Radar-guided ship target video listing method and device based on visual algorithm

Abstract

The invention discloses a radar-guided ship target video listing method and device based on a visual algorithm, and belongs to the field of ship monitoring and management. The method comprises the following steps: calculating a rotation angle of a photoelectric turntable which enables a ship target to meet observation conditions according to the longitude and latitude of the ship target detected by a radar; performing target detection on a video picture acquired by the photoelectric turntable after rotating according to the rotation angle, and screening out a target frame of the to-be-tracked ship target meeting the tracking requirement according to a detection result; and initializing and tracking the ship target to be tracked according to a target frame, adjusting the photoelectric turntable according to a tracking result, and superposing the ship feature information to the periphery of the target frame so as to complete video listing of the ship target to be tracked. According to the invention, the photoelectric turntable guided by the radar can be rectified, so that the tracked ship target can be stably located in the center of a picture.

Description

Technical Field

[0001] The present invention relates to the technical field of ship monitoring and management, and in particular to a radar-guided ship target video listing method and device based on a visual algorithm. Background Art

[0002] To tag a video target means to identify specific targets in the video through video analysis technology, and associate these targets with corresponding information, so as to display this information in some form in the video. At present, radar-guided optoelectronic turntable search, tracking and video tagging of ship targets is an effective solution for radar and optoelectronic fusion perception.

[0003] When traditional radar-guided optoelectronic turntables are tracking ship target videos, they usually only rely on the target direction measured by the radar to guide and control the turntable to the target location. However, due to the delay in radar measurement and the accuracy deviation of the optoelectronic turntable, this method cannot accurately mark the position and other characteristics of the tracked ship in the optoelectronic video image in real time, resulting in low recognition of the tracked ship target.

[0004] Based on this, there is an urgent need for a radar-guided ship target video listing method and device based on visual algorithms to solve the above technical problems. Summary of the invention

[0005] The present invention provides a radar-guided ship target video display method and device based on a visual algorithm, which can solve the problem of insufficient target recognition in related technologies. The technical solution is as follows:

[0006] On the one hand, a radar-guided ship target video listing method based on a visual algorithm is provided, the method comprising:

[0007] According to the longitude and latitude of the ship target detected by the radar, the rotation angle of the photoelectric turntable that enables the ship target to meet the observation conditions is calculated;

[0008] Performing target detection on the video images collected by the photoelectric turntable after being rotated according to the rotation angle, and selecting a target frame of the ship target to be tracked that meets the tracking requirements according to the detection result;

[0009] The ship target to be tracked is tracked according to the target frame initialization, the photoelectric turntable orientation is adjusted according to the tracking result, and the ship feature information is superimposed around the target frame to complete the video listing of the ship target to be tracked.

[0010] On the other hand, a radar-guided ship target video placard device based on a visual algorithm is provided, the device comprising:

[0011] A calculation module, used to calculate the rotation angle of the photoelectric turntable so that the ship target meets the observation conditions according to the longitude and latitude of the ship target detected by the radar;

[0012] A detection module, used for performing target detection on the video images collected by the photoelectric turntable after being rotated according to the rotation angle, and screening out a target frame of the ship target to be tracked that meets the tracking requirements according to the detection result;

[0013] The processing module is used to initialize the tracking of the ship target to be tracked according to the target frame, adjust the orientation of the photoelectric turntable according to the tracking result, and superimpose the ship feature information around the target frame to complete the video listing of the ship target to be tracked.

[0014] On the other hand, a computer device is provided, which includes a memory and a processor, wherein the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to implement the steps of the above-mentioned radar-guided ship target video listing method based on visual algorithms.

[0015] On the other hand, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned radar-guided ship target video listing method based on visual algorithm are implemented.

[0016] On the other hand, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned radar-guided ship target video listing method based on visual algorithm.

[0017] The technical solution provided by the present invention can at least bring the following beneficial effects: first, with the help of the target information detected by the radar, the optoelectronic turntable is initially guided to turn to the approximate direction of the ship target to be listed, and the rough adjustment of the field of view angle is completed; after the radar guidance is stable, the real-time target detection algorithm is called to identify the ship target in the optoelectronic video screen, and the ship target frame with high stability and the smallest pixel deviation change from the center axis of the screen is screened out; finally, the ship target frame information screened out by the target detection algorithm is used to initialize the single target tracking algorithm for stable tracking, and then the rotation of the optoelectronic turntable is controlled by the off-target amount of the target frame in the screen. This method solves the problem that when the radar guides the optoelectronic turntable to track the ship target, the position and information of the tracked ship cannot be accurately marked in real time in the optoelectronic video image, and the tracked ship target cannot be guaranteed to be located in the center of the screen for a long time. It improves the effect of radar and optoelectronic fusion perception in the field of coastal defense and strengthens the intelligent duty capability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of a radar-guided ship target video listing method based on a visual algorithm provided by an embodiment of the present invention;

