Equipment layout method and device for unmanned aerial vehicle countering equipment
By acquiring and reconstructing the target floor map, identifying accessible areas and performing spatial voxelization, optimizing the drone tracks and equipment layout, solving the problem of drone counter-equipment deployment in complex areas, and realizing the drone's Effective countermeasures and improvements in deployment efficiency.
Patent Information
- Application Number
- CN202411184588.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-29
Smart Images

Figure CN119047778A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to a method and apparatus for equipment layout of drone countermeasure equipment. Background Art
[0002] A drone is an unmanned aircraft controlled by a radio remote control device and a self-contained program control device. With the development of drone-related technologies, it has been widely used. However, due to the characteristics of drones such as small size, drones have posed new challenges to the prevention, control and countermeasures of drones in controlled areas (for example, controlled airspace). At present, the way to counter drones is to counter drones through drone countermeasure equipment.
[0003] However, when the above method is adopted, the following technical problems often occur:
[0004] When the control area is complex, it is difficult to effectively and comprehensively deploy drone countermeasure equipment, resulting in uncovered areas and making it impossible to effectively counter drones;
[0005] In the process of adopting technical solutions to solve the above technical problem 1, the following technical problem 2 is often accompanied:
[0006] The common point cloud-based 3D modeling method is unable to effectively collect point cloud data for tall buildings. At the same time, when the controlled area is large, the amount of data processing for 3D modeling is extremely large, thus delaying the effective deployment of drone countermeasures.
[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention
[0008] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0009] Some embodiments of the present disclosure propose a device layout method and apparatus for drone countermeasure equipment to solve one or more of the technical problems mentioned in the above background technology section.
[0010] In a first aspect, some embodiments of the present disclosure provide a device layout method for drone countermeasure equipment, the method comprising: obtaining a target plane map sequence, wherein the target plane map in the target plane map sequence is an area map collected at continuous moments and containing buildings in the target area; performing three-dimensional building reconstruction on the target area according to the target plane map sequence to obtain a three-dimensional area map; determining a traversable area according to the three-dimensional area map, wherein the traversable area represents a three-dimensional area through which a drone can traverse; performing spatial voxelization on the traversable area to generate a voxelized traversable area; performing drone track traversal on the voxelized traversable area to obtain A candidate track information set; determining the track confidence corresponding to each candidate track information in the above candidate track information set; screening out the candidate track information whose corresponding track confidence meets the screening conditions from the above candidate track information set as the target track information, and obtaining the target track information set; determining the hot spot area in the above passable area according to the above target track information set to generate the hot spot area location information; determining the candidate device layout location set according to the above hot spot area location information; determining the device layout location information set according to the candidate device layout location set and the target device information set, wherein the target device information in the above target device information set represents the device parameters of the drone countermeasure device.
[0011] In a second aspect, some embodiments of the present disclosure provide a device layout apparatus for drone countermeasure equipment, the apparatus comprising: an acquisition unit, configured to acquire a target plane map sequence, wherein the target plane map in the target plane map sequence is an area map collected at continuous moments and containing buildings in the target area; a three-dimensional building reconstruction unit, configured to perform three-dimensional building reconstruction on the target area according to the target plane map sequence to obtain a three-dimensional area map; a first determination unit, configured to determine a traversable area according to the three-dimensional area map, wherein the traversable area represents a three-dimensional area through which a drone can traverse; a spatial voxelization unit, configured to perform spatial voxelization on the traversable area to generate a voxelized traversable area; and a drone track traversal unit, configured to perform drone track traversal on the voxelized traversable area. A candidate track information set is obtained; a second determination unit is configured to determine the track confidence corresponding to each candidate track information in the above candidate track information set; a screening unit is configured to screen out the candidate track information whose corresponding track confidence meets the screening conditions from the above candidate track information set as the target track information, and obtain the target track information set; a third determination unit is configured to determine the hot spot area in the above passable area according to the above target track information set to generate the hot spot area location information; a fourth determination unit is configured to determine the candidate device layout location set according to the above hot spot area location information; a fifth determination unit is configured to determine the device layout location information set according to the candidate device layout location set and the target device information set, wherein the target device information in the above target device information set represents the device parameters of the drone countermeasure device.
[0012] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.
