio is greater than or equal to the threshold value T, markingThe pixel point marked with the foreign object target is H1And the pixel point marking the foreign-object-free target smaller than the threshold value T is H2。
Preferably, the threshold value T can be, for example, 15.53 ≦ T ≦ 76.12.
Fig. 8 schematically shows a foreign object target marking result diagram according to an embodiment of the present invention.
According to the embodiment of the invention, as shown in fig. 8, the gray area is an airport runway, the white point is a target pixel point of the foreign object detected in real time, and the number beside the white point is the number of the corresponding white point.
S704, connected domain processing is conducted on the target point, and the connected domain center of mass is taken as the position of the target foreign matter, so that foreign matter detection information is obtained.
According to the embodiment of the invention, after the binary marking of the real-time detection result is finished, the region with the foreign object is processed by using a 4 connected domain, an 8 connected domain or a D connected domain, namely, the mark H is processed1The pixel points of (2) are processed by connected components, such as white points in fig. 8, to determine different connected components of the same foreign object, and the processing of detecting the connected components can also be implemented by using commonly used Two-Pass and Seed Filling methods. After the connected domain is determined, for example, the centroid of the same foreign object target connected domain is used as a target position result, and foreign object target detection result information, that is, foreign object detection information is obtained. For mark H2Although the pixel points of (1) do not contain foreign matters, the pixel points indicate that some changes may be generated on the road surface, and the pixel points can be used for updating the clutter map so as to update some small changes which may occur on the road surface of the airport runway in time.
According to the embodiment of the invention, after the foreign object information is detected, an confusion matrix can be established based on the information and the reference true value, wherein the detection result comprises that the object is M, the object is N, the reference true value comprises that the object is E and the object is F. The test results were evaluated overall and objectively as shown in table 1.
TABLE 1 quantitative index definition of assay Performance
| Detection performance | Test results (with target M) | Test results (No target N) |
| Reference truth value (with target E) | EM | FN |
| Reference truth value (No target F) | FM | EN |
Wherein, as can be derived from table 1, the detection probability P of the detection method based on the embodiment of the present inventiondComprises the following steps:
probability of false alarm PfaComprises the following steps:
probability of missed detection PloComprises the following steps:
the overall expression Kappa coefficient KC is as follows:
wherein the content of the first and second substances,
wherein the content of the first and second substances,
N＝EM+FM+EN+FN (12)
according to the embodiment of the invention, the method can be applied to quantitative evaluation indexes such as detection probability, false alarm probability and missed detection probability of the FOD detection system, and the integral display Kappa coefficient can completely and definitely evaluate the single and integral detection capability performance of the detection system, so that compared with the traditional method that the proportion of the correct number of detection results obtained from the placed target is more comprehensive and objective, the method provides reference for the performance evaluation of the detection system.
Fig. 9 is a flow chart schematically illustrating a detection method applied to an airport runway foreign matter detection radar system according to another embodiment of the present invention.
According to another embodiment of the present invention, as shown in fig. 9, the detection method applied to the radar system for detecting foreign objects on an airport runway, for example, includes the following steps:
s901, the FOD radar scans the airport runway scene in multiple time phases to obtain initial background data continuous in time and detection data to be detected in real time.
And S902, registering the data of different periods according to the azimuth angle, and performing pulse compression in the distance direction to obtain a radar image.
And S903, automatically extracting the region of interest of the runway according to the discontinuous characteristics of the connection part of the pavement and the grassland and the radar layout geometric relationship.
And S904, establishing a stable clutter map by the multi-period initial background data, registering the data to be detected, automatically extracting a runway area, then performing clutter map constant false alarm detection, and extracting the same target connected domain, and then taking the mass center as a detection result.
S905, constructing a confusion matrix by the detection result and the reference true value, and evaluating the detection system by quantifying the index detection probability, the false alarm probability, the missed detection probability and the Kappa coefficient.
For other details of the detection method of the other embodiment, reference may be made to the description of the above embodiment, and further description is omitted here.
It should be noted that the above definitions of the components and methods are not limited to the specific structures, shapes or manners mentioned in the embodiments, and those skilled in the art may simply modify or replace them, for example, in step S501, the runway edge detection algorithm may be replaced by a gradient detection method based on bilateral filtering and an improved method based on the gradient detection method; step S704, the connected component domain detection algorithm can be replaced by basic 4-connected and 8-connected extraction, Two-Pass, Seed Filling, and extraction methods based on the above method; in confusion matrices, different alphabetical characters are used to express the same meaning matrix and probability definition.
