CN117630903A - Target detection method, device, equipment and storage medium - Google Patents
Target detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117630903A CN117630903A CN202311581593.0A CN202311581593A CN117630903A CN 117630903 A CN117630903 A CN 117630903A CN 202311581593 A CN202311581593 A CN 202311581593A CN 117630903 A CN117630903 A CN 117630903A
- Authority
- CN
- China
- Prior art keywords
- grid
- value
- threshold
- determining
- target object
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 147
- 238000000034 method Methods 0.000 claims abstract description 38
- 230000008569 process Effects 0.000 abstract description 12
- 238000012545 processing Methods 0.000 abstract description 12
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 230000008929 regeneration Effects 0.000 description 6
- 238000011069 regeneration method Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The application provides a target detection method, a target detection device, target detection equipment and a target detection storage medium, relates to the field of radar data processing, and can avoid interference of clutter in a target detection process. The method comprises the following steps: acquiring a radar detection area scanning in a current frame to obtain a target object; determining a current statistical value of a first grid where a target object is located, and determining a grid state of the first grid; when the grid state of the first grid is a normal grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a first preset condition; when the grid state of the first grid is a delay grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a second preset condition; when the grid state of the first grid is the shielding grid, the existing movement curve is not updated when the current statistical value is smaller than the first threshold value.
Description
Technical Field
The present disclosure relates to the field of radar data processing, and in particular, to a target detection method, apparatus, device, and storage medium.
Background
Radar is a device for detecting a target using electromagnetic waves, and is based on the principle that the target is detected by transmitting electromagnetic waves, and echo signals are received and analyzed to obtain information such as the position of the target. Therefore, radars are often used in various security scenarios. In practical application, in order to ensure the security effect, a product of radar and a ball machine is generally adopted for security. The radar is used for detecting the occurrence of the target and triggering the alarm, and the dome camera rotates to the position based on the position of the alarm target to perform snapshot of the target image, so that the user can more intuitively and conveniently know the attribute of the target.
In the actual working process, radar detection is interfered by clutter (such as sea clutter generated by sea waves beating the beach, ground clutter generated by leaf shrub disturbance and the like), and a large number of false alarms are generated. The detection effect of a real target is affected, and the ball machine is frequently rotated due to a large number of false alarms, so that the service life of equipment is affected.
Disclosure of Invention
The application provides a target detection method, a device, equipment and a storage medium, which can effectively avoid interference of clutter in a target detection process.
In a first aspect, the present application provides a target detection method, the method comprising: acquiring a target object in a current frame, wherein the target object is obtained by scanning a radar detection area in the current frame; the target object is positioned in the radar detection area and in the range predicted according to the existing movement curve of the radar detection area; the existing movement curve is a movement curve of a target object which is scanned and detected in a radar detection area before the current frame; determining a current statistical value of a first grid where the target object is located, and determining a grid state of the first grid according to the current statistical value; the first grid is any grid in a plurality of grids; the statistic value is used for reflecting the occurrence frequency of the objects in the grid; when the grid state of the first grid is a normal grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a first preset condition; the effective movement curve is used for indicating an actual movement curve generated by the object to be detected; when the grid state of the first grid is a delay grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a second preset condition; the second preset condition is different from the first preset condition; when the mesh state of the first mesh is a mask mesh, the existing movement curve is not updated.
According to the target detection method, after the target object obtained by scanning each frame of radar is obtained, the current statistical value of the first grid where the target object is located is determined, and the grid state of the first grid where the target object is located is determined. Since the statistics reflect the frequency of occurrence of objects in a grid, clutter signals are typically characterized as either clusters or periodic. Therefore, the grid can be divided into three states, a normal grid, a delay grid and a shielding grid according to the current statistical value of the grid. If the grid is shielded, the possibility that clutter occurs at the current moment of the grid is high, so that the updating of the generated target object in the grid to the existing moving curve is forbidden. In the case of a delay grid or a normal grid, the existing movement curve may be updated, but there is a difference in determining the effective movement curve. The scheme determines the grid state of each grid based on characteristics of clutter to further guide whether or not movement curve regeneration is allowed under the grid. And the new generation of the moving curve is forbidden under the shielding grid with denser clutter occurrence, so that the target interference caused by continuous clutter disturbance or periodic clutter disturbance can be effectively avoided, and the radar target detection effect is improved.
In one possible implementation, determining the grid state according to the current statistics includes: when the current statistical value is larger than a first threshold value, determining the grid state of the first grid as a shielding grid; when the current statistical value is smaller than a second threshold value, determining that the grid state of the first grid is a normal grid, and determining that the number of observation points included in the updated existing movement curve is larger than or equal to a third threshold value according to a first preset condition; the second threshold is less than the first threshold; when the current statistical value is smaller than the first threshold value and larger than the second threshold value, determining that the grid state of the first grid is a delay grid, and the second preset condition is that the number of observation points included in the updated existing moving curve is larger than or equal to a fourth threshold value; the fourth threshold is greater than the third threshold.
In another possible implementation manner, determining the current statistics of the first grid where the target object is located includes: counting according to the times of detecting objects in the first grid in a preset period to obtain a count value which is used as a current statistical value of the first grid; counting once in a preset period.
In another possible implementation manner, counting according to the number of times of detecting the object in the first grid to obtain a count value includes: in the current preset period, if the number of times of detecting the object in the first grid is smaller than a fifth threshold value, subtracting one from the count value of the first grid; and in the current preset period, if the number of times of detecting the object in the first grid is greater than a fifth threshold value, adding one to the count value of the first grid.
In yet another possible implementation manner, before adding one to the count value of the first grid, the method further includes: if the count value of the first grid is smaller than the sixth threshold value, adding one to the count value of the first grid; and if the count value of the first grid is greater than the sixth threshold, keeping the count value of the first grid unchanged. It will be appreciated that this may set the statistics to be within a maximum range so as not to be so long that an excessive increase in statistics would cause the subsequent statistics to be reduced below the first threshold value, which would actually be a significant cost, affecting the effectiveness of subsequent target detection.
