Method and system for detecting ground marking elements of landing runway

Abstract

A method and system for detecting at least one ground marking element of at least one landing runway by computer vision and by means of signal processing techniques. The detection system (S) comprises: at least one image acquisition unit (10); a cutting unit (11) for cutting the image (I) into strips (ST1); a determination unit (2) for determining at least one average intensity curve (C) for the at least one strip (ST1); an identification unit (13) for identifying at least one surface marking element (100) of the landing runway (T) in the mean intensity curve (C); a detection unit (2) for detecting the position of at least one ground marking element of the at least one landing runway (T) in the image (I). Because the average intensity curve is determined, the detection of the ground marking elements requires few computing resources.

Description

Technical Field

[0001] The present invention relates to a method and a system for detecting a landing runway using computer vision with the aid of signal processing techniques. Prior art

[0002] The ability to automatically land an aircraft on a landing strip imposes severe constraints on the implementation of the aircraft's navigation system. This feature may require new technologies to extend the possibility of automatic landing to all airports at all times.

[0003] Vision techniques can offer valuable advantages because they do not rely on ground infrastructure, such as instrument landing systems.

[0004] In order for an aircraft to land, its trajectory must be consistent with its current position relative to the landing runway, both with its lateral position and with its vertical position.

[0005] The threshold of a landing runway can be one of the main landmarks that can be used to obtain information about the vertical position of an aircraft relative to the landing runway. In practice, a ground marking consisting of several white and black strips is used on the landing runway to mark the threshold, with a fixed width and spacing between the strips. In addition, these strips are usually placed 6 meters before the threshold. This group of strips forming a ground marking element is often called a "piano". "Ground marking element" is understood to mean a pattern drawn on the ground of the landing runway T and / or a light pattern of an approach lighting system for the landing runway T.

[0006] Computer vision techniques can be used to detect ground landmarks, such as a piano, in order to determine the position of the aircraft.

[0007] However, this technology may be difficult to implement in real time due to the large amount of data to be processed. For example, an 8-bit encoded high-definition color image represents about 2.8MB to be processed. Therefore, a large amount of computing resources is required. Summary of the invention

[0008] The object of the present invention is to propose a method and a system for detecting a landing runway by means of computer vision, which method and system require limited computing resources.

[0009] To this end, the invention relates to a method for detecting at least one ground marking element of at least one landing runway.

[0010] According to the present invention, the detection method at least comprises the following steps:

[0011] - an image acquisition step, implemented by an image acquisition unit, for acquiring at least one image captured by at least one image capture unit, the one or more images being in the form of a pixel matrix having a first dimension and a second dimension;

[0012] - A first set of steps comprising:

[0013] o a first cutting step, implemented by a first cutting unit, for cutting the pixel matrix into first parallel strips, each first parallel strip being associated with a corresponding position of each first strip in the pixel matrix of the one or more images, each first strip corresponding to a first sub-matrix having at least one pixel row and a plurality of pixel columns equal to a first dimension of the pixel matrix;

[0014] o a first determination step, implemented by a first determination unit, for determining an average intensity curve for at least one first strip selected from the first strips resulting from cutting the pixel matrix, the average intensity curve being determined by calculating, for each pixel column of the first submatrix of the selected one or more first strips, an average intensity of one or more pixels in each pixel column;

[0015] o a first recognition step, implemented by a first recognition unit, for recognizing a curve shape characteristic of at least one ground marking element of at least one landing runway in said average intensity curve of the selected one or more first strips;

[0016] The detection method also includes:

[0017] - a detection step implemented by a detection unit for detecting the position of one or more ground marking elements of at least one landing runway in the one or more images based on the position of the identified one or more ground marking elements and the selected one or more first strips in the pixel matrix of the one or more images.

[0018] Thus, due to the determination of the average intensity profile based on the strips of the image, it is possible to detect ground marker elements in a two-dimensional image based on a one-dimensional profile. Thus, the computational resource requirements are significantly reduced compared to detection using conventional shape recognition techniques on two-dimensional images.

[0019] According to a preferred embodiment, the detection method comprises a second set of steps before the detection step, the second set of steps comprising:

[0020] - a second cutting step, implemented by a second cutting unit, for cutting the pixel matrix into second parallel strips, each second parallel strip being associated with a corresponding position of each second strip in the pixel matrix of the one or more images, each second strip corresponding to a second sub-matrix having at least one pixel row and a number of pixel columns equal to a second dimension of the pixel matrix;

[0021] - a second determination step, implemented by a second determination unit, for determining an average intensity curve for at least one second strip selected from the second strips resulting from cutting the pixel matrix, the average intensity curve being determined by calculating, for each pixel column of the second submatrix of the selected one or more second strips, an average intensity of one or more pixels in each pixel column;

[0022] a second recognition step, implemented by a second recognition unit, for recognizing in said average intensity curve of the selected one or more second strips a characteristic curve shape of at least one ground marking element of at least one landing runway;

[0023] The detection step is implemented to detect the positions of one or more ground marking elements of at least one landing runway in the one or more images based on the identified one or more ground marking elements, the positions of the selected one or more first strips in the pixel matrix of the one or more images, and the positions of the selected one or more second strips in the pixel matrix of the one or more images.

[0024] According to a first alternative embodiment, a first recognition step and / or a second recognition step is implemented so as to identify, using a neural network, the curve shape characteristics of at least one ground marking element of one or more landing runways in the average intensity curve of one or more selected first strips and / or one or more selected second strips.

[0025] According to a second alternative embodiment, the first identification step comprises the following sub-steps:

[0026] - a first frequency analysis sub-step, implemented by a first frequency analysis sub-unit, for detecting at least one harmonic in the average intensity curve of the selected one or more first strips;

[0027] - a first data partitioning sub-step, implemented by a first data partitioning sub-unit, for forming at least one group comprising one or more harmonic characteristics of ground marking elements of the landing runway, wherein the one or more harmonic characteristics of ground marking elements are stored in a database;

[0028] A first identification sub-step, implemented by a first identification sub-unit, for identifying at least one ground marking element of the one or more landing runways for the one or more groups formed in the first data partitioning sub-step.