[0013] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
[0014] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the equipment layout method for drone countermeasure equipment of some embodiments of the present disclosure, the effective deployment of drone countermeasure equipment is realized, the existence of blind spots is reduced as much as possible, and the effective countermeasure of drones is realized. Specifically, the reason for the inability to effectively counter the drone is that when the control area is relatively complex, it is difficult to effectively and comprehensively deploy the drone countermeasure equipment, so that there are uncovered areas, and thus the drone cannot be effectively countered. Based on this, the equipment layout method for drone countermeasure equipment of some embodiments of the present disclosure, first, obtain a target plane map sequence, wherein the target plane map in the above target plane map sequence is an area map collected at continuous moments and containing buildings in the target area. Secondly, according to the above target plane map sequence, the above target area is reconstructed into a three-dimensional building to obtain a three-dimensional area map, and the reconstruction of the three-dimensional building is realized by combining the two-dimensional plane map, which is less difficult to implement than the three-dimensional reconstruction method based on point cloud data. Then, according to the above three-dimensional area map, the passable area is determined, wherein the above passable area represents the three-dimensional area where the drone can pass. In this way, the three-dimensional area where the drone can pass is obtained. Furthermore, the above-mentioned traversable area is spatially voxelized to generate a traversable area after voxelization. By voxelization, a dimensionality reduction representation of the traversable area is achieved, reducing the amount of subsequent data processing. In addition, the above-mentioned traversable area after voxelization is traversed by a drone track to obtain a candidate track information set. By traversal, the track that the drone may pass through is determined. In addition, the track confidence corresponding to each candidate track information in the above-mentioned candidate track information set is determined. Then, the candidate track information whose corresponding track confidence meets the screening conditions is filtered out from the above-mentioned candidate track information set as the target track information to obtain the target track information set. By combining the track confidence, the tracks with lower confidence are filtered. Next, based on the above-mentioned target track information set, the hot spot area in the above-mentioned traversable area is determined to generate the hot spot area location information. In this way, the key area passed by the track is obtained. Further, based on the above-mentioned hot spot area location information, the candidate equipment layout location set is determined. Finally, according to the candidate device layout location set and the target device information set, the device layout location information set is determined, wherein the target device information in the above target device information set represents the device parameters of the drone countermeasure device. In this way, the effective deployment of drone countermeasure devices is achieved, and then the effective control and countermeasure of drones in the target area is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.
[0016] Figure 1 is a flow chart of some embodiments of a device layout method for a drone countermeasure device according to the present disclosure;
[0017] Figure 2 It is a structural schematic diagram of some embodiments of the equipment layout device for drone countermeasure equipment according to the present disclosure;
[0018] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION
[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.
[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.
[0025] refer to Figure 1, shows a process 100 of some embodiments of a device layout method for a drone countermeasure device according to the present disclosure. The device layout method for a drone countermeasure device comprises the following steps:
[0026] Step 101, obtaining a target plane map sequence.
[0027] In some embodiments, the execution subject (for example, a computing device) of the equipment layout for the drone countermeasure device can obtain the above-mentioned target plane map sequence by wired connection or wireless connection. Among them, the target plane map in the target plane map sequence is a regional map collected at continuous moments and containing buildings in the target area. The target area can be an area where the drone countermeasure device is to be deployed to control and counter the drone entering the area. In practice, the drone countermeasure device may include: a countermeasure device based on signal interference, a countermeasure device based on sound wave interference, and a countermeasure device based on radio wave interference. Specifically, the countermeasure device based on signal interference can achieve the countermeasure of the drone by interfering with the control signal and / or positioning signal of the drone. The countermeasure device based on sound wave interference can achieve the countermeasure of the drone by emitting sound waves of a specific frequency to the drone so that the gyroscope inside the drone resonates, thereby affecting the operation of the gyroscope. The countermeasure device based on radio wave interference can block the communication of the drone by emitting high-frequency radio waves, thereby achieving the countermeasure of the drone.
[0028] As an example, the target area may be an urban area containing multiple buildings. The execution subject may collect the plane map corresponding to the target area in a time sequence starting from noon at an interval of 1 hour as the target plane map sequence. In practice, the time for collecting the target plane map sequence is avoided as much as possible at noon, so that the collected plane map contains the shadow of the building corresponding to the building, which is used for the subsequent three-dimensional building reconstruction.
[0029] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future.
[0030] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.
[0031] Step 102, based on the target plane map sequence, three-dimensional building reconstruction is performed on the target area to obtain a three-dimensional area map.
[0032] In some embodiments, the execution subject may reconstruct the target area in three dimensions according to the target plane map sequence to obtain a three-dimensional area map. The three-dimensional area map is a map that displays the buildings in the target area in three dimensions. In practice, parameters such as building heights in the three-dimensional area map are scaled proportionally according to the map scale.
[0033] In some optional implementations of some embodiments, the execution subject performs three-dimensional building reconstruction on the target area according to the target plane map sequence to obtain a three-dimensional area map, which may include the following steps:
[0034] In the first step, for each target plane map in the target plane map sequence, target detection is performed on the target plane map to generate a building information group.
[0035] Among them, the building information in the above-mentioned building information group includes: a building image, a building shadow image and a first building image feature. The building information group represents at least one building contained in the target area. The building image represents the image corresponding to the building in the target plane map. The building shadow image represents the shadow image corresponding to the building in the target plane map. In practice, due to the lighting angle (when the sun is not directly overhead), the building will have a corresponding shadow. The first building image feature is the image feature corresponding to the building image. In practice, the above-mentioned execution subject can perform target detection on the target plane map by image segmentation to generate the above-mentioned building information group. Specifically, the above-mentioned execution subject can use a model such as REseg to perform image segmentation on the target plane map to obtain segmented buildings and building shadows to generate corresponding building images and building shadow images, and at the same time, express the features corresponding to the segmented buildings as the corresponding first building image features.
[0036] In the second step, based on the first building image feature included in the building information, clustering processing is performed on the building information in the obtained building information group set to generate a building information cluster set.
[0037] The building information cluster in the above building information cluster set includes: at least one building information, and at least one building information included in the building information cluster corresponds to the same building. In practice, since the target plane map in the target plane map sequence is an area map collected at continuous moments and includes buildings in the target area, target detection is performed on different target plane maps, and different building information extracted may correspond to the same building. Specifically, the above execution subject can perform clustering processing on the building information in the obtained building information group set according to the first building image feature included in the building information through the K-means algorithm to generate a building information cluster set.
