Article detection method, single-chip microcomputer, visual intelligent lock and storage medium
In the item detection method, the detection frequency of the sensor is adjusted using a fuzzy algorithm based on the received target image and scene parameter information, and the item recognition module is awakened when the conditions are met for state recognition, the problem of high energy consumption of the item detection method is solved and a significant energy consumption reduction is achieved.
Patent Information
- Application Number
- CN202510157570.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-12
- Publication Date
- 2025-06-06
AI Technical Summary
Item detection method requires real-time data collection and item detection and analysis, resulting in high energy consumption.
When the target image is received and the target condition is met, the item recognition module is awakened and instructed to perform item status recognition based on the target image, and the detection frequency of the sensor is adjusted by a fuzzy algorithm.
The frequency of item identification module performs item status recognition operations is reduced, unnecessary identification operations are avoided, and equipment energy consumption is significantly reduced.
Smart Images
Figure CN120107883A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of communications, and more specifically, to an object detection method, a single-chip microcomputer, a visual smart lock, a storage medium, an electronic device, and a program product. Background Art
[0002] Object detection methods play a key role in many fields such as smart homes, security monitoring, and logistics management. The object detection methods in related technologies require real-time data collection and object detection and analysis, so they have the problem of high energy consumption. Summary of the invention
[0003] The embodiments of the present invention provide an object detection method, a single-chip microcomputer, a visual smart lock, a storage medium, an electronic device and a program product, so as to at least solve the problem of high energy consumption caused by the need to collect data in real time and perform object detection and analysis in the object detection method in the related art.
[0004] According to one embodiment of the present invention, there is provided an object detection method, comprising: when an object recognition module is in a sleep state and receives a target image, determining whether a target wake-up condition is currently met; when it is determined that the target wake-up condition is met, waking up the object recognition module and transmitting the target image to the object recognition module to instruct the object recognition module to perform a target operation, wherein the target operation comprises: detecting the target image to determine the state of objects stored in an object storage area in the target image; when it is determined that the state of objects stored in the object storage area has changed, waking up a main control to instruct the main control to further detect the state of objects stored in the object storage area based on the target image.
[0005] In an exemplary embodiment, before determining whether the target wake-up condition is currently met, the method further includes: waking up the sensor in response to the radar detecting the target object; and acquiring the target image collected by the sensor according to the target detection frequency.
[0006] In an exemplary embodiment, before obtaining the target image captured by the sensor according to the target detection frequency, the method also includes: obtaining target scene parameter information of the item storage area input by the sensor; calculating the target scene parameter information using a fuzzy algorithm, and adjusting the detection frequency of the sensor to the target detection frequency based on the calculation result.
[0007] In an exemplary embodiment, before using a fuzzy algorithm to calculate the target scene parameter information, the method also includes: configuring a correspondence rule between the scene parameter information of the item storage area and an output action, wherein the output action includes adjusting the detection frequency of the sensor; using a fuzzy algorithm to calculate the target scene parameter information includes: calculating the input target scene parameter information based on the corresponding rule to obtain a target output action.
[0008] In an exemplary embodiment, using a fuzzy algorithm to calculate the target scene parameter information includes: for any scene parameter information included in the target scene parameter information, performing the following operations to determine the input membership corresponding to each scene parameter information: determining a pre-configured first membership function corresponding to a first scene parameter, wherein the first scene parameter is any scene parameter included in the target scene parameters of the item storage area; determining the membership under each function condition included in the first membership function; determining the input membership corresponding to the first scene parameter information based on the function condition corresponding to the parameter value of the first scene parameter included in the first scene parameter information, wherein the first scene parameter information is the parameter information of the first scene parameter; using the fuzzy algorithm to calculate the input membership corresponding to the target scene parameter information.
[0009] In an exemplary embodiment, adjusting the detection frequency of the sensor to the target detection frequency based on the calculation results includes: determining a fuzzy set obtained by calculating the input membership corresponding to the target scene parameter information using the fuzzy algorithm; determining a target fuzzy set included in the fuzzy set and corresponding to adjusting the detection frequency of the sensor; determining a target centroid value of the target fuzzy set; determining the target detection frequency corresponding to the target centroid value from a pre-configured correspondence between the centroid value and the detection frequency; and adjusting the detection frequency of the sensor to the target detection frequency.