[0029] According to a preferred embodiment of the second alternative embodiment, the second identification sub-step includes the following sub-steps:

[0030] - a second frequency analysis sub-step, implemented by a second frequency analysis sub-unit, for detecting at least one harmonic in the average intensity curve of the selected one or more second strips;

[0031] - a second data partitioning sub-step, implemented by a second data partitioning sub-unit, for forming at least one group comprising one or more harmonic characteristics of ground marking elements of the landing runway, wherein the one or more harmonic characteristics of ground marking elements are stored in a database;

[0032] A second identification sub-step, implemented by a second identification unit, for identifying at least one ground marking element of the one or more landing runways for the one or more groups formed in the second data partitioning sub-step.

[0033] According to a third alternative embodiment, the first identification step comprises the following sub-steps:

[0034] - a first correlation sub-step, implemented by a first correlation sub-unit, for determining at least one correlation parameter between the average intensity curve of the selected one or more first strips and at least one synthetic curve characteristic of a ground marking element, wherein the one or more synthetic curves are stored in a database;

[0035] A first identification sub-step, implemented by a first identification sub-unit, is used to identify at least one ground marking element of said one or more landing runways if the correlation parameter determined in said first correlation sub-step is greater than or equal to a predetermined value.

[0036] According to a preferred embodiment of the third alternative embodiment, the second identification step includes the following sub-steps:

[0037] - a second correlation sub-step, implemented by a second correlation sub-unit, for determining at least one correlation parameter between the average intensity curve of the selected one or more second strips and at least one synthetic curve characteristic of the ground marking element, wherein the one or more synthetic curves are stored in a database;

[0038] A second identification sub-step, implemented by a second identification sub-unit, is used to identify at least one ground marking element of said one or more landing runways if the correlation parameter determined in said second correlation sub-step is greater than or equal to a predetermined value.

[0039] Furthermore, the first set of steps comprises:

[0040] a first comparison step, implemented by a first comparison unit, for comparing the average intensity profiles of identical ground marker elements that have been identified, in order to determine whether there is a shift between said average intensity profiles;

[0041] - a first trimming step, implemented by a first trimming unit, if the offset has been determined, for trimming the pixel matrix of the one or more images according to the determined offset;

[0042] The first set of steps is repeated for the pixel matrix of the one or more images trimmed in the first trimming step.

[0043] According to a preferred embodiment, the second set of steps comprises:

[0044] a second comparison step, implemented by a second comparison unit, for comparing the average intensity profiles of identical ground marker elements that have been identified, in order to determine whether there is a shift between said average intensity profiles;

[0045] - a second trimming step, if the offset has been determined, implemented by a second trimming unit for trimming the pixel matrix of the one or more images according to the determined offset;

[0046] The second set of steps is repeated for the pixel matrix of the one or more images trimmed in the second trimming step.

[0047] Furthermore, the detection method comprises a third determination step implemented by a third determination unit for determining the position of at least one entrance of the one or more landing runways based on the position of one or more ground marking elements detected in the one or more images and the characteristics of the one or more landing runways derived from a runway database.

[0048] Furthermore, the detection method comprises a fourth determination step implemented by a fourth determination unit for determining the position of the aircraft based on the position of one or more entrances of the one or more landing runways in the image, the position and angle of the one or more image acquisition units, and the characteristics of the one or more landing runways from the runway database.

[0049] Furthermore, the detection method comprises a transmission step performed by a transmission unit for transmitting a signal to a user device, the signal indicating the position of at least one entrance of the one or more landing runways in the one or more images or the position of the aircraft in the one or more images, or the position of one or more ground marking elements of at least one landing runway in the one or more images.

[0050] The invention also relates to a system for detecting at least one ground marking element of at least one landing runway.

[0051] According to the present invention, the detection system at least comprises:

[0052] - an image acquisition unit configured to acquire at least one image captured by at least one image capture unit, the one or more images being in the form of a pixel matrix having a first dimension and a second dimension;

[0053] - A first group of units comprising:

[0054] o a first cutting unit configured to cut the pixel matrix into first parallel strips, each first parallel strip being associated with a corresponding position of each first strip in the pixel matrix of the one or more images, each first strip corresponding to a first sub-matrix having at least one pixel row and a plurality of pixel columns equal to a first dimension of the pixel matrix;

[0055] o a first determination unit configured to determine an average intensity curve for at least one first strip selected from the first strips resulting from cutting the pixel matrix, the average intensity curve being determined by calculating, for each pixel column of the first submatrix of the selected one or more first strips, an average intensity of one or more pixels in each pixel column;

[0056] o a first recognition unit configured to recognize, in said average intensity curve of the selected one or more first strips, a curve shape characteristic of at least one ground marking element of at least one landing runway;

[0057] The detection system also includes:

[0058] a detection unit configured to detect the positions of the one or more ground marking elements of at least one landing runway in the one or more images based on the positions of the identified one or more ground marking elements and the selected one or more first strips in the pixel matrix of the one or more images.

[0059] According to a preferred embodiment, the detection system comprises a second set of units, which comprises:

[0060] - a second cutting unit configured to cut the pixel matrix into second parallel strips, each second parallel strip being associated with a respective position of each second strip in the pixel matrix of the one or more images, each second strip corresponding to a second sub-matrix having at least one pixel row and a plurality of pixel columns equal to a second dimension of the pixel matrix;

[0061] - a second determination unit configured to determine an average intensity curve for at least one second strip selected from the second strips resulting from cutting the pixel matrix, the average intensity curve being determined by calculating, for each pixel column of the second submatrix of the selected one or more second strips, an average intensity of one or more pixels in each pixel column;

[0062] - a second recognition unit configured to recognize, in said average intensity curve of the selected one or more second strips, a curve shape characteristic of at least one ground marking element of at least one landing runway;

[0063] The detection unit is configured to detect the positions of one or more ground marking elements of at least one landing runway in the one or more images based on the identified one or more ground marking elements, the positions of the selected one or more first strips in the pixel matrix of the one or more images, and the positions of the selected one or more second strips in the pixel matrix of the one or more images.

[0064] The invention also relates to an aircraft comprising a detection system as specified above. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings will explain how the invention can be implemented.In the drawings, the same reference numerals designate similar elements.

[0066] Figure 1 A detection system according to one embodiment is schematically shown.

[0067] Figure 2 A first recognition unit and a second recognition unit according to a second configuration are schematically illustrated.

[0068] Figure 3 A first recognition unit and a second recognition unit according to a third configuration are schematically illustrated.