In summary, the embodiment of the present invention provides a detection method applied to a radar system for detecting a foreign object on an airport runway. The method can be used for improving the efficiency by utilizing an extraction algorithm for automatically extracting the runway region of interest and a clutter map constant false alarm detection algorithm on a time domain, can reduce false alarms of clutter edges, can realize detection in a multi-target and long-distance environment, improves the detection probability to a certain extent, stabilizes the false alarm probability, and meets the requirements of an airport on the real-time property and the continuity of runway foreign object detection. Meanwhile, the disclosed quantitative evaluation indexes completely and definitely show a plurality of quantitative indexes of the detection system, and reference is provided for performance evaluation of the airport pavement foreign matter detection system.
Fig. 10 schematically shows a block diagram of a foreign object detection apparatus according to an embodiment of the present invention.
According to an embodiment of the present invention, as shown in fig. 10, another aspect of the embodiment of the present invention provides a foreign object detection apparatus 1000, for example, including: a data acquisition module 1010, a region of interest acquisition module 1020, and a foreign object information acquisition module 1030. The foreign object detection apparatus may perform the method described above with reference to the method embodiment, and will not be described herein again.
Specifically, the data acquisition module 1010 is configured to continuously scan a target region that does not contain a foreign object to obtain initial background data, and scan an interest region in real time to obtain real-time data.
The region-of-interest obtaining module 1020 is configured to perform azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image, remove other edge lines in the two-dimensional radar image except for the maximum edge line of the target area by using the discontinuity characteristics of the edge of the target area and the layout geometric relationship of the radar device in the target area, and extract the target area in the two-dimensional radar image according to the maximum edge line of the target area to obtain the region of interest.
And the foreign object information obtaining module 1030 is configured to establish a clutter map according to the initial background data, and perform time-domain constant false alarm detection on the real-time data by using the clutter map to obtain foreign object detection information.
The product embodiment is similar to the method embodiment in portions where details are not given, and please refer to the method embodiment, which is not described herein again.
Any of the modules according to embodiments of the present invention, or at least part of the functionality of any of them, may be implemented in one module. Any one or more of the modules according to the embodiments of the present invention may be implemented by being split into a plurality of modules. Any one or more of the modules according to embodiments of the present invention may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging the circuit, or in any one of three implementations, or in any suitable combination of any of the software, hardware and firmware. Alternatively, one or more of the modules according to embodiments of the invention may be implemented at least partly as computer program modules which, when executed, may perform corresponding functions.
For example, any plurality of the data acquisition module 1010, the region of interest acquisition module 1020, and the foreign object information acquisition module 1030 may be combined and implemented in one module, or any one of the modules may be divided into a plurality of modules. Alternatively, at least a portion of the functionality of one or more of these modules may be implemented, at least in part, as hardware circuitry with other modules, such as at least one of the data acquisition module 1010, the region of interest acquisition module 1020, and the foreign object information acquisition module 1030, for example, as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-a-package, an Application Specific Integrated Circuit (ASIC), or in any other reasonable manner in which circuits are integrated or packaged, or in any one of three implementations, or in any suitable combination of any of software, hardware, and firmware. Alternatively, at least one of the data acquisition module 1010, the region of interest acquisition module 1020 and the foreign object information acquisition module 1030 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.
FIG. 11 schematically shows a block diagram of an electronic device according to an embodiment of the invention. The electronic device shown in fig. 11 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 11, electronic device 1100 includes a processor 1110, a computer-readable storage medium 1120. The electronic device 1100 may perform a method according to an embodiment of the invention.
In particular, processor 1110 may include, for example, a general purpose microprocessor, an instruction set processor and/or related chip set and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), and/or the like. The processor 1110 may also include onboard memory for caching purposes. Processor 1110 may be a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the present invention.
Computer-readable storage medium 1120, for example, may be a non-volatile computer-readable storage medium, specific examples including, but not limited to: magnetic storage devices, such as magnetic tape or Hard Disk Drives (HDDs); optical storage devices, such as compact disks (CD-ROMs); a memory, such as a Random Access Memory (RAM) or a flash memory; and so on.