[0038] In the third step, for each building information cluster in the above building information cluster set, the following three-dimensional building reconstruction steps are performed:
[0039] In the first sub-step, the building image included in each building information in the building information cluster is encoded by a coding network to generate a second image feature and obtain a second image feature set.
[0040] The encoding network includes: a first convolutional layer, a second convolutional layer, a first pooling layer, a third convolutional layer, a fourth convolutional layer, a second pooling layer, a fifth convolutional layer, a sixth convolutional layer, a third pooling layer, a seventh convolutional layer, an eighth convolutional layer, a fourth pooling layer, a ninth convolutional layer, a tenth convolutional layer, a fifth pooling layer, an eleventh convolutional layer, a twelfth convolutional layer and a fully connected layer. The convolution kernel size of the first convolutional layer is 7×7. The convolution kernel sizes of the second convolutional layer, the third convolutional layer, the fourth convolutional layer, the fifth convolutional layer, the sixth convolutional layer, the seventh convolutional layer, the eighth convolutional layer, the ninth convolutional layer, the tenth convolutional layer, the eleventh convolutional layer and the twelfth convolutional layer are all 3×3. The input of the fully connected layer is the output of the fifth pooling layer and the output of the twelfth convolutional layer. The input of the twelfth convolutional layer is the output of the eleventh convolutional layer. The input of the eleventh convolutional layer is the output of the fourth pooling layer. The input of the fourth pooling layer is the output of the tenth convolutional layer. The input of the tenth convolutional layer is the output of the ninth convolutional layer. The input of the ninth convolutional layer is the output of the third pooling layer. The input of the third pooling layer is the output of the eighth convolutional layer. The input of the eighth convolutional layer is the output of the seventh convolutional layer. The input of the seventh convolutional layer is the output of the third pooling layer. The input of the third pooling layer is the output of the sixth convolutional layer and the output of the second pooling layer. The input of the sixth convolutional layer is the input of the fifth convolutional layer. The input of the fifth convolutional layer is the output of the second pooling layer. The input of the second pooling layer is the output of the fourth convolutional layer and the output of the first pooling layer. The input of the fourth convolutional layer is the output of the third convolutional layer. The input of the third convolutional layer is the output of the first pooling layer. The input of the first pooling layer is the output of the second convolutional layer and the building image. The input of the second convolutional layer is the output of the first convolutional layer. The input of the first convolutional layer is the building image.
[0041] The second sub-step is to generate a third image feature set based on the three-dimensional feature extraction network and the second image feature set.
[0042] In practice, the above three-dimensional feature extraction network adopts the E3D-LSTM model.
[0043] The third sub-step is to generate a candidate three-dimensional building model for the building corresponding to the building information cluster according to the decoding network and the third image feature set.
[0044] Among them, the encoding network, the three-dimensional feature extraction network and the decoding network are included in the three-dimensional building reconstruction network. In practice, the decoding network includes: a first upper pooling layer, a first 3D convolutional network, a second 3D convolutional network, a second upper pooling layer, a third 3D convolutional network, a fourth 3D convolutional layer, a third upper pooling layer, a fifth 3D convolutional layer, a sixth 3D convolutional layer, a fourth upper pooling layer, a seventh 3D convolutional layer, an eighth 3D convolutional layer, a ninth 3D convolutional layer, a tenth 3D convolutional layer and a 3D Softmax layer. The convolution kernel sizes of the first 3D convolutional layer to the tenth 3D convolutional layer are all 3×3×3. The input of the first upper pooling layer is the output of the three-dimensional feature extraction network. The input of the first 3D convolutional network is the output of the first upper pooling layer. The input of the second 3D convolutional network is the output of the first upper pooling layer. The input of the second upper pooling layer is the output of the second 3D convolutional network and the output of the first upper pooling layer. The input of the third 3D convolutional network is the output of the second upper pooling layer. The input of the fourth 3D convolutional network is the output of the third 3D convolutional network. The input of the third upper pooling layer is the output of the fourth 3D convolutional network and the output of the second upper pooling layer. The input of the fifth 3D convolutional network is the output of the third upper pooling layer. The input of the sixth 3D convolutional network is the output of the fifth 3D convolutional network. The input of the fourth upper pooling layer is the output of the sixth 3D convolutional network and the output of the third upper pooling layer. The input of the seventh 3D convolutional network is the output of the fourth upper pooling layer. The input of the eighth 3D convolutional network is the output of the seventh 3D convolutional network. The input of the ninth 3D convolutional network is the output of the eighth 3D convolutional network. The input of the tenth 3D convolutional network is the output of the ninth 3D convolutional network and the output of the fourth upper pooling layer. The input of the 3DSoftmax layer is the tenth 3D convolutional network.
[0045] The fourth sub-step is to perform model projection on the candidate three-dimensional building model according to the target image acquisition information and the building shadow image included in the building information in the building information cluster to obtain the building parameters of the building corresponding to the building information cluster.
[0046] The target image acquisition information is the image acquisition information of the target plane map corresponding to the building information cluster, and the target image acquisition information includes: image acquisition altitude angle and sun altitude angle.