[0069] Figure 4 A detection method according to an embodiment is schematically illustrated.

[0070] Figure 5 The first identification step and the second identification step according to the second configuration are schematically illustrated.

[0071] Figure 6The first identification step and the second identification step according to the third configuration are schematically illustrated.

[0072] Figure 7 An image captured by an image capturing unit and acquired by an image acquisition unit is shown.

[0073] Figure 8 An image is shown cut into strips according to a first dimension of the image.

[0074] Fig. 9 An image is shown cut into strips according to a second dimension of the image.

[0075] Fig.10 The steps of cutting the pixel matrix of an image are schematically shown.

[0076] Fig.11 It is schematically shown how the average intensity curve is determined based on the average intensity of the pixels.

[0077] Fig.12 The synthetic curve characteristics of the ground marking elements (particularly the piano) are shown.

[0078] Fig.13 Shown is a side view of an aircraft that might land on a landing strip. DETAILED DESCRIPTION

[0079] exist Figure 1 A detection system S is schematically shown in . It is a system for detecting at least one ground marking element 100 of at least one landing runway T. The detection system S is designed to be placed on board an aircraft AC, in particular a transport aircraft.

[0080] A “ground marking element” is understood to mean a pattern drawn on the ground of the landing runway T and / or a light pattern of the approach lighting of the landing runway T. FIG. 1 illustrates an example of a ground marking element 100 corresponding to a piano. However, the detection system S can be used for any other ground marking element 100.

[0081] The detection system S ( Fig.13 ). The detection system S can also be used when the aircraft AC is on the ground during a taxiing procedure. Thus, the detection system S can also detect ground marking elements 100 of an airport taxiway.

[0082] The detection system S comprises at least one image acquisition unit 10 (COLL), a first group of units U1 and a detection unit 2 (DETECT).

[0083] The image acquisition unit 10 is configured for acquiring at least one image I captured by at least one image capturing unit 1. The image or images I are each in the form of a pixel matrix M having a first dimension D1 and a second dimension D2.

[0084] The one or more image capture units 1 may each correspond to a camera on board the aircraft AC.

[0085] In a first embodiment, the first dimension D1 may correspond to a plurality of pixel columns C1, C2, ..., C10 of the pixel matrix M and the second dimension D2 may correspond to a plurality of rows L1, L2, L3, L4, L5, L6 of the pixel matrix M. Fig.10 In the example shown, the pixel matrix M has a first dimension D1 equal to 10 pixel columns and a second dimension equal to 6 pixel rows.

[0086] In a second embodiment (not shown), the first dimension D1 may correspond to a plurality of pixel rows of the pixel matrix M, and the second dimension D2 may correspond to a plurality of columns of the pixel matrix M. In the embodiment of FIG.

[0087] The first group of units U1 includes a first cutting unit 11 (CUT), a first determining unit 12 (DET) and a first recognizing unit 13 (RECOG).

[0088] The first cutting unit 11 is configured to cut the pixel matrix M into first parallel strips ST1. Each first strip ST1 is associated with its corresponding position in the pixel matrix M of one or more images I. Each first strip ST1 corresponds to a first sub-matrix SM1 having at least one pixel row L1, L2, L3, L4, L5, L6 and a plurality of pixel columns C1, C2, ..., C10 equal to a first dimension D1 of the pixel matrix M.

[0089] Fig.10 and Figure 8 The example shown shows a cutting of the pixel matrix M. In this example, the first dimension D1 of the pixel matrix M corresponds to a plurality of pixel columns C1, C2, ..., C10 and the second dimension D2 of the pixel matrix M corresponds to a plurality of rows L1, L2, L3, L4, L5, L6. In this example, each first sub-matrix SM1 has a number of pixel columns C1, C2, ..., C10 equal to the first dimension D1 of the pixel matrix M and a number of pixel rows L1, L2, L3, L4, L5, L6 equal to 2. Fig.10 In the example shown, each first sub-matrix SM1 has a number of pixel columns equal to 10 pixel columns and a number of pixel rows equal to 2 pixel rows.

[0090] Preferably, the number of pixel rows L1, L2, L3, L4, L5, L6 of each sub-matrix is ​​equal to four.

[0091] The first determination unit 12 is configured to determine an average intensity curve C of at least one first strip ST1 selected from the first strips ST1 resulting from cutting the pixel matrix M by the first cutting unit 11 .

[0092] The average intensity curve C may be determined for all first strips ST1. In this case, all first strips ST1 originating from the cut pixel matrix M are selected.

[0093] In this description, intensity corresponds to light intensity. Furthermore, "intensity of a pixel" refers to the light intensity captured and encoded by the pixel.

[0094] However, it is possible to determine an average intensity curve C for a combination of first strips ST1. In this case, only some of the first strips ST1 are selected. For example, they can be selected according to their position in the pixel matrix M.

[0095] exist Fig.10 In the example shown, the average intensity curve C is determined for a first stripe corresponding to a first sub-matrix SM1 formed by the lines L1 and L2 and a first sub-matrix SM1 formed by the lines L5 and L6.

[0096] The average intensity curve C is determined by calculating the average intensity of one or more pixels in each pixel column C1, C2, ..., C10 of the first sub-matrix SM1 of the selected one or more first strips ST1.

[0097] This calculation may correspond to determining a pixel matrix SM2 comprising a pixel row. The intensity of each pixel in the pixel row is equal to the average of the intensities of the pixels in the column to which the pixel belongs. Fig.11 As shown, then based on these pixel matrix SM2 (in Fig.11 The left side of the average intensity curve C is determined (on Fig.11 Each average intensity curve C includes the position of each pixel in the pixel matrix SM2 on the horizontal axis and the average intensity of each pixel in the pixel matrix SM2 on the vertical axis.

[0098] The first recognition unit 13 is configured to recognize at least one curve shape characteristic of at least one ground marking element 100 of at least one landing runway T in the average intensity curve C of the selected one or more first strips ST1 .

[0099] The ground marking element 100 may correspond to a "piano" ( Figure 1 , Figure 7 ).

[0100] exist Fig.11, a pixel matrix SM2 at the bottom of the figure has been determined based on the first submatrix SM1, whose strip ST1 includes ground marking elements 100 corresponding to a piano. The piano corresponds to a pattern that is repeated several times horizontally in the image I. The average intensity curve C determined based on the pixel matrix SM2 shown on the right side of the matrix SM2 includes information 101a about this repeated pattern. Therefore, the average intensity curve C can include information characteristics of the ground marking elements 100.