[0010] In an exemplary embodiment, after calculating the target scene parameter information using a fuzzy algorithm, the method further includes at least one of the following: determining a notification method for notifying that a status change of items stored in the item storage area is occurring based on the calculation result; determining an alarm status of an alarm configured on the target device based on the calculation result.
[0011] According to another embodiment of the present invention, a single chip computer is provided, including: a first determination module, used to determine whether a target wake-up condition is currently met when an object recognition module is in a sleep state and a target image is received; a processing module, used to wake up the object recognition module when it is determined that the target wake-up condition is met, and transmit the target image to the object recognition module to instruct the object recognition module to perform a target operation, wherein the target operation includes: detecting the target image to determine the state of objects stored in an object storage area in the target image; and waking up the main control when it is determined that the state of the objects stored in the object storage area has changed, to instruct the main control to further detect the state of the objects stored in the object storage area based on the target image.
[0012] According to another embodiment of the present invention, there is also provided a visual smart lock, comprising the single chip microcomputer, the object identification module and the main control.
[0013] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when run.
[0014] According to yet another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0015] Through the present invention, since the object recognition module is awakened and instructed to perform object status recognition based on the target image when the target image is received and the target conditions are met, the frequency of the object recognition module performing object status recognition operations is reduced. Therefore, it is possible to solve the problem of high energy consumption caused by the need to collect data in real time and perform object detection analysis in the object detection method in the related art, thereby achieving the effect of avoiding unnecessary recognition operations and significantly reducing equipment energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 is a hardware structure block diagram of a mobile terminal according to an object detection method of an embodiment of the present invention;
[0017] Figure 2 is a flow chart of an object detection method according to an embodiment of the present invention;
[0018] Figure 3 is an interactive schematic diagram of a visual smart lock system according to an embodiment of the present invention;
[0019] Figure 4is a schematic diagram of the working principle of a controller according to an embodiment of the present invention;
[0020] Figure 5 is a structural block diagram of an object detection device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0021] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in combination with the embodiments.
[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0023] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is a hardware structure block diagram of a mobile terminal according to an object detection method of an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.
[0024] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the object detection method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0025] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0026] In this embodiment, a method for detecting an object running on the above mobile terminal or network architecture is provided. Figure 2 is a flow chart of an object detection method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:
[0027] Step S202, when the object recognition module is in a dormant state and receives a target image, determining whether a target wake-up condition is currently met;
[0028] Step S204, when it is determined that the target wake-up condition is met, wake up the object recognition module, and transmit the target image to the object recognition module to instruct the object recognition module to perform a target operation, wherein the target operation includes: detecting the target image to determine the status of the objects stored in the object storage area in the target image; when it is determined that the status of the objects stored in the object storage area has changed, wake up the main control to instruct the main control to further detect the status of the objects stored in the object storage area based on the target image.
[0029] In the above steps, the target wake-up conditions include but are not limited to: the time period for waking up the item recognition module (for example, the time elapsed since the last time the item recognition module was awakened has reached a preset time threshold), and the status of the items stored in the item storage area includes but is not limited to: the number of items stored in the item storage area, the placement of the items stored in the item storage area, etc.
[0030] Among them, the executor of the above steps can be a PID (Proportional-Integral-Derivative) controller, a single-chip microcomputer equipped with a PID controller, other controllers with similar functions to a PID controller, devices equipped with a controller with similar functions to a PID controller, etc., but are not limited to these.
[0031] In the above steps, by waking up and instructing the object recognition module to perform object status recognition based on the target image when the target image is received and the target conditions are met, the frequency of the object recognition module performing object status recognition operations is reduced, unnecessary recognition operations are avoided, and the energy consumption of the device is significantly reduced.
[0032] In an optional embodiment, before determining whether the target wake-up condition is currently met, the method further includes: waking up the sensor in response to the radar detecting the target object; and acquiring the target image collected by the sensor according to the target detection frequency.
[0033] In the above steps, the radar is used to detect the position, speed, status and other information of the target object by transmitting and receiving reflected waves based on electromagnetic wave technology, and the sensor unit is used to capture images in the object storage area.
