CN108407759A - Automobile intelligent starting module based on recognition of face and startup method - Google Patents
Automobile intelligent starting module based on recognition of face and startup method Download PDFInfo
- Publication number
- CN108407759A CN108407759A CN201810486200.0A CN201810486200A CN108407759A CN 108407759 A CN108407759 A CN 108407759A CN 201810486200 A CN201810486200 A CN 201810486200A CN 108407759 A CN108407759 A CN 108407759A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- driver
- pin
- microprocessor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000001815 facial effect Effects 0.000 claims abstract description 15
- 238000003708 edge detection Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004146 energy storage Methods 0.000 claims description 3
- 238000003706 image smoothing Methods 0.000 claims description 3
- 230000002401 inhibitory effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 235000020061 kirsch Nutrition 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 1
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/20—Means to switch the anti-theft system on or off
- B60R25/25—Means to switch the anti-theft system on or off using biometry
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/30—Detection related to theft or to other events relevant to anti-theft systems
- B60R25/31—Detection related to theft or to other events relevant to anti-theft systems of human presence inside or outside the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W2040/0809—Driver authorisation; Driver identity check
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of automobile intelligent starting module and startup method based on recognition of face, the automobile intelligent starting module based on recognition of face, including microprocessor, power-supplying circuit, driver's facial image acquisition circuit, infrared inductor and voice reminder circuit；Driver's facial image acquisition circuit, infrared inductor and the voice reminder circuit is all connected to microprocessor；Infrared inductor is used for judging whether that someone enters driver's cabin；The automobile intelligent starting module and startup method based on recognition of face can control the startup for starting automobile by recognition of face, can effectively achieve the purpose of automobile burglar.
Description
Technical Field
The invention relates to the technical field of intelligent automobiles, in particular to an automobile intelligent starting module and a starting method based on face recognition.
Background
China is becoming a country on wheels, and by the end of 2016, the quantity of cars in China is 1.94 million and is growing at the rate of tens of millions of cars per year. As the number of automobiles increases, thieves are also beginning to look at automobiles as high-grade consumer goods. When a thief gets a key of the automobile or enters the cab of the automobile by an illegal means, the automobile is in an unprotected state, and the thief can easily start the automobile to steal, so that the automobile anti-theft problem becomes the focus of people's attention.
With the rapid development of artificial intelligence and face recognition technology, research and development of an automobile intelligent assistant driving system (ADAS) have become a hot spot of domestic and foreign research, wherein the automobile active safety intelligent detection starting system plays an important role in the assistant driving system, and can judge whether a legal driver is available or not according to the last line of defense such as face recognition under the condition that the automobile is stolen, so that the automobile is protected from being illegally started and stolen, and the safety coefficient of the automobile under a static working condition is greatly improved.
Disclosure of Invention
The invention aims to provide an automobile intelligent starting module and a starting method based on face recognition.
Therefore, the technical scheme of the invention is as follows:
an automobile intelligent starting module based on face recognition comprises a microprocessor, a power supply circuit, a driver face image acquisition circuit, an infrared sensor and a voice reminding circuit; the driver face image acquisition circuit, the infrared sensor and the voice reminding circuit are all connected to the microprocessor; the infrared inductor is used for judging whether a person enters a cab or not, and the power supply circuit provides electric power support for the microprocessor, the driver face image acquisition circuit, the infrared inductor and the voice reminding circuit.
Furthermore, the microprocessor adopts a DM642 high-performance digital signal processor produced by Texas instruments, and the power supply circuit is arranged on the skylight and comprises a solar panel, an energy storage unit and a voltage conversion circuit.
Furthermore, the driver face image acquisition circuit comprises an OV9650 digital camera with 130 ten thousand pixels, and a control pin SCL and a control pin SDA of the OV9650 digital camera are connected with IIC interface hardware of the microprocessor through an IIC bus to form a control channel; image data pins Y7-Y0 of the OV9650 digital camera are in hardware connection with pins 7-0 of an external interface AED of the microprocessor, so that image data flow into a memory of the microprocessor; the clock signal SCLK pin, the field synchronization VSYNC pin and the line synchronization HREF pin of the OV9650 digital camera are respectively in hardware connection with the GP0(4) pin, the GP0(5) pin and the GP0(6) pin of the microprocessor to form a field and line interruption processing mechanism of image data.
Furthermore, the voice reminding circuit comprises a voice chip and an audio power amplifier chip;
the voice chip adopts WT588D voice integrated circuit; the audio power amplifier chip adopts an LM386 integrated circuit; the P00 pin, the P01 pin, the P02 pin and the P03 pin of the WT588D voice chip are connected to a key as trigger pins to record voice and play voice control, the PWM +/DAC pin of the WT588D voice chip is connected with a 0.8W power loudspeaker through an LM386 audio power amplifier circuit, and when a driver verifies that a face image succeeds, the voice reminds the driver of safe driving.
An automobile intelligent starting method of an automobile intelligent starting module based on face recognition comprises the following steps of sequentially carrying out:
1) system initialization setting: the microprocessor carries out guide mode configuration and internal storage area configuration, and the driver facial image acquisition circuit and the voice reminding circuit carry out initialization setting;
2) judging whether the driver enters the cab: the microprocessor receives signals from the infrared sensor in real time, judges whether a driver enters a cab or not, and repeats the step 2 if the judgment result is 'no'); if the judgment result is yes, starting a facial image acquisition circuit of the driver, and then entering the next step;
3) the driver face image acquisition circuit starts to acquire images of the driver face information, the microprocessor judges whether the image acquisition is successful or not, if the judgment result is 'no', the step 3 is repeated, and if the judgment result is 'no', the next step is carried out;
4) preprocessing the image acquired by the driver facial image acquisition circuit in the step 3), reducing the interference of external factors on the original image, and optimizing the matching performance;
5) recognizing the face in the preprocessed image by using a face detection algorithm, and dividing a face area and a non-face area of the image;
6) aiming at the detected face image area, feature extraction is carried out, differences among all pixel points on the face image are found out, and feature vectors are established by utilizing the differences of the pixel points of the image; meanwhile, effective characteristic information in the high-dimensional image is extracted according to a data dimension reduction mode and is led into a subsequent classifier;
7) performing classifier training aiming at the extracted feature information and feature vectors, matching the face image of the driver to be tested with sample data in a database, calculating the matching degree of the face area, and judging whether the identity of the driver to be tested is legal or not according to the matching degree; if the judgment result is yes, the microcontroller sends out an ignition device starting instruction of the automobile engine and broadcasts by voice to drive safely; otherwise, an alarm is given and the automobile cannot be started.
Further, the image preprocessing process in the step 4) includes image graying, image edge detection and image smoothing.
Furthermore, the image edge detection adopts a Canny edge detection algorithm.
Further, the method for detecting the image edge by using the Canny edge detection algorithm comprises the following steps:
1) convolving the image by adopting a Gaussian filter to obtain the pixel value d of any pixel point of the image after Gaussian filteringb；
2) Calculating any one pixel point value d in imagebThe gradient G and the direction θ of;
3) comparing the gradient G of the current pixel with two pixels in the positive and negative gradient directions, if the gradient intensity of the current pixel is the maximum compared with the other two pixels, reserving the pixel point as an edge point, otherwise, inhibiting the pixel point;
4) comparing the gradient value of the edge pixel with a high threshold and a low threshold, and if the gradient value of the edge pixel is higher than the high threshold, marking the edge pixel as a strong edge pixel; if the gradient value of the edge pixel is less than the high threshold and greater than the low threshold, marking it as a weak edge pixel; if the gradient value of the edge pixel is less than the low threshold, it is suppressed.
Further, the face recognition is realized by a face image training sample classifier-Support Vector Machine (SVM) classifier constructed by a radial basis function neural network (RBF).
Compared with the prior art, the automobile intelligent starting module and the starting method based on the face recognition have the following advantages:
1. the automatic starting of the automobile through the face recognition is realized, and the automobile can be effectively prevented from being illegally stolen;
2. the face recognition precision is high, high-precision edge detection is carried out on the image in the face recognition process, the image recognition efficiency is improved, and the recognition matching accuracy is high by extracting face characteristic information, training a classifier and recognizing whether the face in the image is matched with a legal driver or not;
3. the infrared inductor in the intelligent automobile starting module based on the face recognition starts the facial image acquisition circuit of the driver after detecting that someone enters the cab, so that the electric energy is effectively saved;
4. the starting module adopts an embedded design, has small volume and is simple and convenient to install;
5. the face recognition process effectively extracts the features of the image and segments the characters, thereby being beneficial to the reliable and stable operation of the system.
Drawings
Fig. 1 is a structural block diagram of an automobile intelligent starting module based on face recognition provided by the invention.
Fig. 2 is a circuit diagram of a facial image acquisition.
Fig. 3 is a circuit diagram of a voice prompt.
Fig. 4 is a flowchart of the automobile intelligent starting method of the automobile intelligent starting module based on face recognition provided by the invention.
Fig. 5 is a flow chart of face recognition based on classifier training.
Detailed Description
The invention will be further described with reference to the following figures and specific examples, which are not intended to limit the invention in any way.
An automobile intelligent starting module based on face recognition is shown in figure 1 and comprises a microprocessor, a power supply circuit, a driver face image acquisition circuit, an infrared sensor and a voice reminding circuit; the driver face image acquisition circuit, the infrared sensor and the voice reminding circuit are all connected to the microprocessor; the infrared inductor is used for judging whether a person enters a cab or not, and the power supply circuit provides electric power support for the microprocessor, the driver face image acquisition circuit, the infrared inductor and the voice reminding circuit.
The microprocessor adopts a DM642 high-performance digital signal processor produced by Texas instruments, and the power supply circuit is arranged on a skylight of the automobile and comprises a solar panel, an energy storage unit and a voltage conversion circuit, thereby being beneficial to energy conservation and environmental protection and realizing green power supply.
The driver face image acquisition circuit comprises an OV9650 digital camera with 130 ten thousand pixels, as shown in FIG. 2, a control pin SCL and a control pin SDA of the OV9650 digital camera are connected with IIC interface hardware of a microprocessor through an IIC bus to form a control channel; image data pins Y7-Y0 of the OV9650 digital camera are in hardware connection with pins 7-0 of an external interface AED of the microprocessor, so that image data flow into a memory of the microprocessor; the clock signal SCLK pin, the field synchronization VSYNC pin and the line synchronization HREF pin of the OV9650 digital camera are respectively in hardware connection with the GP0(4) pin, the GP0(5) pin and the GP0(6) pin of the microprocessor to form a field and line interruption processing mechanism of image data.
The working principle is as follows: when the camera collects a line of image data, the line of the microprocessor is interrupted at the moment, and the line of image data is taken out from a line interruption service program and is stored in a cache region of the microprocessor; when the camera finishes the collection of a set of image data, the field interruption of the microprocessor is caused, and in a field interruption service program, algorithms such as the preprocessing of a set of complete driver facial images, the face detection, the feature extraction, the classifier training and recognition and the like are carried out.
The voice reminding circuit comprises a voice chip and an audio power amplifier chip;
the voice chip adopts WT588D voice integrated circuit; the audio power amplifier chip adopts an LM386 integrated circuit; as shown in FIG. 3, the P00 pin, the P01 pin, the P02 pin and the P03 pin of the WT588D voice chip are connected to the key as trigger pins to record voice and play voice control, the PWM +/DAC pin of the WT588D voice chip is connected to a 0.8W power horn through an LM386 audio power amplifier circuit, and when the driver verifies that the face image is successful, the voice reminds the driver of safe driving.
An automobile intelligent starting method of an automobile intelligent starting module based on face recognition is shown in fig. 4, and comprises the following steps in sequence:
1) system initialization setting: the microprocessor carries out guide mode configuration and internal storage area configuration, and the driver facial image acquisition circuit and the voice reminding circuit carry out initialization setting;
2) judging whether the driver enters the cab: the microprocessor receives signals from the infrared sensor in real time, judges whether a driver enters a cab or not, and repeats the step 2 if the judgment result is 'no'); if the judgment result is yes, starting a facial image acquisition circuit of the driver, and then entering the next step;
3) the driver face image acquisition circuit starts to acquire images of the driver face information, the microprocessor judges whether the image acquisition is successful or not, if the judgment result is 'no', the step 3 is repeated, and if the judgment result is 'no', the next step is carried out;
4) preprocessing the image acquired by the driver facial image acquisition circuit in the step 3), reducing the interference of external factors to the original image, and optimizing the matching performance, wherein the image preprocessing process comprises image graying, image edge detection and image smoothing, and the image edge detection adopts a Canny edge detection algorithm, so that the edge detection precision is improved, the subsequent image identification process is simplified, and the image identification speed is improved;
5) recognizing the face in the preprocessed image by using a face detection algorithm, and dividing a face area and a non-face area of the image;
6) aiming at the detected face image area, feature extraction is carried out, differences among all pixel points on the face image are found out, and feature vectors are established by utilizing the differences of the pixel points of the image; meanwhile, effective characteristic information in the high-dimensional image is extracted according to a data dimension reduction mode and is led into a subsequent classifier;
7) performing classifier training aiming at the extracted feature information and feature vectors, matching the face image of the driver to be tested with sample data in a database, calculating the matching degree of the face area, and judging whether the identity of the driver to be tested is legal or not according to the matching degree; if the judgment result is yes, the microcontroller sends out an ignition device starting instruction of the automobile engine and broadcasts by voice to drive safely; otherwise, an alarm is given and the automobile cannot be started.
The method for detecting the image edge by using the Canny edge detection algorithm comprises the following steps:
1) convolving the image by adopting a Gaussian filter to obtain the pixel value d of any pixel point of the image after Gaussian filteringb(ii) a The Gaussian filter kernel generation equation with the image pixel point size of (2k +1) × (2k +1) is as follows:
i is more than or equal to 1, j is less than or equal to (2k +1), and aiming at any pixel point value d of the imagefTaking a 3 × 3 local window W as an input, the pixel value of the point filtered by the gaussian filter is db,dbThe expression mode of (A) is as follows:
wherein, is convolution operation, and sum is the sum of all elements in the matrix;
2) calculating any one pixel point value d in imagebThe gradient G and the direction θ of; aiming at any pixel point d in the image subjected to Gaussian filteringbLet the sobel operators in x and y directions be:
then for any one pixel point value d of the imagebTaking a 3 × 3 local window W as input, the gradient values in x and y directions are respectively:
the basis is again:
obtaining any one pixel point value d in the image through formula (7) and formula (8)bThe gradient G and the direction θ of;
3) comparing the gradient intensity G of the current pixel with two pixels in the positive and negative gradient directions, if the gradient intensity of the current pixel is the maximum compared with the other two pixels, reserving the pixel point as an edge point, otherwise, inhibiting the pixel point;
4) comparing the gradient value of the edge pixel with a high threshold and a low threshold, and if the gradient value of the edge pixel is higher than the high threshold, marking the edge pixel as a strong edge pixel; if the gradient value of the edge pixel is less than the high threshold and greater than the low threshold, marking it as a weak edge pixel; if the gradient value of the edge pixel is less than the low threshold, it will be suppressed; the method is favorable for improving the identification precision and speed.
When face detection and characteristic value extraction are carried out, each pixel point of a preprocessed image has a local 3 x 3 neighborhood pixel gray value, the pixel point is located at a neighborhood center position, the gray value of the local 3 x 3 neighborhood is convolved with 8 Kirsch templates to obtain edge gradient values in corresponding directions, i is 0,1, … and 7), the absolute values of the edge gradient values are sequenced, the kth large value is solved, the ith binary number which is larger than or equal to the corresponding ith binary number is set to be 1, the residual 8-i position is 0, an eight-bit binary code is obtained, then weighted summation is carried out according to different positions, and the obtained decimal number is the LDP characteristic value of the pixel point;
the 8 Kirsch operators used are as follows:
for any one pixel point value d of the imagebTaking 3X 3 local window W as input, carrying out 8 Kirsch operator operations to obtain db8 response values of (1), noted as LiWherein i is 0,1,2,3,4,5,6, 7.
According to the formula:
wherein,
sorting 8 response values according to the principle of numerical value, taking m response values with large numerical values to carry out 1 setting operation, and carrying out clear 0 operation on the rest response values; with L0The value is the lowest bit, and binary coding is carried out in reverse time according to 8 response values to obtain the pixel point dbLDP coding of (1). Further, aiming at the target image, according to the formula:
wherein:
obtaining a histogram value of LDP coding of a target image as a characteristic value of face recognition, PiLDP coding values of target image pixel points;
the face identification is realized by a face image training sample classifier-Support Vector Machine (SVM) classifier which is constructed by a radial basis function neural network (RBF); the stability of the operation of the recognition system is improved;
and the face recognition selects a Radial Basis Function (RBF): g (x, y) ═ exp (- γ | | | x-y | | non-conducting phosphor2) Determining a self parameter gamma and an error cost coefficient C of the RBF kernel function to construct a human face image training sample classifier-Support Vector Machine (SVM) classifier; the SVM classifier based on one-to-one voting strategy divides training samples into k categories, and uses F to classify the training samples1、F2、F3、…、FkRepresenting, firstly training two classifiers, and combining the k samples in pairs to obtain the final productAnd the two classifiers are used for obtaining the final characteristic value output of the test sample through statistical calculation, as shown in fig. 5, the identification steps are as follows:
a) initializing the number of votes obtained by the k-type samples: vote (F)1)＝vote(F2)＝vote(F3)...＝vote(Fk)＝0；
b) Voting of each second classifier is carried out, and after test samples of the characteristic values of the facial images of the driver are input into each trained second classifier, the classes of the test samples are respectively judged;
c) the method comprises the steps of counting and comparing ticket obtaining results of all sample categories, outputting the categories with the largest number of tickets, obtaining a final recognition result, judging and fuzzy matching through an SVM classifier, authorizing an ignition device starting instruction of an automobile engine when the matching degree reaches a corresponding threshold value, and broadcasting safe driving through voice, wherein if the matching fails, the operation cannot be carried out, the possibility of illegal driving of the automobile is effectively reduced, and the artificial intelligent automobile driving in the true sense is realized.
Claims (10)
1. An automobile intelligent starting module based on face recognition is characterized by comprising a microprocessor, a power supply circuit, a driver face image acquisition circuit, an infrared sensor and a voice reminding circuit; the driver face image acquisition circuit, the infrared sensor and the voice reminding circuit are all connected to the microprocessor; the infrared inductor is used for judging whether a person enters a cab or not, and the power supply circuit provides electric power support for the microprocessor, the driver face image acquisition circuit, the infrared inductor and the voice reminding circuit.
2. The intelligent automobile starting module based on human face recognition as claimed in claim 1, wherein the microprocessor is a DM642 high-performance digital signal processor manufactured by texas instruments.
3. The intelligent automobile starting module based on the face recognition as claimed in claim 2, wherein the driver face image acquisition circuit comprises an OV9650 digital camera with 130 ten thousand pixels, and a control pin SCL and a control pin SDA of the OV9650 digital camera are connected with IIC interface hardware of the microprocessor through an IIC bus to form a control channel; image data pins Y7-Y0 of the OV9650 digital camera are in hardware connection with pins 7-0 of an external interface AED of the microprocessor, so that image data flow into a memory of the microprocessor; the clock signal SCLK pin, the field synchronization VSYNC pin and the line synchronization HREF pin of the OV9650 digital camera are respectively in hardware connection with the GP0(4) pin, the GP0(5) pin and the GP0(6) pin of the microprocessor to form a field and line interruption processing mechanism of image data.
4. The intelligent automobile starting device based on the face recognition is characterized in that the voice reminding circuit comprises a voice chip and an audio power amplifier chip;
the voice chip adopts WT588D voice integrated circuit; the audio power amplifier chip adopts an LM386 integrated circuit; the P00 pin, the P01 pin, the P02 pin and the P03 pin of the WT588D voice chip are connected to a key as trigger pins to record voice and play voice control, the PWM +/DAC pin of the WT588D voice chip is connected with a 0.8W power loudspeaker through an LM386 audio power amplifier circuit, and when a driver verifies that a face image succeeds, the voice reminds the driver of safe driving.
5. The intelligent automobile starting device based on the face recognition is characterized in that the power supply circuit is arranged on a skylight of an automobile and comprises a solar panel, an energy storage unit and a voltage conversion circuit.
6. An automobile intelligent starting method based on the automobile intelligent starting module based on the face recognition, which is characterized by comprising the following steps in sequence:
1) system initialization setting: the microprocessor carries out guide mode configuration and internal storage area configuration, and the driver facial image acquisition circuit and the voice reminding circuit carry out initialization setting;
2) judging whether the driver enters the cab: the microprocessor receives signals from the infrared sensor in real time, judges whether a driver enters a cab or not, and repeats the step 2 if the judgment result is 'no'); if the judgment result is yes, starting a facial image acquisition circuit of the driver, and then entering the next step;
3) the driver face image acquisition circuit starts to acquire images of the driver face information, the microprocessor judges whether the image acquisition is successful or not, if the judgment result is 'no', the step 3 is repeated, and if the judgment result is 'no', the next step is carried out;
4) preprocessing the image acquired by the driver facial image acquisition circuit in the step 3), reducing the interference of external factors on the original image, and optimizing the matching performance;
5) recognizing the face in the preprocessed image by using a face detection algorithm, and dividing a face area and a non-face area of the image;
6) aiming at the detected face image area, feature extraction is carried out, differences among all pixel points on the face image are found out, and feature vectors are established by utilizing the differences of the pixel points of the image; meanwhile, effective characteristic information in the high-dimensional image is extracted according to a data dimension reduction mode and is led into a subsequent classifier;
7) performing classifier training aiming at the extracted feature information and feature vectors, matching the face image of the driver to be tested with sample data in a database, calculating the matching degree of the face area, and judging whether the identity of the driver to be tested is legal or not according to the matching degree; if the judgment result is yes, the microcontroller sends out an ignition device starting instruction of the automobile engine and broadcasts by voice to drive safely; otherwise, an alarm is given and the automobile cannot be started.
7. The intelligent automobile starting method based on the intelligent automobile starting module with human face recognition as claimed in claim 6, wherein the image preprocessing process in the step 4) comprises image graying, image edge detection and image smoothing.
8. The intelligent automobile starting method based on the human face recognition intelligent starting module as claimed in claim 7, wherein the image edge detection adopts a Canny edge detection algorithm.
9. The intelligent automobile starting method based on the face recognition intelligent automobile starting module according to claim 8, wherein the detection of the image edge by using a Canny edge detection algorithm comprises the following steps:
1) convolving the image by adopting a Gaussian filter to obtain the pixel value d of any pixel point of the image after Gaussian filteringb；
2) Calculating any one pixel point value d in imagebThe gradient G and the direction θ of;
3) comparing the gradient G of the current pixel with two pixels in the positive and negative gradient directions, if the gradient intensity of the current pixel is the maximum compared with the other two pixels, reserving the pixel point as an edge point, otherwise, inhibiting the pixel point;
4) comparing the gradient value of the edge pixel with a high threshold and a low threshold, and if the gradient value of the edge pixel is higher than the high threshold, marking the edge pixel as a strong edge pixel; if the gradient value of the edge pixel is less than the high threshold and greater than the low threshold, marking it as a weak edge pixel; if the gradient value of the edge pixel is less than the low threshold, it is suppressed.
10. The intelligent automobile starting method based on the intelligent automobile starting module for face recognition of the claim 6 is characterized in that the face recognition is realized by a face image training sample classifier-Support Vector Machine (SVM) classifier constructed by a radial basis function neural network (RBF).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486200.0A CN108407759A (en) | 2018-05-21 | 2018-05-21 | Automobile intelligent starting module based on recognition of face and startup method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486200.0A CN108407759A (en) | 2018-05-21 | 2018-05-21 | Automobile intelligent starting module based on recognition of face and startup method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108407759A true CN108407759A (en) | 2018-08-17 |
Family
ID=63140287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810486200.0A Pending CN108407759A (en) | 2018-05-21 | 2018-05-21 | Automobile intelligent starting module based on recognition of face and startup method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108407759A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110525445A (en) * | 2019-08-30 | 2019-12-03 | 南京领行科技股份有限公司 | A kind of control method of vehicle driving, device, equipment, medium and vehicle |
| CN110693508A (en) * | 2019-09-02 | 2020-01-17 | 中国航天员科研训练中心 | Multi-channel cooperative psychophysiological active sensing method and service robot |
| CN111008543A (en) * | 2018-10-08 | 2020-04-14 | 珠海格力电器股份有限公司 | Face recognition method and image acquisition equipment |
| CN111775727A (en) * | 2020-07-28 | 2020-10-16 | 山东爱德邦智能科技有限公司 | Electric system of electric vehicle |
| CN112519787A (en) * | 2019-08-30 | 2021-03-19 | 南京领行科技股份有限公司 | Vehicle control system and vehicle |
| CN113246908A (en) * | 2021-04-22 | 2021-08-13 | 新疆爱华盈通信息技术有限公司 | Vehicle starting method and computer equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005092854A (en) * | 2004-04-16 | 2005-04-07 | Penpower Technology Ltd | Face model production method and face identification method |
| CN1769107A (en) * | 2004-11-03 | 2006-05-10 | 上海杰得微电子有限公司 | Automobile anti-theft method based on human face identification technology |
| US20060261931A1 (en) * | 2003-08-15 | 2006-11-23 | Ziyi Cheng | Automobile security defence alarm system with face identification and wireless communication function |
| CN101131728A (en) * | 2007-09-29 | 2008-02-27 | 东华大学 | Face shape matching method based on Shape Context |
| CN101596895A (en) * | 2009-07-02 | 2009-12-09 | 烟台麦特电子有限公司 | A kind of anti-stealing method for vehicles and device based on video acquisition and biometric facial identification |
| CN102043950A (en) * | 2010-12-30 | 2011-05-04 | 南京信息工程大学 | Vehicle outline recognition method based on canny operator and marginal point statistic |
| CN102582578A (en) * | 2011-09-28 | 2012-07-18 | 福州海景科技开发有限公司 | Anti-theft system for vehicle based on infrared and face recognition technology |
| CN202686280U (en) * | 2012-06-06 | 2013-01-23 | 浙江吉利汽车研究院有限公司杭州分公司 | Vehicle anti-theft and start-up system based on face recognition |
| CN203025911U (en) * | 2013-01-01 | 2013-06-26 | 长安大学 | Fatigue driving detection and identification system based on human face recognition |
| CN103231693A (en) * | 2013-05-14 | 2013-08-07 | 苏州福丰科技有限公司 | Car alarming and monitoring system based on face recognition |
| CN103538563A (en) * | 2013-11-06 | 2014-01-29 | 中山弘博企业管理咨询有限公司 | Intelligent human face recognition automobile anti-theft device |
| CN106022317A (en) * | 2016-06-27 | 2016-10-12 | 北京小米移动软件有限公司 | Face identification method and apparatus |
| CN107264469A (en) * | 2017-06-15 | 2017-10-20 | 深圳森阳环保材料科技有限公司 | A kind of VATS Vehicle Anti-Theft System based on recognition of face |
| CN208439232U (en) * | 2018-05-21 | 2019-01-29 | 辽宁工业大学 | Automobile intelligent starting module based on recognition of face |
-
2018
- 2018-05-21 CN CN201810486200.0A patent/CN108407759A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060261931A1 (en) * | 2003-08-15 | 2006-11-23 | Ziyi Cheng | Automobile security defence alarm system with face identification and wireless communication function |
| JP2005092854A (en) * | 2004-04-16 | 2005-04-07 | Penpower Technology Ltd | Face model production method and face identification method |
| CN1769107A (en) * | 2004-11-03 | 2006-05-10 | 上海杰得微电子有限公司 | Automobile anti-theft method based on human face identification technology |
| CN101131728A (en) * | 2007-09-29 | 2008-02-27 | 东华大学 | Face shape matching method based on Shape Context |
| CN101596895A (en) * | 2009-07-02 | 2009-12-09 | 烟台麦特电子有限公司 | A kind of anti-stealing method for vehicles and device based on video acquisition and biometric facial identification |
| CN102043950A (en) * | 2010-12-30 | 2011-05-04 | 南京信息工程大学 | Vehicle outline recognition method based on canny operator and marginal point statistic |
| CN102582578A (en) * | 2011-09-28 | 2012-07-18 | 福州海景科技开发有限公司 | Anti-theft system for vehicle based on infrared and face recognition technology |
| CN202686280U (en) * | 2012-06-06 | 2013-01-23 | 浙江吉利汽车研究院有限公司杭州分公司 | Vehicle anti-theft and start-up system based on face recognition |
| CN203025911U (en) * | 2013-01-01 | 2013-06-26 | 长安大学 | Fatigue driving detection and identification system based on human face recognition |
| CN103231693A (en) * | 2013-05-14 | 2013-08-07 | 苏州福丰科技有限公司 | Car alarming and monitoring system based on face recognition |
| CN103538563A (en) * | 2013-11-06 | 2014-01-29 | 中山弘博企业管理咨询有限公司 | Intelligent human face recognition automobile anti-theft device |
| CN106022317A (en) * | 2016-06-27 | 2016-10-12 | 北京小米移动软件有限公司 | Face identification method and apparatus |
| CN107264469A (en) * | 2017-06-15 | 2017-10-20 | 深圳森阳环保材料科技有限公司 | A kind of VATS Vehicle Anti-Theft System based on recognition of face |
| CN208439232U (en) * | 2018-05-21 | 2019-01-29 | 辽宁工业大学 | Automobile intelligent starting module based on recognition of face |
Non-Patent Citations (1)
| Title |
|---|
| 雷吴斌;焦纪超;王文宇;李迎弟;茹强;: "基于红外及人脸识别技术的车辆防盗方法研究", 科技经济市场, no. 07 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008543A (en) * | 2018-10-08 | 2020-04-14 | 珠海格力电器股份有限公司 | Face recognition method and image acquisition equipment |
| CN110525445A (en) * | 2019-08-30 | 2019-12-03 | 南京领行科技股份有限公司 | A kind of control method of vehicle driving, device, equipment, medium and vehicle |
| CN112519787A (en) * | 2019-08-30 | 2021-03-19 | 南京领行科技股份有限公司 | Vehicle control system and vehicle |
| CN110693508A (en) * | 2019-09-02 | 2020-01-17 | 中国航天员科研训练中心 | Multi-channel cooperative psychophysiological active sensing method and service robot |
| CN111775727A (en) * | 2020-07-28 | 2020-10-16 | 山东爱德邦智能科技有限公司 | Electric system of electric vehicle |
| CN113246908A (en) * | 2021-04-22 | 2021-08-13 | 新疆爱华盈通信息技术有限公司 | Vehicle starting method and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108407759A (en) | Automobile intelligent starting module based on recognition of face and startup method | |
| Lwin et al. | Automatic door access system using face recognition | |
| US7519201B2 (en) | Detecting humans via their pose | |
| Davis et al. | A two-stage template approach to person detection in thermal imagery | |
| Kukreja et al. | GAN-based synthetic data augmentation for increased CNN performance in Vehicle Number Plate Recognition | |
| Anagnostopoulos et al. | A license plate-recognition algorithm for intelligent transportation system applications | |
| Raghuwanshi et al. | An automated classroom attendance system using video based face recognition | |
| EP2863338B1 (en) | Delayed vehicle identification for privacy enforcement | |
| CN101949241B (en) | Intelligent switch device and method of car door | |
| CN109359697A (en) | Graph image recognition methods and inspection system used in a kind of power equipment inspection | |
| CN101859382A (en) | License plate detection and identification method based on maximum stable extremal region | |
| CN210573856U (en) | Prison vehicle driver verification all-in-one | |
| Peng et al. | Recognition of low-resolution logos in vehicle images based on statistical random sparse distribution | |
| Xia et al. | Real-time infrared pedestrian detection based on multi-block LBP | |
| CN107169479A (en) | Intelligent mobile equipment sensitive data means of defence based on fingerprint authentication | |
| Guo et al. | Real-time hand detection based on multi-stage HOG-SVM classifier | |
| Wang et al. | Fusion of LDB and HOG for Face Recognition | |
| Yaacob et al. | License plate recognition for campus auto-gate system | |
| Saadouli et al. | Automatic and secure electronic gate system using fusion of license plate, car make recognition and face detection | |
| Xing et al. | Fast pedestrian detection based on haar pre-detection | |
| CN208439232U (en) | Automobile intelligent starting module based on recognition of face | |
| Thumthong et al. | Automatic detection and recognition of Thai vehicle license plate from CCTV images | |
| Satsangi et al. | License plate recognition: a comparative study on thresholding, OCR and machine learning approaches | |
| Li et al. | A novel approach for vehicle detection using an AND–OR-graph-based multiscale model | |
| Chowdhury et al. | Identification of unauthorized vehicles by license plate recognition through image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180817 |