In another possible implementation manner, the preset period is N frames, where N is greater than or equal to 1.
In yet another possible implementation manner, the method further includes: counting the first grids in a plurality of different preset periods respectively to obtain a plurality of count values of the first grids; the time intervals of the different preset periods are different.
In a second aspect, the present application provides an object detection apparatus comprising: the device comprises an acquisition module, a determination module and an updating module; the radar detection area is divided into a plurality of grids which are not overlapped with each other; the acquisition module is used for acquiring a target object in the current frame, wherein the target object is obtained by scanning the radar detection area in the current frame; the target object is positioned in a radar detection area and is predicted according to the existing movement curve of the radar detection area; the existing movement curve is a movement curve of a target object which is scanned and detected in a radar detection area before the current frame; the determining module is used for determining the current statistical value of the first grid where the target object is located and determining the network state of the first grid according to the current statistical value; the first grid is any grid in a plurality of grids; the statistic value is used for reflecting the occurrence frequency of the objects in the grid; the updating module is used for updating the observation point of the target object in the current frame to an existing moving curve when the grid state of the first grid is a normal grid, and the updated existing moving curve is determined to be an effective moving curve under the condition that a first preset condition is met; the effective movement curve is used for indicating an actual movement curve generated by the object to be detected; when the grid state of the first grid is a delay grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a second preset condition; the second preset condition is different from the first preset condition; when the mesh state of the first mesh is a mask mesh, the existing movement curve is not updated.
In a possible implementation manner, the determining module is specifically configured to determine, when the current statistics value is greater than a first threshold value, that a grid state of the first grid is a shielding grid; when the current statistical value is smaller than a second threshold value, determining that the grid state of the first grid is a normal grid, and determining that the number of observation points included in the updated existing movement curve is larger than or equal to a third threshold value according to a first preset condition; the second threshold is less than the first threshold; when the current statistical value is smaller than the first threshold value and larger than the second threshold value, determining that the grid state of the first grid is a delay grid, and the second preset condition is that the number of observation points included in the updated existing moving curve is larger than or equal to a fourth threshold value; the fourth threshold is greater than the third threshold.
In another possible implementation manner, the determining module is specifically configured to count according to the number of times of detecting the object in the first grid in a preset period, to obtain a count value, and use the count value as a statistic value of the first grid; counting once in a preset period.
In yet another possible implementation manner, the apparatus further includes a counting module. The counting module is used for subtracting one from the count value of the first grid if the number of times of detecting the object in the first grid is smaller than a fifth threshold value in the current preset period; and in the current preset period, if the number of times of detecting the object in the first grid is greater than a fifth threshold value, adding one to the count value of the first grid.
In yet another possible implementation manner, the counting module is further configured to perform adding one to the count value of the first grid if the count value of the first grid is less than the sixth threshold; and if the count value of the first grid is greater than the sixth threshold, keeping the count value of the first grid unchanged.
In another possible implementation manner, the preset period is N frames, where N is greater than or equal to 1.
In another possible implementation manner, the counting module is further configured to count the first grid in a plurality of different preset periods, and obtain a plurality of count values of the first grid; the time intervals of the different preset periods are different.
In a third aspect, the present application provides an electronic device, comprising: a processor and a memory; the memory stores instructions executable by the processor; the processor is configured to execute the instructions to cause the electronic device to implement the method of the first aspect described above.
In a fourth aspect, the present application provides a computer-readable storage medium comprising: computer software instructions; the computer software instructions, when run in an electronic device, cause the electronic device to implement the method of the first aspect described above.
In a fifth aspect, the present application provides a computer program product which, when run on a computer, causes the computer to perform the steps of the related method described in the first aspect above, to carry out the method of the first aspect above.
Advantageous effects of the second aspect to the fifth aspect described above may refer to corresponding descriptions of the first aspect, and are not repeated.
Drawings
Fig. 1 is a schematic view of a beach scene provided in the present application;
fig. 2 is a schematic diagram of a radar power map and a pseudo-movement curve provided in the present application;
FIG. 3 is a schematic view of an application environment of a target detection method provided in the present application;
FIG. 4 is a schematic view of a radar detection area provided herein;
FIG. 5 is a schematic flow chart of a solution framework provided in the present application;
FIG. 6 is a schematic flow chart of a target detection method provided in the present application;
FIG. 7 is a schematic diagram of a mesh state determination process provided in the present application;
FIG. 8 is a schematic diagram of the composition of an object detection device provided in the present application;
fig. 9 is a schematic diagram of the composition of an electronic device provided in the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It should be noted that, in the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the terms "first", "second", and the like are used to distinguish the same item or similar items having substantially the same function and effect, and those skilled in the art will understand that the terms "first", "second", and the like are not limited in number and execution order.
In order to facilitate understanding of the present solution, the technical terms related to the present solution are first explained.
1. And (3) radar: an apparatus for detecting an object using electromagnetic waves. The radar irradiates a target by emitting electromagnetic waves and receives echoes thereof, thereby obtaining information such as a distance from the target to an electromagnetic wave emission point, a distance change rate (radial velocity), an azimuth, an altitude, and the like.
2. Lei Qiu linkage: a radar and sphere combined device. The radar performs perimeter detection on the surrounding environment, and the linkage ball machine performs target pursuit, amplification, snapshot and the like after triggering radar alarm. In the linkage process, calibration processing is generally required, XY coordinates of a radar target movement curve are converted into PTZ coordinates of a pan/tilt/zoom, and then the control center rotates the spherical camera to the corresponding PTZ coordinates and amplifies the coordinate to the corresponding multiplying power to take a snapshot of the target.