[0101] According to a preferred embodiment, the detection system S may further include a second group of units U2 , which includes a second cutting unit 21 , a second determining unit 22 and a second identifying unit 23 .

[0102] The second cutting unit 21 is configured to cut the pixel matrix M into second parallel strips ST2, each second parallel strip ST2 being associated with a corresponding position of each second strip ST2 in the pixel matrix M of one or more images I. Each second strip ST2 corresponds to a second sub-matrix having at least one pixel row L1, L2 and a plurality of pixel columns C1, C2, ..., C10 equal to a second dimension D2 of the pixel matrix M.

[0103] The second determination unit 22 is configured to determine an average intensity curve C of at least one second strip ST2 selected from the second strips ST2 from which the pixel matrix M is cut by the second cutting unit 21. The average intensity curve C is determined by calculating the average intensity of one or more pixels of each pixel column C1, C2, ..., C10 for each pixel column C1, C2, ..., C10 of the second sub-matrix of the selected one or more second strips ST2. The average intensity curve can be determined in the same manner as the first group unit U1.

[0104] For the first group of cells U1, an average intensity curve C can be determined for all second strips ST2. In this case, all second strips ST2 originating from the pixel matrix M are selected. However, an average intensity curve C can be determined for a combination of second strips ST2. In this case, only specific second strips ST2 are selected. For example, they can be selected according to their position in the pixel matrix M.

[0105] The second recognition unit 23 is configured to recognize the curve shape characteristics of at least one ground marking element 100 of at least one landing runway T in the average intensity curve C of the selected one or more second strips ST2.

[0106] By means of the second set of units U2 (together with the first set of units U1 ), it is possible to detect ground marking elements 100 extending along the first dimension D1 of the image I and ground marking elements extending along the second dimension D2 of the image I.

[0107] Thus, in the case where the detection system only includes the first group of units U1, the detection unit 2 of the detection system S is configured to detect the positions of one or more ground marking elements 100 of at least one landing runway T in one or more images based on the positions of the identified one or more ground marking elements 100 and the selected one or more first strips ST1 in the pixel matrix M of one or more images I.

[0108] Thus, in the case where the detection system includes a first group of units U1 and a second group of units U2, the detection unit 2 of the detection system S is configured to detect the positions of one or more ground marking elements 100 of at least one landing runway T in one or more images based on the identified one or more ground marking elements 100, the positions of the selected one or more first strips ST1 in the pixel matrix M of one or more images I, and the positions of the selected one or more second strips ST2 in the pixel matrix M of one or more images I.

[0109] The detection system S may also include a third determination unit (DET3) 6, which is configured to determine the position of at least one entrance of one or more landing runways T based on the position of one or more ground marking elements 100 detected in one or more images I and the characteristics of one or more landing runways T derived from the runway database (DB1) 41.

[0110] The runway database 41 may correspond to the ICAO database in ICAO (International Civil Aviation Organization) Annex 14.

[0111] The detection system S may further comprise a fourth determination unit (DET4) 7 configured to determine the position of the aircraft AC based on the position of one or more entrances of one or more landing runways T in the image I, the position and angle of one or more image acquisition units 10 and the characteristics of one or more landing tracks T derived from the runway database 41.

[0112] The fourth determination unit 7 determines the lateral position and the vertical position of the aircraft AC when the aircraft AC is flying with the purpose of landing on the landing runway T. The fourth determination unit 7 determines the lateral position of the aircraft AC when the aircraft AC is taxiing.

[0113] The detection system S may further comprise a transmission unit 8. The transmission unit (TRANS) 8 may be configured to send a signal to the user equipment 9, the signal indicating:

[0114] - the position of at least one threshold of one or more landing runways T (determined by the third determination unit 6); or

[0115] - the position of the aircraft AC (determined by the fourth determination unit 7); or

[0116] - The position of one or more ground marking elements 100 of at least one landing runway T in one or more images I (determined by the detection unit 2 ).

[0117] The user device 9 may correspond to a display device. With the help of the detected positions of one or more ground marking elements 100 of at least one landing runway T in one or more images I, the display device may superimpose an image I of the landing runway T and a graphic element highlighting the ground marking element 100 of the landing runway T.

[0118] The user device 9 may also correspond to the flight control system of the aircraft AC. The knowledge of the position of the threshold of the landing runway T in the image I, the knowledge of the position and angle of the image acquisition unit 10 and the knowledge of the characteristics of the landing runway T (such as its width) can be used to determine the vertical position and the lateral position of the aircraft AC. The characteristics of the landing runway T may include the geographical coordinates (latitude, longitude, altitude) of the considered ground landmarks, for example the angular orientation of the runway in terms of width, length, etc. These characteristics of the runway T may originate from the database 41.

[0119] According to a first configuration, the first recognition unit 13 may be configured to use a neural network to recognize the curve shape characteristics of at least one ground marking element 100 of one or more landing runways T in the average intensity curve C of the selected one or more first strips ST1.

[0120] According to a preferred embodiment in the first configuration, the second recognition unit 23 is further configured to use a neural network to recognize the curve shape characteristics of at least one ground marking element 100 of one or more landing runways T in the average intensity curve C of the selected one or more second strips ST2.

[0121] According to the second configuration ( Figure 2 ), the first recognition unit 13 may also include a first frequency analysis subunit 131 (FREQ), a first data partitioning subunit (or “clustering unit”) 132 (CLUST) and a first recognition subunit 133.

[0122] The first frequency analysis subunit 131 is configured to detect at least one harmonic in the average intensity curve C of the selected one or more first strips ST1 .

[0123] The first data partitioning subunit 132 is configured to form at least one group including one or more harmonic characteristics of the ground marking elements 100 of one or more landing runways T. The one or more harmonic characteristics of the ground marking elements 100 are stored in a database 4 (DB2).

[0124] The identification subunit 133 is configured to identify at least one ground marking element 100 of one or more landing runways T for one or more groups formed by the first data partitioning subunit 132 .

[0125] According to the second configuration ( Figure 2 ) in the preferred embodiment, the second identification unit 23 may also include a second frequency analysis subunit 231, a second data partitioning subunit 232 and a second identification subunit 233.

