Monitoring control method and apparatus, and monitoring system

Abstract

The present application relates to a monitoring control method and apparatus, and a monitoring system. The method comprises: by means of radar, acquiring a target region in a monitored region; on the basis of the target region and a preset hot zone in the monitored region, determining an image detection requirement; and when it is determined that image detection is required, acquiring image data of the monitored region, and performing image detection on the image data, wherein the target region is a region in which there is at least one target object, and the image detection requirement comprises image detection being required and image detection being not required. In the method, before image detection is performed, an image detection requirement is pre-determined on the basis of a target region and a preset hot zone in a monitored region, so as to trigger image detection when it is determined that image detection is required, thereby reducing the trigger frequency of image detection, and accordingly reducing the power consumption of a system.

Description

Monitoring and control methods, devices and monitoring systems

[0001] Related applications

[0002] This application claims priority to Chinese patent application filed on August 27, 2024, with application number 2024111870505, entitled "Monitoring and Control Method, Apparatus and Monitoring System", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of monitoring technology, and in particular to a monitoring and control method, device and monitoring system. Background Technology

[0004] With the development of technology, monitoring systems are being used more and more in people's daily production, life and study.

[0005] The monitoring system includes radar and camera equipment. Radar is used to sense changes in the environment, and camera equipment is used to acquire image data. In related technologies, radar acts as a trigger source, which, upon detecting the presence of a target object in the monitored environment, triggers the camera equipment to perform image detection on the acquired image data, such as artificial intelligence (AI) detection, to determine the type of target object.

[0006] However, in practical applications, the relevant technologies frequently trigger image detection, thereby increasing system power consumption. Summary of the Invention

[0007] Therefore, it is necessary to provide a monitoring and control method, device, and monitoring system to address the aforementioned technical problems.

[0008] In a first aspect, this application provides a monitoring and control method applied to a camera device, comprising:

[0009] The target area is acquired through radar within the monitored area; wherein, the target area is an area where at least one target object exists.

[0010] Image detection requirements are determined based on preset hot zones in the target area and the monitoring area; among which, image detection requirements include those that require image detection and those that do not require image detection.

[0011] If image detection is required, acquire image data of the monitored area and perform image detection on the image data.

[0012] In one embodiment, acquiring the target area within the monitored area includes:

[0013] Acquire point cloud data of each target object in the monitoring area determined by radar;

[0014] The target area is determined based on the point cloud data of each target object.

[0015] In one embodiment, determining the target region based on the point cloud data of each target object includes:

[0016] Based on the preset transformation relationship, the point cloud data of each target object is transformed to the image coordinate system to obtain the transformed pixel coordinate system point cloud data of each target object;

[0017] The target region is determined based on the point cloud data of the pixel coordinate system after the transformation of each target object.

[0018] In one embodiment, determining image detection requirements based on preset hot zones in the target area and the monitoring area includes:

[0019] Obtain the intersection information between the target area and the preset hot zone;

[0020] Image detection requirements are determined based on intersection information.

[0021] In one embodiment, the intersection information includes the intersection-union ratio of the target region and a preset hot zone; determining the image detection requirements based on the intersection information includes:

[0022] If the intersection-union ratio is greater than or equal to a preset threshold, the image detection requirement is determined to be that image detection is required.

[0023] If the cross-union ratio is less than a preset threshold, the image detection requirement is determined to be no image detection required.

[0024] In one embodiment, the method further includes:

[0025] Obtain the false trigger ratio of image detection within a preset historical time period;

[0026] The target operating mode of the radar is determined based on the false trigger ratio and fed back to the radar; the target operating mode includes a high power mode and a low power mode.

[0027] When the target's operating mode is high power mode, perform the step of acquiring the target area in the monitored area via radar.

[0028] In one embodiment, determining the radar's target operating mode based on the false trigger ratio includes:

[0029] If the false trigger ratio is greater than or equal to the preset ratio, the target working mode is determined to be the high power consumption mode;

[0030] If the false trigger ratio is less than the preset ratio, the target operating mode is determined to be the low power mode.

[0031] In one embodiment, the method further includes:

[0032] When the target is in low power mode, the radar will be used to obtain the initial detection results of whether there is a target object in the monitored area.

[0033] If the initial inspection results indicate the presence of a target object, the steps of acquiring image data of the monitored area and performing image detection on the image data are executed.

[0034] Secondly, this application also provides a monitoring and control device, comprising:

[0035] The area acquisition module is used to acquire target areas within the monitored area via radar; wherein, the target area is an area where at least one target object exists;

[0036] The requirement determination module is used to determine image detection requirements based on preset hot zones in the target area and the monitoring area; among which, image detection requirements include those that require image detection and those that do not require image detection.

[0037] The image detection module is used to acquire image data of the monitored area and perform image detection on the image data when it is determined that image detection is required.

[0038] In one embodiment, the region acquisition module includes:

[0039] The data acquisition submodule is used to acquire point cloud data of each target object in the monitoring area determined by radar.

[0040] The region determination submodule is used to determine the target region based on the point cloud data of each target object.

[0041] In one embodiment, the region determination submodule includes:

[0042] The data conversion unit is used to convert the point cloud data of each target object to the image coordinate system according to the preset conversion relationship, so as to obtain the converted pixel coordinate system point cloud data of each target object.

[0043] The region determination unit is used to determine the target region based on the pixel coordinate system point cloud data of each target object after transformation.

[0044] In one embodiment, the demand determination module includes:

[0045] The intersection information submodule is used to obtain the intersection information between the target area and the preset hot zone;

[0046] The requirement determination submodule is used to determine image detection requirements based on intersection information.

[0047] In one embodiment, the intersection information includes the intersection-to-union ratio of the target area and the preset hot zone; the demand determination submodule includes:

[0048] The first detection unit is used to determine that image detection is required when the cross-union ratio is greater than or equal to a preset threshold.

[0049] The second detection unit is used to determine that image detection is not required when the cross-union ratio is less than a preset threshold.

[0050] In one embodiment, the above-described apparatus further includes:

[0051] The accidental touch acquisition module is used to acquire the proportion of accidental triggers in image detection within a preset historical time period;

[0052] The mode determination module is used to determine the target operating mode of the radar based on the false trigger ratio and feed it back to the radar; the target operating mode includes a high power mode and a low power mode.

[0053] The high-power mode module is used to perform the step of acquiring the target area in the monitoring area via radar when the target's operating mode is high-power mode.