3. Sea clutter: the marine environment is influenced by typhoons and other factors, the sea condition is complex, and the weather is changeable, so that the marine environment has uncertain propagation and attenuation effects on electromagnetic waves and underwater sound waves, radar echo data are interfered, and the academic world is called sea clutter interference. Sea clutter depends not only on wave height, wind speed, duration, sea state, sea surface temperature, local climatic environment, and the direction of the sea wave relative to the radar beam, but also on parameters of the radar itself such as wave band, pulse width, pulse repetition frequency, ground wiping angle, resolution cell size, polarization mode, etc.
The radar is commonly used in various security scenes, for example, a shore radar can actively detect targets on the sea surface, so that the targets can be navigated, and the like. For example, fig. 1 provides a schematic diagram of a beach scene, and a shore-based radar may be disposed in an application scene illustrated by the schematic diagram to achieve target navigation. Under the scene, the sea surface is affected by sea wind to form a surge, and clutter is formed to further cause a large number of false alarms of the radar. The method is characterized in that the radar power diagram has high intensity in a distance section with clutter disturbance. As shown in fig. 2 a, and forms a large pseudo-movement curve, as shown in fig. 2 b. In addition, the clutter is of a large variety, and ground clutter generated by leaf shrub disturbance and the like exists. The occurrence of clutter not only affects the detection of real information by the radar, but also can cause frequent rotation of the dome camera in the Lei Qiu linkage system due to false alarm of clutter, thereby generating the problem of equipment loss.
In summary, how to avoid the interference of the noise during the radar detection is a problem to be solved.
In the related art, there is a scheme for clutter filtering using mixed gaussian model modeling. However, the applicant found that this scheme can only filter clutter interference with gaussian distribution, such as ground clutter like leaf shrub disturbance, and cannot effectively filter clutter interference with non-gaussian distribution, such as sea clutter (the academia generally considers that the sea clutter is subject to K distribution). In addition, in some scenes, sea waves flap the coast at low frequencies, and surges move along the coast to form a low-frequency and periodically-appearing moving curve similar to a real target, so that the related technology cannot identify the moving curve similar to the real target, and false alarms are easy to generate.
Based on this, the embodiment of the application provides a target detection method, after the target object obtained by scanning the current frame by the radar is obtained, the current statistical value of the first grid where the target object is located is determined, and then when the current statistical value is determined to be smaller than the first threshold value, the moving curve of the target object can be updated to the existing moving curve, and by using the method, interference of the clutter can be effectively avoided in the target detection process.
The target detection method provided by the application can be applied to an application environment shown in fig. 3. As shown in fig. 3, the application environment may include: an object detection device 301 and a radar 302. The object detection device 301 and the radar 302 are connected to each other.
The object detection device 301 may be applied to a server. The server may be a server cluster formed by a plurality of servers, or a single server, or a computer. The object detection means 301 may in particular be a processor in a server. The embodiment of the application does not limit the specific device form of the server. In fig. 3, the application of the object detection device 301 to a single server is exemplified. The object detection device 301 is connected to the radar for processing the radar signal. Specifically, the method comprises radar signal processing and radar data processing. The radar signal processing is based on intermediate frequency sampling signal input of a radar, and distance-speed processing, constant false alarm detection (CFAR) detection and DOA (direction of arrival, DOA) estimation are performed to obtain radar target point cloud. The radar data processing mainly performs point cloud clustering and target detection processing. The target detection method provided by the application is mainly used in the target detection processing process.
The radar 302 is configured to transmit an electromagnetic wave to detect a target and receive an echo signal. As shown in fig. 4, the radar can detect electromagnetic waves emitted from a sector area in front of the radar, and the sector area is the radar detection area.
It should be noted that, the above embodiment is described by taking two different devices as an example, and in some scenarios, the target detection device and the radar may be the same device, and the devices may perform the functions of signal acquisition and data analysis respectively, which is not limited in this embodiment of the present application.
Fig. 5 is a schematic flow chart of a scheme framework provided in the present application. Step 1, firstly, dividing radar detection areas. As shown in fig. 4, the radar detection area (on the X-Y coordinates) is divided into a plurality of grids, each of which is the same size and does not overlap each other. Step 2, the perception of the clutter region, i.e. determining which grids have a higher clutter occurrence probability. The following embodiments are described in detail and are not described in detail herein. And 3, track regeneration. I.e. a movement curve describing a certain target object.
Fig. 6 is a flow chart of a target detection method according to an embodiment of the present application. The target detection method provided by the application can be applied to the application environment shown in fig. 3.
As shown in fig. 6, the target detection method provided in the present application specifically may include the following steps:
s601, the target detection device acquires a target object in the current frame, wherein the target object is obtained by scanning a radar detection area in the current frame.
Wherein the target object is located in the radar detection area in a range predicted from an existing movement curve of the radar detection area. The existing movement curve is a movement curve of a target object which is scanned and detected in a radar detection area before the current frame.
In some embodiments, the radar may scan the radar detection area and the target detection device may acquire the target object in the current frame from the radar. Specifically, information such as the azimuth, the speed, the distance between the radar and the target object can be obtained.
The radar may scan each frame to obtain observation points (may also be referred to as clustering targets, points, etc. in the related literature) of different objects. The target detection device may analyze and determine the range of the current frame target object based on the existing moving curve (also referred to as track in the related literature) of the detected target object scanned before the current frame, that is, according to the moving direction, moving speed and other information of the existing moving curve, and then screen and acquire the target object from a plurality of objects scanned in the current frame.
S602, the target detection device acquires the current statistical value of the first grid where the target object is located, and determines the grid state of the first grid according to the current statistical value.
The first grid is any grid of a plurality of grids which are divided by the radar detection area and are not overlapped with each other. The statistics are used to reflect the frequency of occurrence of objects in the grid.