[0126] The second frequency analysis subunit 231 is configured to detect at least one harmonic in the average intensity curve C of the selected one or more second strips ST2.

[0127] The second data partitioning subunit 232 is configured to form at least one group comprising one or more harmonic characteristics of the ground marking elements 100 of one or more landing runways T. The one or more harmonic characteristics of the ground marking elements 100 are also stored in the database 4 .

[0128] The second identification subunit 233 is configured to identify at least one ground marking element 100 of one or more landing runways T for one or more groups formed by the second data partitioning subunit 232 .

[0129] According to the third configuration ( Figure 3 ), the first identification unit 13 includes a first correlation subunit 134 (COR) and a first identification subunit 135.

[0130] The first correlation subunit 134 is configured for determining at least one correlation parameter between the average intensity curve C of the selected one or more first strips ST1 and at least one synthetic curve CS characteristic of the ground marking element 100. The one or more synthetic curves CS are stored in the database 4. Fig.12 An example of a composite curve CS is shown.

[0131] The first identification subunit 135 is configured to identify at least one ground marking element 100 of one or more landing runways T if the correlation parameter determined by the first correlation subunit 134 is greater than or equal to a predetermined value.

[0132] According to the third configuration ( Figure 3 ) in the preferred embodiment, the second identification unit 23 may further include a second correlation subunit 234 and a second identification subunit 235.

[0133] The second correlation subunit 234 is configured to determine at least one correlation parameter between the average intensity curve C of the selected one or more second strips ST2 and at least one synthetic curve CS characteristic of the ground marking element 100. The one or more synthetic curves CS are stored in the database 4. The database 4 may include a plurality of synthetic curves CS. Each synthetic curve CS may include information characteristics of the ground marking element 100. For example, the synthetic curve CS may include information characteristics of the marking element 100 of a piano.

[0134] The second identification subunit 235 is configured to identify at least one ground marking element 100 of one or more landing runways T if the correlation parameter determined by the second correlation subunit 234 is greater than or equal to a predetermined value.

[0135] Fig.12 The composite curve CS shown in includes the information 101b characteristics of the ground marking element 100 of the piano. Fig.11 The average intensity curve C shown in the lower right of FIG. 1 also includes information 101a characteristic of the ground marking element 100 of the piano. Therefore, implementing the first correlation subunit 134 allows determining a correlation parameter greater than or equal to a predetermined value. Therefore, the piano is identified by the identification subunit 235.

[0136] Furthermore, the first group of units U1 may include a first comparison unit 14 (COMP) and a first trimming unit 15 (RECT).

[0137] The identification subunit 235 may identify any other ground marking elements 100 in the same manner.

[0138] The first comparison unit 14 is configured to compare the average intensity curves C of the same ground marking elements 100 that have been identified in order to determine whether there is a shift between the average intensity curves C.

[0139] If the offset has been determined, a first trimming unit 15 is implemented. It is configured for trimming the pixel matrix M of the one or more images I according to the determined offset.

[0140] The first set of units U1 is then also implemented using the pixel matrix M of the image or images I trimmed by the first trimming subunit 15 .

[0141] According to a preferred embodiment, the second group of units U2 further comprises a second comparing unit 24 and a second trimming unit 25 .

[0142] The second comparison unit 24 is configured to compare the average intensity curves C of the identified identical ground marking elements 100 in order to determine whether there is a shift between the average intensity curves C.

[0143] If the offset has been determined, a second trimming unit 25 is implemented. It is configured for trimming the pixel matrix M of the one or more images I according to the determined offset.

[0144] The second set of units U2 is then also implemented using the pixel matrix M of the image or images I trimmed by the second trimming subunit 25 .

[0145] The invention also relates to a method for detecting at least one ground marking element of at least one landing runway. Figure 4 ).

[0146] The detection method P at least comprises the following steps:

[0147] - an image acquisition step E1 implemented by the image acquisition unit 10 for acquiring at least one image I captured by at least one image capture unit 1, the image or images I being in the form of a pixel matrix M having a first dimension D1 and a second dimension D2;

[0148] - A first set of steps S1 comprising:

[0149] o a first cutting step E11, implemented by the first cutting unit 11, for cutting the pixel matrix M into first parallel strips ST1, each first parallel strip ST1 being associated with a respective position of each first strip ST1 in the pixel matrix M of one or more images I, each first strip ST1 corresponding to a first sub-matrix SM1 having at least one pixel row L1, L2 and a plurality of pixel columns C1, C2, ..., C10 equal to a first dimension D1 of the pixel matrix M;

[0150] o a first determination step E12, implemented by the first determination unit 12, for determining an average intensity curve C for at least one first strip ST1 selected from the first strips ST1 originating from the cut pixel matrix M, the average intensity curve C being determined by calculating, for each pixel column C1, C2, ..., C10 of the first sub-matrix SM1 of the selected one or more first strips ST1, an average intensity of one or more pixels of each pixel column C1, C2, ..., C10;

[0151] o A first recognition step E13 , implemented by the first recognition unit 13 , for recognizing the curve shape characteristics of at least one ground marking element 100 of at least one landing runway T in the average intensity curve C of the selected one or more first strips ST1 .

[0152] The detection method also includes:

[0153] - A detection step E2, implemented by the detection unit 2, for detecting the position of one or more ground marking elements 100 of at least one landing runway T in one or more images I based on the position of the identified one or more ground marking elements 100 and the selected one or more first strips ST1 in the pixel matrix M of one or more images I.

[0154] According to a preferred embodiment, the detection method P also comprises a second set of steps S2 preceding the detection step E2.

[0155] The second set of steps S2 comprises:

[0156] - a second cutting step E21, implemented by the second cutting unit 21, for cutting the pixel matrix M into second parallel strips ST2, each second parallel strip ST2 being associated with a respective position of each second strip ST2 in the pixel matrix M of one or more images I, each second strip ST2 corresponding to a second sub-matrix having at least one pixel row L1, L2 and a plurality of pixel columns C1, C2, ..., C10 equal to a second dimension D2 of the pixel matrix M;

[0157] - a second determination step E22, implemented by the second determination unit 22, for determining, for at least one second strip ST2 selected from the second strips ST2 originating from the cut pixel matrix M, an average intensity curve C, the average intensity curve C being determined by calculating, for each pixel column C1, C2, ..., C10 of the second sub-matrix of the selected one or more second strips ST1, an average intensity of one or more pixels of each pixel column C1, C2, ..., C10;

[0158] A second recognition step E23 , implemented by the second recognition unit 23 , is used to recognize, in the average intensity curve C of the selected one or more second strips ST2 , the characteristic curve shape of at least one ground marking element 100 of at least one landing runway T.