[0034] In an optional embodiment, before determining whether the target wake-up condition is currently met, the method also includes at least one of the following: the sensor collects the target image at the target frequency; the sensor collects the target image under the triggering of the radar, wherein the radar is used to trigger the sensor to collect the target image when it detects the presence of a target object in the item storage area.
[0035] In an optional embodiment, the method also includes: when the object recognition module is in a dormant state and the sensor detects that a target event (for example, the presence of a moving object, a fire, or a water leak) occurs in the storage area of the target area (for example, a larger area including the object storage area), the sensor photographs the object storage area and sends the photographed image to the object recognition module to instruct the object recognition module to detect the image.
[0036] In the above steps, exemplarily, the sensor further includes: a temperature monitoring unit, a humidity monitoring unit, a light monitoring unit, and the like.
[0037] In an optional embodiment, before obtaining the target image captured by the sensor according to the target detection frequency, the method also includes: obtaining target scene parameter information of the item storage area input by the sensor; calculating the target scene parameter information using a fuzzy algorithm, and adjusting the detection frequency of the sensor to the target detection frequency based on the calculation result.
[0038] In the above steps, the target scene parameter information includes but is not limited to: ambient light intensity, speed of the moving object, object size, number of people passing by, shooting time of the target image, etc.
[0039] In the above steps, the detection frequency of the sensor is adjusted based on the fuzzy algorithm according to the scene parameter information of the item storage area, so that when the environment of the item storage area changes, the detection strategy can be automatically adjusted to adapt to different monitoring conditions, thereby improving the effectiveness of item identification.
[0040] In an optional embodiment, before using a fuzzy algorithm to calculate the target scene parameter information, the method also includes: configuring a correspondence rule between the scene parameter information of the item storage area and the output action, wherein the output action includes adjusting the detection frequency of the sensor; using a fuzzy algorithm to calculate the target scene parameter information includes: calculating the input target scene parameter information based on the corresponding rule to obtain the target output action.
[0041] In the above steps, illustratively, the output action includes but is not limited to: notifying the target object (for example, not notifying, SMS notification, phone notification, message push notification, etc.), alarm device alarm (for example, triggering alarm device alarm, not triggering alarm device alarm, etc.), adjusting target detection frequency (adjusting to high target detection frequency, adjusting to low target detection frequency, adjusting to medium target detection frequency, keeping target detection frequency unchanged, etc.), etc., and the output action includes but is not limited to one or more of the above actions. The corresponding rules can be pre-set, and the corresponding rules can be adjusted according to different application scenarios. For example, Table 1 shows the exemplary corresponding rules.
[0042] Table 1
[0043]
[0044]
[0045] In an optional embodiment, using a fuzzy algorithm to calculate the target scene parameter information includes: for any scene parameter information included in the target scene parameter information, performing the following operations to determine the input membership corresponding to each scene parameter information: determining a pre-configured first membership function corresponding to a first scene parameter, wherein the first scene parameter is any scene parameter included in the target scene parameters of the item storage area; determining the membership under each function condition included in the first membership function; determining the input membership corresponding to the first scene parameter information based on the function condition corresponding to the parameter value of the first scene parameter included in the first scene parameter information, wherein the first scene parameter information is the parameter information of the first scene parameter; using the fuzzy algorithm to calculate the input membership corresponding to the target scene parameter information.
[0046] In the above steps, the first membership function includes but is not limited to: triangular membership function, trapezoidal membership function, Gaussian membership function, generalized bell-shaped membership function, S-shaped membership function, Z-shaped membership function, exponential membership function, linear membership function, etc. Exemplarily, the first membership function corresponding to the ambient light intensity includes but is not limited to the triangular membership function, the first membership function corresponding to the detection of whether there is a moving object includes but is not limited to the binary membership function, the first membership function corresponding to the object size includes but is not limited to the Gaussian membership function, the first membership function corresponding to the detection of the number of people passing by includes but is not limited to the trapezoidal membership function, and the first membership function corresponding to the shooting time of the target image includes but is not limited to the triangular membership function.