[0020] Figure 2 It is a structural diagram of a radar-guided ship target video sign-hanging device based on a visual algorithm provided by an embodiment of the present invention;

[0021] Figure 3 It is a hardware architecture diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] As mentioned above, due to various restrictions, the traditional radar guidance method cannot accurately mark the position and other characteristics of the tracked ship in the optoelectronic video image in real time, nor can it ensure that the tracked ship target is located in the center of the picture for a long time, which brings great trouble to the identification of the target.

[0024] Based on this, the idea of ​​the present invention is to use a target detection algorithm and a target tracking algorithm to jointly calibrate the radar guidance to achieve video placarding of ship targets, thereby solving the shortcomings of previous radar-guided optoelectronic turntables in tracking ship targets.

[0025] The specific implementation of the above concept is described below.

[0026] Please refer to Figure 1 , an embodiment of the present invention provides a radar-guided ship target video listing method based on a visual algorithm, the method comprising:

[0027] Step 100, calculating the rotation angle of the photoelectric turntable so that the ship target meets the observation conditions according to the longitude and latitude of the ship target detected by the radar;

[0028] Step 102, performing target detection on the video picture collected by the photoelectric turntable after being rotated according to the rotation angle, and selecting a target frame of the ship target to be tracked that meets the tracking requirements according to the detection result;

[0029] Step 104, initializing tracking of the ship target to be tracked according to the target frame, adjusting the photoelectric turntable according to the tracking result and superimposing the ship characteristic information around the target frame to complete the video placarding of the ship target to be tracked.

[0030] In the embodiment of the present invention, the target information detected by the radar is first used to preliminarily guide the optoelectronic turntable to the approximate direction of the ship target to be listed, and the rough adjustment of the field of view angle is completed; after the radar guidance is stable, the real-time target detection algorithm is called to identify the ship target in the optoelectronic video screen, and the ship target frame with high stability and the smallest pixel deviation change from the center axis of the screen is screened out; finally, the ship target frame information screened out by the target detection algorithm is used to initialize the single target tracking algorithm for stable tracking, and then the rotation of the optoelectronic turntable is controlled by the off-target amount of the target frame in the screen. This method solves the problem that when the radar guides the optoelectronic turntable to track the ship target, the position and information of the tracked ship cannot be accurately marked in real time in the optoelectronic video image, and the tracked ship target cannot be guaranteed to be located in the center of the screen for a long time. It improves the effect of radar and optoelectronic fusion perception in the field of coastal defense and strengthens the intelligent duty capability of the equipment.

[0031] Described below Figure 1 How the various steps are performed.

[0032] First, with respect to step 100, based on the longitude and latitude of the ship target detected by radar, the rotation angle of the optoelectronic turntable that enables the ship target to meet the observation conditions is calculated.

[0033] For ship targets, the radar can detect the target's latitude and longitude [lat1, lon1], length and width, etc. The above information, combined with the equipment's own latitude and longitude [lat0, lon0] and installation height h0, can calculate the horizontal distance d, relative azimuth angle θ, and relative pitch angle β between the target and the observation point.

[0034] Specifically, the horizontal distance d between the ship target and the radar observation point is calculated by the following formula:

[0035]

[0036] Where R is the radius of the earth, which is about 6371 km, and a and c are both process variables;

[0037] The relative azimuth angle θ between the ship target and the radar observation point is calculated by the following formula:

[0038] y=sin(log1-lon0)·cos(lat1)

[0039] x=cos(lat0)·sin(lat1)-sin(lat0)·cos(lat1)·cos(lon1-lon0)

[0040] θ=atan2(y,x)

[0041] Since the observed target is a ship, its altitude is assumed to be 0, so the relative pitch angle β between the ship target and the radar observation point can be calculated by the following formula:

[0042]

[0043] Furthermore, the optoelectronic turntable rotates following the relative azimuth angle θ and the relative pitch angle β to keep the center of the camera image coincident with the center of the radar guidance azimuth.

[0044] Specifically, the field of view of the optoelectronic turntable camera is roughly adjusted based on the length and width of the target detected by the radar and the horizontal distance d between the target and the observation point, so that the length and width of the target occupy approximately 1 / 6 of the length and width of the picture. This allows the picture to not only clearly observe the target, but also have a certain field of view, which is convenient for subsequent target screening and investigation.

