CN109398074B - Oil tank anti-theft system and method based on face recognition and fingerprint recognition - Google Patents
Oil tank anti-theft system and method based on face recognition and fingerprint recognition Download PDFInfo
- Publication number
- CN109398074B CN109398074B CN201811235774.7A CN201811235774A CN109398074B CN 109398074 B CN109398074 B CN 109398074B CN 201811235774 A CN201811235774 A CN 201811235774A CN 109398074 B CN109398074 B CN 109398074B
- Authority
- CN
- China
- Prior art keywords
- feature
- module
- geometric
- matching
- shape
- 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.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K15/00—Arrangement in connection with fuel supply of combustion engines or other fuel consuming energy converters, e.g. fuel cells; Mounting or construction of fuel tanks
- B60K15/03—Fuel tanks
-
- 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
- B60R25/20—Means to switch the anti-theft system on or off
- B60R25/25—Means to switch the anti-theft system on or off using biometry
- B60R25/252—Fingerprint recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K15/00—Arrangement in connection with fuel supply of combustion engines or other fuel consuming energy converters, e.g. fuel cells; Mounting or construction of fuel tanks
- B60K15/03—Fuel tanks
- B60K2015/03328—Arrangements or special measures related to fuel tanks or fuel handling
- B60K2015/03434—Arrangements or special measures related to fuel tanks or fuel handling for preventing theft of fuel
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Sustainable Development (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides an oil tank anti-theft system and method based on face recognition and fingerprint recognition. The system comprises an image acquisition module, a fingerprint identification module, a processing module, an early warning module, a communication module and a monitoring terminal. The method comprises the steps that an image acquisition module acquires an image of a car door area and transmits the image to a processing module, and the processing module extracts the acquisition geometric shape characteristics of eyes, mouths and noses according to a geometric characteristic face recognition algorithm; the processing module extracts standard geometric shape features of eyes, mouths and noses from gray level images manually imported in advance through a geometric feature face recognition algorithm; and comparing the acquired geometric shape features of the eyes, the mouth and the nose with standard geometric shape features of the eyes, the mouth and the nose respectively to obtain eye, mouth and nose feature matching results, comparing the eye, mouth and nose feature matching results with a threshold respectively to obtain face recognition matching results, and performing fingerprint recognition matching according to the face recognition matching results. The method has strong anti-interference capability and high identification accuracy.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring, in particular to an oil tank anti-theft system and method based on face recognition and fingerprint recognition.
Background
Large trucks have become one of the essential important transportation means in modern life, but the problems therewith are increasing, and the phenomenon that gasoline in a fuel tank is stolen is also increasing. The theft event generally occurs when the driver is in a short period of parking, shopping and rest. Aiming at the phenomenon of oil stealing, a plurality of oil stealing prevention devices are also arranged on the market at present, one is mechanical, for example, a lock of an oil tank cover is strengthened, and the opening difficulty is only increased; the other is electronic, for example, an oil quantity detection device is arranged, when the vehicle is shut down, the alarm is given out when the oil quantity is reduced, and the mode also has the problems of high false alarm rate and untimely alarm receiving of the vehicle owner. Therefore, the prior art and the product do not have good oil stealing prevention effect, and the technology needs to be further developed and researched.
Chinese patent document CN 105774754 discloses an oil tank anti-theft system, in which a signal detection circuit is implemented by four infrared sensor modules, three of which are installed on the same plane, and the remaining one is perpendicular to the plane, so as to implement 360-degree omnibearing detection and avoid the occurrence of detection blind areas. The false alarm rate is reduced by setting a safe zone threshold and an alarm zone threshold in the controller. The system detects through the infrared sensor, and although a certain false alarm rate can be improved, a large false alarm rate still exists.
Chinese patent document CN 108275114 discloses an oil tank anti-theft monitoring system, in which an image processing device, an early warning device and a communication module are adopted. The method comprises the steps of detecting pedestrian and moving target identification by utilizing a deep learning algorithm of image processing, judging whether a person moves nearby an oil tank, carrying out local acousto-optic early warning by a system when a suspicious target is detected, and simultaneously sending the suspicious target image to a driver mobile phone end to remind a driver of checking in time. Although the system can detect the pedestrian by utilizing image recognition, the system can be interfered by a light environment, and larger error is generated, so that the recognition accuracy is not high, and still larger false alarm rate exists.