The computer-readable storage medium 1120 may comprise a computer program 1121, and the computer program 1121 may comprise code/computer-executable instructions that, when executed by the processor 1110, cause the processor 1110 to perform a method according to an embodiment of the present invention, or any variation thereof.
The computer programs 1121 can be configured to have, for example, computer program code including computer program modules. For example, in an example embodiment, code in computer program 1121 may include one or more program modules, including, for example, 1121A, 1121B, … …. It should be noted that the division and number of modules are not fixed, and those skilled in the art may use suitable program modules or program module combinations according to actual situations, so that the processor 1110 may execute the method according to the embodiment of the present disclosure or any variation thereof when the program modules are executed by the processor 1110.
According to an embodiment of the present disclosure, at least one of the data acquisition module 1010, the region of interest acquisition module 1020, and the foreign object information acquisition module 1030 may be implemented as a computer program module described with reference to fig. 11, which, when executed by the processor 1110, may implement the respective operations described above.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
Claims (10)
1. A detection method applied to a radar system for detecting foreign matters on an airport runway is characterized by comprising the following steps:
continuously scanning a target area without foreign matters to obtain initial background data;
carrying out azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image;
removing other edge lines except the maximum edge line of the target area in the two-dimensional radar image by using the non-continuity characteristics of the edge of the target area and the layout geometric relationship of the radar equipment in the target area;
extracting the target area in the two-dimensional radar image according to the maximum edge line of the target area to obtain an interested area;
scanning the region of interest in real time to obtain real-time data;
and establishing a clutter map according to the initial background data, and performing constant false alarm detection on the real-time data by using the clutter map to obtain foreign matter detection information.
2. The detection method applied to the radar system for detecting the foreign matters on the airfield runway according to claim 1, wherein the removing of the edge lines except the maximum edge line of the target area in the two-dimensional radar image by utilizing the non-continuity characteristics of the edges of the target area and the layout geometrical relationship of the radar equipment in the target area comprises the following steps:
bilateral filtering preprocessing is carried out on the discontinuity characteristics of the target area edge, and the gradient size and the gradient direction of the preprocessed area edge corresponding to the layout geometric relationship of the radar equipment in the target area are calculated;
and removing other edge lines except the maximum edge line of the target area in the two-dimensional radar image according to the gradient magnitude and the gradient direction.
3. The detection method applied to the radar system for detecting the alien materials on the airfield runway according to claim 1, wherein the establishing of the clutter map according to the initial background data and the constant false alarm detection of the real-time data by using the clutter map to obtain the alien material detection information comprises:
by the formula:
Al(m，n)＝(1-v)Al-1(m，n)+vXl(p，q)
performing iterative computation on the clutter map data;
where l is the number of iterations, AlIs the data of the clutter map after the update, Al-1Is data, X, of a previous update of the clutter maplIs data obtained by scanning the region of interest in real time, and (m, n) is a clutter mapThe coordinates (p, q) of the pixel points in the radar image obtained by scanning the region of interest in real time, the coordinates (m, n) and (p, q) of the pixel points in the radar image correspond to the coordinates of the same point in a target region, v is a weighting coefficient, and the value of v is based on the number l of iterative computation and the constant false alarm probability value of target detection;
registering the real-time data according to the azimuth angle for registering the initial background data;
comparing the ratio of the registered real-time data and the clutter map data subjected to iterative computation with a threshold value, and marking points corresponding to the real-time data which are larger than or equal to the threshold value as target points;
and processing the connected domain of the target point, and taking the center of mass of the connected domain as the position of the target foreign matter to obtain the foreign matter detection information.
4. The detection method applied to the radar system for detecting the foreign matter on the airport runway according to claim 3, wherein the processing the connected domain of the marked points to obtain the foreign matter detection information comprises:
and carrying out connected domain processing on the marked points by any one of a method of a 4-connected domain, a 8-connected domain, a D-connected domain, Two-Pass and Seed Filling to obtain the foreign matter detection information.
5. The detection method applied to the radar system for detecting foreign objects on the airfield runway according to claim 1, wherein the detection method applied to the radar system for detecting foreign objects on the airfield runway further comprises:
and establishing a confusion matrix according to the foreign matter detection information and the foreign matter number in the reference true value, and calculating by the confusion matrix to obtain the detection probability, the false alarm probability, the missed detection probability and the Kappa coefficient.