[0054] In one embodiment, the pattern determination module includes:

[0055] The high-power submodule is used to determine the target operating mode as high-power mode when the false trigger ratio is greater than or equal to a preset ratio.

[0056] The low-power submodule is used to determine the target operating mode as low-power mode when the false trigger ratio is less than the preset ratio.

[0057] In one embodiment, the above-described apparatus further includes:

[0058] The low-power mode module is used to obtain the initial detection result of whether there is a target object in the monitoring area through radar when the target's working mode is low-power mode.

[0059] The image detection module is used to perform image data acquisition and image detection on the monitored area when the initial detection result indicates the presence of a target object.

[0060] Thirdly, this application also provides a monitoring system, including a camera device and a radar. The camera device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above methods.

[0061] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the disclosed drawings without creative effort.

[0063] Figure 1 is a schematic diagram of the monitoring system in one embodiment;

[0064] Figure 2 is a flowchart of a monitoring and control method in one embodiment;

[0065] Figure 3 is a schematic diagram of a monitoring area in one embodiment;

[0066] Figure 4 is a schematic diagram of the process of obtaining the target area in the monitoring area in one embodiment;

[0067] Figure 5 is a flowchart illustrating the process of determining the target area in one embodiment;

[0068] Figure 6 is a flowchart illustrating the process of determining image detection requirements in one embodiment;

[0069] Figure 7 is a schematic diagram of the point cloud data conversion process in one embodiment;

[0070] Figure 8 is a flowchart illustrating the process of determining image detection requirements in another embodiment;

[0071] Figure 9 is a flowchart illustrating the monitoring and control method in another embodiment;

[0072] Figure 10 is a flowchart illustrating the process of determining the target operating mode of a radar in one embodiment;

[0073] Figure 11 is a flowchart of the monitoring and control method in another embodiment;

[0074] Figure 12 is a flowchart of the monitoring and control method in another embodiment;

[0075] Figure 13 is an interactive schematic diagram of the monitoring and control method in one embodiment;

[0076] Figure 14 is a structural block diagram of the monitoring and control device in one embodiment. Detailed Implementation

[0077] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0078] The monitoring and control method provided in this application embodiment can be applied to the monitoring system shown in Figure 1. The monitoring system 100 includes a radar 101 and a camera device 102 that communicate with each other. The radar 101 collects radar data to sense environmental changes in the monitored area, determine whether a target object exists in the monitored area, and identify the area containing at least one target object as the target area. The camera device 102 acquires image data of the monitored area and performs image detection on the image data to determine the type of target object. The camera device 102 can acquire the target area determined by the radar 101, determine image detection requirements based on the target area and preset hot zones in the monitored area, and acquire and perform image detection on the image data when image detection is required.

[0079] The aforementioned radar can be a two-dimensional (2D) scanning lidar or a three-dimensional (3D) scanning lidar.

[0080] In this embodiment of the application, the monitoring system 100 may be an integrated device that combines radar 101 and camera equipment 102.

[0081] Those skilled in the art will understand that the structure shown in Figure 1 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the monitoring system to which the present application is applied. A specific monitoring system may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0082] In one embodiment, as shown in FIG2, a monitoring and control method is provided. Taking the application of this method to the camera device in FIG1 as an example, the method includes the following steps:

[0083] S210. Acquire the target area in the monitoring area through radar; wherein, the target area is an area where at least one target object exists.

[0084] The monitoring area refers to the spatial area covered by the monitoring system, typically the area covered by the camera equipment in the system. The target area is the area where the target object is located within the monitoring area. For example, the target area may include one target object or multiple target objects.

[0085] Optionally, the camera communicates with the radar to directly acquire the area within the monitoring area determined by the radar where at least one target object exists, i.e., the target area. The camera can also determine the target area within the monitoring area based on radar data collected by the radar.

[0086] The radar is equipped with a microcontroller unit (MCU), which can collect radar data in the monitoring area to determine whether a target object exists in the monitoring area based on the radar data, and further determine the location of the target object in the monitoring area if the target object exists.

[0087] For example, radar data can be point cloud data. The MCU / camera device can determine whether a target object exists in the monitored area based on whether the point cloud data changes between adjacent acquisition times. If a change occurs, the presence of a target object in the monitored area is determined; otherwise, the absence of a target object is determined. After determining that a target object exists in the monitored area, the MCU / camera device can identify the portion of the point cloud data whose position has changed relative to the point cloud data at a later acquisition time, and define the area containing this portion of point cloud data within the monitored area as the target area. This point cloud data, acquired by radar, is a three-dimensional data representation composed of a large number of points, each with defined coordinates in three-dimensional space (typically X, Y, and Z coordinates).

[0088] S220. Determine image detection requirements based on preset hot zones in the target area and the monitoring area.

[0089] The preset hotspots within the monitoring area are pre-defined regions of interest / concern within the monitoring area. Image detection requirements characterize whether image detection is necessary, including whether it is required or not. For example, image detection can be AI-based, used to determine the location, type, and other information of a target object.

[0090] In practical applications, as shown in Figure 3, the monitored area M (the fan-shaped area in the figure) is relatively large, while the user only focuses on a local area within the monitored area M (i.e., the preset hot zone H, the hexagonal area in the figure). Triggering image detection based on target objects outside the preset hot zone H is meaningless and, in fact, increases system power consumption and reduces the monitoring system's battery life due to frequent image detection triggers. Therefore, the need for image detection can be determined based on the positional relationship between the target area and the preset hot zone within the monitored area.

[0091] Optionally, the camera device can read preset hot zones in the monitored area and determine image detection requirements based on the positional relationship between the target area and the preset hot zones. For example, a user can select / set an area of ​​interest in the presented monitored area through a terminal device associated with the camera device (an application that logs into and controls the camera device). The camera device will then store the user-selected / set area as a preset hot zone. The positional relationship between the target area and the preset hot zone can include whether the target area is located within the preset hot zone, the distance between the center points of the target area and the preset hot zone, and the intersection status of the target area and the preset hot zone.

[0092] In an optional embodiment, the positional relationship between the target area and the preset hot zone includes whether the target area is located within the preset hot zone. If the target area is located within the preset hot zone, the camera device can determine that image detection is required; otherwise, if the target area is located outside the preset hot zone, or if part of the target area is located within the preset zone and part of the target area is located outside the preset zone, the camera device can determine that image detection is not required.