In some embodiments, after the target object is acquired, the target detection device may determine, according to the radar detection area divided in advance, the first grid where the target object is located based on the azimuth of the target object, and further acquire the current statistical value of the first grid. Further, a grid state of the first grid may be determined based on the current statistics. The grid state includes: normal grid, delay grid, and mask grid.
It should be noted that, each of the multiple grids divided by the radar detection area has its own statistics value, which is used to reflect the intensity of the occurrence of the objects in the grid. Moreover, the statistics are changed in real time to reflect the frequency of occurrence of objects in the grid at different times (or simply grid states at different times).
The process of determining the statistics of the grid continues as described below in connection with particular embodiments.
First, a radar detection area is divided. As an example, let the radar detect distances M and N in the X-direction and Y-direction, respectively, and the side length of each grid divided by the radar be L. After the detection area is equally divided, each grid is numbered, and the number range is [1, MXN/L ] 2 ]. The value of L may be set according to the radar model, the application scenario, and the target type, for example, long-range radars are generally used for detecting large-size targets, and L may be set to be a little larger accordingly, so that the divided grid may accommodate the large-size targets. In contrast, if the short-range radar detects a pedestrian, L may be set smaller accordingly.
After the grids are divided, the processing of each grid is independent of each other. The following is for the ith grid (which may be denoted as BLOCK i ) As described above in the first grid as an example, it should be understood that the statistical value determining process of each grid is consistent, and reference should be made to the statistical value determining process of the first grid. In addition, the statistics also reflect the grid status, which is determined as shown in fig. 7, including the steps of: 1. and (5) accumulating data. 2. And (5) feature learning. 3. And (5) shielding the state update.
Specifically, the object detection device further performs the steps of:
A. And in a preset period, the target detection device counts according to the times of detecting the object in the first grid to obtain a count value which is used as a statistic value of the first grid. Counting once in a preset period.
In some embodiments, the target detection device counts the number of times of detecting the object in the first grid based on the scanning result of the radar in a preset period, and uses the counted value as the statistical value of the first grid. It should be noted that the preset period may be N frames, where N is an integer greater than or equal to 1. That is, the radar may scan a plurality of times and detect an object a plurality of times in one preset period, but count as one detection.
For the first grid, each sweep is recorded in the form of a sliding window for a period of timeThe case of object detection is traced. The detection condition can be recorded. If the object detection is indicated by 1, the no object detection is indicated by 0. For example, taking statistics of 10 frames of data as an example, the object detection situation of the first grid may be denoted as 1100111001, where the right 1 indicates that there is object detection in the current frame, and the object detection results are respectively in the presence, the absence, the presence, the absence, and the absence according to the sequence in the first 9 frames of the current frame. Here is a step describing the DATA accumulation in FIG. 7, the DATA statistics of the first grid may be performed using DATA i And (3) representing.
Further, based on the DATA statistics (DATA i ) A statistical value of the first grid is determined. The object detection device specifically performs: in the current preset period, if the number of times of detecting the object in the first grid is smaller than a fifth threshold value, subtracting one from the count value of the first grid; and in the current preset period, if the number of times of detecting the object in the first grid is greater than a fifth threshold value, adding one to the count value of the first grid.
The fifth threshold is a threshold of the number of times that the object is detected in the preset period. In addition, the number of times the first grid detects the object may be equal to the fifth threshold, and the count value of the first grid may be decremented by one or incremented by one, depending on the actual scene. The preset period may be set according to scene characteristics. For example, taking the occurrence of a period of 1s for sea clutter as an example, the preset period is set to be 1 second, and if the scanning frame rate of the radar is 5, it is indicated that the radar performs five scans within one preset period.
The foregoing data accumulation step is described. The data statistics of the first grid are divided into segments according to 5 frames, and the data is represented as 2 preset periods of data for 1100111001. The object detection case of the first preset period is denoted 11001, indicating that there are 3 object detections in the first preset period. The object detection condition for the second preset period indicates 11001 that there are 3 object detections within the second preset period. If the fifth threshold is set to 0, the first preset period 11001 has 3 times of object detection, and then the count value of the first grid is incremented by one. The second preset period 11001 also has 3 object detections, and then the count value of the first grid is incremented by one. If the object detection condition in the subsequent third preset period is indicated as 00000, which indicates that none of the objects is detected in the third preset period, it can be considered that none of the objects is detected in the third preset period, and the count is decremented by one. Here is a step of describing feature learning in fig. 7.
Note that, the counting of the grid may be achieved by setting a counter. It will be appreciated that each grid has its own counter and that the counts between the grids do not affect each other.
The statistics of the first grid are described below by way of example. Taking the statistical value of the first grid as cnt (n) as an example, the statistical formula is as follows:
wherein n represents a preset cycle sequence.
If the object detection condition of the first grid is 110001000111001010110001100000, it is divided into five frames as one preset period, which may be indicated as 110001000111001010110001100000, that is, the object detection conditions from the first preset period to the sixth preset period are (there are, or there are). Then for the first five preset periods, each period has an object detected, and then the count value of the first grid is 5. In the sixth preset period, if no object is detected, the count value at the end of the previous period is decremented by one, that is, the current statistical value of the first grid in the sixth preset period is 4. If the object is detected in the seventh preset period, the current statistical value of the seventh preset period is added with 1 on the basis of the statistical value of the sixth preset period, and so on.
It will be appreciated that, as clutter generally occurs frequently or periodically, for the radar scanning process, it leads to the visual phenomenon that there is a continuous object detection in a continuous preset period, so that the current statistic value under the grid is large, which indicates that clutter interference is likely to exist in the grid at the current moment.
After obtaining the current statistics of the first grid, the grid State of the first grid at the current time can be determined according to the current statistics (e.g. using State i Representation). If the current statistics are greater than the first threshold, the current grid is higher in the probability of clutter, and the grid state of the grid is marked as a 'shielding grid'. If the current statistical value is larger than the first threshold value and smaller than the second threshold value, indicating that clutter is likely to occur in the current grid, and marking the grid state of the grid as a 'delay grid'. If the current statistical value is smaller than the second threshold value, the current grid is less likely to generate clutter, and the grid state of the grid is marked as a normal grid.
It will be appreciated that since the grid statistics are time-efficient, the grid status of the grid is also time-efficient, i.e. the grid status of the grid is a "mask grid" at one time and may become a "normal grid" at another time. The determination of the mesh state of the mesh is used to describe the step of mask state update in fig. 7. In addition, the mesh state of the mesh may be used to guide the movement curve generation of the target object during radar detection, as described in detail below in S603.
The following may be present. If the frequency of clutter is high for a certain period of time, for example, in some scenes, continuous wind blowing causes sea waves to continuously strike the beach to generate sea clutter, so that statistics in a certain grid are continuously increased, and therefore the target detection device marks the grid as a "shielding grid". However, in calm, the statistics of the grid are too large due to the fact that the previous time clutter is always present, and the statistics decrease too slowly when no object is detected. Even after a long first period of calm, the grid may still be considered a "mask grid" because the statistics do not decrease below the first threshold value later, resulting in subsequent easy omission of detection of a real object in the grid. Therefore, it is necessary to define an upper count limit of the statistic value, and avoid the problem that the statistic value is difficult to be reduced below the first threshold value in the following process due to continuous increase of the statistic value.
In view of the above, the object detection device further performs the following steps before adding one to the count value of the first grid:
B. if the count value of the first grid is smaller than the sixth threshold value, adding one to the count value of the first grid; and if the count value of the first grid is greater than the sixth threshold, keeping the count value of the first grid unchanged.
Wherein the sixth threshold represents an upper count limit of the statistic. The first threshold is smaller than the sixth threshold.
Specifically, if an object is detected in the preset period, the target detection device compares the count value of the first grid with the sixth threshold, and if the count value is smaller than the sixth threshold, the target detection device performs one-adding to the count value of the first grid. If the count value is smaller than the sixth threshold value, the object detection device does not perform incrementing the count value of the first grid, i.e., the count value of the first grid is kept unchanged. It should be noted that, in the case where the count value is equal to the sixth threshold value, whether to perform incrementing the count value of the first grid by one or to perform keeping the count value of the first grid unchanged may be determined according to the actual situation, and the embodiment of the present application is not particularly limited. In addition, the value of the sixth threshold may also be determined based on the maximum value of the counter count according to practical experimental experience, which is not particularly limited in the embodiment of the present application.
In some scenarios, there is clutter interference that occurs at different frequencies. The clutter suppression effect is not capable of covering all clutter by counting according to only one preset period. Thus, depending on the type of clutter that may occur in a scene, multiple preset periods may be set, i.e. multiple counters are set in each grid to count the clutter of disturbances that occur at different frequencies. The object detection device may further perform the steps of:
C. And counting the first grids in a plurality of different preset periods respectively to obtain a plurality of count values of the first grids. Wherein the time intervals of different preset periods are different.
It will be appreciated that in this way, each grid may be provided with a plurality of different counters for counting, and each grid may also have a plurality of statistics, respectively representing how densely the clutter of different frequencies occurs, e.g. for sea clutter, a preset period of 1 for ground clutter, a preset period of 2, etc.
S603, when the grid state of the first grid is a normal grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition that a first preset condition is met; when the grid state of the first grid is a delay grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a second preset condition; when the grid state of the first grid is the shielding grid, the existing movement curve is not updated when the current statistical value is smaller than the first threshold value.
Wherein the effective movement curve is used to indicate the actual movement curve generated by the object to be detected. The second preset condition is different from the first preset condition.
In some embodiments, after determining the mesh state, the object detection device may direct the movement curve of the object in the first mesh to be regenerated based on the mesh state of the first mesh. After determining the current statistical value of the first grid, if the target detection device determines that the current statistical value of the first grid is smaller than the first threshold value, and indicates that the grid where the target object is located is not the 'shielding grid', the target detection device determines that the observation point of the current target object can be used for guiding track regeneration, and updates the position of the target object in the current frame to the existing moving curve by taking the position of the target object in the current frame as the observation point.
In contrast, if the target detection device determines that the current statistical value of the first grid is greater than the first threshold, which indicates that the grid where the target object is located is the "shielding grid", the target object is highly likely to be a clutter object and has no reference meaning, so that it is determined that the observation point of the current target object is not used for guiding track regeneration.
In addition, since clutter may also create a movement profile (as described above, sea waves flap the coast and surges push along the coast), it is further desirable for an existing movement profile to determine whether it is a movement profile of a truly valid target object. In general, when the number of observation points included in the existing movement curve is greater than the third threshold, the existing movement curve can be considered as an effective movement curve, and the radar can perform alarm reminding. In this scheme, the judgment scheme is further refined, and whether the effective movement curve is determined by considering the grid state of the grid.
It can be seen that the delay grid as well as the normal grid updates the existing movement curve. However, the existing movement curves generated in these two cases differ in the determination of the effective movement curve. And under the condition that the first grid is a normal grid, the updated existing movement curve is determined to be an effective movement curve under the condition that the first preset condition is met. In the case that the first grid is a delay grid, the updated existing movement curve is determined to be an effective movement curve under the condition that the second preset condition is satisfied.
The first preset condition is that the number of observation points included in the updated existing movement curve is greater than or equal to a third threshold. The second preset condition is that the number of observation points included in the updated existing movement curve is greater than or equal to a fourth threshold value.
Wherein the fourth threshold is greater than the third threshold.
In short, the grid state is a normal grid, and the probability that the object detected by the grid is disturbance clutter is very small is shown, and the judgment is carried out according to a third threshold under the conventional experience, namely the number of observation points included in the existing movement curve is larger than or equal to the third threshold, so that the effective movement curve can be determined, and then the radar carries out alarm reminding. If the grid state is a delay grid, it is stated that the object detected by the grid is likely to be disturbance clutter, and further observation is needed. Therefore, the number of observation points determined to be effective movement curves is greater than the third threshold under conventional experience. That is, the updated existing movement curve includes the number of observation points greater than or equal to the fourth threshold (the fourth threshold is greater than the third threshold of the conventional experience), and is determined as the effective movement curve.
When needing to be described, all detection points in the grid share the grid state of the current grid. If the current grid is determined to be a "mask grid," then all detection points within the current grid are not used for movement curve regeneration (i.e., updated to an existing movement curve). In addition, the effective movement curve is updated continuously and is used for intuitively displaying the movement route of the effective target object. If the existing movement curve has been determined as the effective movement curve, the new detection point associated with the effective movement curve, even if it falls on the "mask grid", will not affect the updating of the effective movement curve. Furthermore, if the observation points to be updated fall within the "delay grid" during the update of the existing movement curve, the existing movement curve is delayed when it is determined that the effective movement curve is valid, that is, the length required for determining the effective movement curve is longer (or the number of observation points is greater).
The technical scheme provided by the embodiment at least brings the following beneficial effects that the target detection method provided by the embodiment of the application determines the current statistical value in the first grid where the target object is located after the target object obtained by scanning every frame of the radar is obtained, so as to determine the grid state of the degree of density of the object in the first grid where the target object is located. Since the statistics reflect how often objects appear in a grid, clutter signals are typically characterized by the fact that clutter signals typically appear in clusters or periodically. Therefore, the grid can be divided into three states, a normal grid, a delay grid and a shielding grid according to the current statistical value of the grid. If the grid is shielded, the possibility that clutter occurs at the current moment of the grid is high, so that the updating of the generated target object in the grid to the existing moving curve is forbidden. In the case of a delay grid or a normal grid, the existing movement curve may be updated, but there is a difference in determining the effective movement curve. The scheme determines the grid state of each grid based on characteristics of clutter to further guide whether or not movement curve regeneration is allowed under the grid. And the new generation of the moving curve is forbidden under the shielding grid with denser clutter occurrence, so that the target interference caused by continuous clutter disturbance or periodic clutter disturbance can be effectively avoided, and the radar target detection effect is improved.
Furthermore, the scheme can set a plurality of groups of preset periods according to the types of different clutter in an actual scene so as to independently detect various clutter, can be effectively applied to target detection in a scene with complex environment, and effectively inhibits the interference of various clutter. In addition, the scheme is based on the divided grids, the statistical value for describing the occurrence frequency of the object is set for each grid, the statistical value has timeliness, the grid state of any grid at the current moment can be effectively determined, the grids are shielded when clutter appears densely, the grids are normally detected when clutter appears less frequently, the situation that the real object is missed due to absolute shielding is avoided, the application in the actual scene is more met, and the effect of object detection is further ensured.
It can be seen that the foregoing description of the solution provided by the embodiments of the present application has been presented mainly from a method perspective. To achieve the above-mentioned functions, embodiments of the present application provide corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In an exemplary embodiment, the present application also provides an object detection apparatus. The object detection device may comprise one or more functional modules for implementing the object detection method of the above method embodiments.
For example, fig. 8 is a schematic diagram of a composition of an object detection device according to an embodiment of the present application. As shown in fig. 8, the object detection device includes: an acquisition module 801, a determination module 802, and an update module 803. The acquisition module 801, the determination module 802 and the update module 803 are interconnected.
The acquiring module 801 is configured to acquire a target object in a current frame, where the target object is obtained by scanning a radar detection area in the current frame; the target object is positioned in a radar detection area and is predicted according to the existing movement curve of the radar detection area; the existing movement curve is a movement curve of a target object which is scanned and detected in a radar detection area before the current frame.
The determining module 802 is configured to determine a current statistics value of a first grid where the target object is located, and determine a network state of the first grid according to the current statistics value; the first grid is any grid in a plurality of grids; the statistics are used to reflect the frequency of occurrence of objects in the grid.
The updating module 803 is configured to update the observation point of the target object in the current frame to an existing movement curve when the grid state of the first grid is a normal grid, and the updated existing movement curve is determined to be an effective movement curve under the condition that the first preset condition is satisfied; the effective movement curve is used for indicating an actual movement curve generated by the object to be detected; when the grid state of the first grid is a delay grid, updating the observation point of the target object in the current frame to an existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a second preset condition; the second preset condition is different from the first preset condition; when the mesh state of the first mesh is a mask mesh, the existing movement curve is not updated.
In a possible implementation manner, the determining module 802 is specifically configured to determine, when the current statistics are greater than the first threshold, that the grid state of the first grid is a shielding grid; when the current statistical value is smaller than a second threshold value, determining that the grid state of the first grid is a normal grid, and determining that the number of observation points included in the updated existing movement curve is larger than or equal to a third threshold value according to a first preset condition; the second threshold is less than the first threshold; when the current statistical value is smaller than the first threshold value and larger than the second threshold value, determining that the grid state of the first grid is a delay grid, and the second preset condition is that the number of observation points included in the updated existing moving curve is larger than or equal to a fourth threshold value; the fourth threshold is greater than the third threshold.
In another possible implementation manner, the determining module 802 is specifically configured to count according to the number of times of detecting the object in the first grid in a preset period, to obtain a count value, which is used as a statistic value of the first grid; counting once in a preset period.
In yet another possible implementation, the apparatus further includes a counting module 804. The counting module 804 is configured to, in a current preset period, decrement the count value of the first grid by one if the number of times of detecting the object in the first grid is less than a fifth threshold; and in the current preset period, if the number of times of detecting the object in the first grid is greater than a fifth threshold value, adding one to the count value of the first grid.
In yet another possible implementation manner, the counting module 804 is further configured to perform adding one to the count value of the first grid if the count value of the first grid is less than the sixth threshold; and if the count value of the first grid is greater than the sixth threshold, keeping the count value of the first grid unchanged.
In another possible implementation manner, the preset period is N frames, where N is greater than or equal to 1.
In another possible implementation manner, the counting module 804 is further configured to count the first grid in a plurality of different preset periods, and obtain a plurality of count values of the first grid; the time intervals of the different preset periods are different.
In the case of implementing the functions of the integrated modules in the form of hardware, the embodiments of the present application provide a schematic composition diagram of an object detection device, where the object detection device may be the object detection apparatus described above. As shown in fig. 9, the object detection apparatus 900 includes: a processor 902, a communication interface 903, and a bus 904. Optionally, the object detection device may further comprise a memory 901.
The processor 902 may be a logic block, module, and circuitry that implements or performs the various examples described in connection with the present disclosure. The processor 902 may be a central processor, general purpose processor, digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 902 may also be a combination that performs computing functions, e.g., including one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
A communication interface 903 for connecting to other devices via a communication network. The communication network may be an ethernet, a radio access network, a wireless local area network (wireless local area networks, WLAN), etc.
The memory 901 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
As a possible implementation, the memory 901 may exist separately from the processor 902, and the memory 901 may be connected to the processor 902 through the bus 904 for storing instructions or program code. The processor 902, when calling and executing instructions or program code stored in the memory 901, is capable of implementing the object detection method provided in the embodiments of the present application.
In another possible implementation, the memory 901 may also be integrated with the processor 902.
Bus 904, which may be an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The bus 904 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus.
It will be apparent to those skilled in the art from this description that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the object detection apparatus is divided into different functional modules to perform all or part of the above-described functions.
Embodiments of the present application also provide a computer-readable storage medium. All or part of the flow in the above method embodiments may be implemented by computer instructions to instruct related hardware, and the program may be stored in the above computer readable storage medium, and the program may include the flow in the above method embodiments when executed. The computer readable storage medium may be any of the foregoing embodiments or memory. The computer readable storage medium may be an external storage device of the object detection apparatus, such as a plug-in hard disk (SMC) provided in the object detection apparatus, a Secure Digital (SD) card, a flash card, or the like. Further, the computer-readable storage medium may further include both the internal storage unit and the external storage device of the object detection apparatus. The computer-readable storage medium is used to store the computer program and other programs and data required by the object detection device. The above-described computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
Embodiments of the present application also provide a computer program product comprising a computer program which, when run on a computer, causes the computer to perform any of the item target detection methods provided in the embodiments described above.
Although the present application has been described herein in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the figures, the disclosure, and the appended claims. In the claims, the word "Comprising" does not exclude other elements or steps, and the "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
Although the present application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the present application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
The foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (11)
1. A target detection method characterized in that a radar detection area is divided into a plurality of grids that do not overlap each other, the method comprising:
acquiring a target object in the current frame, wherein the target object is obtained by scanning the radar detection area in the current frame; the target object is positioned in the radar detection area and in a range predicted according to the existing movement curve of the radar detection area; the existing movement curve is a movement curve of the target object detected by scanning in the radar detection area before the current frame;
determining a current statistical value of a first grid where the target object is located, and determining a grid state of the first grid according to the current statistical value; the first grid is any grid in the plurality of grids; the statistic value is used for reflecting the occurrence frequency of the objects in the grid;
when the grid state of the first grid is a normal grid, updating the observation point of the target object in the current frame to the existing moving curve, and determining the updated existing moving curve as an effective moving curve under the condition of meeting a first preset condition; the effective movement curve is used for indicating an actual movement curve generated by an object to be detected;
When the grid state of the first grid is a delay grid, updating the observation point of the target object in the current frame to the existing movement curve, and determining the updated existing movement curve as an effective movement curve under the condition of meeting a second preset condition; the second preset condition is different from the first preset condition;
and when the grid state of the first grid is a shielding grid, not updating the existing movement curve.
2. The method of claim 1, wherein determining a grid state from the current statistics comprises:
when the current statistical value is larger than a first threshold value, determining that the grid state of the first grid is a shielding grid;
when the current statistical value is smaller than a second threshold value, determining that the grid state of the first grid is a normal grid, and the first preset condition is that the number of observation points included in the updated existing moving curve is larger than or equal to a third threshold value; the second threshold is less than the first threshold;
when the current statistical value is smaller than the first threshold value and larger than the second threshold value, determining that the grid state of the first grid is a delay grid, and the second preset condition is that the number of observation points included in the updated existing movement curve is larger than or equal to a fourth threshold value; the fourth threshold is greater than the third threshold.
3. The method according to claim 1 or 2, wherein said determining the current statistics of the first grid in which the target object is located comprises:
counting according to the times of detecting objects in the first grid in a preset period to obtain a count value serving as a current statistical value of the first grid; counting once in a preset period.
4. A method according to claim 3, wherein said counting according to the number of times an object is detected in said first grid, to obtain a count value, comprises:
in the current preset period, if the number of times of detecting the object in the first grid is smaller than a fifth threshold value, subtracting one from the count value of the first grid;
and in the current preset period, if the number of times of detecting the object in the first grid is greater than the fifth threshold value, adding one to the count value of the first grid.
5. The method of claim 4, wherein prior to said incrementing the count value of the first grid by one, the method further comprises:
if the count value of the first grid is smaller than a sixth threshold value, executing the adding one to the count value of the first grid;
and if the count value of the first grid is larger than the sixth threshold value, keeping the count value of the first grid unchanged.
6. A method according to claim 3, wherein the predetermined period is N frames, the N being greater than or equal to 1.
7. A method according to claim 3, characterized in that the method further comprises:
counting the first grids in a plurality of different preset periods respectively to obtain a plurality of count values of the first grids; the time intervals of the different preset periods are different.