[0047] In practice, after the candidate three-dimensional building model is constructed, the model size of the candidate three-dimensional building model is known, and the model size can be simplified to height (H): width (W): length (L). The above-mentioned execution subject can determine the shadow length corresponding to the building based on the building shadow image. Therefore, the above-mentioned execution subject can determine the height (H) based on the triangular relationship between the shadow length (S), the image acquisition altitude angle (α), and the solar altitude angle (β), and then determine the width (W) and length (L) as building parameters based on the height (H). Specifically, L = H / tan(α)-H / tan(β). In practice, when the direction of the satellite acquisition target plane map is opposite to the direction of the sun's illumination, that is, when the difference between the image acquisition altitude angle and the solar altitude angle is ≥180°, S = L.
[0048] The fifth sub-step is to generate a blank map.
[0049] The map scale of the blank map is consistent with the map size of the target plane map in the target plane map sequence.
[0050] In a sixth sub-step, based on the building parameters corresponding to the candidate building three-dimensional models and the map scale corresponding to the blank map, the obtained set of candidate building three-dimensional models is projected onto the blank map to obtain the three-dimensional area map.
[0051] In practice, the above-mentioned execution entity can scale the architectural parameters of the candidate building three-dimensional model according to the map scale, and project the scaled candidate building three-dimensional model into the blank map.
[0052] The above-mentioned content of "in some optional implementation methods of some embodiments" as an inventive point of the present disclosure solves the second technical problem mentioned in the background technology, namely, "the common point cloud-based three-dimensional modeling method is difficult to effectively collect point cloud data for tall buildings. At the same time, when the control area is large, the data processing volume of three-dimensional modeling is extremely large, thereby delaying the effective deployment of drone countermeasure equipment." Based on this, firstly, the present disclosure performs target detection on the buildings contained in the target plane map by target detection to generate corresponding building information. Secondly, the present disclosure clusters the building information corresponding to the same building in different target plane maps to obtain building information clusters, so as to obtain the building images and building shadow images corresponding to the same building at different times. Then, the present disclosure realizes three-dimensional building reconstruction based on two-dimensional images through a three-dimensional building reconstruction network. Compared with the point cloud-based modeling method, the data processing volume is smaller, and there is no need to collect point cloud data. Next, since the model size of the candidate three-dimensional model obtained based on image recognition is related to the image size, but may be inconsistent with the actual building size, the present disclosure combines the shadow image, the image acquisition altitude angle and the sun altitude angle to determine the actual building parameters corresponding to each candidate three-dimensional building model. Finally, the present disclosure scales (projects) the candidate three-dimensional building model in combination with the map size to obtain a three-dimensional area map. In this way, compared with the point cloud-based three-dimensional modeling method, the amount of data processing is greatly reduced, and the deployment efficiency of subsequent drone countermeasure equipment is indirectly improved.
[0053] Step 103, determining a traversable area according to the three-dimensional area map.
[0054] In some embodiments, the execution subject may determine the traversable area based on the three-dimensional area map. In practice, the traversable area represents an area where the drone can fly.
[0055] In some optional implementations of some embodiments, the execution subject determines the traversable area according to the three-dimensional area map, which may include the following steps:
[0056] The first step is to determine the map boundary of the above three-dimensional area map.
[0057] In practice, the map boundary can be the same as the region boundary of the target region. When the target region is fixed, the map boundary is known.
[0058] The second step is to determine the building height points in the above three-dimensional area map.
[0059] In practice, the execution subject may traverse the highest height corresponding to the scaled candidate building three-dimensional model in the three-dimensional area map, that is, the maximum height (H) as the building high point.
[0060] The third step is to determine the low point of the building in the above three-dimensional area map.
[0061] Among them, the lowest point corresponding to the three-dimensional area map can be used as the building low point. In practice, the building low point can be simplified to 0 altitude.
[0062] The fourth step is to generate a target three-dimensional area based on the map boundary, the building high point and the building low point.
[0063] The cross-sectional boundary of the horizontal cross-section of the target three-dimensional area is the map boundary, and the area height of the target three-dimensional area is the distance difference between the high point of the building and the low point of the building.
[0064] The fifth step is to determine the area difference between the target three-dimensional area and the three-dimensional area map as the passable area.
[0065] Step 104 , spatially voxelize the traversable area to generate a voxelized traversable area.
[0066] The execution subject may spatially voxelize the passable area to generate a voxelized passable area. In practice, the execution subject may spatially voxelize the passable area by using a grid method to generate a voxelized passable area.
[0067] In some optional implementations of some embodiments, the execution subject spatially voxelizes the traversable area to generate a voxelized traversable area, which may include the following steps:
[0068] The first step is to divide the above-mentioned passable area into regions according to the restricted flight altitude range corresponding to the drone to obtain at least one sub-passable area.
[0069] In practice, the flight altitude ranges of different drones are different. The flight altitude of micro drones does not exceed 50 meters. The flight altitude of light and small drones does not exceed 120 meters. Specifically, the flight altitude refers to the actual height (true height) of the drone from the ground. Specifically, the above-mentioned execution entity can divide the traversable area horizontally according to the restricted flight altitude ranges corresponding to different drones to obtain the above-mentioned at least one sub-traversable area.
