Target object monitoring method, device and system, electronic equipment and storage medium

Abstract

The invention discloses a target object monitoring method, device and system, electronic equipment and a storage medium, and the method comprises the steps: determining the current equipment state of the target equipment according to the obtained speed change data of the target equipment; based on the acquired target detection data, identifying the number of target objects in the target equipment in a static state, and identifying the number of target objects in the target equipment in a motion state; and determining the current state of the target object in the target equipment according to the quantity change condition of the target object in the target equipment under different equipment states. According to the embodiment of the invention, the accuracy of monitoring the target object in the target equipment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method, device, system, electronic device and storage medium for monitoring a target object. Background Art

[0002] With the development of technology and society, public safety has become a key concern. In some public places, it is usually necessary to monitor target objects to ensure public safety. For example, with the gradual rise of the online car-hailing industry, online car-hailing has become a popular choice for people to travel. At the same time, the safety of using online car-hailing has also become a hot topic of social concern. Real-time monitoring of the number of people in an online car-hailing vehicle is crucial for the safety of passengers. However, the accuracy of existing target object monitoring methods is relatively low. Summary of the Invention

[0003] Embodiments of the present invention disclose a method, device, system, electronic device and storage medium for monitoring a target object, which can improve the accuracy of monitoring the target object in the target device.

[0004] In a first aspect, embodiments of the present application disclose a method for monitoring a target object, including:

[0005] Determining the current device state of the target device according to the obtained speed change data for the target device;

[0006] Identifying the number of target objects in the target device when the device state is a stationary state, and identifying the number of target objects in the target device when the device state is a moving state based on the obtained target detection data;

[0007] Determining the current state of the target object in the target device according to the change situation of the number of target objects in the target device in different states.

[0008] In a second aspect, embodiments of the present application disclose a device for monitoring a target object, including:

[0009] A first determination unit, configured to determine the current device state of the target device according to the obtained speed change data for the target device;

[0010] An identification unit, configured to identify the number of target objects in the target device when the device state is a stationary state, and identify the number of target objects in the target device when the device state is a moving state based on the obtained target detection data;

[0011] A second determination unit, configured to determine the current state of the target object in the target device according to the change situation of the number of target objects in the target device in different device states.

[0012] As a possible implementation manner, the identification unit is specifically configured to:

[0013] If the current device state of the target device is a stationary state, then identify the number of target objects in the target device in the stationary state according to the acquired target detection data;

[0014] If it is identified that the device state changes from the stationary state to the moving state, then lock the number of the target objects in the most recent stationary state as the number of the target objects in the moving state, and identify the number of the target objects in the target device in the moving state according to the real-time acquired target detection data and the locked number of the target objects in the moving state.

[0015] As a possible implementation manner, the current state of the target object includes the current quantity state, and the second determination unit is specifically configured to:

[0016] If the number of the target objects identified based on the real-time acquired target detection data in the moving state is the same as the locked number of the target objects in the moving state, then determine that the current quantity state of the target objects in the target device is normal;

[0017] If the identified number of the target objects is different from the locked number of the target objects in the moving state, then determine that the current quantity state of the target objects in the target device is abnormal.

[0018] As a possible implementation manner, if the current quantity state of the target objects in the target device is abnormal, then the second determination unit is further specifically configured to:

[0019] If the identified number of the target objects is greater than the locked number of the target objects in the moving state, then determine the locked number of the target objects in the moving state as the current number of the target objects in the moving state, and re-determine the change situation of the number of the target objects in the moving state, so as to re-determine the current quantity state of the target objects in the target device.

[0020] As a possible implementation manner, a plurality of target positions are included in the target device, and the target object monitoring device further includes:

[0021] A third determination unit, configured to determine the confidence that the positions of the target objects in the moving state are located at the respective target positions based on the real-time acquired target detection data;

[0022] A fourth determination unit, configured to determine the distribution state of the target objects in each target position in the target device according to the confidence of each target position;

[0023] A fifth determination unit, configured to determine the current quantity state of the target objects in the target device based on the distribution state of the target objects in each target position.

[0024] As a possible implementation, the target detection data includes target point cloud data, and the third determination unit is specifically configured to:

[0025] Obtain the historical states of each target position in the target device; the historical states are determined based on the positions of each target object at each target position in the target device in a stationary state;

[0026] Based on the target point cloud data obtained in real time, determine the number of target point clouds and the point cloud signal-to-noise ratio in each target position in the target device;

[0027] According to the number of target point clouds, the point cloud signal-to-noise ratio, and the historical states, determine the confidence levels of the positions of each target object in each target position in a moving state.

[0028] As a possible implementation, the target object monitoring device further includes:

[0029] A sending unit, configured to determine that the current state of the target object in the target device is abnormal if the number of identified target objects is less than the number of target objects in a locked moving state, and send a prompt message to the target terminal; the prompt message is used to prompt a reduction in the target object.

[0030] As a possible implementation, the target object monitoring device further includes:

[0031] An obtaining unit, configured to obtain the point cloud data detected when there are no target objects in the target device;

[0032] A building unit, configured to build a spatial model corresponding to the target device based on the point cloud data; the spatial model includes each target position in the target device; the spatial model and the target positions are used to identify the change in the number of target objects in the target device.

[0033] In a third aspect, an embodiment of the present application discloses a target object monitoring system, which includes a detection device and a target device, where:

[0034] The detection device is configured to detect the speed change data of the target device, and detect the target detection data in the target device, and send the speed change data and the target detection data to the target device;

[0035] The target device is configured to determine the current device state of the target device according to the obtained speed change data; identify the number of target objects in the target device in a stationary state based on the obtained target detection data, and identify the number of target objects in the target device in a moving state; determine the current state of the target objects in the target device according to the change in the number of target objects in the target device under different device states.

[0036] Fourthly, an embodiment of the present application discloses an electronic device, which includes a processor and a memory. The memory stores a computer program, and the processor calls the computer program to implement the above-mentioned target object monitoring method.

[0037] Fifthly, an embodiment of the present application discloses a computer-readable storage medium, in which program code is stored, and the program code can be called by a processor to implement the above-mentioned target object monitoring method.

[0038] Sixthly, an embodiment of the present application discloses a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, the steps in the target object monitoring method of each embodiment of the present application are implemented.

[0039] In the embodiments of the present application, the current device state of the target device can be determined according to the obtained speed change data of the target device. Then, based on the obtained target detection data, the number of target objects in the target device in the stationary state can be identified, and the number of target objects in the target device in the moving state can be identified. Finally, according to the change situation of the number of target objects in the target device in different device states, the current state of the target objects in the target device can be determined. When the current state of the target objects in the target device is monitored in real time, the current state of the target objects can be determined according to different device states, and the current state of the target objects can be accurately judged, thereby improving the accuracy of monitoring the target objects in the target device. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0041] Figure 1 is a schematic structural diagram of a target object monitoring system provided by an embodiment of the present application.

[0042] Figure 2 is a schematic structural diagram of another target object monitoring system provided by an embodiment of the present application.

[0043] Figure 3 is a schematic flowchart of a target object monitoring method disclosed by an embodiment of the present application.

[0044] Figure 4It is a schematic flowchart of another target object monitoring method disclosed in an embodiment of the present application.

[0045] Figure 5 It is a spatial schematic diagram of a spatial model corresponding to a target vehicle disclosed in an embodiment of the present application.

[0046] Figure 6 It is a top view schematic diagram of a spatial model corresponding to a target vehicle disclosed in an embodiment of the present application.

[0047] Figure 7 It is a schematic structural diagram of a target object monitoring device disclosed in an embodiment of the present application.

[0048] Figure 8 It is a schematic structural diagram of another target object monitoring system disclosed in an embodiment of the present application.

[0049] Figure 9 It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

[0050] Figure 10 It is a schematic structural diagram of a computer-readable storage medium disclosed in an embodiment of the present application. Detailed implementation manners

[0051] The following details the implementation manners of the present application. Examples of the implementation manners are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The implementation manners described below by referring to the accompanying drawings are exemplary only for explaining the present application and should not be construed as limiting the present application.

[0052] In order to enable those skilled in the art of the present technology to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of protection of the present application.

[0053] With the development of technology and society, public safety has become a key concern. In some public places, it is usually necessary to monitor target objects to ensure public safety. For example, with the gradual rise of the online car-hailing industry, online car-hailing has become a popular choice for people to travel. At the same time, the safety of using online car-hailing has also become a hot topic of social concern. Real-time monitoring of the number of people in an online car is crucial for the safety of passengers. To detect the number of people in an online car, it is usually through millimeter-wave radar to detect the number of people in the car. However, during the driving process of a car, situations such as accelerating, decelerating, and passing over a speed bump often occur. At this time, objects in the car (such as schoolbags, mineral waters, etc.) will move in the car, causing the millimeter-wave radar to detect the movement of the objects and misdetect the objects as humans, resulting in inaccurate detection of the number of people. To solve the problem of misdetection, machine learning can be used to determine whether the detected target is a human, so as to avoid detecting moving objects as humans. However, the method of judging through machine learning requires collecting data, adding algorithm models, etc., and this method is relatively complex and has low accuracy.

[0054] To solve the above problems, in the embodiments of the present application, the current device state of the target device can be determined according to the obtained speed change data of the target device, and then based on the obtained target detection data, the number of target objects in the target device in a stationary state can be identified, and the number of target objects in the target device in a moving state can be identified. Finally, according to the change situation of the number of target objects in the target device in different device states, the current state of the target objects in the target device can be determined. When real-time monitoring the current state of the target objects in the target device, the current state of the target objects can be determined according to different device states, and the current state of the target objects can be accurately judged, thereby improving the accuracy of monitoring the target objects in the target device.

[0055] To enable those skilled in the art to better understand the solution of the present application, the application environment of the solution of the present application will be described first. The target object monitoring method provided by the present application can be applied to Figure 1 the application environment as shown.

[0056] Please refer to Figure 1 , Figure 1 which is a schematic structural diagram of a target object monitoring system provided by an embodiment of the present application. As Figure 1 shown, the target object monitoring system includes a target device 101, a network device 102 communicatively connected to the target device 101, a cloud server 103, and a user terminal 104. Among them, the target device 101 can be a vehicle such as a sedan, a bus, or a truck, which is not limited here. Among them, the target device 101 may include a detection device.

[0057] The target device 101 accesses the network device 102 in the target object monitoring system and communicates with the network device 102 through its configured communication module, and is thus controlled by the network device 102. In one implementation, the target device 101 accesses the network device 102 through a local area network path or a wide area network path, and is thus deployed in the network device 102. Among them, the local area network may include ZIGBEE or Bluetooth, etc., and the wide area network may include 2G / 3G / 4G / 5G / WIFI, etc.

[0058] The network device 102 establishes a network connection with the user terminal 104 or the cloud server 103 through a router. In one implementation, the network device 102 and the user terminal 104 may establish a network connection through a local area network or a wide area network path. Through this network connection, it interacts with the user terminal 104, so that the user can control the target device 101 accessing the network device 102 through this user terminal 104 to perform corresponding actions.

[0059] Among them, the user terminal 104 may be a smart phone, a notebook computer, a personal computer, a tablet computer, a smart control panel or other electronic devices that can implement network connections, which are not limited here. The cloud server 103 may be implemented by an independent server or a server cluster composed of multiple servers. The target object monitoring method provided in this application can be applied to any of the electronic devices in the target device 101, the network device 102, the cloud server 103, and the user terminal 104.

[0060] Exemplarily, the target object monitoring method can be applied to the target device 101. Specifically, the target device 101 can determine the current device state of the target device 101 according to the obtained speed change data of the target device; then, based on the obtained target detection data, it can identify the number of target objects in the target device 101 in the stationary state, and identify the number of target objects in the target device 101 in the moving state; finally, it can determine the current state of the target objects in the target device 101 according to the change in the number of target objects in the target device 101 in different device states.

[0061] The target object monitoring method provided in this application can also be applied to Figure 2 the application environment as shown.

[0062] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of another target object monitoring system provided by an embodiment of this application. As Figure 2As shown in the figure, the target object monitoring system includes a target device 201, a detection device 202, a network device 203 communicatively connected to the target device 201, a cloud server 204, and a user terminal 205. Among them, the target device 201 can be a vehicle such as a sedan, a bus, or a truck, which is not limited here. Specifically, the detection device 202 can be deployed within the target device 201.

[0063] The target device 201 accesses the network device 203 in the target object monitoring system and communicates with the network device 203 through its own configured communication module, and thus is controlled by the network device 203. In one implementation, the target device 201 accesses the network device 203 through a local area network path or a wide area network path, and thus is deployed in the network device 203. Among them, the local area network can include ZIGBEE or Bluetooth, etc., and the wide area network can include 2G / 3G / 4G / 5G / WIFI, etc.

[0064] The network device 203 establishes a network connection with the detection device 202, the user terminal 205, or the cloud server 204 through a router. In one implementation, the network device 203 and the user terminal 205 can establish a network connection through a local area network or a wide area network path. Through this network connection, it interacts with the user terminal 205, and thus enables the user to control the target device 201 and / or the detection device 202 accessing the network device 203 to perform corresponding actions by means of this user terminal 205.

[0065] Among them, the detection device can be one or more of detection devices such as a millimeter wave radar and an accelerometer, which is not limited here. The user terminal 205 can be a smart phone, a laptop computer, a personal computer, a tablet computer, a smart control panel, or other electronic devices that can implement a network connection, which is not limited here. The cloud server 204 can be implemented by an independent server or a server cluster composed of multiple servers. The target object monitoring method provided in this application can be applied to any of the electronic devices in the target device 201, the detection device 202, the network device 203, the cloud server 204, and the user terminal 205.

[0066] Exemplarily, the target object monitoring method can be applied to the target device 201. Specifically, the target device 201 can determine the current device state of the target device 201 according to the speed change data for the target device 201 obtained from the detection device 202; then it can identify the number of target objects within the target device 201 when the device state is a stationary state and the number of target objects within the target device 201 when the device state is a moving state based on the target detection data obtained from the detection device 202; finally, it can determine the current state of the target objects within the target device 201 according to the change situation of the number of target objects within the target device 201 under different device states.

[0067] Please refer to Figure 3 , Figure 3 which is a schematic flowchart of a target object monitoring method disclosed in an embodiment of the present application. Among them, the target object monitoring method can be applied to an electronic device capable of data processing, and the electronic device can be Figure 1 the target device 101, network device 102, cloud server 103, user terminal 104, etc. in Figure 2 or the target device 201, detection device 202, network device 203, cloud server 204, user terminal 205, etc. in Figure 3 As shown in

[0068] 301. Determine the current device state of the target device according to the obtained speed change data of the target device.

[0069] The target device refers to a device with a target object to be monitored, and the target device can be a vehicle such as a car, bus, or truck. The speed change data of the target device refers to data that can reflect the device state of the target device. The speed change data can be the difference between the speeds of the target device within a preset time period, or the acceleration value of the vehicle within a preset time period, or other numerical values of speed change. The current device state of the target device refers to the current state of the target device, and the device state can be a motion state or a stationary state. For example, the motion state can be the state when the speed of the target device exceeds the preset speed threshold. For example, specifically, it can be the state when the speed is not 0, that is, greater than 0. The stationary state can be the state when the speed of the target device is within the preset speed threshold range. For example, specifically, it can be the state when the speed is 0.

[0070] Exemplarily, if the target device is a car, the speed change data can be the difference between the speeds of the car within a preset time period, or the acceleration value of the car within a preset time period, or other numerical values of speed change.

[0071] The target device can determine the current device state of the target device according to the obtained speed change data of the target device.

[0072] Exemplarily, the target device can obtain the speed change data of the target device through an accelerometer, or through a radar sensor, or through a Global Positioning System (GPS) receiver, or through a wheel speed sensor. The method for the target device to obtain the speed change data is not limited herein.

[0073] Exemplarily, the target device can periodically obtain the speed change data of the target device, and the time interval of each period can be set according to the actual situation. Exemplarily, the time interval of each period can be set to 1 minute, or 3 minutes, or 5 minutes, or any time length.

[0074] 302. Based on the obtained target detection data, identify the number of target objects in the target device when the device state is in a stationary state, and identify the number of target objects in the target device when the device state is in a moving state.

[0075] The target detection data refers to the detection data of the target objects in the target device, and the target detection data can be the point cloud data obtained by detecting the target objects. The target object refers to the object to be detected in the target device, and the target object can be a human body.

[0076] The target device can identify the number of target objects in the target device in different device states according to the obtained target detection data. When the device state is in a stationary state, the target device can identify the number of target objects in the target device according to the target detection data; when the device state is in a moving state, the target device can identify the number of target objects in the target device according to the target detection data.

[0077] Exemplarily, the target device can obtain the target detection data through a millimeter-wave radar, or through an infrared sensor, or through other human presence sensors. The method of obtaining the target detection data is not limited herein.

[0078] The electronic device can periodically obtain the target detection data in the target device, and the time interval of each period can be set according to the actual situation. Exemplarily, the time interval of each period can be set to 1 minute, or 3 minutes, or 5 minutes, or any time length.

[0079] 303. According to the change situation of the number of target objects in the target device in different device states, determine the current state of the target objects in the target device.

[0080] Among them, the change situation of the number of target objects refers to the situation where the number of target objects changes. The change situation of the number of target objects can be a situation where the number increases, or a situation where the number decreases, or a situation where the number remains unchanged. The change situation of the number of target objects depends on the actual situation.

[0081] It can be understood that the current state of the target object can reflect the current state of the target object in the target device, specifically including the distribution state of each target pair in the target device, the quantity state of the target object in the target device, and the normal or abnormal state of the target object. For example, the current state of the target object can be a normal state or an abnormal state.

[0082] The electronic device can determine the current state of the target object in the target device according to the change in the quantity of the target object in the target device under different device states.

[0083] In Figure 3 In the method embodiment described above, the target device can determine the current device state of the target device according to the obtained speed change data for the target device; then, based on the obtained target detection data, it can identify the quantity of the target object in the target device when the device state is the stationary state, and the quantity of the target object in the target device when the device state is the moving state; finally, it can determine the current state of the target object in the target device according to the change in the quantity of the target object in the target device under different device states. When monitoring the current state of the target object in the target device in real time, the current state of the target object can be determined according to different device states, and the current state of the target object can be accurately judged, thereby improving the accuracy of monitoring the target object in the target device.

[0084] In some embodiments, step 302 may include:

[0085] If the current device state of the target device is the stationary state, then identify the quantity of the target object in the target device in the stationary state according to the obtained target detection data;

[0086] If it is recognized that the device state changes from the stationary state to the moving state, then lock the quantity of the target object in the most recent stationary state as the quantity of the target object in the moving state, and identify the quantity of the target object in the target device in the moving state according to the real-time obtained target detection data and the locked quantity of the target object in the moving state.

[0087] The target device can determine whether the current device state of the target device is a stationary state or a state transformed from a stationary state to a moving state. When the current device state of the target device is a stationary state, the number of target objects in the target device in the stationary state can be identified based on the acquired target detection data; when the current device state of the target device is transformed from a stationary state to a moving state, the number of the target objects in the most recent stationary state can be locked as the number of target objects in the moving state, and the number of target objects in the target device in the moving state can be identified based on the real-time acquired target detection data and the locked number of target objects in the moving state.

[0088] Thus, the target device can respectively determine and store the number of target objects in the target device identified in different device states, so that the current state of the target objects in the target device can be monitored based on the number of target objects in the target device in different device states, and further the accuracy of measuring the current state of the target objects in the target device can be improved.

[0089] In some embodiments, the current state of the target object may include the current quantity state, and step 303 includes:

[0090] If the number of target objects identified based on the real-time acquired target monitoring data in the moving state is the same as the locked number of target objects in the moving state, it is determined that the current quantity state of the target objects in the target device is normal;

[0091] If the identified number of target objects is different from the locked number of target objects in the moving state, it is determined that the current quantity state of the target objects in the target device is abnormal.

[0092] The current quantity state refers to the state of the current quantity of the target objects in the target device, and the current quantity state can be normal or abnormal.

[0093] When determining the current state of the target object according to the change situation of the number of target objects in the target device in different device states, the target device can first judge whether the current device state of the target device is a moving state. When the current device state of the target device is a moving state, the target device can compare the number of target objects identified based on the real-time acquired target monitoring data in the moving state with the locked number of target objects in the moving state to determine the change situation of the number of target objects in the target device in different device states.

[0094] When the number of target objects identified from the target monitoring data obtained in real time in the motion state is the same as the number of target objects in the locked motion state, it can be determined that the current quantity state of the target objects in the target device is normal; when the number of identified target objects is different from the number of target objects in the locked motion state, it can be determined that the current quantity state of the target objects in the target device is abnormal.

[0095] Thus, the target device can monitor the number of target objects in the target device in the motion state by judging the change of the number of target objects identified from the target monitoring data obtained in real time in the motion state relative to the number of target objects in the locked motion state, thereby reducing the complexity of monitoring.

[0096] In some embodiments, if the current quantity state of the target objects in the target device is abnormal, the target object monitoring method further includes:

[0097] If the number of identified target objects is greater than the number of target objects in the locked motion state, the number of target objects in the locked motion state is determined as the current number of target objects in the motion state, and the change of the number of target objects in the motion state is re-determined to re-determine the current quantity state of the target objects in the target device.

[0098] When the target device determines that the current quantity state of the target objects is abnormal and the number of identified target objects is greater than the number of target objects in the locked motion state, the target device can determine that there is a misdetection phenomenon in the number of target objects in the motion state. Therefore, the number of target objects in the locked motion state can be determined as the current number of target objects in the motion state, and the change of the number of target objects in the motion state can be re-determined to re-determine the current quantity state of the target objects in the target device.

[0099] Exemplarily, the target device can also re-determine the change of the number of target objects in the motion state according to the confidence levels at each position in the target device.

[0100] Thus, when the current quantity state of the target objects is abnormal and the number of identified target objects is greater than the number of target objects in the locked motion state, the target device determines the number of target objects in the locked motion state as the current number of target objects in the motion state and re-determines the number of target objects in the motion state, thereby solving the problem of error in the quantity state of target objects caused by misdetection, and further improving the accuracy of monitoring the current state of target objects in the target device.

[0101] In some embodiments, the target device includes multiple target positions, and the target object monitoring method may further include:

[0102] Based on the target detection data obtained in real time, determine the confidence that the positions of the target objects in the moving state are located at each target position;

[0103] According to the confidence of each target position, determine the distribution state of the target objects in each target position within the target device;

[0104] Based on the distribution state of the target objects in each target position, determine the current quantity state of the target objects within the target device.

[0105] The target position refers to the position in the target device for distributing the target objects. The distribution state of the target objects in the target position refers to the state of whether there are target objects in each target position.

[0106] Exemplarily, if the target device is a sedan, the seats in the sedan are the target positions. The confidence of the target position refers to the probability that the target object is distributed at this target position.

[0107] The target device may include multiple target positions. When determining the current quantity state of the target objects within the target device, the target device may first determine the confidence that the positions of the target objects in the moving state are located at each target position according to the obtained target detection data; then it may determine the distribution state of the target objects in each target position within the target device according to the confidence of each target position; and then it may determine the current quantity state of the target objects within the target device according to the distribution state of the target objects in each target position.

[0108] Exemplarily, the target positions with a confidence greater than a certain threshold may be determined as the state where there are target objects; then the number of target positions with the distribution state of having target objects may be counted, and this number may be determined as the current quantity state of the target objects within the target device.

[0109] Thus, in the moving state, the target device can determine whether there are target objects in each target position according to the distribution state of the target objects in the target positions included in the target device, so as to determine the current quantity state of the target objects in the target device, and further accurately monitor the quantity of the target objects within the target device.

[0110] In some embodiments, the target detection data includes target point cloud data; determining the confidence that the positions of the target objects in the moving state are located at each target position includes:

[0111] Obtain the historical state of each target position within the target device; the historical state is determined based on the positions of the target objects in each target position within the target device in the stationary state;

[0112] Based on the target point cloud data obtained in real time, determine the number of target point clouds and the point cloud signal-to-noise ratio in each target position within the target device;

[0113] According to the number of target point clouds, the point cloud signal-to-noise ratio, and the historical state, determine the confidence that the positions of each target object in the moving state are located in each target position.

[0114] The target point cloud data refers to a set of vectors in the target three-dimensional coordinate system. The historical state of the target position refers to the distribution state of the target objects in the target position under the most recent device state. This historical state can be stored by the target device, or obtained by the target device from a server or the cloud, or obtained from other devices. The number of target point clouds refers to the number of target point clouds in the target point cloud data. The point cloud signal-to-noise ratio refers to the ratio of the voltage of the output signal of the amplifier to the noise voltage output at the same time.

[0115] The target detection data may include the target point cloud data. When determining the confidence that the position of the target object in the moving state is located in each target position, the target device can obtain the historical state of each target position within the target device. The historical state is determined based on the positions of each target object in each target position within the target device under the most recent stationary state. It can also determine the number of target point clouds and the point cloud signal-to-noise ratio in each target position within the target device according to the target point cloud data obtained in real time. Then, it can determine the confidence that the positions of each target object in the moving state are located in each target position according to the number of target point clouds, the point cloud signal-to-noise ratio, and the historical state.

[0116] Exemplarily, in the case where the number of target point clouds is greater than a certain threshold, the point cloud signal-to-noise ratio is greater than a certain threshold, and the historical state is a state where there are target objects, it can be determined that the confidence of this target position is 100%. Exemplarily, in the case where the number of target point clouds is greater than a certain threshold, the point cloud signal-to-noise ratio is greater than a certain threshold, and the historical state is a state where there are no target objects, it can be determined that the confidence of this target position is 90%. The target device can determine the confidence corresponding to the target position for different numbers of target point clouds, point cloud signal-to-noise ratios, and / or historical states according to the actual situation.

[0117] Thus, the target device can determine the confidence of each target position included in the target device according to the target point cloud data and the historical state, so as to determine the distribution state of the target objects in each target position according to this confidence. Furthermore, in the moving state, the current quantity state of the target objects within the target device can be obtained accurately.

[0118] In some embodiments, the target object monitoring method may further include:

[0119] If the number of identified target objects is less than the number of target objects in the locked motion state, determine that the current state of the target objects in the target device is abnormal, and send a prompt message to the target terminal; the prompt message is used to prompt that the number of target objects has decreased.

[0120] The target terminal refers to the terminal device used to receive the prompt message. The target terminal can be the target device, can also be the target platform, or can be other terminals, and the number of target terminals can be determined according to the actual situation.

[0121] In the case where the number of identified target objects is less than the number of target objects in the locked motion state, the target device can determine that the current state of the target objects in the target device is abnormal, and can send a prompt message to the target terminal to prompt that the number of target objects in the target device has decreased.

[0122] Thus, the target device can, in the case of an abnormal monitoring result, feedback the monitoring result to the target terminal in real time, so as to achieve the purpose of improving safety.

[0123] In some embodiments, the target object monitoring method may further include:

[0124] Obtain the point cloud data detected when there are no target objects in the target device;

[0125] Based on the point cloud data, establish a spatial model corresponding to the target device; the spatial model includes each target position in the target device; the spatial model and the target positions are used to identify the change in the number of target objects in the target device.

[0126] The spatial model refers to a model obtained by abstracting the spatial information in the real world. Specifically, it can be a two-dimensional spatial model or a three-dimensional spatial model obtained by coordinate modeling of the target device. Based on the established spatial model of the target device, the positions and distribution of each target object in the target device can be identified more accurately.

[0127] The target device can obtain the point cloud data when there are no target objects in the target device, and then can, based on the point cloud data, establish a spatial model corresponding to the target device. The spatial model can include each target position in the target device, and the spatial model and the target positions can be used to identify the change in the number of target objects in the target device.

[0128] Thus, after establishing the spatial model corresponding to the target device, the target device can determine the coordinates corresponding to each target position in the target device, so as to determine the point cloud data corresponding to each target position, and thus can determine the distribution state of the target objects in each target position, and further can monitor the current state of the target objects in the target device, improving the accuracy of monitoring.

[0129] Please refer to Figure 4 , Figure 4 which is a schematic flowchart of another target object monitoring method disclosed in an embodiment of the present application. Among them, this target object monitoring method can be applied to a vehicle. As Figure 4 shown, this target object monitoring method may include the following steps.

[0130] 401. Obtain the acceleration values of the target vehicle measured by the accelerometer on three spatial axes.

[0131] When the target vehicle obtains speed change data through the accelerometer, the target vehicle can obtain the acceleration values of the target vehicle measured by the accelerometer on three spatial axes. The accelerometer refers to a measuring device for measuring the acceleration of an object. The three spatial axes refer to three axes that pass through the same point and are perpendicular to each other, and these three axes are the x-axis (i.e., the horizontal axis), the y-axis (i.e., the vertical axis), and the z-axis (i.e., the vertical axis). The target vehicle can periodically obtain speed change data through the accelerometer, and the time interval of each period can be set according to the actual situation. Exemplarily, the time interval of each period can be set to 1 minute, or can be set to 3 minutes, or can be set to 5 minutes, or can be set to any time length.

[0132] 402. Determine the acceleration variance according to the acceleration values on the three spatial axes.

[0133] After obtaining the acceleration values of the target vehicle on the three spatial axes, the target vehicle can determine the corresponding acceleration variance. The acceleration variance refers to the variance between the accelerations of the target vehicle on the three spatial axes. Exemplarily, the target vehicle can first determine the average value of the acceleration values on the three spatial axes, and then determine the acceleration variance according to the acceleration values on the three spatial axes and the average value of the acceleration.

[0134] 403. Determine whether the acceleration variance is greater than a preset threshold. If so, execute step 404; if not, execute step 406.

[0135] After determining the acceleration variance, the target vehicle can determine whether the acceleration variance is greater than a preset threshold. The preset threshold refers to an acceleration critical value that can be used to distinguish whether the target vehicle is in a stationary state or a moving state. The preset threshold can be set according to the actual situation.

[0136] 404. Determine that the vehicle state of the target vehicle is a moving state.

[0137] When the acceleration variance is greater than the preset threshold, the target vehicle can determine that the vehicle state of the target vehicle is a moving state.

[0138] 405. Determine the number of target objects in the target vehicle according to the obtained target detection data detected by the millimeter-wave radar.

[0139] When the vehicle state of the target vehicle is in a moving state, the target vehicle can obtain target detection data through a millimeter-wave radar to determine the number of target objects in the target vehicle. The target detection data refers to the detection data for the target objects in the target vehicle. The target object refers to the object to be detected in the target vehicle. The target vehicle can periodically obtain the target detection data in the target vehicle, and the time interval of each period can be set according to the actual situation.

[0140] Exemplarily, the time interval of each period can be set to 1 minute, can also be set to 3 minutes, can also be set to 5 minutes, and can also be set to any time length.

[0141] In order to obtain more accurate target detection data and thus improve the accuracy of monitoring, the target vehicle can first obtain the point cloud data when there are no target objects in the target vehicle, and then, based on the point cloud data, establish a spatial model corresponding to the target vehicle. The spatial model can include each target position in the target vehicle. Specifically, each target position in the target vehicle can be each target seat in the target vehicle. The spatial model and the target seats can be used to identify the change in the number of target objects in the target vehicle.

[0142] In some embodiments, a spatial model corresponding to the target vehicle can be established according to the position of the millimeter-wave radar. In order to obtain target detection data through the millimeter-wave radar, a millimeter-wave radar can be installed in the target vehicle. Then the target vehicle can obtain the target detection data through the millimeter-wave radar. The position of the millimeter-wave radar can be set according to actual needs. Exemplarily, if the millimeter-wave radar is installed at the position of the front-row rearview mirror of the vehicle, the position of the front-row rearview mirror of the vehicle can be used as the origin of the spatial coordinate system corresponding to the spatial model, or the origin of the spatial coordinate system corresponding to the spatial model can be set directly below the millimeter-wave radar at a certain distance. The method of establishing a spatial model corresponding to the target vehicle according to the millimeter-wave radar can be determined according to actual needs and will not be limited here.

[0143] As Figure 5 shown, Figure 5 is a schematic spatial diagram of a spatial model corresponding to a target vehicle disclosed in an embodiment of the present application. The spatial model can include a spatial coordinate system, and the spatial coordinate system includes an x-axis (i.e., the horizontal axis), a y-axis (i.e., the vertical axis), and a z-axis (i.e., the vertical axis).

[0144] As Figure 6 shown, Figure 6It is a top - down schematic diagram of a spatial model corresponding to a target vehicle disclosed in an embodiment of the present application. The spatial model enables a target vehicle to include a plurality of target seats corresponding to different coordinates, including a first seat 601, a second seat 602, a third seat 603, a fourth seat 604, and a fifth seat 605.

[0145] In some embodiments, when the x - axis of the coordinate system of the spatial model corresponding to the target vehicle is parallel to the x - axis of the coordinate system of the millimeter - wave radar, in order to make the data obtained by the millimeter - wave radar more accurate, the millimeter - wave radar can be tilted by a preset angle in the direction of the vehicle bottom when installing the millimeter - wave radar. Since the coordinates of the target point cloud detected by the millimeter - wave radar are based on the coordinates in the coordinate system of the millimeter - wave radar, it is necessary to map the coordinates of the target point cloud to the coordinate system of the spatial model corresponding to the target vehicle.

[0146] Exemplarily, the coordinates of the target point cloud can be mapped to the coordinate system of the spatial model corresponding to the target vehicle through the following formula:

[0147]

[0148] where (x, y, z) are the coordinates of the target point cloud mapped to the coordinate system of the spatial model corresponding to the target vehicle, (x r , y r , z r ) are the coordinates of the millimeter - wave radar in the coordinate system of the spatial model corresponding to the target vehicle, (x c , y c , z c ) are the coordinates of the target point cloud based on the coordinate system of the millimeter - wave radar, and θ is the angle of the millimeter - wave radar tilted in the direction of the vehicle bottom.

[0149] In some embodiments, the target vehicle may include a plurality of target seats. When determining the current quantity state of target objects in the target vehicle, the target vehicle can first determine the confidence level of the positions of target objects in each target seat in the motion state according to the acquired target detection data; then it can determine the distribution state of target objects in each target seat in the target vehicle according to the confidence level of each target seat; and then it can determine the current quantity state of target objects in the target vehicle according to the distribution state of target objects in each target seat.

[0150] The target seat refers to the position in the target vehicle for distributing target objects. The confidence level of the target seat refers to the probability that the target object is distributed in this target seat. The distribution state of target objects in the target seat refers to the state of whether there are target objects in the target seat.

[0151] Exemplarily, based on the confidence level of the target seat, the target seat with a confidence level greater than a certain threshold can be determined as the state where a target object exists; then, the number of target seats in which the distribution state of the target object is the state where a target object exists can be counted, and this number can be determined as the current number state of the target object in the target vehicle.

[0152] Thus, in the moving state, the target vehicle can determine whether a target object exists in each target seat based on the distribution state of the target object in the target seats included in the target vehicle, so as to determine the current number state of the target object in the target vehicle, and further accurately monitor the number of target objects in the target vehicle.

[0153] In some embodiments, the target detection data may include point cloud data. When determining the position of the target object and the confidence level of each target seat in the moving state, the target vehicle can obtain the historical state of each target seat in the target vehicle. The historical state is determined based on the positions of each target object in each target seat in the target vehicle in the most recent stationary state. The target vehicle can also determine the number of target point clouds and the point cloud signal-to-noise ratio in each target seat in the target vehicle according to the real-time acquired target point cloud data. Then, based on the number of target point clouds, the point cloud signal-to-noise ratio, and the historical state, the confidence level that the position of each target object in the moving state is located in each target seat can be determined. The target point cloud data refers to a set of vectors in the target three-dimensional coordinate system.

[0154] The historical state of the target seat refers to the distribution state of the target object in the target seat in the most recent vehicle state. This historical state can be stored by the target vehicle, or obtained by the target vehicle from the server or the cloud, or obtained from other devices. The number of target point clouds refers to the number of target point clouds in the target point cloud data. The point cloud signal-to-noise ratio refers to the ratio of the voltage of the output signal of the amplifier to the noise voltage output at the same time.

[0155] Exemplarily, in the case where the number of target point clouds is greater than a certain threshold, the point cloud signal-to-noise ratio is greater than a certain threshold, and the historical state is the state where a target object exists, it can be determined that the confidence level of this target seat is 100%. Exemplarily, in the case where the number of target point clouds is greater than a certain threshold, the point cloud signal-to-noise ratio is greater than a certain threshold, and the historical state is the state where no target object exists, it can be determined that the confidence level of this target seat is 90%.

[0156] The target vehicle can determine the confidence level corresponding to the target seat corresponding to different numbers of target point clouds, point cloud signal-to-noise ratios, and / or historical states according to the actual situation. Exemplarily, the confidence level that the position of each target object in the moving state is located in each target seat can be determined by the following formula:

[0157]

[0158] Among them, k1, k2, and k3 represent weights. k1 is the weight of the number of target point clouds, k2 is the weight of the signal-to-noise ratio (SNR) of the point clouds, and k3 is the weight of the historical state of the target seat, and k1 + k2 + k3 = 1. C_L is the confidence of the target seat, n_pc is the number of point clouds of the target seat, n_pc_total is the total number of point clouds of all target seats, SNR is the sum of the signal-to-noise ratios of each point cloud at this position, SNR_total is the sum of the signal-to-noise ratios of the point clouds of all target seats, and status is the historical state of the target seat.

[0159] Thus, the target vehicle can determine the confidence of each target seat included in the target vehicle based on the target point cloud data and the historical state, so as to determine the distribution state of the target objects in each target seat according to the confidence. Furthermore, in the moving state, the current number state of the target objects in the target vehicle can be obtained accurately.

[0160] 406. Determine that the vehicle state of the target vehicle is a stationary state.

[0161] When the acceleration variance is less than or equal to a preset threshold, the target vehicle can determine that the state of the target vehicle is a stationary state.

[0162] 407. Determine the number of target objects in the target vehicle according to the obtained target detection data detected by the millimeter-wave radar.

[0163] When the vehicle state of the target vehicle is a stationary state, the target vehicle can obtain target detection data through the millimeter-wave radar to determine the number of target objects in the target vehicle.

[0164] In some embodiments, the target detection data includes target point cloud data; determining the number of target objects in the target vehicle in the stationary state includes:

[0165] Based on the target point cloud data obtained in real time, determine the number of target point clouds and the signal-to-noise ratio of the point clouds in each target seat in the target vehicle;

[0166] According to the number of target point clouds and the signal-to-noise ratio of the point clouds, determine the number of target objects in the target vehicle in the stationary state.

[0167] The target detection data may include point cloud data. When determining the position of the target object in the stationary state and the confidence of each target seat, the target vehicle can obtain the target point cloud data in real time through the millimeter-wave radar to determine the number of target point clouds and the signal-to-noise ratio of the point clouds in each target seat in the target vehicle, and then can determine the number of target objects in the target vehicle in the stationary state according to the number of target point clouds and the signal-to-noise ratio of the point clouds.

[0168] The target point cloud data refers to a set of vectors in the target three-dimensional coordinate system. The target point cloud quantity refers to the number of target point clouds in the target point cloud data. The point cloud signal-to-noise ratio refers to the ratio of the voltage of the output signal of the amplifier to the noise voltage output simultaneously.

[0169] Exemplarily, the target vehicle may determine a target seat with a target point cloud quantity greater than a certain threshold and a point cloud signal-to-noise ratio greater than a certain threshold as having a target object, and thus may determine the number of target seats with target objects as the number of target objects in the target vehicle.

[0170] 408. Determine the state of the target object in the target vehicle according to the change situation of the number of target objects in the target vehicle in different states.

[0171] The target vehicle may determine the current state of the target object in the target vehicle according to the change situation of the number of target objects in the target vehicle in different vehicle states. The change situation of the number of target objects refers to the change situation of the number of target objects in the target vehicle in a stationary state and in a moving state. The current state of the target object refers to the current state of the target object in the target vehicle. The current state of the target object may include a normal state and an abnormal state.

[0172] In some embodiments, when determining the current state of the target object according to the change situation of the number of target objects in the target vehicle in different vehicle states, the target vehicle may first determine whether the current vehicle state of the target vehicle is a moving state. When the current vehicle state of the target vehicle is a moving state, the target vehicle may compare the number of target objects identified based on the target monitoring data obtained in real time in the moving state with the number of target objects locked in the moving state to determine the change situation of the number of target objects in the target vehicle in different states.

[0173] When the number of target objects identified based on the target monitoring data obtained in real time in the moving state is the same as the number of target objects locked in the moving state, it may be determined that the current quantity state of the target objects in the target vehicle is normal; when the number of target objects identified based on the target monitoring data obtained in real time in the moving state is different from the number of target objects locked in the moving state, it may be determined that the current quantity state of the target objects in the target vehicle is abnormal.

[0174] Thus, the target vehicle may monitor the number of target objects in the target vehicle in the moving state by determining the change situation of the number of target objects identified based on the target monitoring data obtained in real time in the moving state relative to the number of target objects locked in the moving state, thereby reducing the complexity of monitoring.

[0175] In some embodiments, when the target vehicle determines that the current quantity status of the target object is abnormal and the identified quantity of the target object is greater than the quantity of the target object in the locked moving state, the target vehicle may determine that there is a misdetection of the quantity of the target object in the moving state. Therefore, the quantity of the target object in the locked moving state may be determined as the current quantity of the target object in the moving state, and the change in the quantity of the target object in the moving state may be re-determined to re-determine the current quantity status of the target object in the target vehicle.

[0176] Exemplarily, the target vehicle may determine the quantity of the target object in the moving state as the quantity of the target object in the most recent stationary state. Exemplarily, the target vehicle may also re-determine the change in the quantity of the target object in the moving state according to the confidence levels at various positions in the target vehicle.

[0177] Thus, when the current quantity status of the target object is abnormal and the quantity of the target object in the moving state is greater than the quantity of the target object in the most recent stationary state, the target vehicle re-determines the quantity of the target object in the moving state, thereby solving the problem of errors in the quantity status of the target object caused by misdetection, and further improving the accuracy of monitoring the current status of the target object in the target vehicle.

[0178] In some embodiments, when the quantity of the target object in the moving state is less than the quantity of the target object in the most recent stationary state, it may be determined that the current status of the target object in the target vehicle is abnormal, and a prompt message may be sent to the target terminal to prompt that the quantity of the target object in the target vehicle has decreased. The target terminal may be the target vehicle, or a target platform, or other terminals, and the number of target terminals may be determined according to the actual situation.

[0179] Thus, the target vehicle can timely feedback the monitoring result to the target terminal when the monitoring result is abnormal, thereby achieving the purpose of improving safety.

[0180] In Figure 4In the described method embodiments, the target device may obtain the acceleration values of the target vehicle on three spatial axes measured by the accelerometer, and then may determine the acceleration variance based on the acceleration values on the three spatial axes to determine whether the acceleration variance is greater than a preset threshold. In the case where the acceleration variance is greater than the preset threshold, the vehicle state of the target vehicle may be determined as the moving state, and then the number of target objects in the target vehicle may be determined according to the obtained target detection data detected by the millimeter-wave radar. In the case where the acceleration variance is less than or equal to the preset threshold, the vehicle state of the target vehicle may be determined as the stationary state, and then the number of target objects in the target vehicle may be determined according to the obtained target detection data detected by the millimeter-wave radar. Finally, the target vehicle may determine the current state of the target object in the target vehicle according to the change in the number of target objects in the target vehicle in different states. When the current state of the target object in the target device is monitored in real time, the current state of the target object may be determined according to different device states, and the current state of the target object can be accurately judged, thereby improving the accuracy of monitoring the target object in the target device.

[0181] It should be understood that the same or corresponding information in the above different embodiments may be referred to each other.

[0182] It should be understood that although Figure 3 、 4 the steps in the flowchart of Figure 3 、 4 are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps may be executed in other orders. Moreover,

[0183] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of the target object monitoring device disclosed in the embodiments of the present application. The target object monitoring device may include:

[0184] A first determination unit 701, configured to determine the current device state of the target device according to the obtained speed change data for the target device;

[0185] An identification unit 702, configured to identify the number of target objects in a target device when the device state is stationary based on the acquired target detection data, and to identify the number of target objects in the target device when the device state is in motion.

[0186] A second determination unit 703, configured to determine the current state of the target objects in the target device according to the change in the number of target objects in the target device under different device states.

[0187] In some embodiments, the identification unit 702 is specifically configured to:

[0188] If the current device state of the target device is stationary, identify the number of target objects in the target device in the stationary state according to the acquired target detection data;

[0189] If it is recognized that the device state changes from the stationary state to the motion state, lock the number of the target objects in the most recent stationary state as the number of the target objects in the motion state, and identify the number of the target objects in the target device in the motion state according to the real-time acquired target detection data and the locked number of the target objects in the motion state.

[0190] In some embodiments, the current state of the target objects includes the current quantity state. The second determination unit 703 is specifically configured to:

[0191] If the number of target objects identified based on the real-time acquired target detection data in the motion state is the same as the locked number of target objects in the motion state, determine that the current quantity state of the target objects in the target device is normal;

[0192] If the identified number of target objects is different from the locked number of target objects in the motion state, determine that the current quantity state of the target objects in the target device is abnormal.

[0193] In some embodiments, if the current quantity state of the target objects in the target device is abnormal, the second determination unit 703 is further specifically configured to:

[0194] If the identified number of target objects is greater than the locked number of target objects in the motion state, determine the locked number of target objects in the motion state as the current number of target objects in the motion state, and re-determine the change in the number of target objects in the motion state to re-determine the current quantity state of the target objects in the target device.

[0195] In some embodiments, the target device includes a plurality of target positions, and the target object monitoring device further includes:

[0196] A third determination unit, configured to determine the confidence that the positions of target objects in a moving state are located at respective target positions based on the target detection data obtained in real time;

[0197] A fourth determination unit, configured to determine the distribution state of target objects in respective target positions within the target device according to the confidence of respective target positions;

[0198] A fifth determination unit, configured to determine the current quantity state of target objects within the target device based on the distribution state of target objects in respective target positions.

[0199] In some embodiments, the target detection data includes target point cloud data, and the third determination unit 704 is specifically configured to:

[0200] Obtain the historical state of respective target positions within the target device; the historical state is determined based on the positions of respective target objects in respective target positions within the target device in a stationary state;

[0201] Based on the target point cloud data obtained in real time, determine the number of target point clouds and the point cloud signal-to-noise ratio in respective target positions within the target device;

[0202] According to the number of target point clouds, the point cloud signal-to-noise ratio, and the historical state, determine the confidence that the positions of target objects in a moving state are located at respective target positions.

[0203] In some embodiments, the target object monitoring device further includes:

[0204] A sending unit, configured to, if the number of identified target objects is less than the number of target objects in a locked moving state, determine that the current state of target objects within the target device is abnormal, and send a prompt message to the target terminal; the prompt message is used to prompt a reduction in target objects.

[0205] In some embodiments, the target object monitoring device further includes:

[0206] An obtaining unit, configured to obtain the point cloud data detected when there are no target objects within the target device;

[0207] A building unit, configured to build a spatial model corresponding to the target device based on the point cloud data; the spatial model includes respective target positions within the target device; the spatial model and the target positions are used to identify the change in the number of target objects within the target device.

[0208] In Figure 7In the described device embodiments, the current device state of the target device can be determined based on the obtained speed change data for the target device. Then, based on the obtained target detection data, the number of target objects in the target device when the device state is stationary can be identified, and the number of target objects in the target device when the device state is in motion can be identified. Finally, based on the change in the number of target objects in the target device under different device states, the current state of the target objects in the target device can be determined. When the current state of the target objects in the target device is monitored in real time, the current state of the target objects can be determined according to different device states, and the current state of the target objects can be accurately judged, thereby improving the accuracy of monitoring the target objects in the target device.

[0209] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0210] In several embodiments disclosed in the present application, the coupling between units can be electrical, mechanical, or other forms of coupling.

[0211] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0212] Please refer to Figure 8 , Figure 8 which is a schematic structural diagram of another target object monitoring system disclosed in the embodiments of the present application. The target object monitoring system includes a detection device and a target device, where:

[0213] The detection device is configured to detect the speed change data of the target device and the target detection data inside the target device, and send the speed change data and the target detection data to the target device;

[0214] The target device is configured to determine the current device state of the target device according to the obtained speed change data; identify the number of target objects in the target device when the device state is stationary based on the obtained target detection data, and identify the number of target objects in the target device when the device state is in motion; determine the current state of the target objects in the target device according to the change in the number of target objects in the target device under different device states.

[0215] In some embodiments, the target device is specifically configured to:

[0216] If the current device state of the target device is the stationary state, then identify the number of target objects in the target device in the stationary state according to the acquired target detection data;

[0217] If it is identified that the device state changes from the stationary state to the moving state, then identify the number of target objects in the target device in the stationary state according to the acquired target detection data.

[0218] In some embodiments, the current state of the target object includes the current quantity state, and the target device is specifically configured to:

[0219] If the number of target objects in the moving state is the same as the number of target objects in the stationary state, then determine that the current quantity state of the target objects in the target device is normal;

[0220] If the number of target objects in the moving state is different from the number of target objects in the stationary state, then determine that the current quantity state of the target objects in the target device is abnormal.

[0221] In some embodiments, if the current quantity state of the target objects in the target device is abnormal, then the target device is specifically further configured to:

[0222] If the number of target objects in the moving state is greater than the number of target objects in the stationary state, then re-determine the change situation of the number of target objects in the moving state to re-determine the current quantity state of the target objects in the target device.

[0223] In some embodiments, the target device includes multiple target positions, and the target device is further configured to:

[0224] Based on the acquired target detection data in real time, determine the confidence that the positions of the respective target objects in the moving state are located at the respective target positions;

[0225] According to the confidence of the respective target positions, determine the distribution state of the target objects in each target position in the target device;

[0226] Based on the distribution state of the target objects in each target position, determine the current quantity state of the target objects in the target device.

[0227] In some embodiments, the target detection data includes target point cloud data, and the target device is specifically configured to:

[0228] Obtain the historical state of each target position in the target device; the historical state is determined based on the positions of the respective target objects in each target position in the target device in the stationary state;

[0229] Based on the acquired target point cloud data in real time, determine the number of target point clouds and the point cloud signal-to-noise ratio in each target position in the target device;

[0230] Determine the confidence that the positions of target objects in the moving state are located at each target position according to the number of target point clouds, the signal-to-noise ratio of the point clouds, and the historical state.

[0231] In some embodiments, the target device is further configured to:

[0232] If the number of target objects in the moving state is less than the number of target objects in the stationary state, determine that the current state of the target objects in the target device is abnormal, and send a prompt message to the target terminal; the prompt message is used to prompt a reduction in the target objects.

[0233] In some embodiments, the target device is further configured to:

[0234] Obtain the point cloud data detected when there are no target objects in the target device;

[0235] Based on the point cloud data, establish a spatial model corresponding to the target device; the spatial model includes each target position in the target device; the spatial model and the target positions are used to identify the change in the number of target objects in the target device.

