Marine target identification method, system and device and remote sensing satellite

Abstract

The invention discloses a marine target identification method, system and device and a remote sensing satellite, relates to the field of marine target detection, and aims to solve the problems that a marine ship burns fossil energy and discharges a large amount of heat and the temperature is obviously higher than the temperature of seawater in the movement process, and a visible light load and an infrared spectrum load are carried on the remote sensing satellite at the same time. The method comprises the following steps: acquiring a remote sensing image and thermal infrared data representing the temperature condition of each region in the remote sensing image, determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm, and performing region calibration on the remote sensing image based on the surface temperature and a preset temperature segmentation condition to obtain a to-be-identified image marked with a plurality of suspected target regions, and processing the image according to a preset image recognition algorithm so as to recognize each marine target and the position of the marine target. According to the method, region calibration is realized by means of the surface temperature, the efficiency is higher, identification of each target and the position of the target can be accurately realized, and the requirement of rapid online target identification can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of marine target detection, and in particular to a marine target recognition method, system, device and remote sensing satellite. Background Art

[0002] The accurate identification and detection of targets such as ships and submarines in the ocean are of great practical significance. To this end, the main identification method currently adopted is to extract features from the collected satellite images to generate feature maps, generate a large number of candidate regions on the feature maps through RPN (Region Proposal Network), and use the non-maximum suppression algorithm to screen the candidate boxes to obtain the regions of interest, then perform pooling on the regions of interest, and output the recognition results through target position regression and classification. However, the entire process from determining the candidate area to the subsequent screening of the area of ​​interest and then to the subsequent pooling in this scheme takes a considerable amount of time. For example, the process of generating candidate areas using RPN requires traversing the entire satellite image. Taking the coverage of the satellite image as 180km×170km as an example, the resolution is 30m, and the size of the entire image is 5667×6000. Assuming that the sample size of a preferred area is 30×30, the time required to select a candidate area is 0.05 seconds, and the time required to traverse the entire satellite image is 30 minutes. It can be seen that the current target recognition method is inefficient, and due to the limited computing resources on the satellite side, the scheme cannot meet the requirements of fast online recognition.

[0003] Therefore, how to provide an effective solution for maritime target identification is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the present invention provides a method, system, device and remote sensing satellite for identifying marine targets, which are more efficient, can accurately identify various marine targets and their locations, and can meet the needs of rapid online target recognition at remote sensing satellites with limited computing resources.

[0005] In order to solve the above technical problems, the present application provides a method for identifying a marine target, which is applied to a remote sensing satellite. The remote sensing satellite is equipped with a visible light payload and an infrared spectrum payload. The method for identifying a marine target includes:

[0006] Acquire the remote sensing image of the current sea area collected by the visible light payload;

[0007] Acquire thermal infrared data collected by the infrared spectrum payload that characterizes the temperature conditions of each area in the remote sensing image;

[0008] Determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm;

[0009] Based on the surface temperature and the preset temperature segmentation condition, the remote sensing image is regionally calibrated to obtain an image to be identified with multiple suspected target areas marked;

[0010] The image to be identified is processed according to a preset image recognition algorithm to identify various marine targets and their locations.

[0011] Furthermore, after obtaining the remote sensing image of the current sea area collected by the visible light payload, the method further includes:

[0012] The pixel brightness values ​​of the remote sensing image are converted into radiation brightness values ​​by using a preset radiation calibration strategy to obtain a first processed remote sensing image represented by the radiation brightness values.

[0013] Furthermore, after obtaining the first processed remote sensing image represented by the radiance value, the method further includes:

[0014] The first processed remote sensing image is processed according to a preset atmospheric correction strategy to obtain a second processed remote sensing image with atmospheric influence removed.

[0015] Furthermore, the remote sensing image is regionally calibrated based on the surface temperature and a preset temperature segmentation condition, including:

[0016] The area where the surface temperature is not less than a preset temperature threshold is determined as a suspected target area, so as to obtain an image to be identified with multiple suspected target areas marked thereon.

[0017] Furthermore, the remote sensing image is regionally calibrated based on the surface temperature and a preset temperature segmentation condition, including:

[0018] Determining a relative temperature parameter based on the surface temperature and the background temperature;

[0019] The region whose relative temperature parameter is not less than a preset parameter threshold is determined as a suspected target region, so as to obtain an image to be identified with a plurality of suspected target regions marked thereon.

[0020] Further, the thermal infrared data is a first brightness temperature in a first target thermal infrared band;

[0021] Determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm includes:

[0022] Determining the ground surface temperature based on the first brightness temperature and a first preset relationship;

[0023] The first preset relationship is:

[0024]

[0025] Among them, T s represents the surface temperature, a is the first constant coefficient, b is the second constant coefficient, T 10 is the first brightness temperature, T a is the preset atmospheric average working temperature, C is the first intermediate variable determined by the second preset relationship, and D is the second intermediate variable determined by the third preset relationship;

[0026] The second preset relationship is:

[0027] C=ετ

[0028] The third preset relationship is:

[0029] D = (1-τ)[1+(1-ε)τ]

[0030] Among them, ε is the predetermined surface emissivity, and τ is the predetermined atmospheric transmittance.

[0031] Further, the thermal infrared data includes a first brightness temperature in a first target thermal infrared band and a second brightness temperature in a second target thermal infrared band;

[0032] Determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm includes:

[0033] Determine the ground surface temperature according to the first brightness temperature, the second brightness temperature and a fourth preset relationship;

[0034] The fourth preset relationship is:

[0035] T s =A 0 +A 1 T 10 -A 2 T 11 +A 3 (T 10 -T 11 )+A 4 (T 10 -T 11 ) 2 +A 5 (T 10 -T 11 ) 3

[0036] Among them, T s represents the surface temperature, A 0 is the first coefficient determined in advance, A 1 is the predetermined second coefficient, A 2 is the predetermined third coefficient, A 3is the predetermined fourth coefficient, A 4 is the predetermined fifth coefficient, A 5 is the predetermined sixth coefficient, T 10 is the first brightness temperature, T 11 is the second brightness temperature.

[0037] In order to solve the above technical problems, the present application also provides a marine target recognition system, which is applied to a remote sensing satellite. The remote sensing satellite is equipped with a visible light payload and an infrared spectrum payload. The marine target recognition system includes:

[0038] A first acquisition unit, used to acquire the remote sensing image of the current sea area collected by the visible light payload;

[0039] A second acquisition unit is used to acquire thermal infrared data representing the temperature conditions of each area in the remote sensing image collected by the infrared spectrum payload;

[0040] A temperature inversion unit, used to determine the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm;

[0041] A region calibration unit, used for performing region calibration on the remote sensing image based on the surface temperature and a preset temperature segmentation condition, so as to obtain an image to be identified with a plurality of suspected target regions marked thereon;

[0042] The recognition unit is used to process the image to be recognized according to a preset image recognition algorithm to recognize various marine targets and their locations.

[0043] In order to solve the above technical problems, the present application also provides a device for identifying marine targets, including:

[0044] Memory for storing computer programs;

[0045] A processor is used to implement the steps of the method for identifying marine targets as described above when executing the computer program.

[0046] In order to solve the above technical problems, the present application also provides a remote sensing satellite, including a visible light payload and an infrared spectrum payload, and also including a control module;

[0047] The control module is connected to the visible light payload and the infrared spectrum payload respectively, and is used to execute the steps of the marine target identification method as described above.

[0048] The present application provides a method, system, device and remote sensing satellite for identifying marine targets. Considering the particularity of marine ship movement, that is, it will burn fossil energy and emit a large amount of heat during movement, and its temperature will be significantly higher than the seawater temperature, which can be clearly reflected in thermal infrared data. Therefore, the remote sensing satellite is equipped with visible light payload and infrared spectrum payload at the same time, and obtains remote sensing images and thermal infrared data representing the temperature conditions of each region in the remote sensing image. The surface temperature is determined according to the thermal infrared data and the preset temperature inversion algorithm, and then the remote sensing image is regionally calibrated based on the surface temperature and the preset temperature segmentation conditions to obtain an image to be identified with multiple suspected target areas marked, and the image to be identified is processed according to the preset image recognition algorithm to identify each marine target and its location. It can be seen that compared with the current complex processing process, that is, using the RPN algorithm to determine the candidate area, screen the area of ​​interest, and then to the subsequent pooling, the present application relies on the surface temperature to achieve regional calibration, which is more efficient and accurate, can accurately realize the identification of each target and its location, can meet the needs of fast online target recognition at remote sensing satellites with limited computing resources, and is conducive to practical application.

[0049] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0051] Figure 1 A flow chart of a method for identifying a marine target provided by the present invention;

[0052] Figure 2 It is a schematic diagram of the result after ship identification based on the solution in the prior art;

[0053] Figure 3 A schematic diagram of the result of identifying a ship in the same area by using the solution of the present application provided by the present invention;

[0054] Figure 4 A schematic diagram for comparing the effects of an identification solution provided by the present invention;

[0055] Figure 5 The present invention provides a Figure 4 Schematic diagram of the comparison of recognition scheme effects after the local area is enlarged;

[0056] Figure 6 A schematic diagram of the structure of a marine target identification system provided by the present invention;

[0057] Figure 7 A schematic structural diagram of a marine target identification device provided by the present invention. DETAILED DESCRIPTION

[0058] The core of the present invention is to provide a method, system, device and remote sensing satellite for identifying marine targets, which are more efficient, can accurately identify various marine targets and their locations, and can meet the needs of rapid online target recognition at remote sensing satellites with limited computing resources.

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0060] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0061] Please refer to Figure 1 , Figure 1 The present invention provides a flow chart of a method for identifying a marine target.

[0062] The method for identifying a marine target is applied to a remote sensing satellite, which is equipped with a visible light payload and an infrared spectrum payload. The method for identifying a marine target includes:

[0063] S11: Acquire remote sensing images of the current sea area collected by the visible light payload;

[0064] S12: Acquire thermal infrared data representing the temperature conditions of each area in the remote sensing image collected by the infrared spectrum payload;

[0065] In this embodiment, the particularity of the movement of ships at sea is taken into account, that is, they will burn fossil energy and emit a large amount of heat during the movement, and their temperature will be significantly higher than the sea water temperature. Corresponding to the thermal infrared data, its notable feature is that the reflectivity in the thermal infrared band is significantly higher than that in the offshore area, that is, this temperature change will be obviously reflected in the thermal infrared data. Therefore, the remote sensing satellite is equipped with both visible light payload and infrared spectrum payload. Specifically, the infrared spectrum payload here can be a low-resolution, low-cost thermal infrared spectrum payload, and there is no special limitation on the specific resolution of the visible light payload and the infrared spectrum payload. By way of example, the resolution of the visible light payload can be 3m, and the resolution of the infrared spectrum payload can be 10m.

[0066] It is understandable that the thermal infrared data here essentially corresponds to the remote sensing image, and represents the temperature conditions of each area in the remote sensing image; the remote sensing satellite here includes but is not limited to the Landsat 8 remote sensing satellite.

[0067] S13: determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm;

[0068] S14: performing regional calibration on the remote sensing image based on the surface temperature and the preset temperature segmentation condition to obtain an image to be identified with multiple suspected target areas marked;

[0069] Specifically, a preset temperature inversion algorithm is pre-designed and trained to determine the surface temperature. Since the surface temperature corresponding to the area where the ship is located will be higher, reliable calibration of the suspected target area can be achieved based on step S14.

[0070] S15: Processing the image to be recognized according to a preset image recognition algorithm to recognize various marine targets and their locations.

[0071] Specifically, the preset image recognition algorithm here can be various traditional ship detection algorithms, which are not particularly limited here and can be selected according to actual needs.

[0072] In summary, the present application provides a method for identifying marine targets. Compared with the current complex processing process, that is, using the RPN algorithm to determine the candidate area, screen the area of ​​interest, and then perform subsequent pooling, the present application relies on surface temperature to achieve regional calibration, which is more efficient and accurate. It can accurately identify various marine targets and their locations, and can meet the needs of fast online target recognition at remote sensing satellites with limited computing resources, which is conducive to practical applications.

[0073] Based on the above embodiments:

[0074] In some embodiments, after obtaining the remote sensing image of the current sea area collected by the visible light payload, the method further includes:

[0075] The pixel brightness values ​​of the remote sensing image are converted into radiometric brightness values ​​using a preset radiometric calibration strategy to obtain a first processed remote sensing image represented by the radiometric brightness values.

[0076] In this embodiment, the above steps can effectively eliminate the acquisition error of the visible light load itself and the influence of the observation conditions on the acquisition results, so that the first processed remote sensing image has more practical physical meaning. Specifically, remote sensing software such as ENVI (The Environment for Visualizing Images, remote sensing image processing platform) can be used to perform the above radiation calibration operation, and the calibration parameters can be set according to the storage format and related parameters of the remote sensing image data, so as to realize the conversion from the pixel brightness value to the radiation brightness value, so as to obtain the first processed remote sensing image represented by the radiation brightness value.

[0077] In some embodiments, after obtaining the first processed remote sensing image represented by the radiance value, the method further includes:

[0078] The first processed remote sensing image is processed according to a preset atmospheric correction strategy to obtain a second processed remote sensing image with atmospheric influence removed.

[0079] In this embodiment, considering that the atmosphere has a great influence on the transmission of thermal infrared radiation, resulting in a deviation between the radiation brightness value and the actual surface radiation brightness value, the above method can be used to perform atmospheric correction to remove the influence of the atmosphere; specifically, the FLAASH atmospheric correction method can be used to process the first processed remote sensing image, and by inputting the first processed remote sensing image and some related atmospheric parameters such as atmospheric model, aerosol model, etc., a second processed remote sensing image with the atmospheric influence removed can be obtained.

[0080] In some embodiments, the remote sensing image is regionally calibrated based on the surface temperature and a preset temperature segmentation condition, including:

[0081] An area whose surface temperature is not less than a preset temperature threshold is determined as a suspected target area, so as to obtain an image to be identified with multiple suspected target areas marked thereon.

[0082] In this embodiment, a calibration scheme for the suspected target area is provided by a preset temperature threshold, and the implementation method is simple and reliable; specifically, the preset temperature threshold here can be set according to the characteristics of the current research area and the actual application requirements, and is not particularly limited here; and it can be understood that there may be targets, such as ships, in the area where the surface temperature is not less than the preset temperature threshold, and therefore the area is determined to be a suspected target area, and as for the area where the surface temperature is less than the preset temperature threshold, it is a non-high temperature area and no calibration is required.

[0083] In some embodiments, the remote sensing image is regionally calibrated based on the surface temperature and a preset temperature segmentation condition, including:

[0084] Determine relative temperature parameters based on surface temperature and background temperature;

[0085] The region whose relative temperature parameter is not less than the preset parameter threshold is determined as the suspected target region, so as to obtain an image to be identified with multiple suspected target regions marked thereon.

[0086] In this embodiment, a calibration scheme for the suspected target area is provided by using relative temperature parameters, and the implementation method is simple and reliable; specifically, the value of the surface temperature divided by the background temperature can be determined as the relative temperature parameter, and then the suspected target area can be determined according to the numerical relationship between the relative temperature parameter and the preset parameter threshold. Of course, the standard deviation of the surface temperature relative to the background temperature can also be determined as the relative temperature parameter, which is not specifically limited here. Similarly, the preset parameter threshold here can be set according to the characteristics of the current research area and the actual application requirements, and is not specifically limited here.

[0087] In addition, the area where the relative temperature parameter is less than the preset parameter threshold is a non-high temperature area and does not need to be calibrated.

[0088] In some embodiments, the thermal infrared data is a first brightness temperature in a first target thermal infrared band;

[0089] Determine the surface temperature based on thermal infrared data and preset temperature inversion algorithm, including:

[0090] Determining the ground surface temperature based on the first brightness temperature and a first preset relationship;

[0091] The first preset relationship is:

[0092]

[0093] Among them, T s represents the surface temperature, a is the first constant coefficient, b is the second constant coefficient, T 10 is the first brightness temperature, T a is the preset atmospheric average working temperature, C is the first intermediate variable determined by the second preset relationship, and D is the second intermediate variable determined by the third preset relationship;

[0094] The second preset relationship is:

[0095] C=ετ

[0096] The third preset relationship is:

[0097] D = (1-τ)[1+(1-ε)τ]

[0098] Among them, ε is the predetermined surface emissivity, and τ is the predetermined atmospheric transmittance.

[0099] Specifically, when the remote sensing satellite is Landsat8, a can be -67.355351, b can be 0.458606, and the atmospheric transmittance τ here can be determined according to local meteorological data or a pre-designed empirical formula, and the surface emissivity ε here can be determined according to information such as land cover type.

[0100] In addition, taking the remote sensing satellite Landsat 8 as an example, the thermal infrared data here may specifically be the first brightness temperature in the thermal infrared band 10.

[0101] In some embodiments, the thermal infrared data includes a first brightness temperature in a first target thermal infrared band and a second brightness temperature in a second target thermal infrared band;

[0102] Determine the surface temperature based on thermal infrared data and preset temperature inversion algorithm, including:

[0103] Determining the ground surface temperature according to the first brightness temperature, the second brightness temperature and a fourth preset relationship;

[0104] The fourth preset relationship is:

[0105] T s =A 0 +A 1 T 10 -A 2 T 11 +A 3 (T 10 -T 11 )+A 4 (T 10 -T 11 ) 2 +A 5 (T 10 -T 11 ) 3

[0106] Among them, T s represents the surface temperature, A 0 is the first coefficient determined in advance, A 1 is the predetermined second coefficient, A 2 is the predetermined third coefficient, A 3 is the predetermined fourth coefficient, A 4 is the predetermined fifth coefficient, A 5 is the predetermined sixth coefficient, T 10 is the first brightness temperature, T 11 is the second brightness temperature.

[0107] In this embodiment, considering that the above-mentioned surface temperature inversion method is more dependent on the accuracy of atmospheric transmittance τ and surface emissivity ε, the accuracy of determining the surface temperature is limited. For this reason, this application also provides a surface temperature inversion method, as described above; wherein the first to sixth coefficients can be obtained through pre-training, and generally, these coefficients may be different for different study areas.

[0108] In addition, taking the remote sensing satellite Landsat 8 as an example, the thermal infrared data here may specifically include a first brightness temperature in thermal infrared band 10 and a second brightness temperature in thermal infrared band 11.

[0109] As proof of the validity of the solution provided in this application, please first refer to Figure 2 , Figure 2 This is a schematic diagram of the result of ship identification based on the solution in the prior art. Specifically, Figure 2 The yellow boxes in the middle are the identified ships; please refer to Figure 3 , Figure 3 The present invention provides a schematic diagram of the result of identifying a ship in the same area by using the solution in the present application. Specifically, Figure 3 The blue boxes are the identified ships.

[0110] Please refer to Figure 4 , Figure 4 A schematic diagram for comparing the effects of an identification scheme provided by the present invention, that is, Figure 4 Lieutenant General Figure 2 and Figure 3 The recognition results in are also marked in a figure for illustration, and Figure 2 and Figure 3 The targets identified in the application are marked with yellow boxes, while the targets additionally identified according to the scheme in this application are marked with blue boxes; please refer to Figure 5 , Figure 5 The present invention provides a Figure 4 Schematic diagram of the comparison of the recognition scheme effects after the local area is enlarged. Specifically, Figure 5 Will Figure 4 The black frame is enlarged. Figure 4 and Figure 5 It can be clearly seen that the target recognition effect is better and more accurate according to the scheme in this application. In addition, from the perspective of recognition speed, the scheme in this application can shorten the time by about 80% compared with the scheme in the prior art. It can be seen that the recognition efficiency is also significantly improved, thereby proving the effectiveness of the scheme in this application.

[0111] Please refer to Figure 6 , Figure 6 A schematic structural diagram of a marine target identification system provided by the present invention.

[0112] The marine target recognition system is applied to a remote sensing satellite, which is equipped with a visible light payload and an infrared spectrum payload. The marine target recognition system includes:

[0113] A first acquisition unit 21 is used to acquire a remote sensing image of the current sea area collected by a visible light payload;

[0114] The second acquisition unit 22 is used to acquire thermal infrared data representing the temperature conditions of each area in the remote sensing image collected by the infrared spectrum payload;

[0115] The temperature inversion unit 23 is used to determine the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm;

[0116] The region calibration unit 24 is used to perform region calibration on the remote sensing image based on the surface temperature and the preset temperature segmentation condition to obtain an image to be identified with multiple suspected target regions marked;

[0117] The recognition unit 25 is used to process the image to be recognized according to a preset image recognition algorithm to recognize various marine targets and their locations.

[0118] For an introduction to the marine target identification system provided in this application, please refer to the above-mentioned embodiment of the marine target identification method, which will not be repeated here.

[0119] In some embodiments, the marine target identification system further includes:

[0120] The first preprocessing unit is used to convert the pixel brightness values ​​of the remote sensing image into radiometric brightness values ​​by using a preset radiometric calibration strategy after the first acquisition unit 21, so as to obtain a first processed remote sensing image represented by the radiometric brightness values.

[0121] In some embodiments, the marine target identification system further includes:

[0122] The second preprocessing unit is used to process the first processed remote sensing image according to a preset atmospheric correction strategy after the first preprocessing unit to obtain a second processed remote sensing image with atmospheric influence removed.

[0123] In some embodiments, the area calibration unit 24 includes:

[0124] The absolute threshold calibration unit is used to determine that the area where the surface temperature is not less than a preset temperature threshold is a suspected target area, so as to obtain an image to be identified with multiple suspected target areas marked.

[0125] In some embodiments, the area calibration unit 24 includes:

[0126] a parameter determination unit, configured to determine a relative temperature parameter based on the ground surface temperature and the background temperature;

[0127] The relative threshold calibration unit is used to determine that the area where the relative temperature parameter is not less than the preset parameter threshold is a suspected target area, so as to obtain an image to be identified with multiple suspected target areas marked.

[0128] In some embodiments, the temperature inversion unit 23 includes:

[0129] A first temperature inversion subunit, configured to determine the surface temperature based on the first brightness temperature and a first preset relationship;

[0130] The first preset relationship is:

[0131]

[0132] Among them, T s represents the surface temperature, a is the first constant coefficient, b is the second constant coefficient, T 10 is the first brightness temperature, T a is the preset atmospheric average working temperature, C is the first intermediate variable determined by the second preset relationship, and D is the second intermediate variable determined by the third preset relationship;

[0133] The second preset relationship is:

[0134] C=ετ

[0135] The third preset relationship is:

[0136] D = (1-τ)[1+(1-ε)τ]

[0137] Among them, ε is the predetermined surface emissivity, and τ is the predetermined atmospheric transmittance.

[0138] In some embodiments, the temperature inversion unit 23 includes:

[0139] a second temperature inversion subunit, configured to determine the surface temperature according to the first brightness temperature, the second brightness temperature and a fourth preset relationship;

[0140] The fourth preset relationship is:

[0141] T s =A 0 +A 1 T 10 -A 2 T 11 +A 3 (T10 -T 11 )+A 4 (T 10 -T 11 ) 2 +A 5 (T 10 -T 11 ) 3

[0142] Among them, T s represents the surface temperature, A 0 is the first coefficient determined in advance, A 1 is the predetermined second coefficient, A 2 is the predetermined third coefficient, A 3 is the predetermined fourth coefficient, A 4 is the predetermined fifth coefficient, A 5 is the predetermined sixth coefficient, T 10 is the first brightness temperature, T 11 is the second brightness temperature.

[0143] Please refer to Figure 7 , Figure 7 A schematic structural diagram of a marine target identification device provided by the present invention.

[0144] The identification device of the marine target comprises:

[0145] A memory 31, used for storing computer programs;

[0146] The processor 32 is used to implement the steps of the method for identifying marine targets as described above when executing a computer program.

[0147] For the introduction of the marine target identification device provided in the present application, please refer to the above-mentioned embodiment of the marine target identification method, which will not be repeated here.

[0148] The present invention also provides a remote sensing satellite, including a visible light payload and an infrared spectrum payload, and also includes a control module;

[0149] The control module is connected to the visible light payload and the infrared spectrum payload respectively, and is used to execute the steps of the marine target identification method as described above.

[0150] For the introduction of the remote sensing satellite provided in this application, please refer to the above-mentioned embodiment of the method for identifying marine targets, which will not be repeated here.

[0151] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0152] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0153] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying a marine target, characterized in that: Applied to a remote sensing satellite, the remote sensing satellite is equipped with a visible light payload and an infrared spectrum payload, and the method for identifying a marine target includes: Acquire the remote sensing image of the current sea area collected by the visible light payload; Acquire thermal infrared data collected by the infrared spectrum payload that characterizes the temperature conditions of each area in the remote sensing image; Determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm; Based on the surface temperature and the preset temperature segmentation condition, the remote sensing image is regionally calibrated to obtain an image to be identified with multiple suspected target areas marked; The image to be identified is processed according to a preset image recognition algorithm to identify various marine targets and their locations.

2. The method for identifying a marine target according to claim 1, characterized in that: After obtaining the remote sensing image of the current sea area collected by the visible light payload, the method further includes: The pixel brightness values ​​of the remote sensing image are converted into radiation brightness values ​​by using a preset radiation calibration strategy to obtain a first processed remote sensing image represented by the radiation brightness values.

3. The method for identifying a marine target according to claim 2, characterized in that: After obtaining the first processed remote sensing image represented by the radiance value, the method further includes: The first processed remote sensing image is processed according to a preset atmospheric correction strategy to obtain a second processed remote sensing image with atmospheric influence removed.

4. The method for identifying a marine target according to claim 1, characterized in that: The remote sensing image is regionally calibrated based on the surface temperature and a preset temperature segmentation condition, including: The area where the surface temperature is not less than a preset temperature threshold is determined as a suspected target area, so as to obtain an image to be identified with multiple suspected target areas marked thereon.

5. The method for identifying a marine target according to claim 1, characterized in that: The remote sensing image is regionally calibrated based on the surface temperature and a preset temperature segmentation condition, including: Determining a relative temperature parameter based on the surface temperature and the background temperature; The region whose relative temperature parameter is not less than a preset parameter threshold is determined as a suspected target region, so as to obtain an image to be identified with a plurality of suspected target regions marked thereon.

6. The method for identifying a marine target according to any one of claims 1 to 5, characterized in that: The thermal infrared data is a first brightness temperature in a first target thermal infrared band; Determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm includes: Determining the ground surface temperature based on the first brightness temperature and a first preset relationship; The first preset relationship is: Among them, T s represents the surface temperature, a is the first constant coefficient, b is the second constant coefficient, T 10 is the first brightness temperature, T a is the preset atmospheric average working temperature, C is the first intermediate variable determined by the second preset relationship, and D is the second intermediate variable determined by the third preset relationship; The second preset relationship is: C=ετ The third preset relationship is: D = (1-τ)[1+(1-ε)τ] Among them, ε is the predetermined surface emissivity, and τ is the predetermined atmospheric transmittance.

7. The method for identifying a marine target according to any one of claims 1 to 5, characterized in that: The thermal infrared data includes a first brightness temperature in a first target thermal infrared band and a second brightness temperature in a second target thermal infrared band; Determining the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm includes: Determine the ground surface temperature according to the first brightness temperature, the second brightness temperature and a fourth preset relationship; The fourth preset relationship is: T s =A0+A1T 10 -A2T 11 +A3(T 10 -T 11 )+A4(T 10 -T 11 ) 2 +A5(T 10 -T 11 ) 3 Among them, T s represents the surface temperature, A0 is a predetermined first coefficient, A1 is a predetermined second coefficient, A2 is a predetermined third coefficient, A3 is a predetermined fourth coefficient, A4 is a predetermined fifth coefficient, A5 is a predetermined sixth coefficient, T 10 is the first brightness temperature, T 11 is the second brightness temperature.

8. A marine target identification system, characterized in that: Applied to a remote sensing satellite, the remote sensing satellite is equipped with a visible light payload and an infrared spectrum payload, and the marine target recognition system includes: A first acquisition unit, used to acquire the remote sensing image of the current sea area collected by the visible light payload; A second acquisition unit is used to acquire thermal infrared data representing the temperature conditions of each area in the remote sensing image collected by the infrared spectrum payload; A temperature inversion unit, used to determine the surface temperature according to the thermal infrared data and a preset temperature inversion algorithm; A region calibration unit, used for performing region calibration on the remote sensing image based on the surface temperature and a preset temperature segmentation condition, so as to obtain an image to be identified with a plurality of suspected target regions marked thereon; The recognition unit is used to process the image to be recognized according to a preset image recognition algorithm to recognize various marine targets and their locations.

9. A device for identifying a marine target, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for identifying a marine target as claimed in any one of claims 1 to 7 when executing the computer program.

10. A remote sensing satellite, characterized in that: It includes visible light payload and infrared spectrum payload, and also includes a control module; The control module is connected to the visible light payload and the infrared spectrum payload respectively, and is used to execute the steps of the method for identifying marine targets as described in any one of claims 1 to 7.

Images