[0159] In a preferred embodiment, the detection step E2 is implemented to detect the positions of one or more ground marking elements 100 of at least one landing runway T in one or more images I based on the identified one or more ground marking elements 100, the positions of one or more selected first strips ST1 in the pixel matrix M of one or more images I, and the positions of one or more selected second strips ST2 in the pixel matrix M of one or more images I.

[0160] According to a first alternative embodiment, a first identification step E13 and / or a second identification step E23 are implemented in order to identify the curve shape characteristics of at least one ground marking element 100 of one or more landing runways T in the average intensity curve C of one or more selected first strips ST1 and / or one or more selected second strips ST2 using a neural network.

[0161] The average intensity curve C can also be used to train a neural network.

[0162] According to the second alternative embodiment ( Figure 5 ), the first identification step E13 includes the following sub-steps:

[0163] - a first frequency analysis sub-step E131 , implemented by the first frequency analysis sub-unit 131 , for detecting at least one harmonic in the average intensity curve C of the selected first strip or strips ST1 ;

[0164] - a first data partitioning sub-step E132, implemented by the first data partitioning sub-unit 132, for forming at least one group comprising one or more harmonic characteristics of the ground marking elements 100 of the landing runway T, wherein the one or more harmonic characteristics of the ground marking elements 100 are stored in the database 4;

[0165] A first identification sub-step E133 , implemented by a first identification sub-unit 133 , is used to identify at least one ground marking element 100 of one or more landing runways T for the one or more groups formed in the first data partitioning sub-step E132 .

[0166] According to the preferred embodiment of the second alternative embodiment ( Figure 5 ), the second identification step E23 includes the following sub-steps:

[0167] - a second frequency analysis sub-step E231 , implemented by the second frequency analysis sub-unit 231 , for detecting at least one harmonic in the average intensity curve C of the selected one or more second strips ST2 ;

[0168] - a second data partitioning sub-step E232, implemented by the second data partitioning sub-unit 232, for forming at least one group of one or more harmonic characteristics of the ground marking elements 100 of the landing runway T, wherein the one or more harmonic characteristics of the ground marking elements 100 are stored in the database 4;

[0169] A second identification sub-step E233 , implemented by the second identification sub-unit 233 , is used to identify at least one ground marking element 100 of one or more landing runways T for the one or more groups formed in the second data partitioning sub-step E232 .

[0170] According to the third alternative embodiment ( Figure 6 ), the first identification step E13 includes the following sub-steps:

[0171] - a first correlation sub-step E134 , implemented by the first correlation sub-unit 134 , for determining at least one correlation parameter between the average intensity curve C of the selected one or more first strips ST1 and at least one synthetic curve CS characteristic of the ground marking element 100 , wherein the one or more synthetic curves CS are stored in the database 4 ;

[0172] A first identification sub-step E135 , implemented by a first identification sub-unit 135 , is used to identify at least one ground marking element 100 of one or more landing runways T if the correlation parameter determined in the first correlation sub-step E134 is greater than or equal to a predetermined value.

[0173] According to the preferred embodiment of the third alternative embodiment ( Figure 6 ), the second identification step E23 includes the following sub-steps:

[0174] - a second correlation sub-step E234 , implemented by the second correlation sub-unit 234 , for determining at least one correlation parameter between the average intensity curve C of the selected one or more second strips ST2 and at least one synthetic curve CS characteristic of the ground marking element 100 , wherein the one or more synthetic curves CS are stored in the database 4 ;

[0175] A second identification sub-step E235 , implemented by the second identification sub-unit 235 , is used to identify at least one ground marking element 100 of one or more landing runways T if the correlation parameter determined in the second correlation sub-step E234 is greater than or equal to a predetermined value.

[0176] Furthermore, the first set of steps S1 may include:

[0177] a first comparison step E14 , implemented by the first comparison unit 14 , for comparing the average intensity curves C of identical ground marking elements 100 that have been identified, in order to determine whether there is a shift between said average intensity curves C;

[0178] A first trimming step E15 , if an offset has been determined, is implemented by a first trimming unit 15 for trimming the pixel matrix M of the image or images I according to the determined offset.

[0179] The first set of steps S1 may then be repeated for the pixel matrix M of the one or more images I trimmed in the first trimming step E14 .

[0180] According to a preferred embodiment, the second set of steps S2 may include:

[0181] a second comparison step E24 , implemented by the second comparison unit 24 , for comparing the average intensity curves C of identical ground marking elements 100 that have been identified, in order to determine whether there is a shift between said average intensity curves C;

[0182] A second trimming step E25 , if an offset has been determined, is implemented by the second trimming unit 25 for trimming the pixel matrix M of the image or images I according to the determined offset.

[0183] The second set of steps S2 may then be repeated for the pixel matrix M of the one or more images I trimmed in the second trimming step E24 .

[0184] The detection method P may also include a third determination step E3, which is implemented by a third determination unit 6, for determining the position of at least one entrance of one or more landing runways T based on the position of one or more ground marking elements 100 detected in one or more images I and the characteristics of one or more landing runways T derived from the runway database 41.

[0185] The detection method P may further comprise a fourth determination step E4, which is implemented by a fourth determination unit 7, for determining the position of the aircraft AC based on the position of one or more entrances of one or more landing runways T in the image I, the position and angle of one or more image acquisition units 10, and the characteristics of one or more landing runways T from a runway database 41.

[0186] The detection method P may also include a transmission step E5, which is implemented by the transmission unit 8 to send a signal to the user device 9, which represents the position of at least one entrance of one or more landing runways T in one or more images I, or the position of the aircraft AC in one or more images I, or the position of one or more ground marking elements 100 of at least one landing runway T in one or more images I.