6. The detection method applied to the radar system for detecting the foreign matters on the airfield runway according to claim 1, wherein the step of performing azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image comprises the following steps:
taking the azimuth angle of the first scanning data as a main value, and registering the data obtained by subsequent scanning to the same angle as the main value through any one algorithm of linear interpolation, polynomial interpolation or sinc interpolation;
and performing pulse compression and relative amplitude correction on the registered data in the distance direction to obtain the two-dimensional radar image.
7. The detection method as claimed in claim 3, wherein the creating of the clutter map according to the initial background data and the detecting of the CFAR of the real-time data by using the clutter map to obtain the foreign object detection information further comprises:
marking the point corresponding to the real-time data smaller than the threshold value as a non-target point;
iteratively updating the clutter map using the non-target points.
8. The detection method applied to the radar system for detecting foreign objects on the airfield runway according to claim 3, characterized in that the clutter map data is calculated at least 10 times iteratively according to the formula;
wherein the value range of v corresponding to the iterative computation for at least 10 times is less than 0.5.
9. A detection device applied to a radar system for detecting foreign matters on an airport runway, which is characterized by comprising:
the data acquisition module is used for continuously scanning a target area without foreign matters to obtain initial background data and scanning an interested area in real time to obtain real-time data;
the interesting region acquisition module is used for carrying out azimuth angle registration and range pulse compression on the initial background data to obtain a two-dimensional radar image, removing other edge lines except the maximum edge line of the target region in the two-dimensional radar image by utilizing the non-continuity characteristics of the edge of the target region and the layout geometric relationship of radar equipment in the target region, and extracting the target region in the two-dimensional radar image according to the maximum edge line of the target region to obtain the interesting region;
and the foreign matter information acquisition module is used for establishing a clutter map according to the initial background data and performing constant false alarm detection on the real-time data in a time domain by using the clutter map to obtain foreign matter detection information.
10. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the detection method of any one of claims 1 to 8 as applied to an airport runway foreign object detection radar system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110364726.3A CN113064162B (en) | 2021-04-02 | 2021-04-02 | Detection method and device applied to radar system for detecting foreign matters on airfield runway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110364726.3A CN113064162B (en) | 2021-04-02 | 2021-04-02 | Detection method and device applied to radar system for detecting foreign matters on airfield runway |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113064162A true CN113064162A (en) | 2021-07-02 |
| CN113064162B CN113064162B (en) | 2023-03-14 |
Family
ID=76565960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110364726.3A Active CN113064162B (en) | 2021-04-02 | 2021-04-02 | Detection method and device applied to radar system for detecting foreign matters on airfield runway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113064162B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114415142A (en) * | 2022-01-28 | 2022-04-29 | 北京海兰信数据科技股份有限公司 | Rain clutter identification method and system based on navigation radar |
| CN114578348A (en) * | 2022-05-05 | 2022-06-03 | 深圳安德空间技术有限公司 | Autonomous intelligent scanning and navigation method for ground penetrating radar based on deep learning |
| CN116400379A (en) * | 2023-06-08 | 2023-07-07 | 合肥国家实验室 | Three-dimensional imaging system and three-dimensional imaging method of single-photon laser radar |
| CN116704446A (en) * | 2023-08-04 | 2023-09-05 | 武汉工程大学 | Real-time detection method and system for foreign matters on airport runway pavement |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103247045A (en) * | 2013-04-18 | 2013-08-14 | 上海交通大学 | Method of obtaining artificial scene main directions and image edges from multiple views |
| CN107238821A (en) * | 2017-05-31 | 2017-10-10 | 中国电子科技集团公司第二十九研究所 | The airfield runway foreign matter detecting method and device of a kind of feature based spectrum signature |
