Classification method, device and equipment for intelligent lighting and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, can be applied to the field of smart pension, and discloses a classification method, device and equipment for smart lighting and a storage medium, and the method comprises the steps: obtaining a current radar signal collected by a target radar; extracting a first signal and a second signal in the current radar signal; acquiring a displacement value between the first signal and the second signal; when the displacement value meets a preset condition, acquiring a feature vector of the current radar signal; inputting the feature vector of the current radar signal into a classifier, and obtaining a current classification label output by the classifier; and when the current classification tag is the pedestrian tag or the non-motor vehicle tag, controlling the lighting equipment to be in an on state. The method is beneficial to improving the classification efficiency of pedestrians or non-motor vehicles, is also beneficial to saving computing power, gives consideration to improvement of road safety and saving of power consumption of lighting equipment, and can be widely applied to intelligent old-age care scenes such as communities and hospitals.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and smart elderly care, and in particular to a classification method, device, equipment and storage medium for smart lighting. Background Art

[0002] Smart lighting is a system that intelligently controls lighting equipment. Smart lighting provides adequate lighting for pedestrians, reducing safety hazards when walking at night. It also illuminates the road for non-motor vehicle drivers, reducing the risk of traffic accidents. In addition, smart lighting is used in elderly care scenarios to ensure that the elderly can get timely lighting when needed, enhancing the safety and convenience of living space.

[0003] However, the classification process of pedestrians or non-motor vehicles by existing intelligent lighting is cumbersome, which is not conducive to improving the classification efficiency of pedestrians or non-motor vehicles. The reason is that the classification process of pedestrians or non-motor vehicles by existing intelligent lighting requires the capture and classification of pedestrian or non-motor vehicle images, and the process of capturing and classifying pedestrian or non-motor vehicle images is often accompanied by high computational complexity, which will result in a relatively long classification time for pedestrians or non-motor vehicles. Therefore, it is not conducive to improving the classification efficiency of pedestrians or non-motor vehicles. Summary of the invention

[0004] The present invention provides a classification method, device, computer equipment and storage medium for intelligent lighting to solve the technical problem that the classification process of pedestrians or non-motor vehicles in existing intelligent lighting is cumbersome and is not conducive to improving the classification efficiency of pedestrians or non-motor vehicles.

[0005] In a first aspect, a classification method for intelligent lighting is provided, comprising:

[0006] Obtain the current radar signal collected by the target radar;

[0007] Extracting a first signal and a second signal from the current radar signal;

[0008] Acquire a displacement value between the first signal and the second signal;

[0009] When the displacement value meets a preset condition, obtaining a feature vector of the current radar signal;

[0010] Inputting the feature vector of the current radar signal into a classifier to obtain a current classification label output by the classifier;

[0011] When the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state.

[0012] Further, extracting the first signal and the second signal from the current radar signal includes:

[0013] Acquire a first sliding window and a second sliding window, where the second sliding window is a next window of the first sliding window;

[0014] A first signal is extracted from the current radar signal through the first sliding window, and a second signal is extracted from the current radar signal through the second sliding window.

[0015] Further, the obtaining the displacement value between the first signal and the second signal includes:

[0016] Acquire a phase difference between the first signal and the second signal;

[0017] The phase difference is converted into a time difference, and the time difference is multiplied by a propagation speed to obtain a displacement value between the first signal and the second signal.

[0018] Further, when the displacement value satisfies a preset condition, obtaining a feature vector of the current radar signal includes:

[0019] When the displacement value is greater than a preset value, feature extraction is performed on the first signal and the second signal respectively by a preset feature extractor to obtain a feature vector of the first signal and a feature vector of the second signal;

[0020] The feature vector of the first signal and the feature vector of the second signal are concatenated to generate a feature vector of the current radar signal.

[0021] Furthermore, the step of inputting the feature vector of the current radar signal into a classifier to obtain a current classification label output by the classifier includes:

[0022] Obtain a model file of a classifier, load the model file, and obtain a loading result of the model file;

[0023] When the loading result is successful, the feature vector of the current radar signal is input into the classifier to obtain the current classification label output by the classifier.

[0024] Furthermore, when the current classification label is a pedestrian label or a non-motor vehicle label, controlling the lighting device to be in an on state includes:

[0025] When the current classification tag is a pedestrian tag or a non-motor vehicle tag, reading the current state of the lighting device;

[0026] When the current state is the off state, the lighting device is controlled to switch from the off state to the on state.

[0027] Furthermore, after inputting the feature vector of the current radar signal into the classifier and obtaining the current classification label output by the classifier, the classification method includes:

[0028] When the current classification tag is an animal tag or a motor vehicle tag, the lighting device is controlled to be in an off state.

[0029] In a second aspect, a classification device for intelligent lighting is provided, comprising:

[0030] A first acquisition module is used to acquire a current radar signal collected by a target radar;

[0031] An extraction module, used to extract a first signal and a second signal from the current radar signal;

[0032] A second acquisition module, used to acquire a displacement value between the first signal and the second signal;

[0033] A third acquisition module, configured to acquire a feature vector of the current radar signal when the displacement value meets a preset condition;

[0034] An input module, used to input the feature vector of the current radar signal into a classifier, and obtain a current classification label output by the classifier;

[0035] The classification module is used to control the lighting device to be in an on state when the current classification label is a pedestrian label or a non-motor vehicle label.

[0036] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned classification method when executing the computer program.

[0037] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned classification method are implemented.

[0038] The present application provides a classification method, device, computer equipment and storage medium for intelligent lighting, which obtains a current radar signal collected by a target radar; extracts a first signal and a second signal from the current radar signal; obtains a displacement value between the first signal and the second signal; when the displacement value meets a preset condition, obtains a feature vector of the current radar signal; inputs the feature vector of the current radar signal into a classifier to obtain a current classification label output by the classifier; when the current classification label is a pedestrian label or a non-motor vehicle label, controls the lighting device to be in an on state, and has beneficial effects in two aspects. On the one hand, inputs the feature vector of the current radar signal into a classifier to obtain a current classification label output by the classifier. Classification label, when the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in the on state, the pedestrian label is the label of the pedestrian, and the non-motor vehicle label is the label of the non-motor vehicle. Since there is no need to capture and classify the images of pedestrians or non-motor vehicles, the classification time of pedestrians or non-motor vehicles is reduced, which is beneficial to improving the classification efficiency of pedestrians or non-motor vehicles. At the same time, it is beneficial to save computing power, improve road safety and save electricity consumption of lighting equipment. It can be widely used in smart elderly care scenarios such as communities and hospitals; on the other hand, when the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in the on state, which avoids the power loss caused by invalid lighting and is beneficial to saving electricity. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0040] Figure 1 is a schematic diagram of an application environment of a classification method in an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of a flow chart of a classification method provided by an embodiment of the present invention;

[0042] Figure 3 yes Figure 1 A schematic flow chart of a specific implementation of step S23;

[0043] Figure 4 yes Figure 1 A schematic flow chart of a specific implementation of step S25;

[0044] Figure 5 yes Figure 1 A schematic flow chart of a specific implementation of step S26;

[0045] Figure 6 is a structural schematic diagram of a classification device in one embodiment of the present invention;

[0046] Figure 7 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0047] Figure 8 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] See also Figure 1 , Figure 1 is a schematic diagram of an application environment of a classification method in an embodiment of the present invention. The classification method provided by the embodiment of the present invention can be applied in the following situations: Figure 1 In an application environment, a client communicates with a server through a network.

[0050] The server obtains the current radar signal collected by the target radar through the client;

[0051] Extracting a first signal and a second signal from the current radar signal;

[0052] Acquire a displacement value between the first signal and the second signal;

[0053] When the displacement value meets a preset condition, obtaining a feature vector of the current radar signal;

[0054] Inputting the feature vector of the current radar signal into a classifier to obtain a current classification label output by the classifier;

[0055] When the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state.

[0056] In the scheme implemented by the above-mentioned classification method, device, equipment and medium, the beneficial effects are in two aspects. On the one hand, the characteristic vector of the current radar signal is input into the classifier to obtain the current classification label output by the classifier. When the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state. The pedestrian label is a pedestrian label, and the non-motor vehicle label is a non-motor vehicle label. Since there is no need to capture and classify the images of pedestrians or non-motor vehicles, the classification time of pedestrians or non-motor vehicles is reduced, which is beneficial to improving the classification efficiency of pedestrians or non-motor vehicles. At the same time, it is beneficial to save computing power, improve road safety and save electricity consumption of lighting equipment. It can be widely used in smart elderly care scenarios such as communities and hospitals; on the other hand, when the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state, which avoids power loss due to invalid lighting and is beneficial to saving power.

[0057] The device running the client is referred to as a client device.

[0058] The device running the server is referred to as the server device.

[0059] The client devices may include but are not limited to various personal computers, laptops, smart phones, tablet computers, and portable wearable devices.

[0060] The server device can be implemented by an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0061] See also Figure 2 , Figure 2 A flow chart of a classification method provided in an embodiment of the present invention includes the following steps:

[0062] S21, obtaining the current radar signal collected by the target radar;

[0063] Among them, the target radar includes but is not limited to Doppler radar and frequency modulated continuous wave radar.

[0064] Among them, Doppler radar, also known as pulse Doppler radar, is a radar that can perform positioning, speed measurement, and distance measurement. Doppler radar usually emits a continuous wave of a fixed frequency and measures the target's speed and position by analyzing the frequency changes of the echo signal. The transmitter of the Doppler radar is always on, and this continuous working mode gives the Doppler radar excellent speed resolution.

[0065] Among them, FMCW radar refers to a continuous wave radar whose transmission frequency is modulated by a specific signal. FMCW radar transmits a continuous wave whose frequency changes linearly with time.

[0066] Exemplarily, before acquiring the current radar signal collected by the target radar, the classification method includes:

[0067] Obtaining a preset radar signal, inputting the preset radar signal into a preset support vector machine, and obtaining a predicted classification label output by the support vector machine;

[0068] Obtaining a loss value between the predicted classification label and the actual classification label, and training the support vector machine according to the loss value;

[0069] When the preset value is less than the preset value, the trained support vector machine is selected as the classifier.

[0070] Among them, the true classification label is the true classification label.

[0071] The preset radar signal is a preset continuous electromagnetic wave signal.

[0072] Among them, the current radar signal is the current continuous electromagnetic wave signal.

[0073] S22, extracting a first signal and a second signal from the current radar signal;

[0074] The extracting the first signal and the second signal from the current radar signal includes:

[0075] Acquire a first sliding window and a second sliding window, where the second sliding window is a next window of the first sliding window;

[0076] A first signal is extracted from the current radar signal through the first sliding window, and a second signal is extracted from the current radar signal through the second sliding window.

[0077] For example, the time of the first sliding window and the second sliding window includes but is not limited to 0.5 seconds and 1 second.

[0078] For the sake of illustration, an example is given below:

[0079] For example, there is a continuous current radar signal. The position of the first sliding window starts from the starting point of the current radar signal, covering the signal from 0 seconds to 0.5 seconds of the current radar signal. The position of the second sliding window starts from 0.5 seconds of the current radar signal, covering the signal from 0.5 seconds to 1 second of the current radar signal. The first sliding window is used to extract the signal from 0 seconds to 0.5 seconds of the current radar signal as the first signal, and the second sliding window is used to extract the signal from 0.5 seconds to 1 second of the current radar signal as the second signal.

[0080] For example, there is a continuous current radar signal. The position of the first sliding window starts from the starting point of the current radar signal and covers the signal from 0 seconds to 1 second of the current radar signal. The position of the second sliding window starts from 1 second of the current radar signal and covers the signal from 1 second to 2 seconds of the current radar signal. The first sliding window is used to extract the signal from 0 seconds to 1 second of the current radar signal as the first signal, and the second sliding window is used to extract the signal from 1 second to 2 seconds of the current radar signal as the second signal.

[0081] Among them, through the first sliding window and the second sliding window, we can focus on a specific time period in the current radar signal, which can reduce the calculation complexity, save calculation resources, and help improve the processing speed.

[0082] S23, obtaining a displacement value between the first signal and the second signal;

[0083] Among them, the displacement value between the first signal and the second signal is obtained. This displacement value reflects the position change of the target object relative to the target radar and is the basis for realizing target monitoring.

[0084] S24, when the displacement value meets a preset condition, obtaining a feature vector of the current radar signal;

[0085] Wherein, when the displacement value satisfies a preset condition, obtaining the characteristic vector of the current radar signal includes:

[0086] When the displacement value is greater than a preset value, feature extraction is performed on the first signal and the second signal respectively by a preset feature extractor to obtain a feature vector of the first signal and a feature vector of the second signal;

[0087] The feature vector of the first signal and the feature vector of the second signal are concatenated to generate a feature vector of the current radar signal.

[0088] When the displacement value is greater than a preset value, feature extraction is performed on the first signal and the second signal respectively by a preset feature extractor to obtain a feature vector of the first signal and a feature vector of the second signal, including:

[0089] When the displacement value is greater than a preset value, a preset feature extractor is used to extract features of the first signal to obtain a signal amplitude, a signal phase, and a spectrum feature of the first signal, and the signal amplitude, signal phase, and spectrum feature of the first signal are selected as a feature vector of the first signal;

[0090] The features of the second signal are extracted by a preset feature extractor to obtain the signal amplitude, signal phase and spectral features of the second signal, and the signal amplitude, signal phase and spectral features of the second signal are selected as the feature vector of the second signal.

[0091] Among them, signal amplitude is a physical quantity that describes the maximum degree or energy size of the signal waveform deviation from its baseline.

[0092] Among them, signal phase is a physical quantity that describes the deviation of the signal waveform relative to a reference point or a reference waveform, and is an important measure of the change of the signal waveform.

[0093] The spectral features are features extracted based on the spectrum distribution, including but not limited to the maximum power spectrum, the spectrum centroid, and the spectrum spread.

[0094] Among them, a preset value is set, and when the displacement value is greater than the preset value, the feature extractor can be triggered to perform further analysis measures. This ensures that even if the target object moves slowly or is far away, the target object can be detected in time, which is conducive to automatically screening out the target objects that need attention.

[0095] Among them, the feature vector of the first signal and the feature vector of the second signal are spliced ​​to generate the feature vector of the current radar signal. The feature vector of the current radar signal combines the feature vector of the first signal and the feature vector of the second signal. Therefore, the feature vector of the current radar signal increases the dimension of the data, so that the classifier can capture richer information.

[0096] S25, inputting the feature vector of the current radar signal into a classifier, and obtaining a current classification label output by the classifier;

[0097] The feature vector of the current radar signal is input into the classifier, and the classifier directly uses the feature vector of the current radar signal without directly processing the current radar signal, so that the classifier can focus more on the relationship between the feature vector of the current radar signal and the current classification label, thereby improving the accuracy of the current classification label.

[0098] S26, when the current classification label is a pedestrian label or a non-motor vehicle label, control the lighting device to be in an on state.

[0099] Among them, this application can be used in smart elderly care scenarios such as communities and hospitals.

[0100] For the sake of illustration, an example is given below:

[0101] In the community, when the current classification label is a pedestrian label or a non-motor vehicle label, the lighting equipment is controlled to be turned on. This personalized lighting solution not only creates a safe and comfortable living environment for the elderly, but also helps reduce safety hazards caused by improper lighting. For example, at night, the system can sense the movement trajectory of the elderly and turn on soft lights in advance to guide the elderly to walk safely, creating a safer living environment for the elderly.

[0102] In a hospital environment, when the current classification label is a pedestrian label or a non-motor vehicle label, the lighting equipment is controlled to be in the on state, which not only reduces the medical staff's dependence on manually operated lighting equipment, allowing medical staff to devote more time and energy to personalized care and concern for the elderly, but also improves the elderly's quality of life and happiness, ensuring that the elderly are properly cared for. This not only optimizes the elderly's rehabilitation environment, but also promotes the humanization and efficiency of medical services.

[0103] Among them, pedestrian label is the label of pedestrian.

[0104] Among them, the non-motor vehicle label is a label for non-motor vehicles.

[0105] Among them, when the current classification label is a pedestrian label, the lighting device is controlled to be in an on state. The lighting of the lighting device helps pedestrians to clearly see the road, crosswalks, traffic signs and obstacles ahead, thereby reducing the risk of traffic accidents.

[0106] Among them, when the current classification label is a non-motor vehicle label, the lighting device is controlled to be in an on state. For non-motor vehicles, the lighting device is controlled to be in an on state. The illumination of the lighting device helps the rider to clearly see the road and obstacles ahead, avoiding falls or collisions with other vehicles or pedestrians due to unclear vision.

[0107] Among them, lighting equipment refers to various equipment and devices used to provide light sources and lighting effects. They illuminate the surrounding environment by emitting light and create suitable lighting conditions for people.

[0108] Among them, lighting equipment includes but is not limited to street lights, landscape lights, garden lights, and lawn lights.

[0109] Street lights: Used to provide lighting services at night or in low light conditions. Street lights provide sufficient light so that pedestrians and non-motorized vehicle riders can clearly see the road ahead, crosswalks, traffic signs and obstacles, thereby reducing the risk of traffic accidents.

[0110] Landscape lights: used to beautify outdoor environments, such as parks, squares, building facades, etc., highlighting landscape features through lighting design.

[0111] Garden lights: Lamps installed in courtyards, sidewalks and other human-scale places, with various shapes and both lighting and decorative functions.

[0112] Lawn lamp: used for lighting low spaces such as trails and lawns, usually designed to be small and exquisite to add to the beauty of the environment. After inputting the feature vector of the current radar signal into the classifier and obtaining the current classification label output by the classifier, the classification method includes:

[0113] When the current classification tag is an animal tag or a motor vehicle tag, the lighting device is controlled to be in an off state.

[0114] Among them, animal labels are labels of other animals. Other animals are animals other than humans.

[0115] Among them, the motor vehicle label is the label of the motor vehicle.

[0116] Among them, when the current classification label is an animal label or a motor vehicle label, the lighting device is controlled to be in an off state, which is conducive to reducing carbon emissions and has positive significance for environmental protection and sustainable development.

[0117] In the embodiment of the present invention, the beneficial effects are in two aspects. On the one hand, the feature vector of the current radar signal is input into the classifier to obtain the current classification label output by the classifier. When the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state. The pedestrian label is a label for pedestrians, and the non-motor vehicle label is a label for non-motor vehicles. Since there is no need to capture and classify images of pedestrians or non-motor vehicles, the classification time of pedestrians or non-motor vehicles is reduced, which is beneficial to improving the classification efficiency of pedestrians or non-motor vehicles. At the same time, it is beneficial to save computing power, improve road safety and save electricity consumption of lighting equipment. It can be widely used in smart elderly care scenarios such as communities and hospitals. On the other hand, when the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state, which avoids power loss due to invalid lighting and is beneficial to saving power.

[0118] See also Figure 3 , Figure 3 yes Figure 1 A specific implementation flow diagram of step S23 is described in detail as follows:

[0119] S31, obtaining a phase difference between the first signal and the second signal;

[0120] The phase difference refers to the difference between the phase offsets of the first signal and the second signal relative to a reference point at the same frequency.

[0121] S32: Convert the phase difference into a time difference, and multiply the time difference by a propagation speed to obtain a displacement value between the first signal and the second signal.

[0122] Exemplarily, converting the phase difference into a time difference, and multiplying the time difference by a propagation speed to obtain a displacement value between the first signal and the second signal includes:

[0123] The angular frequencies of the first signal and the second signal are obtained, and a time difference is obtained by dividing the phase difference by the angular frequency. The time difference and the propagation speed are multiplied to obtain a product, and the product is selected as the displacement value between the first signal and the second signal.

[0124] In an embodiment of the present invention, when a target is displaced within the monitoring range, the phases of the first signal and the second signal will also change according to the direction of movement. Therefore, the phase difference can be converted into a time difference, and the time difference and the propagation speed are multiplied to obtain the displacement value between the first signal and the second signal.

[0125] See also Figure 4 , Figure 4 yes Figure 1 A specific implementation flow diagram of step S25 is described in detail as follows:

[0126] S41, obtaining a model file of a classifier, loading the model file, and obtaining a loading result of the model file;

[0127] S42, when the loading result is successful, inputting the feature vector of the current radar signal into the classifier, and obtaining the current classification label output by the classifier.

[0128] In an embodiment of the present invention, the feature vector of the current radar signal is input into the classifier to obtain the current classification label output by the classifier. This process not only greatly reduces the classification time, but also can significantly improve the classification efficiency of the current radar signal.

[0129] See also Figure 5 , Figure 5 yes Figure 1 A specific implementation flow diagram of step S26 is described in detail as follows:

[0130] S51, when the current classification tag is a pedestrian tag or a non-motor vehicle tag, reading the current state of the lighting device;

[0131] S52: When the current state is the off state, control the lighting device to switch from the off state to the on state.

[0132] In an embodiment of the present invention, when the current state is the off state, the lighting device is controlled to be converted from the off state to the on state. Since there is no need to capture and classify images of pedestrians or non-motor vehicles, the classification time of pedestrians or non-motor vehicles is reduced, which is beneficial to improving the classification efficiency of pedestrians or non-motor vehicles. At the same time, it is beneficial to save computing power, improve road safety and save electricity consumption of lighting equipment. It can be widely used in smart elderly care scenarios such as communities and hospitals.

[0133] See also Figure 6 , Figure 6 : is a schematic diagram of a structure of a classification device in one embodiment of the present invention, Figure 6 As shown, the classification device includes a first acquisition module 101, an extraction module 102, a second acquisition module 103, a third acquisition module 104, an input module 105, and a classification module 106. The functional modules are described in detail as follows:

[0134] A first acquisition module 101 is used to acquire a current radar signal collected by a target radar;

[0135] An extraction module 102, configured to extract a first signal and a second signal from the current radar signal;

[0136] A second acquisition module 103, configured to acquire a displacement value between the first signal and the second signal;

[0137] A third acquisition module 104, configured to acquire a feature vector of the current radar signal when the displacement value meets a preset condition;

[0138] An input module 105, configured to input the feature vector of the current radar signal into a classifier, and obtain a current classification label output by the classifier;

[0139] The classification module 106 is used to control the lighting device to be in an on state when the current classification label is a pedestrian label or a non-motor vehicle label.

[0140] In one embodiment, the extraction module 102 includes:

[0141] A first acquisition subunit is used to acquire a first sliding window and a second sliding window, where the second sliding window is a next window of the first sliding window;

[0142] The first extraction subunit is configured to extract a first signal from the current radar signal through the first sliding window, and to extract a second signal from the current radar signal through the second sliding window.

[0143] In one embodiment, the second acquisition module 103 includes:

[0144] A second acquisition subunit, configured to acquire a phase difference between the first signal and the second signal;

[0145] The conversion subunit is used to convert the phase difference into a time difference, and multiply the time difference by a propagation speed to obtain a displacement value between the first signal and the second signal.

[0146] In one embodiment, the third acquisition module 104 includes:

[0147] A second extraction subunit is used for, when the displacement value is greater than a preset value, respectively extracting features from the first signal and the second signal through a preset feature extractor to obtain a feature vector of the first signal and a feature vector of the second signal;

[0148] The splicing subunit is used to splice the feature vector of the first signal and the feature vector of the second signal to generate the feature vector of the current radar signal.

[0149] In one embodiment, the input module 105 includes:

[0150] A loading subunit is used to obtain a model file of a classifier, load the model file, and obtain a loading result of the model file;

[0151] The input subunit is used to input the feature vector of the current radar signal into the classifier when the loading result is successful, and obtain the current classification label output by the classifier.

[0152] In one embodiment, the classification module 106 includes:

[0153] A classification subunit, used for reading the current state of the lighting device when the current classification tag is a pedestrian tag or a non-motor vehicle tag;

[0154] The control subunit is used for controlling the lighting device to switch from the off state to the on state when the current state is the off state.

[0155] In one embodiment, the classification device further includes:

[0156] The control module is used to control the lighting device to be in an off state when the current classification tag is an animal tag or a motor vehicle tag.

[0157] In the embodiment of the present invention, the beneficial effects are in two aspects. On the one hand, the feature vector of the current radar signal is input into the classifier to obtain the current classification label output by the classifier. When the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state. The pedestrian label is a label for pedestrians, and the non-motor vehicle label is a label for non-motor vehicles. Since there is no need to capture and classify images of pedestrians or non-motor vehicles, the classification time of pedestrians or non-motor vehicles is reduced, which is beneficial to improving the classification efficiency of pedestrians or non-motor vehicles. At the same time, it is beneficial to save computing power, improve road safety and save electricity consumption of lighting equipment. It can be widely used in smart elderly care scenarios such as communities and hospitals. On the other hand, when the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state, which avoids power loss due to invalid lighting and is beneficial to saving power.

[0158] For the specific limitations on the classification device, please refer to the limitations on the classification method above, which will not be repeated here.