[0187] The detection system S and the detection method P have many advantages, in particular:

[0188] - It facilitates data management for testing or training purposes in the case of deep learning models. In fact, a one-dimensional signal (mean intensity curve C) is significantly lighter than a two-dimensional signal (image I). This provides advantages for transmitting data, storing data and processing data;

[0189] - Processing one-dimensional signals is also faster than processing two-dimensional signals. This allows reducing the computing power of the computing devices on board the aircraft AC, and therefore reducing their cost and power consumption;

[0190] - generating one-dimensional synthetic signals (curves) is easier to implement and cheaper than generating two-dimensional images of landing strips, which requires the use of expensive tools and simulators, in terms of data that can be used to test or train neural networks;

[0191] -Another advantage in the aviation context is the aspect related to interpretability. Deep learning based algorithms would be a black box in terms of interpreting the results output from the neural network. The proposed approach makes it easier to understand why a specific result has been observed. This is because signal processing techniques are already widely proven in the aviation field.

Claims

1. A method for detecting at least one ground marking element of at least one landing runway, It is characterized in that The method comprises at least the following steps: - an image acquisition step (E1) implemented by an image acquisition unit (10) for acquiring at least one image (I) captured by at least one image capture unit (1), said one or more images (I) being in the form of a pixel matrix (M) having a first dimension (D1) and a second dimension (D2); - A first set of steps (S1) comprising: o a first cutting step (E11), implemented by a first cutting unit (11), for cutting the pixel matrix (M) into first parallel strips (ST1), each first parallel strip (STl) being associated with a respective position of each first strip (STl) in the pixel matrix (M) of the one or more images (I), each first strip (ST1) corresponding to a first submatrix (SM1) having at least one pixel row (L1, L2) and a plurality of pixel columns (C1, C2, ..., C10) equal to a first dimension (D1) of the pixel matrix (M); o a first determination step (E12), implemented by a first determination unit (12) for determining an average intensity curve (C) for at least one first strip (ST1) selected from the first strips (ST1) resulting from cutting the pixel matrix (M), the average intensity curve (C) being determined by calculating, for each pixel column (C1, C2, ..., C10) of the first sub-matrix (SM1) of the selected one or more first strips (ST1), an average intensity of one or more pixels of each pixel column (C1, C2, ..., C10); o a first recognition step (E13), implemented by a first recognition unit (13), for recognizing, in the average intensity curve (C) of the selected one or more first strips (ST1), a curve shape characteristic of at least one ground marking element (100) of at least one landing runway (T); The detection method also includes a detection step (E2), which is implemented by the detection unit (2) to detect the position of one or more ground marking elements (100) of at least one landing runway (T) in the one or more images (I) based on the position of the identified one or more ground marking elements (100) and the selected one or more first strips (ST1) in the pixel matrix (M) of the one or more images (I).

2. The method according to claim 1, It is characterized in that The method comprises a second set of steps (S2) before the detection step (E2), wherein the second set of steps (S2) comprises: - a second cutting step (E21), implemented by a second cutting unit (21), for cutting the pixel matrix (M) into second parallel strips (ST2), each second parallel strip (ST2) being associated with a respective position of each second strip (ST2) in the pixel matrix (M) of the one or more images (I), each second strip (ST2) corresponding to a second submatrix having at least one pixel row (L1, L2) and a plurality of pixel columns (C1, C2, ..., C10) equal to a second dimension (D2) of the pixel matrix (M); - a second determination step (E22), implemented by a second determination unit (22), for determining an average intensity curve (C) for at least one second strip (ST2) selected from the second strips (ST2) resulting from cutting the pixel matrix (M), the average intensity curve (C) being determined by calculating, for each pixel column (C1, C2, ..., C10) of the second submatrix of the selected one or more second strips (ST1), an average intensity of one or more pixels of each pixel column (C1, C2, ..., C10); - a second recognition step (E23), implemented by a second recognition unit (23), for recognizing, in the average intensity curve (C) of the selected one or more second strips (ST2), a curve shape characteristic of at least one ground marking element (100) of at least one landing runway (T); The detection step (E2) is implemented to detect the position of one or more ground marking elements (100) of at least one landing runway (T) in the one or more images (I) based on the identified one or more ground marking elements (100), the position of one or more selected first strips (ST1) in the pixel matrix (M) of the one or more images (I), and the position of one or more selected second strips (ST2) in the pixel matrix (M) of the one or more images (I).

3. The method according to any one of claims 1 or 2, It is characterized in that The first recognition step (E13) and / or the second recognition step (E23) are implemented so as to recognize the curve shape characteristics of at least one ground marking element (100) of the one or more landing runways (T) in the average intensity curve (C) of the selected one or more first strips (ST1) and / or the selected one or more second strips (ST2) using a neural network.

4. The method according to any one of claims 1 or 2, It is characterized in that The first identification step (E13) comprises the following sub-steps: - a first frequency analysis sub-step (E131) implemented by a first frequency analysis sub-unit (131) for detecting at least one harmonic in the average intensity curve (C) of the selected first strip or strips (ST1); - a first data partitioning sub-step (E132), implemented by a first data partitioning sub-unit (132) for forming at least one group comprising one or more harmonic characteristics of ground marking elements (100) of the landing runway (T), wherein the one or more harmonic characteristics of the ground marking elements (100) are stored in a database (4); - a first identification sub-step (E133), implemented by a first identification sub-unit (133), for identifying at least one ground marking element (100) of the one or more landing runways (T) for the one or more groups formed in the first data partitioning sub-step (E132).

5. The method according to claim 4, It is characterized in that The second identification step (E23) comprises the following sub-steps: - a second frequency analysis sub-step (E231) implemented by a second frequency analysis sub-unit (231) for detecting at least one harmonic in the average intensity curve (C) of the selected one or more second strips (ST2); - a second data partitioning sub-step (E232), implemented by the second data partitioning sub-unit (232), for forming at least one group comprising one or more harmonic characteristics of ground marking elements (100) of the landing runway (T), wherein the one or more harmonic characteristics of the ground marking elements (100) are stored in the database (4); - a second identification sub-step (E233), implemented by a second identification sub-unit (233), for identifying at least one ground marking element (100) of the one or more landing runways (T) for the one or more groups formed in the second data partitioning sub-step (E232).

6. The method according to any one of claims 1 or 2, It is characterized in that The first identification step (E13) comprises the following sub-steps: - a first correlation sub-step (E134), implemented by a first correlation sub-unit (134), for determining at least one correlation parameter between the average intensity curve (C) of the selected one or more first strips (ST1) and at least one synthetic curve (CS) characteristic of the ground marking element (100), wherein the one or more synthetic curves (CS) are stored in a database (4); - a first identification sub-step (E135), implemented by a first identification sub-unit (135), for identifying at least one ground marking element (100) of said one or more landing runways (T) if the correlation parameter determined in said first correlation sub-step (E134) is greater than or equal to a predetermined value.