[0093] S230. If it is determined that image detection is required, acquire image data of the monitored area and perform image detection on the image data.

[0094] Optionally, when it is determined that image detection is required, the camera device can acquire image data of the monitored area collected by the camera and perform image detection on the image data. The image data used for image detection may be acquired at the same time as the radar data used to determine whether a target object exists in the monitored area, or it may be acquired at a different time.

[0095] For example, the camera device includes a main control chip and a camera. The main control chip can acquire image data of the monitored area captured by the camera and perform AI detection on the image data to determine the type of target object in the image data for subsequent processing. For example, if the type of the target object is a pre-set monitoring type, an alarm will be triggered or a recorded video file will be generated.

[0096] In this embodiment, a target area within a monitoring zone is acquired via radar. Image detection requirements are determined based on the target area and preset hot zones within the monitoring zone. If image detection is required, image data of the monitoring zone is acquired and image detection is performed on the image data. The target area is an area containing at least one target object. Image detection requirements include those requiring image detection and those not requiring image detection. In this method, before performing image detection, the image detection requirements are pre-judged based on the target area and preset hot zones within the monitoring zone. This allows image detection to be triggered if it is determined that it is required, reducing the frequency of image detection triggering and consequently reducing system power consumption.

[0097] The target area within the monitoring area can be determined based on point cloud data of the target object acquired by radar. Therefore, in one embodiment, as shown in Figure 4, the acquisition of the target area within the monitoring area via radar in S210 includes:

[0098] S410. Acquire point cloud data of each target object in the monitoring area determined by radar.

[0099] Optionally, the camera communicates with the radar to directly acquire point cloud data of each target object within the monitoring area determined by the radar. The radar can identify the portion of point cloud data whose position has changed relative to the point cloud data at a later acquisition time, and determine the point cloud data corresponding to different target objects from this portion of point cloud data to obtain the point cloud data for each target object.

[0100] For example, the radar can perform clustering processing on the aforementioned partial point cloud data to classify the point cloud data into one category as the point cloud data of a target object. The clustering processing includes, but is not limited to, the K-means clustering algorithm.

[0101] Optionally, the camera device can also directly acquire the aforementioned partial point cloud data determined by the radar, and then perform clustering processing on this partial point cloud data to obtain the point cloud data of each target object. The camera device can also acquire point cloud data collected by the radar at adjacent acquisition times, and based on this, determine the portion of point cloud data whose position has changed relative to the point cloud data at the later acquisition time, and then perform clustering processing on this portion of point cloud data to obtain the point cloud data of each target object.

[0102] S420. Determine the target area based on the point cloud data of each target object.

[0103] Optionally, after obtaining the point cloud data of each target object, the camera device can obtain the location of the point cloud data of each target object in the monitoring area, and obtain the target area by taking the union of the points cloud data.

[0104] In this embodiment, point cloud data of each target object in the monitoring area determined by radar is acquired, and the target area is determined based on the point cloud data of each target object. In the above method, the point cloud data of each target object in the monitoring area can accurately represent the position of the target object in the monitoring area, thus improving the accuracy and reliability of the target area determined based on the point cloud data of the target object.

[0105] The point cloud data of the target object is the point cloud data collected by the radar in radar coordinates, and the target area in the monitoring area is the position area in the image coordinate system. Based on this, in one embodiment, as shown in Figure 5, the above-mentioned S420, determining the target area based on the point cloud data of each target object, includes:

[0106] S510. Based on the preset transformation relationship, the point cloud data of each target object is transformed to the image coordinate system to obtain the transformed pixel coordinate system point cloud data of each target object.

[0107] The preset transformation relationship is used to characterize the transformation relationship between the radar coordinate system used by the radar and the image coordinate system used by the camera equipment, and can be obtained based on the intrinsic parameter matrix of the camera equipment. For example, the radar coordinate system can be a spherical coordinate system.

[0108] Optionally, after obtaining the point cloud data of the target objects, the camera device can read a pre-calibrated preset transformation relationship to transform the point cloud data of each target object in the radar coordinate system to the image coordinate system according to the preset transformation relationship, thereby obtaining the transformed pixel coordinate system point cloud data of each target object. Alternatively, the camera device can read a pre-stored intrinsic parameter matrix, calibrate the aforementioned preset transformation relationship, and perform transformation processing on the point cloud data of each target object to transform it to the image coordinate system. For example, the transformation processing may also include distortion reduction, data filtering, and other processing steps. When the point cloud data is transformed to the image coordinate system, the three-dimensional coordinates (x, y, z) of the point cloud data are mapped to the coordinates (u, v) of the pixel coordinate system point cloud data.

[0109] S520. Determine the target area based on the pixel coordinate system point cloud data of each target object after transformation.

[0110] Optionally, after the camera device obtains the pixel coordinate system point cloud data of each target object, it can extract the edge point cloud from all the converted point cloud data and take the area formed by sequentially connecting the edge point clouds as the target area.

[0111] In an optional embodiment, to simplify the conversion process, the camera device can acquire edge point clouds from all point cloud data and convert the edge point clouds to the image coordinate system according to a preset conversion relationship. The region formed by sequentially connecting the converted edge point clouds is then used as the target region. Alternatively, the camera device can acquire edge point clouds from the point cloud data of each target object, and for each target object, acquire the geometric center and contour shape of the region formed by sequentially connecting the edge point clouds. The geometric centers are then converted to the image coordinate system, and a region whose shape matches the contour shape is formed using the converted geometric center as the center, which is then used as the target region.

[0112] In this embodiment, the point cloud data of each target object is converted to an image coordinate system according to a preset conversion relationship, resulting in converted pixel coordinate system point cloud data for each target object. The target region is then determined based on this converted pixel coordinate system point cloud data. This method unifies the coordinate system between the point cloud data and the target region, improving the accuracy of the obtained target region.

[0113] To determine whether image detection is required, in one embodiment, as shown in FIG6, the above-described S220, determining the image detection requirement based on preset hot zones in the target area and the monitoring area, includes:

[0114] S610, Obtain the intersection information between the target area and the preset hot zone.

[0115] The intersection information between the target area and the preset hot zone can be determined based on the positional relationship between the target area and the preset hot zone.