[0045] Then, for step 102, target detection is performed on the video images collected by the photoelectric turntable after being rotated according to the rotation angle, and a target frame of the ship target to be tracked that meets the tracking requirements is screened out according to the detection result.

[0046] In an embodiment of the present invention, the process of detecting and screening the video images includes: inputting the video images into a pre-trained target detection model, and outputting target information of all ships in the images;

[0047] Match the target information using an association algorithm to determine the same ship target in consecutive detection frames, and record the number of detections and position changes of each ship within the target time;

[0048] The recorded results are screened to determine that the ship target that can be stably detected and has the smallest pixel deviation change between the center position of the target frame and the central axis of the picture is the ship target to be tracked, and the target frame of the ship target to be tracked is obtained.

[0049] Specifically, the above-mentioned target detection model is obtained by training the YOLOv5 network architecture using a ship dataset containing 12 types of ships. The algorithm can not only detect ship targets in the image in real time, but also determine the category of the detected ship. The video image is input into the above-mentioned algorithm, and the algorithm undergoes image pre-processing, model real-time inference, and result post-processing to finally obtain the target information of all ships in the picture, including the position, size, confidence and category of ship targets.

[0050] Furthermore, the above association algorithm is a Sort multi-target tracking algorithm, which establishes a Kalman tracker for each detected target and uses position correspondence to complete the matching association of the same target, which can ensure the stability of the target existence and reduce the errors caused by false detection and missed detection of the target detection algorithm.

[0051] Furthermore, this embodiment determines that a ship target that has been detected no less than 10 times in 20 consecutive detection frames is a target that can be stably detected, and the pixel deviation change of the center position of the target frame from the central axis of the picture is the change in the pixel position offset of the center of the target frame compared to the central axis of the picture within 5 seconds.

[0052] With respect to step 104, the ship target to be tracked is tracked according to the target frame initialization, the photoelectric turntable is adjusted according to the tracking result, and the ship feature information is superimposed around the target frame.

[0053] In an embodiment of the present invention, the tracking initialization process for a ship target includes: initializing a feature template of a single target tracking algorithm according to the position of the target frame and the latest frame image; for the next frame image, searching for a position that best matches the feature template around the target frame of the previous frame, determining a position prediction value of the ship target to be tracked in the new frame, and updating the feature template according to the position prediction value combined with the new frame image.

[0054] Specifically, the single target tracking algorithm adopted in the present embodiment of the above process is the SiamRPN++ algorithm based on the twin network architecture. The twin network of the algorithm shares weights, and the algorithm has anti-occlusion capability and can achieve stable tracking. During the tracking process, the latest detection frame of the ship target is used to construct a tracking template, and the template frame and the tracking frame are simultaneously sent to the twin network with shared weights to generate deep feature maps of the template frame and the detection frame, and sent to the target classification and position frame regression network. The similarity of each position of the two feature maps is calculated using the cross-correlation operation, and finally the prediction result of the tracking target position is obtained.

[0055] In an embodiment of the present invention, the video placarding process for a ship target includes: calculating the target miss amount based on the difference between the position prediction value and the center of the picture; adjusting the photoelectric turntable to the optimal position based on the target miss amount so that the ship target to be tracked is located in the center of the picture; when the tracking is stable, superimposing the ship feature information obtained by radar detection and target detection around the target frame of the stably tracked ship target to complete the video placarding of the ship target to be tracked.

[0056] It is worth noting that if the deviation between the center position of the tracked target and the center of the radar guidance azimuth exceeds the threshold during the tracking process, the target listing is considered to be wrong. At this time, the turntable control is changed from using the tracking miss amount control to radar azimuth guidance, and the target detection algorithm is called. After excluding the previous tracking target, other ship targets that meet the requirements are selected for listing.

[0057] In summary, the method of the present invention introduces a target detection algorithm and a target tracking algorithm to correct the radar-guided optoelectronic turntable on the basis of the traditional radar-guided optoelectronic tracking of ships, so that the tracked ship target can be stably located in the center of the picture, and then the multi-source information of the equipment and the algorithm is integrated to list the target in the video. The method improves the linkage effect between basic coastal defense equipment such as radar and optoelectronic turntable, and further strengthens the intelligent duty capability of the coastal defense perception terminal.

[0058] Please refer to Figure 2 The embodiment of the present invention provides a radar-guided ship target video sign device based on a visual algorithm, the device comprising:

[0059] The calculation module 200 is used to calculate the rotation angle of the photoelectric turntable so that the ship target meets the observation conditions according to the longitude and latitude of the ship target detected by the radar;

[0060] The detection module 202 is used to perform target detection on the video picture collected by the photoelectric turntable after being rotated according to the rotation angle, and select the target frame of the ship target to be tracked that meets the tracking requirements according to the detection result;

[0061] The processing module 204 is used to initialize the tracking of the ship target to be tracked according to the target frame, adjust the photoelectric turntable according to the tracking result and superimpose the ship feature information around the target frame to complete the video listing of the ship target to be tracked.

[0062] In the embodiment of the present invention, when the calculation module 200 calculates the rotation angle of the photoelectric turntable that enables the ship target to meet the observation conditions according to the longitude and latitude of the ship target detected by radar, it is specifically used to perform the following operations:

[0063] According to the latitude and longitude information [lat0, lon0] of the radar, the installation height h0 and the latitude and longitude information [lat1, lon1] of the ship target, the horizontal distance d between the ship target and the radar observation point is calculated:

[0064]

[0065] Where R is the radius of the earth, a and c are process variables;

[0066] Calculate the relative azimuth angle θ between the ship target and the radar observation point:

[0067] y=sin(lon1-lon0)·cos(lat1)

[0068] x=cos(lat0)·sin(lat1)-sin(lat0)·cos(lat1)·cos(lon1-lon0)

[0069] θ=atan2(y,x)

[0070] Calculate the relative pitch angle β between the ship target and the radar observation point:

[0071]

[0072] In the embodiment of the present invention, when the detection module 202 performs target detection on the video picture collected by the photoelectric turntable after rotating according to the rotation angle, and selects the target frame of the ship target to be tracked that meets the tracking requirements according to the detection result, it is specifically used to perform the following operations: input the video picture into a pre-trained target detection model, and output the target information of all ships in the picture; wherein the target detection model is obtained by training the YOLOv5 network architecture using a ship data set containing 12 types of ships, and the target information includes the position, size, confidence and category of the ship target; the target information is analyzed using an association algorithm The same ship target in the continuous detection frames is determined by row matching, and the number of detections and position changes of each ship within the target time are recorded; the recorded results are screened to determine that the ship target that can be stably detected and the pixel deviation change of the center position of the target frame from the central axis of the picture is the smallest is the ship target to be tracked, and the target frame of the ship target to be tracked is obtained; wherein, the target that can be stably detected is a ship target that is detected no less than 10 times in 20 continuous detection frames, and the pixel deviation change of the center position of the target frame from the central axis of the picture is the change of the pixel position offset of the center of the target frame compared to the central axis of the picture within 5 seconds.

[0073] In the embodiment of the present invention, when the processing module 204 performs the initialization tracking of the ship target to be tracked according to the target frame, it is specifically used to perform the following operations: initialize the feature template of the single target tracking algorithm according to the position of the target frame and the latest frame image; for the next frame image, search for the position that best matches the feature template around the target frame of the previous frame, determine the position prediction value of the ship target to be tracked in the new frame, and update the feature template according to the position prediction value combined with the new frame image.

[0074] In an embodiment of the present invention, when the processing module 204 adjusts the photoelectric turntable according to the tracking results and superimposes the ship characteristic information around the target frame, it is specifically used to perform the following operations: calculate the target miss amount according to the difference between the position prediction value and the center of the picture; adjust the photoelectric turntable to the optimal position according to the target miss amount so that the ship target to be tracked is located in the center of the picture; when the tracking is stable, superimpose the ship characteristic information obtained by radar detection and target detection around the target frame of the stably tracked ship target to complete the video listing of the ship target to be tracked.

[0075] In an embodiment of the present invention, after completing the video posting of the ship target to be tracked, the processing module 204 is also used to execute: when the target miss amount is greater than a preset deviation threshold, determining that the posted ship target is an erroneous target, adjusting the optoelectronic turntable from rotation guidance based on the target miss amount to rotation guidance based on a radar method, and after excluding the erroneous target, detecting and screening other ship targets that meet the requirements for tracking and video posting.

[0076] It should be noted that the radar-guided ship target video signage device based on visual algorithm provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the radar-guided ship target video signage device based on visual algorithm provided in the above embodiment and the radar-guided ship target video signage method embodiment based on visual algorithm belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0077] The embodiment of the present application also provides a computer device, please refer to Figure 3 The computer device includes a processor and a memory, in which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the radar-guided ship target video listing method based on a visual algorithm provided in the above-mentioned method embodiments.

[0078] An embodiment of the present application also provides a computer-readable storage medium, on which is stored at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the radar-guided ship target video listing method based on visual algorithm provided in the above-mentioned method embodiments.

[0079] An embodiment of the present application also provides a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the radar-guided ship target video listing method based on a visual algorithm as described in any of the above embodiments.

[0080] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0081] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0082] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth 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 "include", "comprise" 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, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0083] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A radar-guided ship target video listing method based on visual algorithm, characterized in that: The method comprises: According to the longitude and latitude of the ship target detected by the radar, the rotation angle of the photoelectric turntable that enables the ship target to meet the observation conditions is calculated; Performing target detection on the video images collected by the photoelectric turntable after being rotated according to the rotation angle, and selecting a target frame of the ship target to be tracked that meets the tracking requirements according to the detection result; The ship target to be tracked is tracked according to the target frame initialization, the photoelectric turntable is adjusted according to the tracking result, and the ship feature information is superimposed around the target frame to complete the video listing of the ship target to be tracked.

2. The method according to claim 1, characterized in that The rotation angle includes the relative azimuth and relative elevation between the ship target and the radar observation point, wherein: According to the latitude and longitude information [lat0, lon0] of the radar, the installation height h0 and the latitude and longitude information [lat1, lon1] of the ship target, the horizontal distance d between the ship target and the radar observation point is calculated: d=R·c Where R is the radius of the earth, a and c are process variables; Calculate the relative azimuth angle θ between the ship target and the radar observation point: y=sin(lon1-lon0)·cos(lat1) x=cos(lat0)·sin(lat1)-sin(lat0)·cos(lat1)·cos(lon1-lon0) θ=atan2(y,x) Calculate the relative pitch angle β between the ship target and the radar observation point:

3. The method according to claim 1, characterized in that The target detection is performed on the video picture collected by the photoelectric turntable after being rotated according to the rotation angle, and the target frame of the ship target to be tracked that meets the tracking requirements is screened out according to the detection result, including: The video image is input into a pre-trained target detection model, and the target information of all ships in the image is output; wherein the target detection model is obtained by training the YOLOv5 network architecture using a ship data set containing 12 types of ships, and the target information includes the position, size, confidence and category of the ship target; Match the target information using an association algorithm to determine the same ship target in consecutive detection frames, and record the number of detections and position changes of each ship within the target time; The recorded results are screened to determine that the ship target that can be stably detected and has the smallest pixel deviation change from the center position of the target frame to the central axis of the picture is the ship target to be tracked, and the target frame of the ship target to be tracked is obtained; wherein, the target that can be stably detected is a ship target that has been detected no less than 10 times in 20 consecutive detection frames, and the pixel deviation change from the center position of the target frame to the central axis of the picture is the change in the pixel position offset of the center of the target frame compared to the central axis of the picture within 5 seconds.

4. The method according to claim 1, characterized in that: The initializing tracking of the ship target to be tracked according to the target frame includes: Initialize a feature template of a single target tracking algorithm according to the position of the target frame and the latest frame image; For the next frame of image, search for the position that best matches the feature template around the target frame of the previous frame, determine the position prediction value of the ship target to be tracked in the new frame, and update the feature template based on the position prediction value combined with the new frame of image.

5. The method according to claim 4, characterized in that The step of adjusting the photoelectric turntable according to the tracking result and superimposing the ship feature information around the target frame includes: Calculate the target miss distance according to the difference between the position prediction value and the center of the picture; According to the target miss amount, the photoelectric turntable is adjusted to the optimal position so that the ship target to be tracked is located at the center of the picture; When the tracking is stable, the ship feature information obtained by radar detection and target detection is superimposed around the target frame of the stably tracked ship target to complete the video listing of the ship target to be tracked.

6. The method according to claim 5, characterized in that After the video of the ship target to be tracked is completed, the method further includes: When the target miss amount is greater than a preset deviation threshold, the listed ship target is determined to be an erroneous target, and the optoelectronic turntable is adjusted from rotation guidance based on the target miss amount to rotation guidance based on the radar method. After eliminating the erroneous target, other ship targets that meet the requirements are detected and screened for tracking and video listing.

7. A radar-guided ship target video signage device based on a visual algorithm, characterized in that: The device comprises: A calculation module, used to calculate the rotation angle of the photoelectric turntable so that the ship target meets the observation conditions according to the longitude and latitude of the ship target detected by the radar; A detection module, used for performing target detection on the video images collected by the photoelectric turntable after being rotated according to the rotation angle, and screening out a target frame of the ship target to be tracked that meets the tracking requirements according to the detection result; The processing module is used to initialize the tracking of the ship target to be tracked according to the target frame, adjust the photoelectric turntable according to the tracking result and superimpose the ship feature information around the target frame to complete the video listing of the ship target to be tracked.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of any one of the methods described in claims 1-6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images