[0047] In an optional embodiment, adjusting the detection frequency of the sensor to the target detection frequency based on the calculation result includes: determining a fuzzy set obtained by calculating the input membership corresponding to the target scene parameter information using the fuzzy algorithm; determining a target fuzzy set included in the fuzzy set and corresponding to adjusting the detection frequency of the sensor; determining a target center of gravity value of the target fuzzy set; determining the target detection frequency corresponding to the target center of gravity value from a pre-configured correspondence between the center of gravity value and the detection frequency; and adjusting the detection frequency of the sensor to the target detection frequency.
[0048] In the above steps, exemplarily, a fuzzy algorithm is used to determine the membership with low detection frequency, the membership with medium detection frequency and the membership with high detection frequency included in the target fuzzy set through the input membership of the ambient light intensity, the detection of whether there is a moving object, the object size, the detection of the number of people passing by and the shooting time of the target image included in the target scene parameter information, and the target centroid value of the target fuzzy set is determined according to the membership with low detection frequency, the membership with medium detection frequency and the membership with high detection frequency, so as to determine the target detection frequency according to the target centroid value.
[0049] Exemplarily, the first membership function corresponding to the ambient light intensity includes but is not limited to the triangular membership function, the first membership function corresponding to the detection of moving objects includes but is not limited to the binary membership function, the first membership function corresponding to the object size includes but is not limited to the Gaussian membership function, the first membership function corresponding to the number of people passing by includes but is not limited to the trapezoidal membership function, and the first membership function corresponding to the shooting time of the target image includes but is not limited to the triangular membership function.
[0050] Exemplarily, the first membership degree corresponding to the ambient light intensity can be calculated by using a triangular membership function. Here, \(x\) is the input value, \(a\) is the left vertex of the triangle, defined as the starting point where the membership degree value is 1, \(b\) is the top of the triangle, defined as the point where the membership degree value is the largest (usually 1), and \(c\) is the right vertex of the triangle, defined as the ending point where the membership degree value is 1. When \((x < a)\), the membership degree is 0, indicating that \((x)\) does not belong to this fuzzy set. When \((a\leq x < b)\), the membership degree increases linearly, from 0 to 1. When \((b\leq x < c)\), the membership degree decreases linearly, from 1 to 0. When \((x\geq c)\), the membership degree is 0, indicating that \((x)\) no longer belongs to this fuzzy set.
[0051] The calculation formula for the triangular membership function \((\mu_A(x))\) is as follows:
[0053] \(\mu_A(x)=\)
[0054] \(\begin{cases}
[0055] 0&\text{if}x < a
[0056] \frac{x - a}{b - a}&\text{if}a\leq x < b
[0057] \frac{c - x}{c - b}&\text{if}b\leq x < c
[0058] 0&\text{if}x\geq c
[0059] \end{cases}
[0061] Exemplarily, a triangular membership function is defined to describe low ambient light intensity. Setting the parameters \((a = 0)\), \((b = 5)\), and \((c = 10)\), the membership function for low ambient light intensity can be expressed as:
[0063] \(\mu_{\text{low}}(x)=\)
[0064] \(\begin{cases}
[0065] 0&\text{if}x < 0
[0066] \frac{x - 0}{5 - 0}=\frac{x}{5}&\text{if}0\leq x < 5
[0067] \frac{10-x}{10-5}=2-\frac{x}{5}&\text{if}5\leq x<10\
[0068] 0&\text{if}x\geq 10
[0069] \end{cases} ]
[0071] For the range from (x=0) to (x=10), the membership of each value can be calculated, for example:
[0072] When (x=3), (\mu_{\text{low}}(3)=\frac{3}{5}=0.6)
[0073] When (x=7), (\mu_{\text{low}}(7)=2-\frac{7}{5}=2-1.4=0.6)
[0074] For example, when the membership of the low detection frequency is 0.2, the membership of the medium detection frequency is 0.5, and the membership of the high detection frequency is 0.8, the target centroid value includes but is not limited to being calculated by the following method:
[0075] molecular: [
[0077] \text{Numerator}=(0\times 0.2)+(1\times 0.5)+(2\times 0.8)=0+0.5+1.6=2.1 ]
[0079] Denominator: [
[0081] \text{denominator}=0.2+0.5+0.8=1.5 ]
[0083] Center of Gravity (C): [
[0085] C = \frac{2.1}{1.5}\approx 1.4\quad(\text{close to the frequency}) ]
[0087] Among them, 0 is the weight of the membership with low detection frequency, 1 is the weight of the membership with medium detection frequency, and 2 is the weight of the membership with high detection frequency. The target centroid value is 1.4, and 1.4 corresponds to medium detection frequency. The above weights are pre-set and can be adjusted according to different application scenarios.