| CN109471098A (en) * | 2018-09-27 | 2019-03-15 | 中科宇达（北京）科技有限公司 | Utilize the airfield runway foreign matter detecting method of FOD radar phase coherence information |
| CN112215137A (en) * | 2020-10-10 | 2021-01-12 | 中国电子科技集团公司第十四研究所 | Low false alarm target detection method based on region constraint |
-
2021
- 2021-04-02 CN CN202110364726.3A patent/CN113064162B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103247045A (en) * | 2013-04-18 | 2013-08-14 | 上海交通大学 | Method of obtaining artificial scene main directions and image edges from multiple views |
| CN107238821A (en) * | 2017-05-31 | 2017-10-10 | 中国电子科技集团公司第二十九研究所 | The airfield runway foreign matter detecting method and device of a kind of feature based spectrum signature |
| CN109471098A (en) * | 2018-09-27 | 2019-03-15 | 中科宇达（北京）科技有限公司 | Utilize the airfield runway foreign matter detecting method of FOD radar phase coherence information |
| CN112215137A (en) * | 2020-10-10 | 2021-01-12 | 中国电子科技集团公司第十四研究所 | Low false alarm target detection method based on region constraint |
Non-Patent Citations (1)
| Title |
|---|
| 吴静等: "非高斯背景下跑道异物监测雷达的杂波图CFAR技术", 《现代雷达》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114415142A (en) * | 2022-01-28 | 2022-04-29 | 北京海兰信数据科技股份有限公司 | Rain clutter identification method and system based on navigation radar |
| CN114578348A (en) * | 2022-05-05 | 2022-06-03 | 深圳安德空间技术有限公司 | Autonomous intelligent scanning and navigation method for ground penetrating radar based on deep learning |
| CN116400379A (en) * | 2023-06-08 | 2023-07-07 | 合肥国家实验室 | Three-dimensional imaging system and three-dimensional imaging method of single-photon laser radar |
| CN116400379B (en) * | 2023-06-08 | 2023-09-12 | 合肥国家实验室 | Three-dimensional imaging system and three-dimensional imaging method of single-photon laser radar |
| CN116704446A (en) * | 2023-08-04 | 2023-09-05 | 武汉工程大学 | Real-time detection method and system for foreign matters on airport runway pavement |
| CN116704446B (en) * | 2023-08-04 | 2023-10-24 | 武汉工程大学 | Real-time detection method and system for foreign matters on airport runway pavement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113064162B (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113064162B (en) | Detection method and device applied to radar system for detecting foreign matters on airfield runway | |
| CN109583293B (en) | Aircraft target detection and identification method in satellite-borne SAR image | |
| CN107154040B (en) | Tunnel lining surface image crack detection method | |
| WO2021143778A1 (en) | Positioning method based on laser radar | |
| Sohn et al. | Extraction of buildings from high resolution satellite data | |
| CN106910177B (en) | A kind of multi-angle SAR image fusion method that local image index optimizes | |
| Zhao et al. | Building detection from urban SAR image using building characteristics and contextual information | |
| CN109471098B (en) | Airport runway foreign matter detection method utilizing FOD radar phase coherence information | |
| Wang et al. | Recognition of roads and bridges in SAR images | |
| Silva et al. | Computer-based identification and tracking of Antarctic icebergs in SAR images | |
| Geiss et al. | Inpainting radar missing data regions with deep learning | |
| CN113570632B (en) | Small moving target detection method based on high-time-phase space-borne SAR sequential image | |
| Li et al. | Building detection in sar images based on bi-dimensional empirical mode decomposition algorithm | |
| CN109063564B (en) | Target change detection method | |
| Liang et al. | Research on airport runway FOD detection algorithm based on texture segmentation | |
| CN107729903A (en) | SAR image object detection method based on area probability statistics and significance analysis | |
| CN115407282B (en) | SAR active deception jamming detection method based on interference phase under short base line | |
| Yi-Bo et al. | A survey on feature extraction of SAR images | |
| Arivazhagan et al. | Optimal Gabor sub-band-based spectral kurtosis and Teager Kaiser energy for maritime target detection in SAR images | |
| CN113343819B (en) | Efficient unmanned airborne SAR image target segmentation method | |
| Cao et al. | Detecting the number of buildings in a single high-resolution SAR image | |
| CN115131555A (en) | Overlapping shadow detection method and device based on superpixel segmentation | |
| Xing et al. | Research on crack extraction based on the improved tensor voting algorithm | |
| CN106897985A (en) | A kind of multi-angle SAR image fusion method based on visibility classification | |
| Wang et al. | An automatic bridge detection technique for high resolution SAR images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |