ISAR image data learning device, target classification device and radar device

Abstract

To provide an ISAR (Inverse Synthetic Aperture Radar) image data learning device that can generate results of learning to limit the range of results of learning used for classification, and a target classification device and a radar device using the ISAR image data learning device.SOLUTION: The present invention includes: an ISAR image input unit 3 in which ISAR image data is input for each target; a wave height information input unit 4 in which information of the wave height is input for each ISAR image data; and a learning unit 5 for learning the ISAR image data corresponding to the information of the wave height input to the wave height information input unit 4 and the type of the target in relation to each other.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an ISAR image data learning device that learns ISAR image data, and a target classification device and a radar device that use the same. [Background technology]

[0002] Conventionally, inverse synthetic aperture radar (ISAR) has been used for target identification processing using ISAR images created from radar echoes. For example, there is a method of simulating and matching a target captured by ISAR with a target shape model stored in a database in advance, and a method of extracting multiple feature points from both the ISAR image and the target shape model.

[0003] Conventionally, some target classification devices extract the overall length of a target and the size of a structure from an ISAR image and classify the target based on the extracted information in order to always accurately identify the target from the ISAR image (see, for example, Patent Document 1). Also, some target classification devices generate a pseudo ISAR image from a three-dimensional model of a recognized target using the attitude change due to the rotational motion of the recognized target as a parameter (see, for example, Patent Document 2).

[0004] Furthermore, in classifying ISAR images, there are those that compensate for the influence of discrete distribution of observation specification parameters, generate filters with high compatibility, and perform highly accurate type determination (see, for example, Patent Document 3). Furthermore, when identifying targets from ISAR images, there are those that generate pseudo ISAR images based on target models selected from a target model database, environmental conditions such as sea states obtained during actual observation, and observation conditions such as radar specifications (see, for example, Patent Document 4). On the other hand, there are those that create learning models by machine learning using AI (Artificial Intelligence) for use in classifying ISAR images (see, for example, Patent Document 5). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2001-221857 A [Patent Document 2] JP 2004-93166 A [Patent Document 3] JP 2012-127920 A [Patent Document 4] JP 2006-214755 A [Patent Document 5] WO2020-3586 Summary of the Invention [Problem to be solved by the invention]

[0006] However, conventional machine learning such as that disclosed in Patent Document 5 has a problem in that a learning model that limits the range of learning results used for classification is not considered.

[0007] The present disclosure has been made to solve the above-mentioned problems, and aims to provide an ISAR image data learning device that generates learning results so as to limit the range of learning results used for classification, and a target classification device and radar device using the same. [Means for solving the problem]

[0008] The ISAR image data learning device according to the present disclosure is an ISAR image data learning device that generates learning results for classifying targets from ISAR image data obtained by an inverse synthetic aperture radar installed at an observation point. 、I an ISAR image input unit to which SAR image data is input; ,eye a wave height information input section for inputting information on the wave height of the sea area where the target is located; ,wave The ISAR image data corresponding to the wave height information input to the wave height information input section Eyes A learning unit that learns to classify the mark. The ISAR image input unit receives ISAR image data associated with information indicating the distance from the observation point to the target, or the wave height information input unit receives wave height information associated with information indicating the distance from the observation point to the target, and the learning unit learns using ISAR image data obtained by converting the ISAR image data to a predetermined scale based on the information indicating the distance. It is something.

[0009] The target classification device according to the present disclosure comprises: Obtained by an inverse synthetic aperture radar installed at the observation point an ISAR image input unit to which ISAR image data is input; and a wave height information input unit to which information on the wave height of the sea area in which the target exists is input. ,wave The information entered into the high-speed information input section Wave Responding to high information I SAR image data? Eyes A learning unit that learns to classify marks. The ISAR image input unit receives ISAR image data associated with information indicating the distance from the observation point to the target, or the wave height information input unit receives wave height information associated with information indicating the distance from the observation point to the target, and the learning unit learns using ISAR image data obtained by converting the ISAR image data to a predetermined scale based on the information indicating the distance. an ISAR image data learning device; and a new ISAR image input unit to which newly obtained new ISAR image data is input; ,eye The mark exists The sea a new wave height information input section for inputting new wave height information obtained in the area; , studies The study department Using new ISAR image data and new wave height information Based on the learning outcomes learned ,new Supports standard ISAR image data Eyes and a target classification unit for classifying the target.

[0010] The radar device according to the present disclosure comprises: Obtained by an inverse synthetic aperture radar installed at the observation point an ISAR image input unit to which ISAR image data is input; and a wave height information input unit to which information on the wave height of the sea area in which the target exists is input. ,wave The information entered into the high-speed information input section Wave Responding to high information I SAR image data? Eyes A learning unit that learns to classify marks. The ISAR image input unit receives ISAR image data associated with information indicating the distance from the observation point to the target, or the wave height information input unit receives wave height information associated with information indicating the distance from the observation point to the target, and the learning unit learns using ISAR image data obtained by converting the ISAR image data to a predetermined scale based on the information indicating the distance. an ISAR image data learning device; and a new ISAR image input unit to which newly obtained new ISAR image data is input; ,eye The mark exists The sea a new wave height information input section for inputting new wave height information obtained in the area; , studies The study department Using new ISAR image data and new wave height information Based on the learning outcomes learned ,new Supports standard ISAR image data Eyes a target classification device having a target classification unit for classifying targets; ,new To obtain new ISAR image data ,eye It is equipped with an inverse synthetic aperture radar that transmits a transmit beam to a target. Effect of the Invention

[0011] According to the present disclosure, it is possible to obtain an ISAR image data learning device that can obtain learning results that enable classification even for ISAR image data obtained at a specific wave height, and a target classification device and radar device using the same. [Brief description of the drawings]

[0012] [Figure 1] FIG. 2 is a functional block diagram of an ISAR image data learning device according to the first embodiment. [Diagram 2] 4 is a flowchart for explaining the operation of the ISAR image data training device (ISAR image data training method) according to the first embodiment. [Diagram 3] FIG. 1 is an illustrative diagram showing a radar device according to embodiment 1 for acquiring ISAR image data (new ISAR image data to be input to a target classification device according to embodiment 1) to be input to the ISAR image data learning device according to embodiment 1, its scanning range, and targets. [Figure 4] 1 is a functional block diagram of an ISAR image data learning device, a target classification device, and a radar device according to a first embodiment. FIG. [Diagram 5] 1 is a functional block diagram of an ISAR image data learning device, a target classification device, and a radar device according to a first embodiment. FIG. [Figure 6] 1 is a functional block diagram of an ISAR image data learning device, a target classification device, and a radar device according to a first embodiment. FIG. [Figure 7] 4 is a flowchart for explaining the operation (target classification method) of the ISAR image data learning device and the target classification device according to the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Embodiment 1 Hereinafter, an ISAR image data learning device according to embodiment 1, and a target classification device and radar device using the same (target classification device according to embodiment 1, radar device according to embodiment 1) will be described with reference to Fig. 1 to Fig. 7. In the drawings, the same reference numerals indicate the same or corresponding parts, and detailed description thereof will be omitted. As mentioned above, ISAR is an abbreviation for Inverse Synthetic Aperture Radar, which means an inverse synthetic aperture radar.

[0014] In Fig. 3, the target 1 to be observed is, for example, a moving object such as a ship moving on the water. The body of the target 1 has, for example, a linear structure. In the present application, learning is performed on the premise that there are multiple types of targets 1. Therefore, as the amount of learning progresses, even when new ISAR image data described later is of an unknown target 1, it is possible to determine whether there is a similar type or whether there is no similar object.

[0015] In Fig. 1, an ISAR image data learning device 2 generates learning results so that when classifying corresponding targets 1 from ISAR image data obtained by an inverse synthetic aperture radar 12 (ISAR12) installed at an observation point and determining the type corresponding to the target 1, the learning results can be limited in range of learning results used for classification from information on wave height in the sea area where the target 1 exists (ISAR image data learning device according to embodiment 1). Here, the wave height information is a class value set according to the wave height. The class value set according to the wave height is, for example, a value of the wind wave class (SEA STATE) which classifies wave height into 10 classes from 0 to 9.

[0016] In FIG. 1, the ISAR image input unit 3 receives ISAR image data for each target 1. The wave height information input unit 4 receives wave height information for each ISAR image data input to the ISAR image input unit 3. The ISAR image data may be actually acquired by the ISAR 12, or may be simulated data acquired by simulation. Similarly, the wave height information may be acquired by wave height in the sea area where the ISAR image data is actually acquired, or may be simulated data acquired by simulation. The learning unit 5 learns by associating the ISAR image data corresponding to the wave height information input to the wave height information input unit 4 with the type of target 1. The information on the type of target 1 may be added to the ISAR image data. The learning unit 5 may also generate the learning result for each wave height information.

[0017] The type of target 1 may include at least one of the model name, aircraft dimensions, aircraft performance, and the country and organization to which the aircraft belongs. In addition, even if the type of target 1 is the same, if the information on the wave height from which the ISAR image data was acquired is different, the shape of target 1 represented in the ISAR image data will be different. In other words, even if the type of target 1 is the same, the ISAR image data input to the ISAR image input unit 3 may have different information on the wave height input to the wave height information input unit 4. For example, if the wave height of the sea area in which target 1 exists becomes high, the shaking of target 1 becomes large, and the amount of movement of target 1 per unit time becomes large. Therefore, the speed of target 1 becomes high, and the Doppler frequency included in the radar echo of target 1 becomes high. ISAR image data is generated based on the Doppler frequency included in the radar echo of target 1. Therefore, the shape of target 1 represented in the generated ISAR image data will be different depending on whether the wave height of the sea area in which target 1 exists is high or low. In other words, even if the type of target 1 is the same, if the wave height of the sea area in which target 1 exists is different, the shape of target 1 represented in the generated ISAR image data will be different. In particular, in target 1, parts such as the mast that are far from the water surface experience greater vibrations due to waves than parts near the water surface, and therefore the change in Doppler frequency is more noticeable.

[0018] FIG. 1(A) shows an ISAR image data learning device 2 in which the learning unit 5 does not learn information on the distance from the observation point to the target 1. On the other hand, FIG. 1(B) shows an ISAR image data learning device 2 in which the learning unit 5 learns information on the distance from the observation point to the target 1. The distance information to be learned by the learning unit 5 may be input via the ISAR image input unit 3 or via the wave height information input unit 4, as shown in FIG. 1(B). In other words, the ISAR image input unit 3 may receive ISAR image data associated with information on the distance from the observation point to the target 1. The wave height information input unit 4 may receive wave height information associated with information on the distance from the observation point to the target 1. If there is information on the distance from the observation point to the target 1, the learning unit 5 can learn ISAR image data at a predetermined scale from the distance information.

[0019] The wave height information input unit 4 may be input with wave height information calculated from the signal strength of sea clutter in the sea area where the target 1 exists, obtained from an inverse synthetic aperture radar 12 (ISAR 12). Also, the wave height information input unit 4 may be input with wave height information obtained from a device that measures wave height in the sea area. Also, the wave height information input unit 4 may be input with wave height information obtained from meteorological information in the sea area where the target 1 exists.

[0020] In Fig. 3, a radar device 10 (ISAR 12) is grounded at an observation point. The observation point itself may be movable. In other words, the radar device 10 may be mounted on a moving body such as a ship or an aircraft. A scanning range 13 is an imaginary range that can be scanned by the radar device 10 (ISAR 12) centered on the observation point, shown by a dotted line. The radar device 10 shown is capable of scanning 360 degrees in the azimuth direction.

[0021] Next, the operation of the ISAR image data learning device according to the first embodiment (ISAR image data learning method according to the first embodiment) will be described with reference to Fig. 2. In Fig. 2, step 1 is a processing step in which ISAR image data is input to the ISAR image input unit 3 for each target 1. Step 2 is a processing step in which wave height information for each ISAR image data input to the ISAR image input unit 3 is input to the wave height information input unit 4. The order of processing of steps 1 and 2 does not matter. They may be performed simultaneously. Step 3 is a processing step in which, based on the ISAR image data and the wave height information, the learning unit 5 learns by associating the ISAR image data corresponding to the wave height information input to the wave height information input unit 4, which is the basis for classification (determination), with the type of target 1. Information on the type of target 1 may be added to the ISAR image data when performing step 1.

[0022] 4 to 6, the target classification device 6 uses the learning results (learning model) of the ISAR image data learning device 2 shown in Fig. 1 and Fig. 4 to 6 (the target classification device according to the first embodiment). The new ISAR image input unit 7 receives newly obtained ISAR image data. The new wave height information input unit 8 receives wave height information for each of the newly obtained ISAR image data input to the new ISAR image input unit 7.

[0023] The new ISAR image data (newly obtained ISAR image data) referred to here may be acquired by a radar device 10 (radar device according to the first embodiment) described later. The new wave height information (newly obtained wave height information) referred to here may be acquired by a device that measures wave height, or by an inverse synthetic aperture radar 12 (ISAR12), or from meteorological information. FIG. 4 is a functional block diagram of the ISAR image data learning device, the target classification device, and the radar device when the new wave height information (newly obtained wave height information) is acquired by a device that measures wave height. FIG. 5 is a functional block diagram of the ISAR image data learning device, the target classification device, and the radar device when the new wave height information (newly obtained wave height information) is acquired by an inverse synthetic aperture radar 12 (ISAR12). FIG. 6 is a functional block diagram of the ISAR image data learning device, the target classification device, and the radar device when the new wave height information (newly obtained wave height information) is acquired from meteorological information.

[0024] In detail, as shown in FIG. 4, the new wave height information input unit 8 may receive wave height information obtained from a device (wave height measuring device 11) that measures the wave height in the sea area where the target 1 exists. The wave height measuring device 11 may be, for example, a radar different from the ISAR 12, a water pressure type wave height gauge, a buoy type wave height gauge, etc. Note that the wave height may be measured visually instead of using the wave height measuring device 11. The wave height measuring device 11 may be configured to be provided in the radar device 10, or may be configured outside the radar device 10 as shown in FIG. 4. For example, the radar device 10 (ISAR 12) may be mounted on a moving body such as a ship or an aircraft, and the wave height measuring device 11 may be fixed on land. In this way, the radar device 10 and the wave height measuring device 11 may be provided in different locations.

[0025] 5, the new wave height information input unit 8 may receive wave height information calculated from the signal strength of sea clutter in the sea area where the target 1 exists, obtained from an inverse synthetic aperture radar 12 (ISAR 12). Also, as shown in Fig. 6, the new wave height information input unit may receive wave height information obtained from meteorological information in the sea area where the target 1 exists, as the wave height information.

[0026] In Figs. 4 to 6, the target classification unit 9 classifies the target 1 corresponding to the newly obtained ISAR image data based on the learning result learned by the learning unit 5, and determines the type corresponding to the target 1. In addition, when the learning unit 5 also learns information on the distance from the observation point to the target 1, the target classification unit 9 may convert the newly obtained ISAR image data to a predetermined scale based on the learning result learned by the learning unit 5, and then classify the corresponding target 1 and determine the type corresponding to the target 1. The new ISAR image data and new wave height information classified by the target classification unit 9 may be simulated data obtained by simulation. By having the target classification unit 9 classify using this simulated data, the performance of the learning unit 5 and the target classification unit 9 can be confirmed.

[0027] In order to speed up processing, the target classification unit 9 may limit the range of learning results used for classification based on the wave height information for each newly obtained ISAR image data. Note that, when the learning unit 5 generates learning results for each wave height information, the target classification unit 9 can classify the target 1 based on the learning results that the learning unit 5 has learned and generated for each wave height information, and determine the type corresponding to the target 1.

[0028] As the learning unit 5 progresses, when the wave height information for each newly obtained ISAR image data does not match the wave height information input to the wave height information input unit 4, or the error from the wave height information input to the wave height information input unit 4 is not within a predetermined range, the target classification unit 9 becomes able to classify target 1 based on the learning results of the wave height information with the closest height and determine the type corresponding to target 1.

[0029] 4 to 6, a radar device 10 having a target classification device 6 (ISAR image data learning device 2 and target classification device 6) has the following configuration. An inverse synthetic aperture radar 12 (ISAR 12) is the same radar as the one described above, and transmits a transmission beam to a target 1 to send newly obtained ISAR image data to a new ISAR image input unit 7.

[0030] The illustrative diagram showing the radar device 10, the scanning range 13, and the target 1 when new ISAR image data is acquired by the radar device 10 is the same as that shown in FIG.

[0031] Finally, the operation of the target classification device according to the first embodiment (the target classification method according to the first embodiment) will be mainly described with reference to Fig. 5. In Fig. 5, step 11 is a processing step in which newly acquired ISAR image data is input to a new ISAR image input unit 7. Step 12 is a processing step in which newly acquired wave height information for each ISAR image data is input to a new wave height information input unit 8. The order of processing of steps 11 and 12 does not matter. They may be performed simultaneously. The new ISAR image data (newly acquired ISAR image data) referred to here may be acquired by a radar device 10 (a radar device according to the first embodiment). Also, the new wave height information (newly acquired wave height information) may be acquired from a device that measures wave height, or from an inverse synthetic aperture radar 12 (ISAR12), or from meteorological information.

[0032] Step 13 is a processing step in which new ISAR image data (newly obtained ISAR image data) and new wave height information (newly obtained wave height information) are input from new ISAR image input unit 7 and new wave height information input unit 8 to learning unit 5, and the learning model is used. Step 14 is a processing step in which target 1 corresponding to the newly obtained ISAR image data is classified based on the learning result (learning model) learned by learning unit 5, and the type corresponding to target 1 is determined. Other target classification methods according to embodiment 1 are mainly the same as the operations of the target classification device according to embodiment 1 described above, so descriptions will be omitted.

[0033] In the ISAR image data learning device according to embodiment 1, and the target classification device and radar device using the same, the ISAR image data and wave height information learned by the learning unit 5 may be simulated data obtained by simulation. Similarly, new ISAR image data and wave height information classified by the target classifier 9 may also be simulated data obtained by simulation. By having the target classifier 9 classify using this simulated data, the performance of the learning unit 5 and the target classifier 9 can be confirmed.

[0034] As described above, the ISAR image data learning device of embodiment 1, and the target classification device and radar device using the same learn to associate ISAR image data corresponding to wave height information with the type of target 1, or utilize the learning results, and therefore can classify target 1 taking into account the wave height of the sea area in which target 1 exists. [Explanation of symbols]

[0035] 1 Target 1, 2 ISAR image data learning device, 3 ISAR image input unit, 4 wave height information input unit, 5 learning unit, 6 target classification device, 7 new ISAR image input unit, 8 new wave height information input unit, 9 target classification unit, 10 radar device, 11 wave height measuring device, 12 inverse synthetic aperture radar (ISAR), 13 scanning range.

Claims

1. An ISAR image data learning device that generates learning results for classifying targets from ISAR image data obtained by an inverse synthetic aperture radar installed at an observation point, comprising: an ISAR image input unit to which the ISAR image data is input; a wave height information input unit to which information on wave height in the sea area where the target is present is input; a learning unit configured to learn to classify the target from the ISAR image data corresponding to the wave height information input to the wave height information input unit; The ISAR image input unit receives the ISAR image data associated with information indicating a distance from the observation point to the target, or the wave height information input unit receives the wave height information associated with information indicating a distance from the observation point to the target, The learning unit is an ISAR image data learning device that learns using the ISAR image data obtained by converting the ISAR image data to a predetermined scale based on information indicating the distance.