[0070] In the second step, for each sub-traversable area in the at least one sub-traversable area, the following spatial voxelization steps are performed:
[0071] The first sub-step is to determine the relative position of the sub-traversable area in the traversable area.
[0072] In the second sub-step, the voxel granularity is mapped according to the above relative positions.
[0073] The voxel granularity represents the size of a unit voxel block used for spatial voxelization. In practice, the lower the relative position, the smaller the corresponding voxel granularity.
[0074] The third sub-step is to perform octree voxelization on the above-mentioned sub-traversable area with the above-mentioned voxel granularity to obtain the voxelized sub-traversable area.
[0075] In the third step, the obtained voxelized traversable areas are spliced to obtain the above-mentioned voxelized traversable areas.
[0076] Step 105, traverse the voxelized traversable area with drone tracks to obtain a candidate track information set.
[0077] In some embodiments, the above-mentioned execution entity can perform drone track traversal on the voxelized traversable area to obtain a set of candidate track information.
[0078] In some optional implementations of some embodiments, the execution subject performs drone track traversal on the voxelized traversable area to obtain a candidate track information set, which may include the following steps:
[0079] With the target condition group as the conditional constraint, the UAV track traverses the above voxelized traversable area to obtain a set of candidate track information.
[0080] Among them, the target condition group includes: the first target condition, the second target condition, and the third target condition. The first target condition is: the core area in the target area is the end point of the path, the second target condition is: any unit voxel block on the boundary of the passable area after voxelization is the starting point of the path, and the third target condition is: the number of times the candidate track information passes through each unit voxel block is 1. In practice, if the UAV track traversal is directly performed on the passable area, the number of tracks obtained at this time is huge. In theory, the number of tracks obtained by directly traversing the passable area by the UAV track tends to infinity, which will cause the UAV track traversal process to consume a lot of computing resources. When the UAV track traversal is performed on the passable area after voxelization, since the passable area is gridded and the traversal conditions are set, the traversal difficulty and computer resource consumption during the traversal process are greatly reduced.
[0081] Step 106: determine the track confidence corresponding to each candidate track information in the candidate track information set.
[0082] In some embodiments, the execution entity may determine the track confidence corresponding to each candidate track information in the candidate track information set.
[0083] Among them, the track confidence represents the confidence that the candidate track information corresponds to a track that is available to the drone. In practice, during the drone track traversal process, only the number of passes through the path starting point, path end point and unit voxel block is limited, but some of the candidate track information obtained through the traversal corresponds to the track. In actual situations, the drone will not fly along this track. Therefore, it is necessary to combine the track confidence to score for subsequent filtering.
[0084] Optionally, the candidate track information in the candidate track information set includes: a voxel block position sequence, wherein the voxel block position represents the position of a unit voxel block passed by the track corresponding to the candidate track information in the above-mentioned traversable area after voxelization.
[0085] In some optional implementations of some embodiments, determining the track confidence corresponding to each candidate track information in the candidate track information set may include the following steps:
[0086] In the first step, track features are extracted from the voxel block position sequence included in the candidate track information to generate track features.
[0087] In practice, the execution entity may extract track features from the voxel block position sequence included in the candidate track information through an RNN (Recurrent Neural Network) model to generate track features.
[0088] In the second step, the track confidence for the candidate track information is generated through the track classification model and the track feature extraction model.
[0089] In practice, the track feature extraction model can be a two-classification model. The classification labels output by the track feature extraction model can be: a first classification label and a second classification label. Among them, the first classification label represents that the candidate track information corresponds to a track that the drone can fly. The second classification label represents that the candidate track information corresponds to a track that the drone cannot fly. Specifically, when the classification label is the first classification label, the track confidence is equal to the label confidence corresponding to the first classification label. When the classification label is the second classification label, the track confidence is equal to the negative label confidence corresponding to the first classification label.
[0090] Step 107, selecting candidate track information whose corresponding track confidence meets the screening condition from the candidate track information set as target track information, and obtaining the target track information set.
[0091] In some embodiments, the above-mentioned execution entity can filter out candidate track information whose corresponding track confidence meets the filtering conditions from the candidate track information set as the target track information, and obtain the target track information set. Among them, the filtering condition can be that the track confidence is greater than or equal to K. Specifically, the value range of K is (0, 1]. In practice, the closer the value of K is to 0, the more target track information is filtered out, and the more accurate the hot spot area location information is obtained. The value of K can be adjusted in combination with the actual available computing resources.
[0092] Step 108, determining the hotspot area in the traversable area according to the target track information set to generate the hotspot area position information.
[0093] In some embodiments, the execution subject determines the hotspot area in the passable area based on the target track information set to generate the hotspot area location information. The hotspot area location information represents an area with more track segments containing the track corresponding to the target track information. In practice, for example, multiple tracks pass through area A, so area A can be used as the hotspot area corresponding to the hotspot area location information.
[0094] In some optional implementations of some embodiments, the execution subject determines the hotspot area in the traversable area according to the target track information set to generate the hotspot area location information, which may include the following steps:
[0095] In the first step, according to the target track information in the target track information set, the heat value of the unit voxel block in the above-mentioned passable area after voxelization is updated to obtain the passable area after the heat value is updated.