8. An object detection apparatus characterized in that a radar detection area is divided into a plurality of grids that do not overlap each other, the apparatus comprising: the device comprises an acquisition module, a determination module and an updating module;
the acquisition module is used for acquiring a target object in the current frame, wherein the target object is obtained by scanning the radar detection area in the current frame; the target object is positioned in the radar detection area and is predicted according to the existing movement curve of the radar detection area; the existing movement curve is a movement curve of the target object detected by scanning in the radar detection area before the current frame;
the determining module is used for determining a current statistical value of a first grid where the target object is located and determining a network state of the first grid according to the current statistical value; the first grid is any grid in the plurality of grids; the statistic value is used for reflecting the occurrence frequency of the objects in the grid;
The updating module is used for updating the observation point of the target object in the current frame to the existing moving curve when the grid state of the first grid is a normal grid, and the updated existing moving curve is determined to be an effective moving curve under the condition that a first preset condition is met; the effective movement curve is used for indicating an actual movement curve generated by an object to be detected;
when the grid state of the first grid is a delay grid, updating the observation point of the target object in the current frame to the existing movement curve, and determining the updated existing movement curve as an effective movement curve under the condition of meeting a second preset condition; the second preset condition is different from the first preset condition;
and when the grid state of the first grid is a shielding grid, not updating the existing movement curve.
9. The apparatus of claim 8, wherein the apparatus further comprises: a counting module;
the determining module is specifically configured to determine, when the current statistical value is greater than a first threshold, that a grid state of the first grid is a shielding grid; when the current statistical value is smaller than a second threshold value, determining that the grid state of the first grid is a normal grid, and the first preset condition is that the number of observation points included in the updated existing moving curve is larger than or equal to a third threshold value; the second threshold is less than the first threshold; when the current statistical value is smaller than the first threshold value and larger than the second threshold value, determining that the grid state of the first grid is a delay grid, and the second preset condition is that the number of observation points included in the updated existing movement curve is larger than or equal to a fourth threshold value; the fourth threshold is greater than the third threshold;
The determining module is specifically configured to count according to the number of times of detecting the object in the first grid in a preset period, to obtain a count value, and to use the count value as a statistic value of the first grid; counting once in a preset period;
the counting module is used for subtracting one from the count value of the first grid if the number of times of detecting objects in the first grid is smaller than a fifth threshold value in the current preset period; in the current preset period, if the number of times of detecting the object in the first grid is greater than the fifth threshold value, adding one to the count value of the first grid;
the counting module is further configured to perform the adding one to the count value of the first grid if the count value of the first grid is less than a sixth threshold; if the count value of the first grid is greater than the sixth threshold, keeping the count value of the first grid unchanged;
the preset period is N frames, and N is greater than or equal to 1;
the counting module is further used for counting the first grid in a plurality of different preset periods respectively to obtain a plurality of count values of the first grid; the time intervals of the different preset periods are different.
10. An object detection apparatus, characterized in that the object detection apparatus comprises: a processor and a memory;
The memory stores instructions executable by the processor;
the processor is configured to, when executing the instructions, cause the object detection device to implement the method of any one of claims 1-7.
11. A computer-readable storage medium, the computer-readable storage medium comprising: computer software instructions;
when the computer software instructions are run in a computer, the computer is caused to carry out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311581593.0A CN117630903A (en) | 2023-11-23 | 2023-11-23 | Target detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311581593.0A CN117630903A (en) | 2023-11-23 | 2023-11-23 | Target detection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117630903A true CN117630903A (en) | 2024-03-01 |
Family
ID=90026318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311581593.0A Pending CN117630903A (en) | 2023-11-23 | 2023-11-23 | Target detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117630903A (en) |
-
2023
- 2023-11-23 CN CN202311581593.0A patent/CN117630903A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111562581B (en) | Traffic radar, target detection method and device thereof, electronic equipment and storage medium | |
| CN111624567B (en) | Constant false alarm detection method and device | |
| CN111708022B (en) | Method and device for calculating scanning area boundary of millimeter wave radar | |
| CN109154655A (en) | Target Signal Detection, equipment, unmanned plane and agriculture unmanned plane | |
| CN107561509B (en) | Airborne millimeter wave radar power line detection method | |
| CN110109067B (en) | Ground-based FMCW region monitoring radar data processing method | |
| KR102440355B1 (en) | Deep Learning-based Ocean Cluster Data Measurement System Using Sea Level Wave Reflectance | |
| CN103529438A (en) | System and method for monitoring moving target on ground by marine radar | |
| CN103995257B (en) | The detection method of target and device | |
| CN111323757B (en) | Target detection method and device for marine radar | |
| CN111323756A (en) | Deep learning-based marine radar target detection method and device | |
| CN109100697A (en) | A kind of target condensing method based on ground surveillance radar system | |
| CN113625232B (en) | Method, device, medium and equipment for restraining multipath false target in radar detection | |
| Xia et al. | Signal chain architectures for efficient airport surface movement radar video processing | |
| CN115184915A (en) | Sea clutter suppression method and system based on random clutter loitering behavior | |
| CN113687429A (en) | Device and method for determining boundary of millimeter wave radar monitoring area | |
| CN113253219A (en) | No-reference object self-calibration method, device, equipment and medium of millimeter wave radar | |
| CN117630903A (en) | Target detection method, device, equipment and storage medium | |
| CN108985292A (en) | A kind of SAR image CFAR object detection method and system based on multi-scale division | |
| CN114415123B (en) | Non-coherent neighborhood based weighting pulse accumulation processing method and system | |
| CN109239677B (en) | Environment self-adaptive constant false alarm rate detection threshold determination method | |
| CN113985376B (en) | Radar comprehensive display and control excitation system | |
| CN113625267B (en) | Low-slow small target detection method based on four-dimensional steady-state clutter map under strong clutter background | |
| JP2022001864A (en) | Method, device and electronic apparatus for detecting moving object | |
| CN112837346A (en) | Method and device for detecting in-place of moving target |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |