CN115315036A

CN115315036A - Microwave distance measurement system and distance measurement method based on brightness adjustment device

Info

Publication number: CN115315036A
Application number: CN202210990727.3A
Authority: CN
Inventors: 汤剑刚; 何飞飞
Original assignee: Ningbo Yingxin Microelectronics Technology Co ltd
Current assignee: Ningbo Yingxin Microelectronics Technology Co ltd
Priority date: 2022-08-18
Filing date: 2022-08-18
Publication date: 2022-11-08

Abstract

The invention discloses a microwave distance measuring system and a distance measuring method based on a brightness adjusting device.A sensing unit is used for detecting whether a moving object exists in a preset area or not, an infrared identification module is used for identifying and judging whether the moving object is a human body or not, and when the moving object is the human body, a distance measuring unit is awakened; otherwise, the system keeps a dormant state without measuring distance in real time, thereby effectively saving electric energy; the invention adjusts the illumination brightness according to the distance measurement result, the closer the distance between the human body and the illumination device is, the higher the brightness is, the distance measurement result is obtained visually from the illumination brightness, and more convenience is brought to the life of people.

Description

Microwave distance measurement system and distance measurement method based on brightness adjustment device

Technical Field

The invention relates to the field of distance measurement, in particular to a microwave distance measurement system and a distance measurement method based on a brightness adjusting device.

Background

The ranging system is mainly applied to an aerospace system at first, is generally used for acquiring information of a detection satellite, a tracking satellite or other planets, and is gradually applied to industrial fields, resource surveying, construction sites, backing reminding and some intelligent household equipment along with the development of production and life. The distance measuring system mainly adopts the technologies of laser distance measurement, electromagnetic wave distance measurement and ultrasonic distance measurement, wherein the laser distance measurement is used for accurately measuring the distance of a target by utilizing laser, the measurement precision is high, the cost is relatively high, the volume of a common laser distance measuring instrument is large, and the common laser distance measuring instrument is generally applied to metal industry, bridge buildings, rail railways and storage logistics; the electromagnetic wave ranging is characterized in that the electromagnetic wave is used as a carrier wave, the time interval between a transmitting wave and an echo is measured, the distance is measured, the measuring efficiency is high, the performance is stable, the electromagnetic wave ranging is widely applied to urban planning, the ultrasonic ranging is not easily interfered by the environment, and the ultrasonic ranging is suitable for remote measurement and is mostly applied to the field of ship measurement.

The distance measuring system needs to continuously supply power when in work, and for scenes without real-time distance measurement, such as intelligent home equipment, a backing reminding distance measuring or service robot and the like which work according to the distance between a human body and the equipment, when no human body exists around, continuous distance measurement operation wastes a large amount of electric energy; the measurement result of the distance measurement method is not displayed intuitively, and the measurement result is generally obtained by checking a specific numerical value through a background computer or a handheld device, so that the distance measurement system and the method which are low in power consumption and capable of visually displaying the distance measurement result are needed, can be widely applied to production and life of people, and achieve the purposes of saving energy, reducing emission, reducing cost and improving life quality.

Disclosure of Invention

The invention aims to provide a microwave distance measuring system and a distance measuring method based on a brightness adjusting device, which can solve the problems of energy waste and non-visual distance measuring result display in the existing lighting system.

A luminance adjustment device comprising: the device comprises a power module, a detection module, a control module and a signal output module, wherein the power module is electrically connected with the detection module, the control module and the signal output module;

the power supply module is used for supplying power to the detection module, the control module and the signal output module;

the detection module is used for detecting an induction signal generated by object displacement in an external environment and detecting the distance between an object and the brightness adjusting device;

the control module is used for receiving the sensing signal and the distance output by the detection module, respectively sending a ranging signal and an adjusting signal to the detection module and the signal output module, and adjusting the detection module and the signal output module to enter a corresponding working state;

the signal output module is used for receiving the adjusting signal and adjusting the brightness according to the adjusting signal.

Preferably, the control module comprises a control circuit and an indication circuit;

the control circuit comprises a micro control chip and a crystal oscillator;

the micro control chip is provided with a plurality of control pins in advance, the working voltage of the micro control chip is 2.5-4.8V, the working current is 50-1350 uA, the working frequency is 10.5-10.55 GHz, and the micro control chip is respectively connected with the power supply module, the detection module and the signal output module through the plurality of control pins; one end of the micro control chip is grounded through a capacitor C3;

the crystal oscillator is connected with the micro control chip through one control pin and is used for providing clock frequency for the micro control chip;

the indicating circuit comprises a resistor R1, a resistor R2, a light emitting diode LED1 and a light emitting diode LED2; the resistor R1 and the resistor R2 are respectively connected with a control pin of the micro control chip through the light emitting diode LED1 and the light emitting diode LED 2.

Preferably, the power module comprises a power circuit, and the power circuit comprises an external power supply, a voltage reduction chip IC2, a voltage stabilization chip IC1, a capacitor C1 and a capacitor C2; the external power supply is connected with the voltage stabilizing chip IC1 through the voltage reducing chip IC2 and the capacitor C1, the output end of the voltage stabilizing chip IC1 is connected with the control pin of the micro control chip through the capacitor C2, and the voltage stabilizing chip IC1, the capacitor C1 and the capacitor C2 are all grounded.

Preferably, the signal output module comprises a signal output circuit, and the signal output circuit comprises a resistor R3, a resistor R4, a capacitor C4, a light emitting diode LED, an NPN type triode Q1, and a bidirectional trigger diode BT1; the light emitting diode LED is connected with the resistor R3 through the bidirectional trigger diode BT1, the base electrode of the NPN type triode Q1 is connected with the control pin of the micro-control chip through the resistor R4, the collector electrode of the NPN type triode Q1 is connected with the resistor R3, and the emitter electrode of the NPN type triode Q1 and the capacitor C4 are both grounded; the NPN type triode Q1 is used for outputting pulse modulation signals with different duty ratios.

Preferably, the detection module comprises a sensing unit and a ranging unit;

the sensing unit is used for sensing the displacement information of an object in a preset area and sending a corresponding sensing signal to the micro control chip;

the distance measuring unit is used for receiving a working signal sent by the micro control chip to enter a working state, measuring the distance between the object and the brightness adjusting device and sending the corresponding distance to the micro control chip.

A microwave distance measuring system comprises the brightness adjusting device, an infrared identification module, a storage module and an illumination module;

the infrared identification module is used for acquiring and identifying an infrared image of a preset area and outputting an infrared identification result;

the illumination module displays corresponding brightness according to the pulse modulation signal output by the signal output module;

the storage module is used for storing duty cycles corresponding to the pulse modulation signals when different distances are preset and infrared identification results corresponding to the infrared images.

Preferably, the infrared identification module comprises an acquisition sub-module and an identification sub-module;

the acquisition submodule is used for acquiring the infrared image of the preset area and preprocessing the infrared image;

the recognition submodule is used for analyzing the infrared image and outputting an infrared recognition result, and judging whether an object in the infrared image is a human body; if the human body is detected, a first identification signal is sent to the micro control chip; and if the human body is not the human body, sending a second identification signal to the micro control chip.

Preferably, the obtaining sub-module includes:

the camera shooting unit is used for collecting the infrared image of the preset area;

the characteristic description unit is used for performing polygon fitting and normalization processing on the edge of the target based on the infrared image and extracting boundary points with high curvature as characteristic points for target identification;

and the feature extraction unit is used for extracting the geometric features after the normalization processing from the infrared image, wherein the geometric features comprise perimeter, area, polar distance sum, maximum vertex angle and maximum polar angle.

Preferably, the recognition sub-module recognizes the preprocessed infrared image by constructing a human body recognition neural network model, and comprises a model construction unit and a model training unit;

the model building unit is built based on a radial basis function neural network model, and the radial basis function neural network model is a three-layer unidirectional network and is provided with an input layer, a hidden layer and an output layer; the input vector corresponding to the input layer selects the geometric characteristics of the infrared image, the hidden layer selects a Gaussian function to perform one-time nonlinear transformation on the input vector, and the output layer corresponds to a classification mode, namely an infrared image recognition result; wherein the dimensions of the input layer and the hidden layer are the same and set to 5, and the dimension of the output layer is set to 2;

the model training unit is used for training the human body recognition neural network model through a training sample; the training sample selects an identified infrared image; the training includes training of the hidden layer and training of the output layer.

A microwave ranging method including a microwave ranging system as claimed in the preceding claims, comprising:

s1, acquiring an induction signal of a preset area in real time, and sending the induction signal to a micro control chip;

s2, acquiring an infrared image of the preset area through an infrared identification module, identifying an object in the infrared image, and sending an infrared identification result to the micro control chip;

s3, measuring the distance between the object and the brightness adjusting device based on the infrared identification result, and sending the corresponding distance to the micro control chip;

and S4, the signal output module adjusts the brightness of the illumination module according to different distances.

Preferably, the S1 includes:

s11, when the induction signal indicates that the object is far away, the micro control chip sends a control signal to a power module to enable the infrared identification module to be powered off and enter a dormant state;

and S12, when the induction signal indicates that the object is close to the infrared identification module, the micro control chip sends a control signal to the power module to enable the infrared identification module to be powered on to enter a working state.

Preferably, the S3 includes:

s311, when the infrared recognition result is that the human body is detected, the control module sends a control signal to the power module to enable the distance measurement unit, the signal output module and the illumination module to be powered on to enter a working state;

s312, the micro control chip sends a brightness adjusting signal to the signal output module according to the distance, so that the signal output module outputs a corresponding pulse modulation signal;

and S313, the lighting module displays corresponding brightness according to the pulse modulation signals with different duty ratios.

Preferably, the S3 further includes:

and S32, when the infrared identification result is a non-human body, the control module sends a control signal to the power supply module to enable the infrared identification module, the distance measurement unit, the signal output module and the illumination module to be powered off to enter a dormant state.

Preferably, the S312 includes:

when the distance is within a first preset distance range, the duty ratio of the pulse modulation signal is 30%;

when the distance is within a second preset distance range, the duty ratio of the pulse modulation signal is 50%;

when the distance is within a third preset distance range, the duty ratio of the pulse modulation signal is 100%.

Preferably, the acquiring and recognizing the infrared image in S2 includes:

carrying out feature description processing on the infrared image;

carrying out feature extraction processing on the feature description;

acquiring the recognized infrared image as a training sample, and constructing and training a human body recognition neural network model;

and extracting the processed data according to the current characteristics, and obtaining an infrared recognition result through the trained human body recognition neural network model.

Preferably, the constructing the human body recognition neural network model includes:

extracting the geometric features of the infrared images in the training sample as input values of a training stage, and selecting a corresponding recognition result as an output value of the training stage;

the method for constructing the radial basis function neural network model comprises the following steps:

the input layer is represented as

I _i ＝X _i i＝1,2,…,I

Wherein I is 5;

gaussian function of the hidden layer, expressed as

In the formula Z _i Is the central vector, σ, of the ith neuron _i Is the shape parameter of the ith neuron;

the output layer is the linear combination of hidden layers, namely the output of the human body recognition neural network model is

In the formula W _ik Taking J to be 2 in the formula, wherein J is the connection weight between the hidden layer and the output layer;

training the human recognition neural network model comprises:

training the hidden layer, determining the central vector of the hidden layer node by K-means clustering method, and determining the central vector Z _i And training mode X to calculate shape parameters

In the formula, ζ _i Is the center Z of the neighboring cluster _i Training pattern set of (1), P _i Is Z _i The number of modes of (c);

training an output layer, and obtaining a learning formula of a connection weight between the hidden layer and the output layer by adopting a steepest descent method, wherein the learning formula comprises the following steps:

W _ik (t+1)＝W _ik (t)-ηδ _k h _i

in the formula, wherein delta _k Is the output error of the kth mode, i.e. delta _k ＝f _k (X)-F _k (W,X)，f _k (X) is the desired output for the kth mode.

The technical scheme has the following advantages or beneficial effects:

according to the invention, the detection module senses and detects the information of the preset area, and the working states of the detection module and the signal output module are adjusted, so that the corresponding distance measurement unit and the corresponding lighting device are awakened when distance measurement is required, real-time distance measurement is not needed, and the energy consumption of a distance measurement system is reduced; the invention judges whether a moving object exists or not by acquiring the sensing signal of the preset area through the sensing unit, identifies whether the moving object is a human body or not, and carries out multiple verification before ranging, thereby improving the awakening precision, reducing the energy waste caused by mistaken awakening and being beneficial to environmental protection; according to the different distances between the human body and the brightness adjusting device, the signal output module outputs pulse modulation signals with different duty ratios to adjust the illumination brightness, wherein the illumination brightness corresponds to the preset distance range one by one, so that the visual display of the distance measurement result is realized, and the method is suitable for the fields of smart homes, robots, automobiles and the like, and brings convenience to the life of people.

Drawings

FIG. 1 is a schematic structural diagram of a brightness adjusting device according to the present invention;

FIG. 2 is a circuit schematic of the power module of the present invention;

FIG. 3 is a circuit schematic of the control module of the present invention;

FIG. 4 is a circuit schematic of the signal output module of the present invention;

FIG. 5 is a circuit diagram of a brightness adjusting device according to the present invention;

FIG. 6 is a schematic diagram of a microwave ranging system of the present invention;

fig. 7 is a schematic flow chart of a microwave distance measuring method according to the present invention.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.

As shown in fig. 1 to 7, a luminance adjusting apparatus 1 includes: the device comprises a power module 10, a detection module 11, a control module 12 and a signal output module 13, wherein the power module 10 is electrically connected with the detection module 11, the control module 12 and the signal output module 13, and the control module 12 is electrically connected with the detection module 11 and the signal output module 13 respectively;

the power module 10 is configured to supply power to the detection module 11, the control module 12, and the signal output module 13;

the detection module 11 is used for detecting an induction signal generated by object displacement in an external environment and detecting the distance between an object and the brightness adjusting device 1;

the control module 12 is configured to receive the sensing signal and the distance output by the detection module 11, send a ranging signal and an adjusting signal to the detection module 11 and the signal output module 13, and adjust the ranging signal and the adjusting signal to enter corresponding operating states;

the signal output module 13 is configured to receive the adjustment signal and adjust the brightness according to the adjustment signal.

Further, the control module 12 includes a control circuit and an indication circuit;

the control circuit comprises a micro control chip and a crystal oscillator;

a plurality of control pins are preset in the micro control chip, the working voltage of the micro control chip is 2.5-4.8V, the working current is 50-1350 uA, the working frequency is 10.5-10.55 GHz, and the micro control chip is respectively connected with the power module 10, the detection module 11 and the signal output module 13 through the plurality of control pins; one end of the micro control chip is grounded through a capacitor C3;

Preferably, the micro-control chip adopts a mature CMOS process, fully utilizes a digital-analog hybrid technology, simultaneously integrates a microwave transceiver, a radar intermediate frequency amplification circuit, a signal processor and the like on a single chip, is a fully integrated SOC, and has good consistency and ultrahigh cost performance compared with the traditional radar sensing module; the chip is defaulted to work in a frequency band of 10.5 GHz-10.55 GHz, the frequency is flexible and configurable, and various interference problems can be effectively solved due to the integration of the self-adaptive calibration algorithm on the chip, so that the reliability and the practicability of the sensor are greatly improved; the micro control chip integrates the LDO and adopts an ultra-low power consumption architecture, and because the power consumption is low and the wide voltage is supported, the power supply scheme directly adopts a battery for power supply and keeps a long-time standby state; the chip is internally integrated with a signal processor, can directly output induction control signals, and is matched with a small number of components at the periphery to form a complete microwave radar induction sensor.

The working principle is as follows: microwave signals generated inside the chip are amplified and radiated out through the antenna, the signals are reflected when encountering objects in the air, when the objects are in a motion state, a certain frequency difference exists between the reflected signals and the transmitted signals, namely Doppler effect, the received reflected signals and the transmitted signals are mixed to obtain corresponding intermediate frequency signals, and the intermediate frequency signals are analyzed to reversely extract object motion information, so that a sensing function is realized.

Further, the power module 10 includes a power circuit, and the power circuit includes an external power supply, a voltage-reducing chip IC2, a voltage-stabilizing chip IC1, a capacitor C1, and a capacitor C2; the external power supply is connected with the voltage stabilizing chip IC1 through the voltage reducing chip IC2 and the capacitor C1, the output end of the voltage stabilizing chip IC1 is connected with the control pin of the micro control chip through the capacitor C2, and the voltage stabilizing chip IC1, the capacitor C1 and the capacitor C2 are all grounded.

Further, the signal output module 13 includes a signal output circuit, and the signal output circuit includes a resistor R3, a resistor R4, a capacitor C4, a light emitting diode LED, an NPN type triode Q1, and a bidirectional trigger diode BT1; the light emitting diode LED is connected with the resistor R3 through the bidirectional trigger diode BT1, the base electrode of the NPN type triode Q1 is connected with the control pin of the micro-control chip through the resistor R4, the collector electrode of the NPN type triode Q1 is connected with the resistor R3, and the emitter electrode of the NPN type triode Q1 and the capacitor C4 are both grounded; the NPN type triode Q1 is used for outputting pulse modulation signals with different duty ratios.

Further, the detection module 11 includes a sensing unit 111 and a ranging unit 112;

the sensing unit 111 is configured to sense object displacement information of a preset area, and send a corresponding sensing signal to the micro control chip;

the distance measuring unit 112 is configured to receive a working signal sent by the micro control chip and enter a working state, measure a distance between the object and the brightness adjusting device 1, and send a corresponding distance to the micro control chip.

A microwave distance measuring system comprises the brightness adjusting device 1, an infrared identification module 2, a storage module 3 and an illumination module 4;

the infrared identification module 2 is used for acquiring and identifying an infrared image of a preset area and outputting an infrared identification result;

the lighting module 4 displays corresponding brightness according to the pulse modulation signal output by the signal output module 13;

the storage module 3 is configured to store duty cycles corresponding to the pulse modulation signals when different distances are preset and infrared identification results corresponding to the infrared images.

Preferably, the lighting module 4 includes, but is not limited to, a lighting device in a home, a lighting device in a factory, or a lighting device in a public place, and a common lamp may select an energy saving lamp, an incandescent lamp, a fluorescent lamp, an LED lamp, or the like according to a light source.

Further, the infrared identification module 2 includes an acquisition submodule 21 and an identification submodule 22;

the obtaining submodule 21 is configured to obtain an infrared image of the preset area and preprocess the infrared image;

the identification submodule 22 is configured to analyze the infrared image and output an infrared identification result, and determine whether an object in the infrared image is a human body; if the human body is detected, a first identification signal is sent to the micro control chip; and if the human body is not the human body, sending a second identification signal to the micro control chip.

Further, the obtaining sub-module 21 includes:

the camera unit 211 is configured to collect an infrared image of a preset area;

a feature description unit 212, configured to perform polygon fitting and normalization processing on the edge of the target based on the infrared image, and extract boundary points with high curvature as feature points for target identification;

and a feature extraction unit 213, configured to extract, from the infrared image, geometric features after normalization processing, where the geometric features include a perimeter, an area, a sum of polar distances, a maximum vertex angle, and a maximum polar angle.

Preferably, the camera unit 211 can be an electronic device with a photographing function, including but not limited to a video camera, a still camera, a mobile phone and a computer; the feature description unit 212 and the feature extraction unit 213 may employ devices with calculation and storage functions.

Further, the recognition sub-module 22 recognizes the preprocessed infrared image by constructing a human recognition neural network model, including a model construction unit 221 and a model training unit 222;

the model building unit 221 is built based on a radial basis function neural network model, wherein the radial basis function neural network model is a three-layer unidirectional network and is provided with an input layer, a hidden layer and an output layer; the input vector corresponding to the input layer selects the geometric characteristics of the infrared image, the hidden layer selects a Gaussian function to perform one-time nonlinear transformation on the input vector, and the output layer corresponds to a classification mode, namely an infrared image recognition result; wherein the dimension of the input layer and the dimension of the hidden layer are the same and are set to be 5, and the dimension of the output layer is set to be 2;

the model training unit 222 trains the human recognition neural network model through training samples; the training sample selects the recognized infrared image; the training includes training of the hidden layer and training of the output layer.

Preferably, 150 infrared image sample sets of human bodies and 150 infrared image sample sets of non-human bodies can be selected as training samples, and the greater the number of training samples, the higher the accuracy of the model identification.

Further, the S1 includes:

Preferably, when the preset area is not sensed to have the object, the infrared recognition module, the signal output module and the lighting module are all kept in a dormant state, and electric energy is saved.

Further, the S3 includes:

s311, when the infrared recognition result is that the human body exists, the control module sends a control signal to the power module to enable the distance measuring unit, the signal output module and the lighting module to be electrified to enter a working state;

Further, the S3 further includes:

Further, the S312 includes:

Preferably, the first, second and third preset distance ranges may be set to 3 to 6 meters, 6 to 8 meters and 8 to 10 meters, respectively.

Further, the acquiring and recognizing the infrared image in S2 includes:

performing feature description processing on the infrared image;

carrying out feature extraction processing on the feature description;

acquiring an identified infrared image as a training sample, and constructing and training a human body identification neural network model;

and extracting processed data according to the current characteristics, and obtaining an infrared recognition result through the trained human body recognition neural network model.

Preferably, in an embodiment, after performing image segmentation, boundary extraction and edge tracking on an acquired infrared image, an ordered target boundary point set is obtained and recorded as an ordered target boundary point set

P＝{p _i ＝(x _i ,y _i ),i＝1,2,…,M}

Where M is the number of pixels in the set of boundary points, p ₁ And p _M Respectively representing the start and end points of the boundary. The infrared image feature description processing is to adopt a local large curvature detection method to perform target edge polygon fitting, and comprises the following steps:

step a, setting a starting point p ₁ To fit the first vertex of a polygon, p _m ＝p ₁ ，p _n ＝p _m+2 ＝p ₃ At p of _m And p _n An indirect straight line segment;

b, regarding the point p in the boundary set _k (m<k<n), calculating p _k D (m, n, k) is the Euclidean distance from the straight line segment, and if all d (m, n, k) are within a preset threshold value, the step d is turned to; otherwise, turning to the step c;

step c, taking the point p with the maximum distance _i Set as the new vertex of the polygon, set p _m ＝p _i ，p _n ＝p _i+2 At p of _m And p _n B, connecting straight line segments indirectly, and repeating the step b;

step 4, setting n = n +1, and if n is less than M, turning to step b; otherwise, the calculation is ended.

The ordered point set F = { F) of polygon vertexes can be obtained through the operation ₁ ,f ₂ ,…,f _N And a preset threshold value can be set according to the precision requirement, and can be 2.0-3.0.

Preferably, the normalization process includes: let the coordinate of the center of the target pattern be f _c (x _c ，y _c ) Then there is

Where M is the number of pixels in the set of boundary points and the normalization factor is expressed as

Where N is the number of vertices of the polygon and N is the number of vertices f 'of the normalized polygon' _i (x′ _i ，y′ _i ) F from the original polygon vertex _i (x _i ，y _i ) The corresponding relation is

x′ _i ＝(x′ _i ，x _c )/D，y′ _i ＝(y _i ，y _c )/D i＝1，2，...，N

And N is the number of vertices of the polygon.

Optionally, the feature extraction processing is to extract geometric features including a perimeter, an area, a polar distance sum, a maximum vertex angle, and a maximum polar angle;

wherein the perimeter is defined as

In the formula L _i Is of characteristic f' _i And f' _i+1 The euclidean distance therebetween;

definition of the area if from the characteristic point f' _i 、f′ _i+1 And the target centroid f _c The enclosed area is defined as

Then the area of the polygon is

The polar distance is the sum of Euclidean distances from the target centroid to each vertex and is defined as

In the formula r _i Is characteristic point f' _i And the centroid f _c The distance between them;

the definition of the maximum vertex angle is set as theta _i As vectors

And

angle therebetween is then theta _i Has a cosine of

In the formula

The maximum apex angle of the polygon is

A＝max(θ _i )＝max(cos ^-1 (θ _i ))i＝1，2，...，N；

Definition of the maximum polar angle, let phi _i As vectors

And

the angle therebetween is phi _i Has a cosine of

In the formula

The maximum polar angle of the polygon is

B＝max(φ _i )＝max(cos ^-1 (φ _i ))i＝1，2，...，N

Preferably, the feature space X = { X ] is composed of the above-described geometric feature vectors ₁ ，x ₂ ，x ₃ ，x ₄ ，x ₅ }＝{L，S，R，A，B}。

Further, constructing the human recognition neural network model comprises:

extracting geometric features of infrared images in the training sample as input values of a training stage, and selecting corresponding recognition results as output values of the training stage;

the input layer is represented as

I _i ＝X _i i＝1,2,…,I

In the formula, I takes 5 and corresponds to five characteristic values of perimeter, area, polar distance sum, maximum vertex angle and maximum polar angle;

gaussian function of the hidden layer, expressed as

the output layer is the linear combination of the hidden layers, namely the output of the human body recognition neural network model is

In the formula W _ik Taking J as 2 in the formula for the connection weight between the hidden layer and the output layer, wherein the J corresponds to two recognition results of a human body and a non-human body;

training the human recognition neural network model comprises:

training the hidden layer, determining the central vector of the hidden layer node by K-means clustering method, and determining the central vector Z _i And inputting the sample X to calculate the shape parameter

In the formula, ζ _i Is the center Z of the neighboring cluster _i Training pattern set of (1), P _i Is Z _i The number of modes of (1);

training the output layer, and obtaining a learning formula of a connection weight between the hidden layer and the output layer by adopting a steepest descent method, wherein the learning formula comprises the following steps:

W _ik (t+1)＝W _ik (t)-ηδ _k h _i

in the formula, wherein delta _k Is the output error of the k-th mode, i.e. delta _k ＝f _k (X)-F _k (W,X)，f _k (X) is the desired output for the kth mode.

An electronic device, comprising: a memory and one or more processors;

wherein the memory is communicatively coupled to the one or more processors, the memory having stored therein instructions executable by the one or more processors, the instructions when executed by the one or more processors, the electronic device being configured to implement a microwave ranging method as in any of the above.

In particular, the processor and the memory may be connected by a bus or other means, such as by a bus connection. The processor may be a Central Processing Unit (CPU). The Processor may also be other general purpose Processor, digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or a combination thereof.

The memory, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor executes various functional applications and data processing of the processor by executing non-transitory software programs/instructions and functional modules stored in the memory.

The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network, such as through a communications interface. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

A computer-readable storage medium having stored thereon computer-executable instructions, which when executed by a computing device, may be used to implement a microwave ranging method as described in any one of the above.

The aforementioned computer-readable storage media include physical volatile and nonvolatile, removable and non-removable media implemented in any manner or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media specifically include, but are not limited to, a USB flash drive, a removable hard drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), an erasable programmable Read-Only Memory (EPROM), an electrically erasable programmable Read-Only Memory (EEPROM), flash Memory or other solid state Memory technology, a CD-ROM, a Digital Versatile Disk (DVD), an HD-DVD, a Blue-Ray or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer.

While the subject matter described herein is provided in the general context of execution in conjunction with the execution of an operating system and application programs on a computer system, those skilled in the art will recognize that other implementations may also be performed in combination with other types of program modules. Generally, program modules include routines, programs, components, data structures, and other types of structures that perform particular tasks or implement particular abstract data types. Those skilled in the art will appreciate that the subject matter described herein may be practiced with other computer system configurations, including hand-held devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, minicomputers, mainframe computers, and the like, and in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Those of ordinary skill in the art will appreciate that the various illustrative elements and method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, or portions thereof, which substantially or partly contribute to the prior art, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method described in the embodiments of the present application.

In summary, the microwave ranging system of the present invention utilizes microwave to sense the environmental information of the preset area, and when there is a moving object, wakes up the infrared recognition module to recognize whether the moving object is a human body, and wakes up the ranging unit to measure the distance between the human and the brightness adjustment device after determining that the object is a human body; the microwave distance measuring system does not need to measure the distance of surrounding objects in real time, thereby reducing unnecessary power consumption and cost, and improving the accuracy of identifying the target to be measured by microwave induction and human body identification; the invention adjusts the illumination brightness according to the distance measurement result, can visually acquire the distance measurement result, and can play a precise prompting role when being applied to automobiles or related equipment.

While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made without departing from the spirit and scope of the invention.

In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and operate, and thus should not be construed as limiting the present invention.

Claims

1. A luminance adjustment device, characterized by comprising: the device comprises a power module, a detection module, a control module and a signal output module, wherein the power module is electrically connected with the detection module, the control module and the signal output module;

2. A brightness adjusting device according to claim 1, characterized in that said control module comprises a control circuit and an indication circuit;

the control circuit comprises a micro control chip and a crystal oscillator;

a plurality of control pins are preset in the micro control chip, the working voltage of the micro control chip is 2.5-4.8V, the working current is 50-1350 uA, the working frequency is 10.5-10.55 GHz, and the micro control chip is respectively connected with the power module, the detection module and the signal output module through the plurality of control pins; one end of the micro control chip is grounded through a capacitor C3;

3. A luminance regulating apparatus according to claim 2, wherein said power supply module includes a power supply circuit including an external power supply, a step-down chip IC2, a voltage-stabilizing chip IC1, a capacitor C1 and a capacitor C2; the external power supply is connected with the voltage stabilizing chip IC1 through the voltage reducing chip IC2 and the capacitor C1, the output end of the voltage stabilizing chip IC1 is connected with the control pin of the micro control chip through the capacitor C2, and the voltage stabilizing chip IC1, the capacitor C1 and the capacitor C2 are all grounded.

4. A brightness adjusting device according to claim 2, wherein the signal output module comprises a signal output circuit, the signal output circuit comprises a resistor R3, a resistor R4, a capacitor C4, a light emitting diode LED, an NPN type triode Q1, and a diac BT1; the light emitting diode LED is connected with the resistor R3 through the bidirectional trigger diode BT1, the base electrode of the NPN type triode Q1 is connected with the control pin of the micro-control chip through the resistor R4, the collector electrode of the NPN type triode Q1 is connected with the resistor R3, and the emitter electrode of the NPN type triode Q1 and the capacitor C4 are both grounded; the NPN type triode Q1 is used for outputting pulse modulation signals with different duty ratios.

5. A brightness adjusting device according to claim 2, characterized in that the detecting module comprises a sensing unit and a distance measuring unit;

the distance measuring unit is used for receiving the distance measuring signal sent by the micro control chip and entering a working state, then measuring the distance between the object and the brightness adjusting device, and sending the corresponding distance to the micro control chip.

6. A microwave distance measuring system, comprising a brightness adjusting device as claimed in claims 1-5, characterized by further comprising an infrared recognition module, a storage module and an illumination module;

7. A microwave ranging system according to claim 6, wherein the infrared identification module comprises an acquisition sub-module and an identification sub-module;

8. A microwave ranging system in accordance with claim 7 wherein the acquisition sub-module comprises:

and the characteristic extraction unit is used for extracting the geometric characteristics after normalization processing from the infrared image, wherein the geometric characteristics comprise perimeter, area, polar distance sum, maximum vertex angle and maximum polar angle.

9. The microwave distance measuring system of claim 7, wherein the recognition sub-module recognizes the preprocessed infrared image by constructing a human recognition neural network model, and comprises a model construction unit and a model training unit;

the model building unit is built based on a radial basis function neural network model, and the radial basis function neural network model is a three-layer unidirectional network and is provided with an input layer, a hidden layer and an output layer; the input vector corresponding to the input layer selects the geometric characteristics of the infrared image, the hidden layer selects a Gaussian function to perform one-time nonlinear transformation on the input vector, and the output layer corresponds to a classification mode, namely an infrared image recognition result; wherein the dimension of the input layer and the dimension of the hidden layer are the same and are set to be 5, and the dimension of the output layer is set to be 2;

10. A microwave ranging method comprising a microwave ranging system according to claims 6-9, comprising:

11. A microwave ranging method according to claim 10, wherein the S1 comprises:

s11, when the induction signal indicates that the object is far away from the infrared identification module, the micro control chip sends a control signal to a power module to enable the infrared identification module to be powered off and enter a dormant state;

12. A microwave ranging method according to claim 10, wherein the S3 comprises:

13. A microwave ranging method according to claim 10, wherein the S3 further includes:

14. A microwave ranging method in accordance with claim 12, wherein the S312 comprises:

15. A microwave ranging method as claimed in claim 10, wherein the step of collecting and identifying the infrared image in S2 comprises:

performing feature description processing on the infrared image;

performing feature extraction processing on the feature description;

16. The microwave ranging method of claim 15, wherein constructing the human recognition neural network model comprises:

the input layer is represented as

I _i ＝X _i i＝1,2,…,I

In the formula, I is 5;

gaussian function of the hidden layer, expressed as

training the human recognition neural network model comprises:

W _ik (t+1)＝W _ik (t)-ηδ _k h _i

in the formula, wherein delta _k Is the output error of the kth mode, i.e. delta _k ＝f _k (X)-F _k (W,X)，f _k (X) is the desired output of the kth mode.