[0096] In practice, the heat value corresponding to the unit voxel block in the traversable area after voxelization is initialized to 0. When the unit voxel block is a unit voxel block passed by the track, the corresponding heat value is +1. In addition, the heat value can also be updated in a decaying manner according to the distance between the unit voxel block and the track. For example, if unit voxel block A is adjacent to unit voxel block B passed by the track, the heat value corresponding to unit voxel block B is +1. The heat value corresponding to unit voxel block A can be +0.9.
[0097] In the second step, the area where the unit voxel blocks whose corresponding heat values meet the hot spot area screening conditions are located in the passable area after the above-mentioned heat value is updated is determined as the hot spot area in the above-mentioned passable area to generate the hot spot area location information.
[0098] The hotspot area screening condition is: the sum of the corresponding thermal values of each unit voxel block contained in the area is greater than the preset thermal value. The hotspot area position information represents the position of the hotspot area in the above-mentioned passable area.
[0099] Step 109: Determine a set of candidate device layout locations based on the hotspot area location information.
[0100] In some embodiments, the above-mentioned execution entity can determine a set of candidate device layout locations based on the hot spot area location information.
[0101] The candidate device layout position represents the layout position of the candidate drone countermeasure device. In practice, the hotspot area corresponding to the hotspot area location information may be a suspended area, where drone countermeasure devices cannot be directly arranged. Therefore, the above-mentioned execution entity may use the area adjacent to the hotspot area location corresponding to the hotspot area location information, on the building or in the building as the candidate device layout position set.
[0102] Step 110: Determine a device layout position information set according to the candidate device layout position set and the target device information set.
[0103] In some embodiments, the execution entity may determine a device layout position information set based on a candidate device layout position set and a target device information set.
[0104] Among them, the target device information in the above-mentioned target device information set characterizes the device parameters of the drone countermeasure device. In practice, the device parameters may include: device type, device coverage angle and other parameters. Since different devices have different coverage angles, it is necessary to further combine the target device information and the device layout position information to further determine the optimal layout position of the drone countermeasure device corresponding to each target device information. Specifically, the above-mentioned execution entity can determine the optimal layout position of the drone countermeasure device corresponding to each target device information as the device layout position information by matching the candidate device layout position with the target device information, and obtain the above-mentioned device layout position information set.
[0105] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the equipment layout method for drone countermeasure equipment of some embodiments of the present disclosure, the effective deployment of drone countermeasure equipment is realized, the existence of blind spots is reduced as much as possible, and the effective countermeasure of drones is realized. Specifically, the reason for the inability to effectively counter the drone is that when the control area is relatively complex, it is difficult to effectively and comprehensively deploy the drone countermeasure equipment, so that there are uncovered areas, and thus the drone cannot be effectively countered. Based on this, the equipment layout method for drone countermeasure equipment of some embodiments of the present disclosure, first, obtain a target plane map sequence, wherein the target plane map in the above target plane map sequence is an area map collected at continuous moments and containing buildings in the target area. Secondly, according to the above target plane map sequence, the above target area is reconstructed into a three-dimensional building to obtain a three-dimensional area map, and the reconstruction of the three-dimensional building is realized by combining the two-dimensional plane map, which is less difficult to implement than the three-dimensional reconstruction method based on point cloud data. Then, according to the above three-dimensional area map, the passable area is determined, wherein the above passable area represents the three-dimensional area where the drone can pass. In this way, the three-dimensional area where the drone can pass is obtained. Furthermore, the above-mentioned traversable area is spatially voxelized to generate a traversable area after voxelization. By voxelization, a dimensionality reduction representation of the traversable area is achieved, reducing the amount of subsequent data processing. In addition, the above-mentioned traversable area after voxelization is traversed by a drone track to obtain a candidate track information set. By traversal, the track that the drone may pass through is determined. In addition, the track confidence corresponding to each candidate track information in the above-mentioned candidate track information set is determined. Then, the candidate track information whose corresponding track confidence meets the screening conditions is filtered out from the above-mentioned candidate track information set as the target track information to obtain the target track information set. By combining the track confidence, the tracks with lower confidence are filtered. Next, based on the above-mentioned target track information set, the hot spot area in the above-mentioned traversable area is determined to generate the hot spot area location information. In this way, the key area passed by the track is obtained. Further, based on the above-mentioned hot spot area location information, the candidate equipment layout location set is determined. Finally, according to the candidate device layout location set and the target device information set, the device layout location information set is determined, wherein the target device information in the above target device information set represents the device parameters of the drone countermeasure device. In this way, the effective deployment of drone countermeasure devices is achieved, and then the effective control and countermeasure of drones in the target area is achieved.
[0106] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a device layout device for a drone countermeasure device. These device embodiments are similar to Figure 1Corresponding to the method embodiments shown, the device layout apparatus for drone countermeasure equipment can be specifically applied to various electronic devices.
[0107] like Figure 2 As shown, some embodiments of the equipment layout device 200 for drone countermeasure equipment include: an acquisition unit 201, a three-dimensional building reconstruction unit 202, a first determination unit 203, a spatial voxelization unit 204, a drone track traversal unit 205, a second determination unit 206, a screening unit 207, a third determination unit 208, a fourth determination unit 209 and a fifth determination unit 210. Among them, the acquisition unit 201 is configured to acquire a target plane map sequence, wherein the target plane map in the above target plane map sequence is an area map collected at continuous moments and containing buildings in the target area; the three-dimensional building reconstruction unit 202 is configured to perform three-dimensional building reconstruction on the above target area according to the above target plane map sequence to obtain a three-dimensional area map; the first determination unit 203 is configured to determine a traversable area according to the above three-dimensional area map, wherein the traversable area represents a three-dimensional area where a drone can traverse; the spatial voxelization unit 204 is configured to perform spatial voxelization on the above traversable area to generate a voxelized traversable area; the drone track traversal unit 205 is configured to perform drone track traversal on the above voxelized traversable area to obtain a candidate track information set; the second determination unit 206 is configured to determine the above candidate track information set The track confidence corresponding to each candidate track information in the set; the screening unit 207 is configured to screen out the candidate track information whose corresponding track confidence meets the screening condition from the above-mentioned candidate track information set, as the target track information, to obtain the target track information set; the third determination unit 208 is configured to determine the hot spot area in the above-mentioned passable area according to the above-mentioned target track information set to generate the hot spot area location information; the fourth determination unit 209 is configured to determine the candidate device layout position set according to the above-mentioned hot spot area location information; the fifth determination unit 210 is configured to determine the device layout position information set according to the candidate device layout position set and the target device information set, wherein the target device information in the above-mentioned target device information set represents the device parameters of the drone counter-measure device. It can be understood that the various units recorded in the device layout device 200 of the drone counter-measure device and the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device layout apparatus 200 for drone countermeasure equipment and the units contained therein, and will not be repeated here.
[0108] Reference below Figure 3, which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0109] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. Various programs and data required for the operation of the electronic device 300 are also stored in the random access memory 303. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other via a bus 304. An input / output interface 305 is also connected to the bus 304.
[0110] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0111] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.
[0112] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0113] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0114] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains a target plane map sequence, wherein the target plane map in the above-mentioned target plane map sequence is an area map collected at continuous moments and containing buildings in the target area; performs three-dimensional building reconstruction on the above-mentioned target area according to the above-mentioned target plane map sequence to obtain a three-dimensional area map; determines a traversable area according to the above-mentioned three-dimensional area map, wherein the above-mentioned traversable area represents a three-dimensional area where a drone can traverse; spatially voxelizes the above-mentioned traversable area to generate a voxelized traversable area; and performs drone track traversal on the above-mentioned voxelized traversable area. history, obtain a candidate track information set; determine the track confidence corresponding to each candidate track information in the above candidate track information set; filter out the candidate track information whose corresponding track confidence meets the filtering conditions from the above candidate track information set as the target track information, and obtain the target track information set; according to the above target track information set, determine the hot spot area in the above passable area to generate the hot spot area location information; according to the above hot spot area location information, determine the candidate device layout location set; according to the candidate device layout location set and the target device information set, determine the device layout location information set, wherein the target device information in the above target device information set represents the device parameters of the drone counter-device.
[0115] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0116] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0117] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a three-dimensional building reconstruction unit, a first determination unit, a spatial voxelization unit, a drone track traversal unit, a second determination unit, a screening unit, a third determination unit, a fourth determination unit, and a fifth determination unit. Among them, the names of these units do not constitute limitations on the units themselves in certain circumstances. For example, the screening unit may also be described as "a unit that screens out candidate track information whose corresponding track confidence meets the screening conditions from the above-mentioned candidate track information set as target track information, and obtains a target track information set".
[0118] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0119] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.
Claims
1. A device layout method for drone countermeasure equipment, include: Acquire a target plane map sequence, wherein the target plane maps in the target plane map sequence are area maps collected at consecutive moments and containing buildings in the target area; According to the target plane map sequence, three-dimensional building reconstruction is performed on the target area to obtain a three-dimensional area map; Determine a traversable area according to the three-dimensional area map, wherein the traversable area represents a three-dimensional area that the drone can traverse; Performing spatial voxelization on the traversable area to generate a voxelized traversable area; Traversing the voxelized traversable area with UAV tracks to obtain a candidate track information set; Determining a track confidence corresponding to each candidate track information in the candidate track information set; Filter out candidate track information whose corresponding track confidence meets the filtering condition from the candidate track information set as target track information to obtain a target track information set; Determine a hotspot area in the traversable area according to the target track information set to generate hotspot area position information; Determine a set of candidate device layout locations according to the hotspot area location information; A device layout position information set is determined according to the candidate device layout position set and the target device information set, wherein the target device information in the target device information set represents device parameters of the drone countermeasure device.
2. The method according to claim 1, in, The determining of the traversable area according to the three-dimensional area map includes: Determining a map boundary of the three-dimensional area map; Determining building high points in the three-dimensional area map; determining a building low point in the three-dimensional area map; Generate a target three-dimensional area according to the map boundary, the building high point and the building low point, wherein the cross-sectional boundary of the horizontal cross-section of the target three-dimensional area is the map boundary, and the area height of the target three-dimensional area is the distance difference between the building high point and the building low point; An area difference between the target three-dimensional area and the three-dimensional area map is determined as the traversable area.