2. 2. The ISAR image data learning device according to claim 1, wherein the learning unit learns by associating the ISAR image data corresponding to the wave height information input to the wave height information input unit with the type of the target.

3. The ISAR image data learning device according to claim 2 , wherein the type of the target is information including at least one of the name of the target, the dimensions of the target, the performance of the target, the country to which the target belongs, and the organization to which the target belongs.

4. 4. The ISAR image data learning device according to claim 1, wherein the wave height information input unit inputs a class value set according to the wave height as the wave height information.

5. 5. The ISAR image data learning device according to claim 1, wherein the wave height information input unit receives input of the wave height information obtained from a device for measuring wave heights in the sea area.

6. The ISAR image data learning device according to any one of claims 1 to 4, wherein the wave height information input unit inputs information on the wave height calculated from the signal strength of sea clutter in the sea area obtained from the inverse synthetic aperture radar.

7. The ISAR image data learning device according to claim 1 , wherein the wave height information input unit inputs, as the wave height information, wave height information obtained from meteorological information in the sea area.

8. An ISAR image data learning device comprising: an ISAR image input unit to which ISAR image data obtained by an inverse synthetic aperture radar installed at an observation point is input; a wave height information input unit to which information on wave height in an ocean area in which a target is present is input; and a learning unit which learns to classify the target from the ISAR image data corresponding to the wave height information input to the wave height information input unit, wherein the ISAR image input unit receives the ISAR image data associated with information indicating the distance from the observation point to the target, or the wave height information input unit receives the wave height information associated with information indicating the distance from the observation point to the target, and the learning unit learns using the ISAR image data obtained by converting the ISAR image data to a predetermined scale from the information indicating the distance; a new ISAR image input unit to which newly obtained new ISAR image data is input; a new wave height information input unit to which newly obtained new wave height information of the sea area where the target exists is input; A target classification device comprising: a target classification unit that classifies the target corresponding to the new ISAR image data based on a learning result learned by the learning unit using the new ISAR image data and the new wave height information.

9. The target classification device according to claim 8 , wherein the target classification unit limits the range of the learning results used for classification based on the new wave height information for each of the new ISAR image data.

10. The learning unit generates a learning result for each piece of wave height information, The target classification device according to claim 8 or claim 9, wherein the target classification unit classifies the targets and determines the type corresponding to the targets based on the learning results generated by the learning unit through learning for each wave height information.

11. A target classification device as described in any one of claims 8 to 10, wherein when the new wave height information for each of the new ISAR image data does not match the wave height information inputted to the wave height information input unit, or when the error from the wave height information inputted to the wave height information input unit is not within a predetermined range, the target classification unit classifies the target based on the learning result of the wave height information that is closest in height, and determines the type corresponding to the target.

12. An ISAR image data learning device comprising: an ISAR image input unit to which ISAR image data obtained by an inverse synthetic aperture radar installed at an observation point is input; a wave height information input unit to which information on wave height in an ocean area in which a target is present is input; and a learning unit which learns to classify the target from the ISAR image data corresponding to the wave height information input to the wave height information input unit, wherein the ISAR image input unit receives the ISAR image data associated with information indicating the distance from the observation point to the target, or the wave height information input unit receives the wave height information associated with information indicating the distance from the observation point to the target, and the learning unit learns using the ISAR image data obtained by converting the ISAR image data to a predetermined scale from the information indicating the distance; a target classification device having a new ISAR image input unit to which newly obtained new ISAR image data is input, a new wave height information input unit to which newly obtained new wave height information of the sea area in which the target exists is input, and a target classification unit that classifies the target corresponding to the new ISAR image data based on a learning result obtained by the learning unit using the new ISAR image data and the new wave height information; A radar device comprising an inverse synthetic aperture radar that transmits a transmission beam to the target to acquire the new ISAR image data.

Images