[0088] In an optional embodiment, after calculating the target scene parameter information using a fuzzy algorithm, the method further includes at least one of the following: determining a notification method for notifying that a status of items stored in the item storage area has changed based on the calculation result; determining an alarm status of an alarm configured on the target device based on the calculation result.
[0089] In the above steps, the notification methods include but are not limited to: no notification, SMS notification, and phone notification, and the alarm status includes but is not limited to: triggering an alarm device to alarm, not triggering an alarm device to alarm, etc. Exemplarily, the method further includes: using a fuzzy algorithm to determine the membership of no notification, SMS notification, and phone notification included in the target fuzzy set through the input membership of the ambient light intensity, the detection of whether there is a moving object, the object size, the detection of the number of people passing by, and the shooting time of the target image included in the target scene parameter information, and determining the target centroid value of the target fuzzy set based on the membership of no notification, SMS notification, and phone notification, thereby determining the notification method and the alarm status of the alarm based on the target centroid value.
[0090] For example, when the membership of SMS notification is 0.6, the membership of phone notification is 0.3, and the membership of no notification is 0.1, the target centroid value includes but is not limited to being calculated by the following method:
[0091] molecular: [
[0093] \text{Numerator}=(1.5\times 0.6)+(2.5\times 0.3)+(0\times 0.1)=0.9+0.75+0=1.65 ]
[0095] Denominator: [
[0097] \text{Denominator}=0.6+0.3+0.1=1.0 ]
[0099] Center of Gravity (C): [
[0101] C = \frac{1.65}{1.0} = 1.65\quad(\text{approaching SMS notification}) ]
[0103] Among them, 1.5 is the weight of the membership degree of SMS notification, 2.5 is the weight of the membership degree of telephone notification, and 0 is the weight of the membership degree of no notification. The target centroid value is 1.65, and the notification method corresponding to 1.65 is SMS notification.
[0104] For example, when the membership degree of triggering the alarm device alarm is 0.6 and the membership degree of not triggering the alarm device alarm is 0.4, the target centroid value includes but is not limited to being calculated by the following method:
[0105] molecular: [
[0107] \text{Numerator}=(0\times 0.4)+(1\times 0.6)=0+0.6=0.6 ]
[0109] Denominator: [
[0111] \text{Denominator}=0.4+0.6=1.0 ]
[0113] Center of Gravity (C): [
[0115] C = \frac{0.6}{1.0} = 0.6\quad(\text{close to the sound}) ]
[0117] Among them, 0 is the weight of the membership that does not trigger the alarm device alarm, 1 is the weight of the membership that triggers the alarm device alarm, and the target centroid value is 0.6, and 0.6 corresponds to triggering the alarm device alarm. The above weights are preset and can be adjusted according to different application scenarios.
[0118] The following is an exemplary description of the solution in this application in conjunction with specific embodiments:
[0119] The solution in this application can be applied in a visual smart lock system. Figure 3 is an interactive schematic diagram of a visual smart lock system according to an embodiment of the present invention. Figure 3As shown, the visual intelligent lock system includes: hardware sensors, single-chip microcomputers, package identification algorithm modules and main control. Among them, the hardware sensors include radars and sensors, and the single-chip microcomputer is equipped with a PID controller. The radar in the hardware sensor is used to send a message to the PID controller when a parameter change is detected. After receiving the message sent by the radar, the PID controller sends an instruction to the sensor for image acquisition and photosensitive parameters, and performs screen inspection regularly. The sensor transmits the collected soft photosensitive parameters to the PID controller in the single-chip microcomputer. The PID controller wakes up the package identification algorithm module and instructs the package identification algorithm module to judge whether the number of packages in the current screen has changed from the number of packages in the previous screen according to the image and soft photosensitive parameters collected by the sensor, and returns the judgment result of the change in the number of packages to the PID controller. In the case of a change in the number of packages, the main control is awakened for business processing, and then the package identification algorithm module enters sleep. After being awakened, the main control performs business processing (for example, using its own computing power to re-judge the number of packages in the current screen, if the number of packages changes, it is reported to the cloud platform and pushed to the user end), and enters sleep after the business processing is completed. The PID controller determines whether to modify the interval of the sensor for periodic dynamic inspection based on the result of the change in the number of packages detected, and sends a modification instruction if it is determined that modification is required.
[0120] In the above-mentioned visual smart lock system, the interval setting of the image sensor's regular dynamic detection is realized by combining the PID controller and the fuzzy controller. Specifically, according to the brightness value in the environment, the image sensor's dynamic detection interval is automatically adjusted through the adaptive fuzzy control algorithm, thereby realizing the all-weather package guard function while reducing product power consumption. Figure 4 Shown is a schematic diagram of the working principles of PID controller and fuzzy controller.
[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0122] In this embodiment, a single-chip microcomputer device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.
[0123] Figure 5 is a structural block diagram of an object detection device according to an embodiment of the present invention. Figure 5 As shown, the single chip computer includes: a first determination module 52, which is used to determine whether a target wake-up condition is currently met when the object recognition module is in a sleep state and receives a target image; a processing module 54, which is used to wake up the object recognition module and transmit the target image to the object recognition module to instruct the object recognition module to perform a target operation when it is determined that the target wake-up condition is met, wherein the target operation includes: detecting the target image to determine the state of the objects stored in the object storage area in the target image; and waking up the main control when it is determined that the state of the objects stored in the object storage area has changed, to instruct the main control to further detect the state of the objects stored in the object storage area based on the target image.
[0124] In an optional embodiment, the single chip microcomputer also includes: a wake-up module, used to wake up the sensor in response to the radar monitoring the target object before determining whether the target wake-up condition is currently met; a first acquisition module, used to acquire the target image collected by the sensor according to the target detection frequency.
[0125] In an optional embodiment, the single chip microcomputer also includes: a second acquisition module, which is used to obtain the target scene parameter information of the item storage area input by the sensor before obtaining the target image collected by the sensor according to the target detection frequency; a calculation module, which is used to calculate the target scene parameter information using a fuzzy algorithm, and adjust the detection frequency of the sensor to the target detection frequency based on the calculation result.
[0126] In an optional embodiment, the single chip computer also includes: a configuration module, which is used to configure the correspondence rules between the scene parameter information of the item storage area and the output action before using the fuzzy algorithm to calculate the target scene parameter information, wherein the output action includes adjusting the detection frequency of the sensor; the calculation module includes: a first calculation unit, which is used to calculate the input target scene parameter information based on the corresponding rules to obtain the target output action.
[0127] In an optional embodiment, the calculation module includes: a processing unit, used to perform the following operations for any scene parameter information included in the target scene parameter information to determine the input membership corresponding to each scene parameter information: determine a pre-configured first membership function corresponding to a first scene parameter, wherein the first scene parameter is any scene parameter included in the target scene parameters of the item storage area; determine the membership under each function condition included in the first membership function; determine the input membership corresponding to the first scene parameter information based on the function condition corresponding to the parameter value of the first scene parameter included in the first scene parameter information, wherein the first scene parameter information is the parameter information of the first scene parameter; a second calculation unit, used to use the fuzzy algorithm to calculate the input membership corresponding to the target scene parameter information.
[0128] In an optional embodiment, the calculation module includes: a first determination unit, used to determine a fuzzy set obtained by calculating the input membership corresponding to the target scene parameter information using the fuzzy algorithm; a second determination unit, used to determine a target fuzzy set included in the fuzzy set and corresponding to adjusting the detection frequency of the sensor; a third determination unit, used to determine a target center of gravity value of the target fuzzy set; a fourth determination unit, used to determine the target detection frequency corresponding to the target center of gravity value from a pre-configured correspondence between the center of gravity value and the detection frequency; and an adjustment unit, used to adjust the detection frequency of the sensor to the target detection frequency.
[0129] In an optional embodiment, the single chip computer also includes: a second determination module, which is used to determine, based on the calculation result, after calculating the target scene parameter information using a fuzzy algorithm, a notification method for notifying that the status of the items stored in the item storage area has changed; and a third determination module, which is used to determine the alarm status of an alarm configured on the target device based on the calculation result.
[0130] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.
[0131] The embodiment of the present invention further provides a visual smart lock, comprising: the single chip microcomputer, the object recognition module and the main control. Exemplarily, the visual smart lock comprises the following components: a single chip microcomputer, a sensor for detecting an image of an object storage area, an object recognition module, a main control, and the like.
[0132] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.
[0133] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.
[0134] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0135] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0136] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.
[0137] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0138] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for detecting an object, characterized in that: include: When the object recognition module is in a dormant state and receives a target image, determining whether a target wake-up condition is currently met; When it is determined that the target wake-up condition is met, the object recognition module is woken up, and the target image is transmitted to the object recognition module to instruct the object recognition module to perform a target operation, wherein the target operation includes: detecting the target image to determine the state of the objects stored in the object storage area in the target image; when it is determined that the state of the objects stored in the object storage area has changed, waking up the main control to instruct the main control to further detect the state of the objects stored in the object storage area based on the target image.
2. The method according to claim 1, characterized in that Before determining whether the target wake-up condition is currently reached, the method further includes: In response to the radar detecting a target object, waking up the sensor; The target image collected by the sensor according to the target detection frequency is obtained.
3. The method according to claim 2, characterized in that Before acquiring the target image collected by the sensor according to the target detection frequency, the method further includes: Acquire target scene parameter information of the item storage area input by the sensor; The target scene parameter information is calculated using a fuzzy algorithm, and the detection frequency of the sensor is adjusted to the target detection frequency based on the calculation result.
4. The method according to claim 3, characterized in that Before calculating the target scene parameter information using a fuzzy algorithm, the method further includes: Configuring a correspondence rule between the scene parameter information of the item storage area and the output action, wherein the output action includes adjusting the detection frequency of the sensor; Calculating the target scene parameter information using a fuzzy algorithm includes: calculating the input target scene parameter information based on the corresponding rule to obtain a target output action.
5. The method according to claim 3, characterized in that: Calculating the target scene parameter information using a fuzzy algorithm includes: For any scene parameter information included in the target scene parameter information, the following operations are performed to determine the input membership corresponding to each scene parameter information: determining a pre-configured first membership function corresponding to a first scene parameter, wherein the first scene parameter is any scene parameter included in the target scene parameter of the item storage area; determining the membership under each function condition included in the first membership function; determining the input membership corresponding to the first scene parameter information based on the function condition corresponding to the parameter value of the first scene parameter included in the first scene parameter information, wherein the first scene parameter information is the parameter information of the first scene parameter; The fuzzy algorithm is used to calculate the input membership corresponding to the target scene parameter information.
6. The method according to claim 5, characterized in that Adjusting the detection frequency of the sensor to the target detection frequency based on the calculation result includes: Determine a fuzzy set obtained by calculating the input membership corresponding to the target scene parameter information using the fuzzy algorithm; Determining a target fuzzy set included in the fuzzy set and corresponding to adjusting the detection frequency of the sensor; Determining a target centroid value of the target fuzzy set; Determining the target detection frequency corresponding to the target center of gravity value from a pre-configured correspondence relationship between the center of gravity value and the detection frequency; The detection frequency of the sensor is adjusted to the target detection frequency.
7. The method according to claim 3, characterized in that After calculating the target scene parameter information using a fuzzy algorithm, the method further includes at least one of the following: Determining a notification method for notifying that a state of an item stored in the item storage area has changed based on the calculation result; The alarm state of the alarm configured on the target device is determined based on the calculation result.
8. A single chip microcomputer, characterized in that: include: A first determination module is used to determine whether a target wake-up condition is currently met when the object recognition module is in a dormant state and receives a target image; A processing module is used to wake up the object recognition module when it is determined that the target wake-up condition is met, and transmit the target image to the object recognition module to instruct the object recognition module to perform a target operation, wherein the target operation includes: detecting the target image to determine the status of the objects stored in the object storage area; and waking up the main control when it is determined that the status of the objects stored in the object storage area has changed, so as to instruct the main control to further detect the status of the objects stored in the object storage area based on the target image.
9. A visual smart lock, characterized in that: include: The single chip microcomputer, the object identification module and the main control as described in claim 8.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 7 when executed by a processor.
11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.
12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.