[0116] Optionally, the camera device can determine the positional relationship between the target area and the preset hot zone based on the location of the target area and the location of the preset hot zone in the monitoring area, thereby obtaining the intersection information between the target area and the preset hot zone. This intersection information may include the intersection state (whether the target area and the preset hot zone intersect) or the degree of intersection (or overlap) between the target area and the preset hot zone.

[0117] For example, as shown in Figure 7, after the camera device transforms the point cloud data n of the target object in the radar coordinate system to the image coordinate system, it obtains the target region G. This allows it to obtain the preset hot zone H and the target region G, both in the image coordinate system. Furthermore, it acquires the intersection information between the target region G and the preset hot zone H, such as whether they intersect. The degree of intersection can be represented by the intersection / overlap area between the target region and the preset hot zone. Continuing with the example above, the camera device can also acquire the intersection / overlap area between the preset hot zone H and the target region G as the intersection information between the target region and the preset hot zone.

[0118] S620. Determine image detection requirements based on intersection information.

[0119] Optionally, after obtaining the intersection information between the target area and the preset hot zone, the camera device can determine whether image detection is required based on the intersection information. For example, the intersection information includes the intersection state of the target area and the preset hot zone. If the intersection information indicates that the target area and the preset hot zone do not intersect, the camera device determines that image detection is not required; conversely, if the intersection information indicates that the target area and the preset hot zone intersect, the camera device determines that image detection is required.

[0120] The degree of intersection between the target region and the preset hot zone can be characterized by the intersection-union ratio (IU / R), i.e., the intersection information includes the IU / R of the target region and the preset hot zone. Based on this, in one embodiment, as shown in FIG8, the above-mentioned S620, determining the image detection requirement based on the intersection information, includes:

[0121] S810. If the cross-union ratio is greater than or equal to a preset threshold, determine that the image detection requirement is required.

[0122] Among them, if the intersection-to-union ratio is greater than or equal to the preset threshold, it indicates that the intersection between the target area and the preset hot zone is relatively large, the target object is close to the preset hot zone, and the target object needs to be given special attention.

[0123] Optionally, after obtaining the cross-union ratio (CUI) between the target area and the preset hot zone, the camera device can compare the CUI with a preset threshold. If the CUI is greater than or equal to the preset threshold, the image detection requirement is determined to be image detection, so as to trigger image detection and determine the relevant information of the target object in the monitored area, such as its location or type.

[0124] S820. If the cross-union ratio is less than a preset threshold, determine that the image detection requirement is not required.

[0125] If the intersection-to-union ratio is less than the preset threshold, it indicates that the degree of intersection between the target area and the preset hot zone is small, the target object is far away from the preset hot zone, and the target object can be temporarily ignored.

[0126] Optionally, after obtaining the cross-union ratio (CUI) between the target area and the preset hot zone, the camera device can compare the CUI with a preset threshold. If the CUI is less than the preset threshold, it can be determined that the image detection requirement is not required, and image detection does not need to be triggered.

[0127] In this embodiment, intersection information between the target region and a preset hotspot is obtained to determine image detection requirements. The intersection information includes the intersection-union ratio (IUR) between the target region and the preset hotspot. Specifically, if the IUR is greater than or equal to a preset threshold, the image detection requirement is determined to be that image detection is necessary; if the IUR is less than the preset threshold, the image detection requirement is determined to be that image detection is not necessary. In this method, the intersection information between the target region and the preset hotspot accurately reflects their positional relationship, improving the accuracy of the determined image detection requirements. Furthermore, obtaining the IUR between regions is convenient and quick, simultaneously improving the efficiency of determining image detection requirements.

[0128] To ensure that the target area determined by radar meets accuracy requirements and facilitates subsequent determination of intersection information with preset hot zones, the radar needs to operate in a high-power mode to obtain high-precision radar data (e.g., within 0.5m) to determine the target area. However, the high-power mode will increase the power consumption of the entire monitoring system.

[0129] Research has found that in some application scenarios, radar in high-power mode determines the target area and triggers image detection when the target area is determined to require it. This method has lower overall power consumption. In other application scenarios, radar in low-power mode determines the presence of a target object and triggers image detection when the object is confirmed to be present. This method also has lower overall power consumption. The detailed analysis process is as follows:

[0130] For example, assuming the normal operating time of the camera equipment in the monitoring system is 20 seconds per unit, then 24 * 3600 / 20 equals 4320 units per day. The camera equipment performs image detection for 100 units per day, of which 30 units are falsely triggered. The Wi-Fi module in the camera equipment is used to determine whether to wake up the main control chip for image detection. The overall power consumption calculation process for the monitoring system's radar in both high-power and low-power modes is as follows: W radar低功耗 =W Soc工作 *100+W Soc待机 **4220+W Wifi工作 100+W Wifi待机 **4220+W radarL *4320 W radar高功耗 =W Soc工作 *30+W Soc待机 *4290+W Wifi工作 *30+W Wifi待机 *4290+W radarL *4290 +W radarH *30

[0131] Where Wradar low power and Wradar high power represent the overall power consumption of the monitoring system in low power mode and high power mode, respectively; WSoc working and WSoc standby represent the working power consumption and standby power consumption of the main control chip in the camera device, respectively; WWifi working and WWifi standby represent the working power consumption and standby power consumption of the Wifi module in the camera device, respectively; WradarL and WradarH represent the working power consumption in low power mode and high power mode, respectively. Δ power difference = W radar低功耗 -W radar高功耗

[0132] Wherein, Δ power difference > 0 indicates that the overall power consumption of the monitoring system in the low power mode of the radar is greater than that in the high power mode of the radar; Δ power difference = 0 indicates that the overall power consumption of the monitoring system in the low power mode of the radar is equal to that in the high power mode of the radar; Δ power difference < 0 indicates that the overall power consumption of the monitoring system in the low power mode of the radar is less than that in the high power mode of the radar.

[0133] After sorting, we get:

[0134] 30 / 4320 represents the percentage of false triggers, Q, which can be derived from the above formula:

[0135] Then Δ power consumption difference > 0, indicating that the overall power consumption of the monitoring system is lower in the high power consumption mode of the radar;

[0136] If the power consumption difference Δ is less than 0, it indicates that the overall power consumption of the monitoring system is lower in the low-power mode of the radar.

[0137] Therefore, in practical applications, the actual application scenario of the monitoring system can be determined based on the false trigger ratio of image detection, thereby determining the target operating mode of the radar to achieve different detection and control steps, thus reducing the overall power consumption of the monitoring system. In one embodiment, as shown in Figure 9, the above method further includes:

[0138] S910: Obtain the false trigger ratio of image detection within a preset historical time period.