[0236] In Figure 8 In the described system embodiment, the detection device can detect the speed change data of the target device, and then can send the speed change data to the target device. The target device can determine the current device state of the target device according to the obtained speed change data. The detection device can detect the target detection data in the target device, and then can send the target detection data to the target device. The target device can identify the number of target objects in the target device in the stationary state based on the obtained target detection data, and identify the number of the target objects in the target device in the moving state; then can determine the current state of the target objects in the target device according to the change in the number of the target objects in the target device under different device states. When the current state of the target objects in the target device is monitored in real time, the current state of the target objects can be determined according to different device states, and the current state of the target objects can be accurately judged, thereby improving the accuracy of monitoring the target objects in the target device.

[0237] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described detection device and target device can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0238] As Figure 9As shown, an embodiment of the present application also discloses a schematic structural diagram of an electronic device. The electronic device includes a processor 901 and a memory 902. The memory 902 stores computer program instructions. When the computer program instructions are called by the processor 901, the various method steps disclosed in the above embodiments can be executed. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the electronic device, and it may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. Among them:

[0239] The processor 901 may include one or more processing cores. The processor 901 uses various interfaces and lines to connect various parts within the entire battery management system. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 902, calling data stored in the memory 902, executing various functions of the battery management system and processing data, and executing various functions of the electronic device and processing data, the electronic device can be monitored as a whole. Optionally, the processor 901 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 901 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the display content; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 901 and may be implemented separately through a communication chip.

[0240] The memory 902 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. The memory 902 can be used to store instructions, programs, code, code sets or instruction sets. The memory 902 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data created during the use of the electronic device (such as a phone book, audio and video data, chat record data, etc.). Correspondingly, the memory 902 may also include a memory controller to facilitate access to the memory 902 by the processor 901.

[0241] Although not shown, the electronic device may also include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 901 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 902 according to the following instructions, and the processor 901 will run the application programs stored in the memory 902 to implement the various method steps disclosed in the foregoing embodiments.

[0242] As Figure 10 shown, an embodiment of the present application also discloses a computer-readable storage medium, in which computer program instructions are stored, and the computer program instructions can be called by a processor to execute the methods described in the above embodiments.

[0243] The computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk or a ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has a storage space for program codes for executing any of the method steps in the above methods. These program codes can be read from or written into one or more computer program products. The program codes can be compressed in an appropriate form, for example.

[0244] According to one aspect of the present application, a computer program product or a computer program is disclosed. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the methods disclosed in the various optional implementation manners disclosed in the above embodiments.

[0245] The above are only the preferred embodiments of the present application and do not impose any formal restrictions on the present application. Although the present application has been disclosed above with the preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to equivalent embodiments by using the above-disclosed technical content within the scope of the technical solution of the present application. However, as long as it does not depart from the content of the technical solution of the present application, any brief modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present application still fall within the scope of the technical solution of the present application.

Claims

1. A method for monitoring a target object, characterized in that, The method includes: Determining the current device state of the target device according to the obtained speed change data for the target device; Based on the obtained target detection data, identifying the number of target objects in the target device when the device state is in a stationary state, and identifying the number of the target objects in the target device when the device state is in a moving state; Determining the current state of the target objects in the target device according to the change situation of the number of the target objects in the target device under different device states.

2. The method according to claim 1, characterized in that, The step of, based on the obtained target detection data, identifying the number of target objects in the target device when the device state is in a stationary state, and identifying the number of the target objects in the target device when the device state is in a moving state, includes: If the current device state of the target device is in a stationary state, then identifying the number of target objects in the target device in the stationary state according to the obtained target detection data; If it is recognized that the device state changes from the stationary state to a moving state, then locking the number of the target objects in the most recent stationary state as the number of the target objects in the moving state, and identifying the number of the target objects in the target device in the moving state according to the real-time obtained target detection data and the locked number of the target objects in the moving state.

3. The method according to claim 2, characterized in that, The current state of the target objects includes the current quantity state; The step of determining the current state of the target objects in the target device according to the change situation of the number of the target objects in the target device under different device states includes: If the number of the target objects identified based on the real-time obtained target detection data in the moving state is the same as the locked number of the target objects in the moving state, then determining that the current quantity state of the target objects in the target device is normal; If the identified number of the target objects is different from the locked number of the target objects in the moving state, then determining that the current quantity state of the target objects in the target device is abnormal.

4. The method according to claim 3, characterized in that, If the current quantity state of the target objects in the target device is abnormal, then the method further includes: If the identified number of the target objects is greater than the locked number of the target objects in the moving state, then determining the locked number of the target objects in the moving state as the current number of the target objects in the moving state, and re-determining the change situation of the number of the target objects in the moving state to re-determine the current quantity state of the target objects in the target device.

5. The method according to any one of claims 1-4, characterized in that, The target device includes a plurality of target positions; The method further includes: Based on the real-time obtained target detection data, determining the confidence that the positions of the target objects in the moving state are located at each of the target positions; According to the confidence of each of the target positions, determining the distribution state of the target objects in each of the target positions in the target device; Based on the distribution state of the target objects in each of the target positions, determining the current quantity state of the target objects in the target device.

6. The method according to claim 5, characterized in that, The target detection data includes target point cloud data; Determining the confidence that the positions of the target objects in the motion state are located at the respective target positions includes: Obtaining the historical states of the respective target positions in the target device; the historical states are determined based on the positions of the respective target objects at the respective target positions in the target device in the stationary state; Based on the target point cloud data obtained in real time, determining the number of target point clouds and the point cloud signal-to-noise ratio in the respective target positions in the target device; According to the number of target point clouds, the point cloud signal-to-noise ratio, and the historical states, determining the confidence that the positions of the respective target objects in the motion state are located at the respective target positions.

7. The method according to any one of claims 1-4, characterized in that, The method further includes: If the number of identified target objects is less than the number of target objects in the locked motion state, determining that the current state of the target objects in the target device is abnormal, and sending a prompt message to the target terminal; the prompt message is used to prompt that the target objects are reduced.

8. The method according to any one of claims 1-4, characterized in that, The method further includes: Obtaining the point cloud data detected when there are no target objects in the target device; Based on the point cloud data, establishing a spatial model corresponding to the target device; the spatial model includes the respective target positions in the target device; the spatial model and the target positions are used to identify the change in the number of target objects in the target device.

9. A device for monitoring a target object, characterized in that, The apparatus includes: A first determination unit, configured to determine the current device state of the target device according to the obtained speed change data of the target device; An identification unit, configured to identify the number of target objects in the target device when the device state is the stationary state based on the obtained target detection data, and to identify the number of target objects in the target device when the device state is the motion state; A second determination unit, configured to determine the current state of the target objects in the target device according to the change in the number of target objects in the target device in different device states.

10. A target object monitoring system, characterized in that, The system includes a detection device and a target device, where: The detection device is configured to detect the speed change data of the target device, and to detect the target detection data in the target device, and send the speed change data and the target detection data to the target device; The target device is configured to determine the current device state of the target device according to the obtained speed change data; to identify the number of target objects in the target device when the device state is the stationary state based on the obtained target detection data, and to identify the number of target objects in the target device when the device state is the motion state; and to determine the current state of the target objects in the target device according to the change in the number of target objects in the target device in different device states.

11. An electronic device, comprising a processor and a memory, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the method according to any one of claims 1-8.

12. A computer-readable storage medium storing a computer program or computer instructions, characterized in that, When the computer program or computer instructions are executed by the processor, the method according to any one of claims 1-8 is implemented.

Images