[0159] Each module in the above classification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0160] See also Figure 7 , Figure 7 is a schematic diagram of a computer device in one embodiment of the present invention. In one embodiment, a computer device is provided. The computer device may be a server device, and its internal structure diagram may be as shown in FIG. Figure 7 The computer device includes a processor, a memory, a network interface and a database connected through a system bus.

[0161] The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the computer program is executed by the processor, a function or step of a classification method for intelligent lighting can be implemented on the server device.

[0162] See also Figure 8 , Figure 8 is another structural diagram of a computer device in one embodiment of the present invention. In one embodiment, a computer device is provided. The computer device may be a client device, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the computer program is executed by the processor, a function or step of a classification method for intelligent lighting can be implemented on a client device.

[0163] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor.

[0164] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant description in the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.

[0165] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0166] The above description and accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent possible changes only. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. Parts and subsamples of some embodiments may be included in or replace parts and subsamples of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of a stated sub-sample, whole, step, operation, element, and / or component, but do not exclude the presence or addition of one or more other sub-samples, wholes, steps, operations, elements, components and / or groups of these. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0167] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. Technicians can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0168] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some sub-samples can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0169] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A classification method for intelligent lighting, characterized in that: include: Obtain the current radar signal collected by the target radar; Extracting a first signal and a second signal from the current radar signal; Acquire a displacement value between the first signal and the second signal; When the displacement value meets a preset condition, obtaining a feature vector of the current radar signal; Inputting the feature vector of the current radar signal into a classifier to obtain a current classification label output by the classifier; When the current classification label is a pedestrian label or a non-motor vehicle label, the lighting device is controlled to be in an on state.

2. The classification method according to claim 1, characterized in that: The extracting the first signal and the second signal from the current radar signal comprises: Acquire a first sliding window and a second sliding window, where the second sliding window is a next window of the first sliding window; A first signal is extracted from the current radar signal through the first sliding window, and a second signal is extracted from the current radar signal through the second sliding window.

3. The classification method according to claim 1, characterized in that: The obtaining the displacement value between the first signal and the second signal includes: Acquire a phase difference between the first signal and the second signal; The phase difference is converted into a time difference, and the time difference is multiplied by a propagation speed to obtain a displacement value between the first signal and the second signal.

4. The classification method according to claim 1, characterized in that: When the displacement value satisfies a preset condition, obtaining a feature vector of the current radar signal comprises: When the displacement value is greater than a preset value, feature extraction is performed on the first signal and the second signal respectively by a preset feature extractor to obtain a feature vector of the first signal and a feature vector of the second signal; The feature vector of the first signal and the feature vector of the second signal are concatenated to generate a feature vector of the current radar signal.

5. The classification method according to claim 1, characterized in that: The step of inputting the feature vector of the current radar signal into a classifier and obtaining a current classification label output by the classifier includes: Obtain a model file of a classifier, load the model file, and obtain a loading result of the model file; When the loading result is successful, the feature vector of the current radar signal is input into the classifier to obtain the current classification label output by the classifier.

6. The classification method according to claim 1, characterized in that: When the current classification label is a pedestrian label or a non-motor vehicle label, controlling the lighting device to be in an on state includes: When the current classification tag is a pedestrian tag or a non-motor vehicle tag, reading the current state of the lighting device; When the current state is the off state, the lighting device is controlled to switch from the off state to the on state.

7. The classification method according to any one of claims 1 to 6, characterized in that: After inputting the feature vector of the current radar signal into the classifier and obtaining the current classification label output by the classifier, the classification method includes: When the current classification tag is an animal tag or a motor vehicle tag, the lighting device is controlled to be in an off state.

8. A classification device for intelligent lighting, characterized in that: include: A first acquisition module is used to acquire a current radar signal collected by a target radar; An extraction module, used to extract a first signal and a second signal from the current radar signal; A second acquisition module, used to acquire a displacement value between the first signal and the second signal; A third acquisition module, configured to acquire a feature vector of the current radar signal when the displacement value meets a preset condition; An input module, used to input the feature vector of the current radar signal into a classifier, and obtain a current classification label output by the classifier; The classification module is used to control the lighting device to be in an on state when the current classification label is a pedestrian label or a non-motor vehicle label.

9. A computer 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 classification method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the classification method according to any one of claims 1 to 7 are implemented.

Images