[0139] The false trigger ratio is the percentage of false triggers in image detection out of the total number of triggers. If, after triggering image detection, the target object is detected as not being within the preset hot zone, this is called a false trigger. Conversely, if, after triggering image detection, the target object is detected as being within the preset hot zone, this is called a valid trigger.

[0140] Optionally, before executing S210 above, the camera device may obtain the total number of times image detection is triggered within a preset historical time period, as well as the number of false triggers, and obtain the proportion of false triggers in the total number of triggers to obtain the false trigger ratio of image detection within the preset historical time period. For example, the camera device may obtain the total number of times image detection is triggered M and the number of false triggers m within 24 hours or 7 days prior to the current time, thereby obtaining the false trigger ratio m / M of image detection within the preset historical time period.

[0141] S920 determines the radar's target operating mode based on the false trigger ratio and feeds it back to the radar; the target operating mode includes a high power mode and a low power mode.

[0142] The radar's target operating mode is the mode adapted to the current application environment, which can be either a high-power mode or a low-power mode. The current application environment can be determined based on the false triggering ratio of image detection. For example, a higher false triggering ratio corresponds to a high-frequency false triggering scenario in the current application environment; a lower false triggering ratio corresponds to a low-frequency false triggering scenario in the current application environment.

[0143] Optionally, the camera device determines the current application scenario based on the false triggering ratio of image detection within a preset historical time period, determines the radar operating mode corresponding to the current application scenario as the radar's target operating mode, and feeds back the target operating mode to the radar to instruct the radar to operate in the target operating mode. For example, if the camera device determines the current application scenario based on the false triggering ratio to be a high-frequency false triggering scenario, it determines the radar's target operating mode to be a high-power mode; if it determines the current application scenario based on the false triggering ratio to be a low-frequency false triggering scenario, it determines the radar's target operating mode to be a low-power mode.

[0144] S930. When the target's operating mode is high power mode, perform the step of acquiring the target area in the monitoring area through radar.

[0145] Optionally, if the camera device determines that the radar's target operating mode is a high-power mode, it can execute the steps S210-S230 above to determine the image detection requirements based on the high-precision target area and preset hot zone obtained by the radar. Then, if image detection is required, it can acquire image data of the monitored area and perform image detection on the image data.

[0146] In this embodiment, the false trigger ratio of image detection within a preset historical time period is obtained. Based on this ratio, the target operating mode of the radar is determined and fed back to the radar. This allows for the execution of the step of acquiring the target area within the monitoring area via the radar when the target operating mode is a high-power mode, and also for acquiring the target area within the monitoring area when the target operating mode is still in a high-power mode. In this method, the false trigger ratio of image detection within the preset historical time period accurately reflects the actual application scenario of the monitoring system. This allows for subsequent implementation of different control strategies based on the actual application scenario, taking into account both radar operating power consumption and image detection power consumption, thereby reducing system power consumption.

[0147] To simplify the determination of the target operating mode, in one embodiment, as shown in FIG10, the determination of the radar's target operating mode based on the false trigger ratio in S920 includes:

[0148] S1010. If the false trigger ratio is greater than or equal to the preset ratio, determine the target working mode as high power consumption mode.

[0149] Among them, if the false trigger ratio is greater than or equal to the preset ratio, it indicates that the false trigger ratio is relatively large, and the current application environment is a high-frequency false trigger scenario.

[0150] Optionally, after obtaining the false trigger ratio of image detection within a preset historical time period, the camera device can compare the false trigger ratio with the preset ratio, and if the false trigger ratio is greater than or equal to the preset ratio, determine that the target working mode is the high power consumption mode.

[0151] S1020. If the false trigger ratio is less than the preset ratio, determine the target working mode as low power mode.

[0152] Among them, if the false trigger ratio is greater than or equal to the preset ratio, it indicates that the false trigger ratio is relatively small, and the current application environment is a low-frequency false trigger scenario.

[0153] Optionally, after obtaining the false trigger ratio of image detection within a preset historical time period, the camera device can compare the false trigger ratio with the preset ratio, and if the false trigger ratio is less than the preset ratio, determine the target working mode as a low power mode.

[0154] It should be noted that the radar's high-power mode and low-power mode have different operating parameters, resulting in higher power consumption in the high-power mode compared to the low-power mode. For example, the radar's operating parameters may include frame value and chirp value.

[0155] The camera determines the radar target's operating mode as high-power mode. After feedback to the radar, the radar can then collect radar data using the high-power mode operating parameters, resulting in higher-precision radar data (e.g., within 0.5m). Conversely, if the camera determines the radar target's operating mode as low-power mode, the radar can collect radar data using the low-power mode operating parameters, resulting in lower-precision radar data (e.g., within 1m). The higher-precision radar data can be used to determine a higher-precision target area; the lower-precision radar data can be used to determine the presence of a target object.

[0156] In this embodiment, when the false triggering ratio is greater than or equal to a preset ratio, the target operating mode is determined to be a high-power mode; when the false triggering ratio is less than the preset ratio, the target operating mode is determined to be a low-power mode. In the above method, the target operating mode of the radar is determined by comparing the false triggering ratio with the preset ratio. This comparison process is convenient and quick, simplifying the determination of the target operating mode and correspondingly improving the determination efficiency and overall detection and control efficiency.

[0157] Since the radar operates in a low-power mode, in one embodiment, as shown in Figure 11, the method further includes:

[0158] S1110. When the target's operating mode is low power mode, the radar is used to obtain the initial detection results of whether there is a target object in the monitored area.

[0159] Optionally, the camera communicates with the radar. If the radar's target operating mode is determined to be low power mode, it can directly obtain the preliminary detection result of whether there is a target object in the monitoring area determined by the radar, or it can obtain the radar data collected by the radar and determine the preliminary detection result of whether there is a target object in the monitoring area based on the radar data.

[0160] For example, radar data can be point cloud data. Radar or camera equipment can determine whether a target object exists in the monitored area based on whether the point cloud data changes at adjacent acquisition times. If a change occurs, it is determined that a target object exists in the monitored area; if no change occurs, it is determined that a target object does not exist in the monitored area.

[0161] S1120. If the initial inspection result indicates the presence of a target object, proceed with the steps of acquiring image data of the monitored area and performing image detection on the image data.

[0162] Optionally, if the initial detection indicates the presence of a target object, the camera device can acquire image data of the monitored area collected by the camera and perform image detection on this image data. The image data used for image detection may be acquired at the same time as the radar data used to determine the presence of a target object in the monitored area, or it may be acquired at a different time.

[0163] For example, the camera device includes a main control chip and a camera. The main control chip can acquire image data of the monitored area captured by the camera and perform AI detection on the image data to determine the type of target object in the image data for subsequent processing. For example, if the type of the target object is a pre-set monitoring type, an alarm will be triggered or a recorded video file will be generated.

[0164] In this embodiment, when the target operating mode is low-power mode, a preliminary detection result is obtained to determine whether a target object exists in the monitored area. If the preliminary detection result indicates the presence of a target object, image data of the monitored area is acquired and image detection is performed on the image data. In the above method, when the radar's target operating mode is determined to be low-power mode, image detection is directly triggered based on the preliminary detection result to adapt to actual application scenarios, taking into account both radar operating power consumption and image detection power consumption, thereby reducing the overall system power consumption.

[0165] To facilitate understanding by those skilled in the art, the monitoring and control method provided in this application is described in detail below. As shown in Figure 12, the method may include:

[0166] S1201. Obtain the false trigger ratio of image detection within a preset historical time period;

[0167] S1202. When the false triggering ratio is greater than or equal to the preset ratio, the radar's target operating mode is determined to be high power mode; when the false triggering ratio is less than the preset ratio, the radar's target operating mode is determined to be low power mode.

[0168] S1203: The target operating mode of the radar is fed back to the radar, instructing the radar to operate according to the target operating mode;

[0169] S1204. When the target's working mode is low power mode, acquire point cloud data of each target object in the monitoring area determined by radar.

[0170] S1205. Convert the point cloud data of each target object to the image coordinate system according to the preset conversion relationship to obtain the converted point cloud data of each target object;

[0171] S1206. Determine the target area in the monitoring area where at least one target object exists based on the point cloud data after the conversion of each target object;

[0172] S1207. Obtain the crossover ratio of the target area and the preset hot zones in the monitoring area;

[0173] S1208. If the intersection-to-union ratio (IoU) is greater than or equal to a preset threshold, determine that image detection is required; if the IoU is less than the preset threshold, determine that image detection is not required.

[0174] S1209. If it is determined that image detection is required, acquire image data of the monitored area and perform image detection on the image data;

[0175] S1210. When the target working mode is low power mode, obtain the preliminary detection result of whether the target object exists in the monitoring area;

[0176] S1211. If the initial inspection result indicates the presence of a target object, acquire image data of the monitored area and perform image detection on the image data.

[0177] It should be noted that the descriptions in S1201-S1211 above can be found in the relevant descriptions in the above embodiments, and their effects are similar, so they will not be repeated here.

[0178] In an optional embodiment, as shown in Figure 13, the camera device in the monitoring system includes a main control chip and a Wi-Fi module, and the radar includes an MCU. When it is determined that the radar's target operating mode is a high-power operating mode, the data interaction process of the monitoring system is as follows:

[0179] Users select / set areas of interest within the displayed monitoring area via a terminal device associated with the camera (logged into the application controlling the camera). The main control chip normalizes the coordinates of the selected / set area of ​​interest and uses it as a preset hotspot, sending it along with camera intrinsic parameters and lens distortion parameters to the Wi-Fi module for storage. The Wi-Fi module communicates with the radar MCU. When the MCU detects a target object in the monitoring area, it sends the point cloud data collected by the radar to the Wi-Fi module. The Wi-Fi module performs coordinate transformation on the point cloud data sent by the radar to obtain the target area in the monitoring area containing at least one target object in the image coordinate system, thus determining the positional relationship between the target area and the preset area. If the intersection-over-union ratio (IoU) between the target area and the preset area is greater than or equal to a preset threshold, the Wi-Fi module sends a trigger command to the main control chip to wake it up and trigger image detection. If the IoU between the target area and the preset area is less than the preset threshold, the Wi-Fi module does not need to wake up the main control chip, and image detection is not triggered accordingly.

[0180] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0181] Based on the same inventive concept, this application also provides a monitoring and control device for implementing the monitoring and control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more monitoring and control device embodiments provided below can be found in the limitations of the monitoring and control method described above, and will not be repeated here.

[0182] In one embodiment, as shown in FIG14, a monitoring and control device is provided, including: an area acquisition module 1401, a demand determination module 1402, and an image detection module 1403, wherein:

[0183] The area acquisition module 1401 is used to acquire the target area in the monitoring area through radar; wherein, the target area is an area where at least one target object exists;

[0184] The requirement determination module 1402 is used to determine image detection requirements based on preset hot zones in the target area and the monitoring area; wherein, the image detection requirements include those that require image detection and those that do not require image detection.

[0185] The image detection module 1403 is used to acquire image data of the monitored area and perform image detection on the image data when it is determined that image detection is required.

[0186] In one embodiment, the region acquisition module 1401 includes:

[0187] The data acquisition submodule is used to acquire point cloud data of each target object in the monitoring area determined by radar.

[0188] The region determination submodule is used to determine the target region based on the point cloud data of each target object.

[0189] In one embodiment, the region determination submodule includes:

[0190] The data conversion unit is used to convert the point cloud data of each target object to the image coordinate system according to the preset conversion relationship, so as to obtain the converted pixel coordinate system point cloud data of each target object.

[0191] The region determination unit is used to determine the target region based on the pixel coordinate system point cloud data of each target object after transformation.

[0192] In one embodiment, the demand determination module 1402 includes:

[0193] The intersection information submodule is used to obtain the intersection information between the target area and the preset hot zone;

[0194] The requirement determination submodule is used to determine image detection requirements based on intersection information.

[0195] In one embodiment, the intersection information includes the intersection-to-union ratio of the target area and the preset hot zone; the demand determination submodule includes:

[0196] The first detection unit is used to determine that image detection is required when the cross-union ratio is greater than or equal to a preset threshold.

[0197] The second detection unit is used to determine that image detection is not required when the cross-union ratio is less than a preset threshold.

[0198] In one embodiment, the above-described apparatus further includes:

[0199] The accidental touch acquisition module is used to acquire the proportion of accidental triggers in image detection within a preset historical time period;

[0200] The mode determination module is used to determine the target operating mode of the radar based on the false trigger ratio and feed it back to the radar; the target operating mode includes a high power mode and a low power mode.

[0201] The high-power mode module is used to perform the step of acquiring the target area in the monitoring area via radar when the target's operating mode is high-power mode.

[0202] In one embodiment, the pattern determination module includes:

[0203] The high-power submodule is used to determine the target operating mode as high-power mode when the false trigger ratio is greater than or equal to a preset ratio.

[0204] The low-power submodule is used to determine the target operating mode as low-power mode when the false trigger ratio is less than the preset ratio.

[0205] In one embodiment, the above-described apparatus further includes:

[0206] The low-power mode module is used to obtain the initial detection result of whether there is a target object in the monitoring area through radar when the target's working mode is low-power mode.

[0207] The image detection module is used to perform image data acquisition and image detection on the monitored area when the initial detection result indicates the presence of a target object.

[0208] Each module in the aforementioned monitoring and control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0209] In one embodiment, a monitoring system is provided, including a camera device and a radar. The camera device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0210] The target area in the monitoring area is acquired by radar; wherein the target area is an area where at least one target object exists; the image detection requirements are determined based on the target area and the preset hot zones in the monitoring area; wherein the image detection requirements include those that require image detection and those that do not require image detection; if it is determined that image detection is required, image data of the monitoring area is acquired and image detection is performed on the image data.

[0211] In one embodiment, the processor further performs the following steps when executing the computer program:

[0212] Acquire point cloud data of each target object in the monitoring area determined by radar; determine the target area based on the point cloud data of each target object.

[0213] In one embodiment, the processor further performs the following steps when executing the computer program:

[0214] The point cloud data of each target object is converted to the image coordinate system according to the preset conversion relationship, and the pixel coordinate system point cloud data of each target object is obtained; the target area is determined according to the pixel coordinate system point cloud data of each target object.

[0215] In one embodiment, the processor further performs the following steps when executing the computer program:

[0216] Obtain the intersection information between the target area and the preset hot zone; determine the image detection requirements based on the intersection information.

[0217] In one embodiment, the intersection information includes the intersection-to-union ratio of the target region and the preset hot zone; the processor also performs the following steps when executing the computer program:

[0218] If the cross-union ratio (CUR) is greater than or equal to a preset threshold, the image detection requirement is determined to be that image detection is required; if the CUR is less than the preset threshold, the image detection requirement is determined to be that image detection is not required.

[0219] In one embodiment, the processor further performs the following steps when executing the computer program:

[0220] Obtain the false trigger ratio of image detection within a preset historical time period; determine the target operating mode of the radar based on the false trigger ratio and feed it back to the radar; wherein, the target operating mode includes a high power mode and a low power mode; when the target operating mode is a high power mode, perform the step of acquiring the target area in the monitoring area through the radar.

[0221] In one embodiment, the processor further performs the following steps when executing the computer program:

[0222] If the false trigger ratio is greater than or equal to the preset ratio, the target operating mode is determined to be high power mode; if the false trigger ratio is less than the preset ratio, the target operating mode is determined to be low power mode.

[0223] In one embodiment, the processor further performs the following steps when executing the computer program:

[0224] When the target is in low power mode, the radar obtains the initial detection result of whether the target object exists in the monitoring area; if the initial detection result indicates that the target object exists, the steps of acquiring image data of the monitoring area and performing image detection on the image data are executed.

[0225] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0226] The target area in the monitoring area is acquired by radar; wherein the target area is an area where at least one target object exists; the image detection requirements are determined based on the target area and the preset hot zones in the monitoring area; wherein the image detection requirements include those that require image detection and those that do not require image detection; if it is determined that image detection is required, image data of the monitoring area is acquired and image detection is performed on the image data.

[0227] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0228] Acquire point cloud data of each target object in the monitoring area determined by radar; determine the target area based on the point cloud data of each target object.

[0229] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0230] The point cloud data of each target object is converted to the image coordinate system according to the preset conversion relationship, and the pixel coordinate system point cloud data of each target object is obtained; the target area is determined according to the pixel coordinate system point cloud data of each target object.

[0231] In one embodiment, the processor further performs the following steps when executing the computer program:

[0232] Obtain the intersection information between the target area and the preset hot zone; determine the image detection requirements based on the intersection information.

[0233] In one embodiment, the intersection information includes the intersection-to-union ratio of the target region and the preset hot zone; when the computer program is executed by the processor, it also performs the following steps:

[0234] If the cross-union ratio (CUR) is greater than or equal to a preset threshold, the image detection requirement is determined to be that image detection is required; if the CUR is less than the preset threshold, the image detection requirement is determined to be that image detection is not required.

[0235] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0236] Obtain the false trigger ratio of image detection within a preset historical time period; determine the target operating mode of the radar based on the false trigger ratio and feed it back to the radar; wherein, the target operating mode includes a high power mode and a low power mode; when the target operating mode is a high power mode, perform the step of acquiring the target area in the monitoring area through the radar.

[0237] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0238] If the false trigger ratio is greater than or equal to the preset ratio, the target operating mode is determined to be high power mode; if the false trigger ratio is less than the preset ratio, the target operating mode is determined to be low power mode.

[0239] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0240] When the target is in low power mode, the radar obtains the initial detection result of whether the target object exists in the monitoring area; if the initial detection result indicates that the target object exists, the steps of acquiring image data of the monitoring area and performing image detection on the image data are executed.

[0241] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0242] The target area in the monitoring area is acquired by radar; wherein the target area is an area where at least one target object exists; the image detection requirements are determined based on the target area and the preset hot zones in the monitoring area; wherein the image detection requirements include those that require image detection and those that do not require image detection; if it is determined that image detection is required, image data of the monitoring area is acquired and image detection is performed on the image data.

[0243] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0244] Acquire point cloud data of each target object in the monitoring area determined by radar; determine the target area based on the point cloud data of each target object.

[0245] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0246] The point cloud data of each target object is converted to the image coordinate system according to the preset conversion relationship, and the pixel coordinate system point cloud data of each target object is obtained; the target area is determined according to the pixel coordinate system point cloud data of each target object.

[0247] In one embodiment, the processor further performs the following steps when executing the computer program:

[0248] Obtain the intersection information between the target area and the preset hot zone; determine the image detection requirements based on the intersection information.

[0249] In one embodiment, the intersection information includes the intersection-to-union ratio of the target region and the preset hot zone; when the computer program is executed by the processor, it also performs the following steps:

[0250] If the cross-union ratio (CUR) is greater than or equal to a preset threshold, the image detection requirement is determined to be that image detection is required; if the CUR is less than the preset threshold, the image detection requirement is determined to be that image detection is not required.

[0251] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0252] Obtain the false trigger ratio of image detection within a preset historical time period; determine the target operating mode of the radar based on the false trigger ratio and feed it back to the radar; wherein, the target operating mode includes a high power mode and a low power mode; when the target operating mode is a high power mode, perform the step of obtaining the target area in the monitoring area.

[0253] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0254] If the false trigger ratio is greater than or equal to the preset ratio, the target operating mode is determined to be high power mode; if the false trigger ratio is less than the preset ratio, the target operating mode is determined to be low power mode.

[0255] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0256] When the target is in low power mode, the radar obtains the initial detection result of whether the target object exists in the monitoring area; if the initial detection result indicates that the target object exists, the steps of acquiring image data of the monitoring area and performing image detection on the image data are executed.

[0257] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0258] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0259] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A monitoring and control method, wherein, Applied to a camera device, the method includes: The target area is acquired by radar within the monitored area; wherein, the target area is an area where at least one target object exists. Image detection requirements are determined based on the target area and preset hot zones in the monitoring area; wherein, the image detection requirements include those that require image detection and those that do not require image detection. If it is determined that image detection is required, image data of the monitored area is acquired and image detection is performed on the image data.

2. The method according to claim 1, wherein, The acquisition of the target area within the monitoring area via radar includes: Acquire point cloud data of each target object in the monitoring area determined by the radar; The target region is determined based on the point cloud data of each target object.

3. The method according to claim 2, wherein, Determining the target region based on the point cloud data of each target object includes: According to the preset transformation relationship, the point cloud data of each target object is transformed to the image coordinate system to obtain the transformed pixel coordinate system point cloud data of each target object; The target region is determined based on the pixel coordinate system point cloud data of each target object after transformation.

4. The method according to any one of claims 1-3, wherein, The step of determining image detection requirements based on the target area and preset hot zones in the monitoring area includes: Obtain the intersection information between the target area and the preset hot zone; The image detection requirement is determined based on the intersection information.

5. The method according to claim 4, wherein, The intersection information includes the intersection-to-union ratio between the target region and the preset hot zone; Determining the image detection requirement based on the intersection information includes: If the cross-union ratio is greater than or equal to a preset threshold, the image detection requirement is determined to be that image detection is required. If the cross-union ratio is less than the preset threshold, it is determined that the image detection requirement is not required.

6. The method according to claim 2 or 3, wherein, The method further includes: Obtain the false trigger ratio of image detection within a preset historical time period; The target operating mode of the radar is determined based on the false trigger ratio and fed back to the radar; wherein, the target operating mode includes a high power mode and a low power mode; When the target operating mode is high power mode, the step of acquiring the target area in the monitoring area via radar is performed.

7. The method according to claim 6, wherein, Determining the radar's target operating mode based on the false trigger ratio includes: If the false trigger ratio is greater than or equal to a preset ratio, the target operating mode is determined to be a high-power mode. If the false trigger ratio is less than the preset ratio, the target operating mode is determined to be a low-power mode.

8. The method according to claim 6, wherein, The method further includes: When the target's operating mode is low power mode, the radar is used to obtain the initial detection result of whether the target object exists in the monitoring area; If the initial detection result indicates the presence of the target object, the steps of acquiring image data of the monitored area and performing image detection on the image data are executed.

9. A monitoring and control device, wherein, The device includes: The area acquisition module is used to acquire target areas within a monitored area via radar; wherein, the target area is an area where at least one target object exists; The requirement determination module is used to determine image detection requirements based on the target area and preset hot zones in the monitoring area; wherein, the image detection requirements include those that require image detection and those that do not require image detection; The image detection module is used to acquire image data of the monitored area and perform image detection on the image data when it is determined that image detection is required.

10. The apparatus according to claim 9, wherein, The region acquisition module includes: The data acquisition submodule is used to acquire point cloud data of each target object in the monitoring area determined by the radar; The region determination submodule is used to determine the target region based on the point cloud data of each target object.

11. The apparatus according to claim 10, wherein, The region determination submodule includes: The data conversion unit is used to convert the point cloud data of each target object to the image coordinate system according to a preset conversion relationship, so as to obtain the converted pixel coordinate system point cloud data of each target object. The region determination unit is used to determine the target region based on the pixel coordinate system point cloud data of each target object after transformation.

12. The apparatus according to any one of claims 9-10, wherein, The requirement determination module includes: The intersection information submodule is used to obtain the intersection information between the target area and the preset hot zone; The requirement determination submodule is used to determine the image detection requirement based on the intersection information.

13. The apparatus according to claim 12, wherein, The intersection information includes the intersection-to-union ratio between the target area and the preset hot zone; The requirement determination submodule includes: The first detection unit is used to determine that the image detection requirement is required when the cross-union ratio is greater than or equal to a preset threshold. The second detection unit is used to determine that the image detection requirement is not required when the cross-union ratio is less than the preset threshold.

14. The apparatus according to any one of claims 10 or 11, wherein, The device further includes: The accidental touch acquisition module is used to acquire the proportion of accidental triggers in image detection within a preset historical time period; A mode determination module is used to determine the target operating mode of the radar based on the false trigger ratio and feed it back to the radar; wherein, the target operating mode includes a high power mode and a low power mode; The high-power mode module is used to perform the step of acquiring the target area in the monitoring area via radar when the target operating mode is high-power mode.

15. The apparatus according to claim 14, wherein, The pattern determination module includes: The high-power submodule is used to determine the target operating mode as a high-power mode when the false trigger ratio is greater than or equal to a preset ratio. The low-power submodule is used to determine the target operating mode as a low-power mode when the false trigger ratio is less than the preset ratio.

16. The apparatus according to claim 14, wherein, The aforementioned device further includes: The low-power mode module is used to obtain the initial detection result of whether the target object exists in the monitoring area through radar when the target working mode is low-power mode; The image detection module is used to perform the steps of acquiring image data of the monitored area and performing image detection on the image data when the initial detection result indicates that the target object exists.

17. A monitoring system comprising a camera and a radar, wherein the camera includes a memory and a processor, the memory storing a computer program, wherein... When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

Images