7. The method according to claim 6, It is characterized in that The second identification step (E23) comprises the following sub-steps: - a second correlation sub-step (E234), implemented by the second correlation sub-unit (234), for determining at least one correlation parameter between the average intensity curve (C) of the selected one or more second strips (ST2) and at least one synthetic curve (CS) characteristic of the ground marking element (100), wherein the one or more synthetic curves (CS) are stored in the database (4); - a second identification sub-step (E235), implemented by a second identification sub-unit (235), for identifying at least one ground marking element (100) of said one or more landing runways (T) if the correlation parameter determined in said second correlation sub-step (E234) is greater than or equal to a predetermined value.

8. The method according to any one of claims 1 to 5, It is characterized in that The first set of steps (S1) comprises: - a first comparison step (E14), implemented by a first comparison unit (14), for comparing the average intensity curves (C) of the same ground marking elements (100) that have been identified, in order to determine whether there is a shift between said average intensity curves (C); - a first trimming step (E15), implemented by a first trimming unit (15), if the offset has been determined, for trimming the pixel matrix (M) of the one or more images (I) according to the determined offset; The first set of steps (S1) is repeated for the pixel matrix (M) of the one or more images (I) trimmed in the first trimming step (E14).

9. The method according to claim 8, It is characterized in that The second set of steps (S2) comprises: - a second comparison step (E24), implemented by a second comparison unit (24), for comparing the average intensity curves (C) of the same ground marking elements (100) that have been identified, in order to determine whether there is a shift between said average intensity curves (C); - a second trimming step (E25), if the offset has been determined, implemented by a second trimming unit (25) for trimming the pixel matrix (M) of the one or more images (I) according to the determined offset, The second set of steps (S2) is repeated for the pixel matrix (M) of the one or more images (I) trimmed in the second trimming step (E24).

10. The method according to any one of claims 1 to 9, It is characterized in that The method further comprises a third determination step (E3), which is implemented by a third determination unit (6) for determining the position of at least one entrance of the one or more landing runways (T) based on the position of the one or more ground marking elements (100) detected in the one or more images (I) and the characteristics of the one or more landing runways (T) derived from the runway database (41).

11. The method according to any one of claims 1 to 10, It is characterized in that The method further comprises a fourth determination step (E4), which is implemented by a fourth determination unit (7) for determining the position of the aircraft (AC) based on the position of one or more entrances of the one or more landing runways (T) in the image (I), the position and angle of the one or more image acquisition units (10) and the characteristics of the one or more landing runways (T) from the runway database (41).

12. The method according to any one of claims 1 to 11, It is characterized in that The method comprises a transmission step (E5), which is implemented by a transmission unit (8) for sending a signal to a user device (9), wherein the signal represents the position of at least one entrance of the one or more landing runways (T) in the one or more images (I), or the position of the aircraft (AC) in the one or more images (I), or the position of one or more ground marking elements (100) of at least one landing runway (T) in the one or more images (I).

13. A system for detecting at least one ground marking element of at least one landing runway, It is characterized in that The system includes at least: - an image acquisition unit (10) configured to acquire at least one image (I) captured by at least one image capture unit (1), the one or more images (I) being in the form of a pixel matrix (M) having a first dimension (D1) and a second dimension (D2); - A first group of units (U1) comprising: o a first cutting unit (11) configured to cut the pixel matrix (M) into first parallel strips (ST1), each first parallel strip (STl) being associated with a corresponding position of each first strip (STl) in the pixel matrix (M) of the one or more images (I), each first strip (ST1) corresponding to a first submatrix (SM1) having at least one pixel row (L1, L2) and a plurality of pixel columns (C1, C2, ..., C10) equal to a first dimension (D1) of the pixel matrix (M); o a first determination unit (12) configured to determine an average intensity curve (C) for at least one first strip (ST1) selected from the first strips (ST1) resulting from cutting the pixel matrix (M), the average intensity curve (C) being determined by calculating an average intensity of one or more pixels of each pixel column (C1, C2, ..., C10) of each pixel column (C1, C2, ..., C10) of the first sub-matrix (SM1) of the selected one or more first strips (ST1); o a first recognition unit (13) configured to recognize, in the average intensity curve (C) of the selected one or more first strips (ST1), a curve shape characteristic of at least one ground marking element (100) of at least one landing runway (T); The detection system (S) also includes: - a detection unit (2) configured to detect the position of the one or more ground marking elements (100) in the one or more images (I) based on the position of the one or more identified ground marking elements (100) and the selected one or more first strips (ST1) in the pixel matrix (M) of the one or more images (I).

14. The system according to claim 13, It is characterized in that The system comprises a second set of units (U2) comprising: - a second cutting unit (21) configured to cut the pixel matrix (M) into second parallel strips (ST2), each second parallel strip (ST2) being associated with a respective position of each second strip (ST2) in the pixel matrix (M) of the one or more images (I), each second strip (ST2) corresponding to a second submatrix having at least one pixel row (L1, L2) and a plurality of pixel columns (C1, C2, ..., C10) equal to a second dimension (D2) of the pixel matrix (M); - a second determination unit (22) configured to determine an average intensity curve (C) for at least one second strip (ST2) selected from the second strips (ST2) resulting from cutting the pixel matrix (M), the average intensity curve (C) being determined by calculating, for each pixel column (C1, C2, ..., C10) of the second submatrix of the selected one or more second strips (ST1), an average intensity of one or more pixels of each pixel column (C1, C2, ..., C10); a second recognition unit (23) configured to recognize, in the average intensity curve (C) of the selected one or more second strips (ST2), a curve shape characteristic of at least one ground marking element (100) of at least one landing runway (T); The detection unit (2) is configured to detect the positions of one or more ground marking elements (100) of at least one landing runway (T) in the one or more images (I) based on the identified one or more ground marking elements (100), the positions of the selected one or more first strips (ST1) in the pixel matrix (M) of the one or more images (I), and the positions of the selected one or more second strips (ST2) in the pixel matrix (M) of the one or more images (I).

15. An aircraft, It is characterized in that The aircraft comprises a detection system (S) according to any one of claims 13 and 14.

Images