3. The method according to claim 2, in, The spatial voxelization of the traversable area to generate a voxelized traversable area includes: Divide the passable area according to the restricted flight altitude range corresponding to the drone to obtain at least one sub-passable area; For each sub-traversable area of the at least one sub-traversable area, the following spatial voxelization step is performed: Determining a relative position of the sub-traversable area in the traversable area; Mapping to obtain a voxel granularity according to the relative position, wherein the voxel granularity represents the size of a unit voxel block used for spatial voxelization; Performing octree voxelization on the sub-traversable area at the voxel granularity to obtain a voxelized sub-traversable area; The obtained voxelized traversable areas are spliced to obtain the voxelized traversable areas.
4. The method according to claim 3, in, The step of performing drone track traversal on the voxelized traversable area to obtain a candidate track information set includes: With the target condition group as a conditional constraint, the UAV track traverses the voxelized traversable area to obtain a set of candidate track information, wherein the target condition group includes: a first target condition, a second target condition, and a third target condition. The first target condition is that the core area in the target area is the end point of the path, the second target condition is that any unit voxel block on the area boundary of the voxelized traversable area is the starting point of the path, and the third target condition is that the number of times the candidate track information passes through each unit voxel block is 1.
5. The method according to claim 4, in, The candidate track information in the candidate track information set includes: a voxel block position sequence, wherein the voxel block position represents the position of the unit voxel block passed by the track corresponding to the candidate track information in the traversable area after voxelization; and The determining of the track confidence corresponding to each candidate track information in the candidate track information set includes: Extracting track features from the voxel block position sequence included in the candidate track information to generate track features; A track confidence for the candidate track information is generated through a track classification model and the track feature extraction model.
6. The method according to claim 5, in, The step of determining a hotspot area in the traversable area according to the target track information set to generate hotspot area position information includes: According to the target track information in the target track information set, the heat value of the unit voxel block in the voxelized traversable area is updated to obtain the traversable area after the heat value is updated; The area where the unit voxel blocks whose corresponding heat values meet the hot spot area screening condition are located in the passable area after the heat value is updated is determined as the hot spot area in the passable area to generate the hot spot area position information.
7. The method according to claim 6, in, The step of reconstructing the target area into three-dimensional buildings according to the target plane map sequence to obtain a three-dimensional area map comprises: For each target plane map in the target plane map sequence, target detection is performed on the target plane map to generate a building information group, wherein the building information in the building information group includes: a building image, a building shadow image, and a first building image feature; According to the first building image feature included in the building information, clustering processing is performed on the building information in the obtained building information group set to generate a building information cluster set, wherein the building information cluster in the building information cluster set includes: at least one building information, and at least one building information included in the building information cluster corresponds to the same building; For each building information cluster in the building information cluster set, the following three-dimensional building reconstruction steps are performed: By means of a coding network, image coding is performed on the building image included in each building information in the building information cluster to generate a second image feature, thereby obtaining a second image feature set; Generate a third image feature set according to the three-dimensional feature extraction network and the second image feature set; Generate a candidate three-dimensional building model for the building corresponding to the building information cluster according to the decoding network and the third image feature set, wherein the encoding network, the three-dimensional feature extraction network and the decoding network are included in a three-dimensional building reconstruction network; According to the target image acquisition information and the building shadow image included in the building information in the building information cluster, the candidate three-dimensional building model is model projected to obtain the building parameters of the building corresponding to the building information cluster, wherein the target image acquisition information is the image acquisition information of the target plane map corresponding to the building information cluster, and the target image acquisition information includes: image acquisition altitude angle and sun altitude angle; generating a blank map, wherein the map scale of the blank map is consistent with the map size of the target planar map in the target planar map sequence; According to the building parameters corresponding to the candidate building three-dimensional models and the map scale corresponding to the blank map, the obtained set of candidate building three-dimensional models is projected onto the blank map to obtain the three-dimensional area map.
8. A device layout device for drone countermeasure equipment, include: An acquisition unit is configured to acquire a target plane map sequence, wherein the target plane maps in the target plane map sequence are area maps collected at consecutive moments and containing buildings in the target area; A three-dimensional building reconstruction unit is configured to perform three-dimensional building reconstruction on the target area according to the target plane map sequence to obtain a three-dimensional area map; A first determining unit is configured to determine a traversable area according to the three-dimensional area map, wherein the traversable area represents a three-dimensional area where the drone can traverse; A spatial voxelization unit, configured to perform spatial voxelization on the traversable area to generate a voxelized traversable area; A drone track traversal unit is configured to perform drone track traversal on the voxelized traversable area to obtain a candidate track information set; A second determining unit is configured to determine a track confidence corresponding to each candidate track information in the candidate track information set; A screening unit is configured to screen out candidate track information whose corresponding track confidence meets the screening condition from the candidate track information set as target track information to obtain a target track information set; a third determining unit, configured to determine a hotspot area in the traversable area according to the target track information set, so as to generate hotspot area position information; A fourth determining unit is configured to determine a set of candidate device layout locations according to the hotspot area location information; The fifth determining unit is configured to determine a device layout position information set according to the candidate device layout position set and the target device information set, wherein the target device information in the target device information set represents device parameters of the drone countermeasure device.
9. An electronic device, include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.
10. A computer readable medium having a computer program stored thereon, in, When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Distributed deployment method and system for three-dimensional wireless communication network of unmanned aerial vehicle
CN121665253A