Chinese patent document CN 206456237 discloses an alarm system for preventing diesel oil from being stolen for large trucks, wherein a detection device in the system uses a magnetic oil float and a magnetic displacement sensor, when a large truck stops running, if the oil level in an oil tank is reduced, the magnetic oil float is caused to change, and at the moment, the magnetic displacement sensor detects a related signal, converts the signal through an a/D converter and then transmits the converted signal to a single chip, and the single chip controls a switch to be turned on, so that a warning indicator is turned on to send out an alarm signal. Although the system can detect the change of the oil level in the oil tank, various conditions of the liquid level change are ignored, for example, the oil tank is inclined due to the inclination of a vehicle body, or magnetic interference is generated by a magnetic device to disturb an internal magnetic detection device, in addition, the rate standard of liquid level reduction is not made, if the slow oil pumping is possibly not detected, and the like, the detection is inaccurate.
Disclosure of Invention
In order to solve the technical problems, the invention provides an oil tank anti-theft system and method based on face recognition and fingerprint recognition, which utilize the image processing technology of face recognition and the method of fingerprint recognition to judge whether the picture shot by an image acquisition device can be successfully matched with the input picture, and if the matching is successful, the next fingerprint recognition operation can be carried out. If the matching is not successful, the fingerprint identification operation is directly carried out, the system gives an alarm, and sends the suspicious target image to the monitoring terminal to remind the driver to check in time.
The technical scheme of the system is that the oil tank anti-theft system based on face recognition and fingerprint recognition comprises an image acquisition module, a fingerprint recognition module, a processing module, an early warning module, a communication module and a monitoring terminal; the image acquisition module is connected with the processing module; the processing module is connected with the fingerprint identification module; the early warning module is connected with the processing module; the processing module is connected with the communication module; the communication module is connected with the monitoring terminal.
Preferably, the image acquisition module is arranged on the rearview mirror and used for acquiring images of the vehicle door area, and the image acquisition module is a black-and-white CCD high-definition camera.
Preferably, the fingerprint identification module is an optical fingerprint identification module of the punctuation atom AS608, and is configured to output a high level to the processing module when fingerprint identification matching is successful, and output a low level to the processing module when fingerprint identification matching is unsuccessful.
Preferably, the processing module performs face recognition through a face recognition algorithm based on geometric features, and judges whether the fingerprint recognition is successfully matched according to the level output by the fingerprint recognition module.
Preferably, the early warning module is used for giving an alarm when the face recognition matching is unsuccessful and the fingerprint recognition is unsuccessful or giving an audible and visual alarm when the face recognition matching is successful and the fingerprint matching is unsuccessful.
Preferably, the communication module is a communication module of the GMS, and is configured to send information to the driver.
Preferably, the monitoring terminal is a mobile phone used by a driver for receiving the information from the communication module.
The technical scheme of the method is that the oil tank anti-theft method based on face recognition and fingerprint recognition specifically comprises the following steps:
step 1: the method comprises the steps that an image acquisition module acquires an image of a car door area and transmits the image to a processing module, and the processing module extracts eye acquisition geometric shape features, mouth acquisition geometric shape features and nose acquisition geometric shape features according to a geometric feature face recognition algorithm;
step 2: the processing module extracts standard geometric shape features of eyes, standard geometric shape features of mouths and standard geometric shape features of noses from gray level images manually imported in advance through a geometric feature face recognition algorithm;
and step 3: comparing the eye acquisition geometric shape features with the eye standard geometric shape features to obtain eye feature matching results, comparing the mouth acquisition geometric shape features with the mouth standard geometric shape features to obtain mouth feature matching results, comparing the nose acquisition geometric shape features with the nose standard geometric shape features to obtain nose feature matching results, comparing the eye feature matching results, the mouth feature matching results and the nose feature matching results with threshold values respectively to obtain face recognition matching results, and performing fingerprint recognition matching according to the face recognition matching results.
Preferably, the door region image in step 1 is:
A(i,j)i∈[1,N]j∈[1,N]
the vehicle door area image A is a gray image with N rows and N columns, and A (i, j) is a pixel in the ith row and ith column;
the geometric characteristics of the acquisition shape of the eye in step 1 are as follows:
L1(a,b)a∈[1,M]b∈[1,M]
where M is the number of rows and columns of the feature matrix, the geometric feature L of the acquired shape of the eye1Is a feature matrix of M rows and M columns, L1(a,b)Characteristic values of the a row and the b column of the geometric characteristic of the acquired shape of the eye;
the geometric characteristics of the acquisition shape of the mouth in step 1 are as follows:
L2(c,d)c∈[1,M]D∈[1,M]
wherein M is the number of rows and columns of the feature matrix, and the acquisition shape geometric feature L of the mouth2Is a feature matrix of M rows and M columns, L2(c, d) is the characteristic value of the c row and d column of the geometric characteristic of the acquisition shape of the mouth;
the geometric characteristics of the collection shape of the nose in step 1 are as follows:
L3(e,f)e∈[1,M]f∈[1,M]
wherein M is the number of rows and columns of the feature matrix, and the collected shape geometric feature L of the nose3Is a feature matrix of M rows and M columns, L3(e, f) feature values of the No. e row and No. f column of the geometric feature of the collected shape of the nose;
preferably, the previously manually-imported grayscale image in step 2 is:
B(i*,j*)i*∈[1,N]j*∈[1,N]
wherein the gray scale image B artificially introduced in advance is a gray scale image with N rows and N columns, B (i)*,j*) Is the ith*Line i*Pixels of a column;
the standard shape geometry of the eye in step 2 is:
L4(a*,b*)a*∈[1,M]b*∈[1,M]
where M is the number of rows and columns of the feature matrix, the standard shape geometric feature L of the eye4Is a feature matrix of M rows and M columns, L4(a*,b*) As a standard geometric feature of the eye*Line b*A characteristic value of the column;
the standard shape geometry of the port in step 2 is characterized by:
L5(c*,d*)c*∈[1,M]d*∈[1,M]
wherein M is characterizedNumber of rows and columns of the matrix, standard shape geometry L of the ports5Is a feature matrix of M rows and M columns, L5(c*,d*) As a standard geometry feature of the mouth c*Line d*A characteristic value of the column;
the standard shape geometry of the nose in step 2 is characterized by:
L6(e*,f*)e∈[1,M]f*∈[1,M]
where M is the number of rows and columns of the feature matrix, and the standard shape geometric feature L of the nose6Is a feature matrix of M rows and M columns, L6(e*,f*) As standard geometric features of the nose e*Line f*A characteristic value of the column;
preferably, the result of the eye feature matching in step 3 is:
statistical eye acquisition geometry feature L1Standard geometric shape feature L of eye4The number of consistent eigenvalues at the same position of the matrix is X;
the characteristic matching result of the port in the step 3 is as follows:
collection geometry characteristics L of statistical port2Standard geometric shape characteristic of mouth L5The number of consistent eigenvalues at the same position of the matrix is Y;
the feature matching result of the nose in step 3 is:
statistical nose collection geometry feature L3Standard geometric shape characteristic L of nose6The number of consistent eigenvalues at the same position of the matrix is Z;
the face recognition matching result in the step 3 is as follows:
if X is more than M K, Y is more than M K, and Z is more than M K, the face recognition matching is successful, otherwise, the face recognition matching is unsuccessful;
wherein M × K is the threshold in step 3, K is a threshold coefficient, and M is the number of rows and columns of the feature matrix;
the fingerprint identification matching according to the face identification matching result in the step 3 is as follows:
if the face identification matching is unsuccessful and the fingerprint identification matching is directly carried out, the processing module controls the early warning module to carry out red light and sound alarm for reminding a driver, and the vehicle door area image A in the step 1 is sent to a monitoring terminal through the communication module to remind the driver to check in time;
if the face identification matching is successful, the processing module acquires a fingerprint identification result according to the fingerprint identification module, if the fingerprint identification module outputs a low level to indicate that the fingerprint identification matching is unsuccessful, the processing module controls the early warning module to perform red light and sound alarm to remind a driver, and the vehicle door area image A in the step 1 is sent to the monitoring terminal through the communication module to remind the driver to check in time;
if the face recognition matching is successful, the fingerprint recognition matching is carried out, the processing module acquires a fingerprint recognition result according to the fingerprint recognition module, and if the fingerprint recognition module outputs a high level to indicate that the fingerprint recognition matching is successful, the oil tank is unlocked.
The invention has the advantages that: the method adopts double verification measures, uses a black-and-white CCD camera with high pixels for capturing images, calculates by a CPU with high main frequency and high performance, then greatly improves the accuracy of identification by utilizing an advanced face identification algorithm, and secondly ensures the reliability of matching by adopting an advanced fingerprint identification module and internally arranging a mature identification algorithm.
Drawings
FIG. 1: the invention is a system block diagram;
FIG. 2: the method of the invention is a work flow diagram.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the technical solution of the system in the embodiment of the present invention is an oil tank anti-theft system based on face recognition and fingerprint recognition, including an image acquisition module, a fingerprint recognition module, a processing module, an early warning module, a communication module and a monitoring terminal; the image acquisition module is connected with the processing module; the processing module is connected with the fingerprint identification module; the early warning module is connected with the processing module; the processing module is connected with the communication module; the communication module is connected with the monitoring terminal.
The image acquisition module is arranged on the rearview mirror and used for acquiring images of the car door area, and the image acquisition module is a black-and-white CCD high-definition camera. The fingerprint identification module is an optical fingerprint identification module of the punctuation atom AS608 and is used for outputting a high level to the processing module when the fingerprint identification matching is successful and outputting a low level to the processing module when the fingerprint identification matching is unsuccessful. The processing module carries out face recognition through a face recognition algorithm based on geometric features, and judges whether the fingerprint recognition is successfully matched according to the level output by the fingerprint recognition module. The early warning module is used for giving an alarm when the face recognition matching is unsuccessful and the fingerprint recognition is unsuccessful or giving an audible and visual alarm when the face recognition matching is successful and the fingerprint matching is unsuccessful. The communication module is a communication module of GMS and is used for sending information to a driver. The monitoring terminal is used by a driver through a mobile phone and used for receiving the information from the communication module.
The image acquisition module is selected as a camera OK _ AM1300 of a black and white area array CCD; the fingerprint identification module is an optical fingerprint identification module of a punctuation atom AS 608; the processing module is selected to be based on a Cortex-A8 kernel S5PV210 chip; the early warning module is an LTL-1101J model audible and visual alarm; the communication module is a LongSung U9507C 4G module; the type of the monitoring terminal is selected as a driver mobile phone.
Embodiments of the present invention will be described below with reference to fig. 1 to 2. The embodiment of the invention discloses an oil tank anti-theft method based on face recognition and fingerprint recognition, which specifically comprises the following steps:
step 1: the method comprises the steps that an image acquisition module acquires an image of a car door area and transmits the image to a processing module, and the processing module extracts eye acquisition geometric shape features, mouth acquisition geometric shape features and nose acquisition geometric shape features according to a geometric feature face recognition algorithm;
in the step 1, the vehicle door region image is as follows:
A(i,j)i∈[1,N]j∈[1,N]
the vehicle door area image A is a grayscale image with N rows and N columns, A (i, j) is a pixel in the ith row and the ith column, and N is 1024;
the geometric characteristics of the acquisition shape of the eye in step 1 are as follows:
L1(a,b)a∈[1,M]b∈[1,M]
where M is the number of rows and columns of the feature matrix, the geometric feature L of the acquired shape of the eye1Is a feature matrix of M rows and M columns, L1(a, b) is the characteristic value of the geometric characteristic of the acquisition shape of the eye in the a-th row and the b-th column, and M is 300;
the geometric characteristics of the acquisition shape of the mouth in step 1 are as follows:
L2(c,d)c∈[1,M]D∈[1,M]
wherein M is the number of rows and columns of the feature matrix, and the acquisition shape geometric feature L of the mouth2Is a feature matrix of M rows and M columns, L2(c, d) is the characteristic value of the geometric characteristic of the acquired shape of the mouth in the c th row and the d th column, and M is 300;
the geometric characteristics of the collection shape of the nose in step 1 are as follows:
L3(e,f)e∈[1,M]f∈[1,M]
wherein M is the number of rows and columns of the feature matrix, and the collected shape geometric feature L of the nose3Is a feature matrix of M rows and M columns, L3(e, f) is the characteristic value of the geometric characteristic of the acquired shape of the nose in the e th row and the f th column, and M is 300;
step 2: the processing module extracts standard geometric shape features of eyes, standard geometric shape features of mouths and standard geometric shape features of noses from gray level images manually imported in advance through a geometric feature face recognition algorithm;
preferably, the previously manually-imported grayscale image in step 2 is:
B(i*,j*)i*∈[1,N]j*∈[1,N]
wherein the gray scale image B artificially introduced in advance is a gray scale image with N rows and N columns, B (i)*,j*) Is the ith*Line i*Pixels of a column, N1024;
the standard shape geometry of the eye in step 2 is:
L4(a*,b*)a*∈[1,M]b*∈[1,M]
where M is the number of rows and columns of the feature matrix, the standard shape geometric feature L of the eye4Is a feature matrix of M rows and M columns, L4(a*,b*) As a standard geometric feature of the eye*Line b*The column eigenvalue, M300;
the standard shape geometry of the port in step 2 is characterized by:
L5(c*,d*)c*∈[1,M]d*∈[1,M]
where M is the number of rows and columns of the feature matrix, the standard shape geometry of the port, L5Is a feature matrix of M rows and M columns, L5(c*,d*) As a standard geometry feature of the mouth c*Line d*The column eigenvalue, M300;
the standard shape geometry of the nose in step 2 is characterized by:
L6(e*,f*)e∈[1,M]f*∈[1,M]
where M is the number of rows and columns of the feature matrix, and the standard shape geometric feature L of the nose6Is a feature matrix of M rows and M columns, L6(e*,f*) As standard geometric features of the nose e*Line f*The column eigenvalue, M300;
and step 3: comparing the eye acquisition geometric shape feature with the eye standard geometric shape feature to obtain an eye feature matching result, comparing the mouth acquisition geometric shape feature with the mouth standard geometric shape feature to obtain a mouth feature matching result, comparing the nose acquisition geometric shape feature with the nose standard geometric shape feature to obtain a nose feature matching result, comparing the eye feature matching result, the mouth feature matching result and the nose feature matching result with a threshold value respectively to obtain a face recognition matching result, and performing fingerprint recognition matching according to the face recognition matching result;
preferably, the result of the eye feature matching in step 3 is:
statistical eye acquisition geometry feature L1Standard geometric shape feature L of eye4The number of consistent eigenvalues at the same position of the matrix is X;
the characteristic matching result of the port in the step 3 is as follows:
collection geometry characteristics L of statistical port2Standard geometric shape characteristic of mouth L5The number of consistent eigenvalues at the same position of the matrix is Y;
the feature matching result of the nose in step 3 is:
statistical nose collection geometry feature L3Standard geometric shape characteristic L of nose6The number of consistent eigenvalues at the same position of the matrix is Z;
the face recognition matching result in the step 3 is as follows:
if X is more than M K, Y is more than M K, and Z is more than M K, the face recognition matching is successful, otherwise, the face recognition matching is unsuccessful;
wherein, M × K is the threshold in step 3, K is a threshold coefficient, M is the number of rows and columns of the feature matrix, and M is 300;
the fingerprint identification matching according to the face identification matching result in the step 3 is as follows:
if the face identification matching is unsuccessful and the fingerprint identification matching is directly carried out, the processing module controls the early warning module to carry out red light and sound alarm for reminding a driver, and the vehicle door area image A in the step 1 is sent to a monitoring terminal through the communication module to remind the driver to check in time;
if the face identification matching is successful, the processing module acquires a fingerprint identification result according to the fingerprint identification module, if the fingerprint identification module outputs a low level to indicate that the fingerprint identification matching is unsuccessful, the processing module controls the early warning module to perform red light and sound alarm to remind a driver, and the vehicle door area image A in the step 1 is sent to the monitoring terminal through the communication module to remind the driver to check in time;
if the face recognition matching is successful, the fingerprint recognition matching is carried out, the processing module acquires a fingerprint recognition result according to the fingerprint recognition module, and if the fingerprint recognition module outputs a high level to indicate that the fingerprint recognition matching is successful, the oil tank is unlocked.
Although image acquisition modules, fingerprint identification modules, processing modules, early warning modules, communication modules and monitoring terminals are used more often herein; and the like, but does not exclude the possibility of using other terms. These terms are used merely to more conveniently describe the nature of the invention and they are to be construed as any additional limitation which is not in accordance with the spirit of the invention.
It should be understood that the above description of the preferred embodiments is given for clarity and not for any purpose of limitation, and that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (1)
1. An oil tank anti-theft method based on face recognition and fingerprint recognition is characterized by comprising the following steps:
step 1: the method comprises the steps that an image acquisition module acquires an image of a car door area and transmits the image to a processing module, and the processing module extracts eye acquisition geometric shape features, mouth acquisition geometric shape features and nose acquisition geometric shape features according to a geometric feature face recognition algorithm;
step 2: the processing module extracts standard geometric shape features of eyes, standard geometric shape features of mouths and standard geometric shape features of noses from gray level images manually imported in advance through a geometric feature face recognition algorithm;
and step 3: comparing the eye acquisition geometric shape feature with the eye standard geometric shape feature to obtain an eye feature matching result, comparing the mouth acquisition geometric shape feature with the mouth standard geometric shape feature to obtain a mouth feature matching result, comparing the nose acquisition geometric shape feature with the nose standard geometric shape feature to obtain a nose feature matching result, comparing the eye feature matching result, the mouth feature matching result and the nose feature matching result with a threshold value respectively to obtain a face recognition matching result, and performing fingerprint recognition matching according to the face recognition matching result;
an oil tank anti-theft system based on face recognition and fingerprint recognition, which is applied to the oil tank anti-theft method based on face recognition and fingerprint recognition, comprises:
the system comprises an image acquisition module, a fingerprint identification module, a processing module, an early warning module, a communication module and a monitoring terminal; the image acquisition module is connected with the processing module; the processing module is connected with the fingerprint identification module; the early warning module is connected with the processing module; the processing module is connected with the communication module; the communication module is connected with the monitoring terminal; the image acquisition module is arranged on the rearview mirror and used for acquiring an image of a vehicle door area, and the image acquisition module is a black-and-white CCD high-definition camera; the fingerprint identification module is used for outputting a high level to the processing module when the fingerprint identification matching is successful, and outputting a low level to the processing module when the fingerprint identification matching is unsuccessful; the processing module carries out face recognition through a face recognition algorithm based on geometric features and judges whether the fingerprint recognition is successfully matched according to the level output by the fingerprint recognition module; the early warning module is used for giving an alarm when the face recognition matching is unsuccessful and the fingerprint recognition is unsuccessful or giving an audible and visual alarm when the face recognition matching is successful and the fingerprint matching is unsuccessful; the communication module is a GMS communication module and is used for sending information to a driver; the monitoring terminal is used by a driver through a mobile phone and is used for receiving information from the communication module;
in the step 1, the vehicle door region image is as follows:
A(i,j)i∈[1,N]j∈[1,N]
the vehicle door area image A is a gray image with N rows and N columns, and A (i, j) is a pixel in the ith row and ith column;
the geometric characteristics of the acquisition shape of the eye in step 1 are as follows:
L1(a,b)a∈[1,M]b∈[1,M]
where M is the number of rows and columns of the feature matrix, the geometric feature L of the acquired shape of the eye1Is a feature matrix of M rows and M columns, L1(a, b) characteristic values of a row a and a column b of geometric characteristics of the acquired shape of the eye;
the geometric characteristics of the acquisition shape of the mouth in step 1 are as follows:
L2(c,d)c∈[1,M]d∈[1,M]
wherein M is the number of rows and columns of the feature matrix, and the acquisition shape geometric feature L of the mouth2Is a feature matrix of M rows and M columns, L2(c, d) is the characteristic value of the c row and d column of the geometric characteristic of the acquisition shape of the mouth;
the geometric characteristics of the collection shape of the nose in step 1 are as follows:
L3(e,f)e∈[1,M]f∈[1,M]
wherein M is the number of rows and columns of the feature matrix, and the collected shape geometric feature L of the nose3Is a feature matrix of M rows and M columns, L3(e, f) feature values of the No. e row and No. f column of the geometric feature of the collected shape of the nose;
the gray level image imported manually in advance in the step 2 is as follows:
B(i*,j*)i*∈[1,N]j*∈[1,N]
wherein the gray scale image B artificially introduced in advance is a gray scale image with N rows and N columns, B (i)*,j*) Is the ith*Line i*Pixels of a column;
the standard shape geometry of the eye in step 2 is:
L4(a*,b*)a*∈[1,M]b*∈[1,M]
where M is the row of the feature matrixAnd number of columns, standard shape geometry L of said eye4Is a feature matrix of M rows and M columns, L4(a*,b*) As a standard geometric feature of the eye*Line b*A characteristic value of the column;
the standard shape geometry of the port in step 2 is characterized by:
L5(c*,d*)c*∈[1,M]d*∈[1,M]
where M is the number of rows and columns of the feature matrix, the standard shape geometry of the port, L5Is a feature matrix of M rows and M columns, L5(c*,d*) As a standard geometry feature of the mouth c*Line d*A characteristic value of the column;
the standard shape geometry of the nose in step 2 is characterized by:
L6(e*,f*)e∈[1,M]f*∈[1,M]
where M is the number of rows and columns of the feature matrix, and the standard shape geometric feature L of the nose6Is a feature matrix of M rows and M columns, L6(e*,f*) As standard geometric features of the nose e*Line f*A characteristic value of the column;
the eye feature matching result in step 3 is:
statistical eye acquisition geometry feature L1Standard geometric shape feature L of eye4The number of consistent eigenvalues at the same position of the matrix is X;
the characteristic matching result of the port in the step 3 is as follows:
collection geometry characteristics L of statistical port2Standard geometric shape characteristic of mouth L5The number of consistent eigenvalues at the same position of the matrix is Y;
the feature matching result of the nose in step 3 is:
statistical nose collection geometry feature L3Standard geometric shape characteristic L of nose6The number of consistent eigenvalues at the same position of the matrix is Z;
the face recognition matching result in the step 3 is as follows:
if X is more than M K, Y is more than M K, and Z is more than M K, the face recognition matching is successful, otherwise, the face recognition matching is unsuccessful;
wherein M × K is the threshold in step 3, K is a threshold coefficient, and the number of rows of the feature matrix and the number of columns of the feature matrix are both M;
the fingerprint identification matching according to the face identification matching result in the step 3 is as follows:
if the face identification matching is unsuccessful and the fingerprint identification matching is directly carried out, the processing module controls the early warning module to carry out red light and sound alarm for reminding a driver, and the vehicle door area image A in the step 1 is sent to a monitoring terminal through the communication module to remind the driver to check in time;
if the face identification matching is successful, the processing module acquires a fingerprint identification result according to the fingerprint identification module, if the fingerprint identification module outputs a low level to indicate that the fingerprint identification matching is unsuccessful, the processing module controls the early warning module to perform red light and sound alarm to remind a driver, and the vehicle door area image A in the step 1 is sent to the monitoring terminal through the communication module to remind the driver to check in time;
if the face recognition matching is successful, the fingerprint recognition matching is carried out, the processing module acquires a fingerprint recognition result according to the fingerprint recognition module, and if the fingerprint recognition module outputs a high level to indicate that the fingerprint recognition matching is successful, the oil tank is unlocked.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811235774.7A CN109398074B (en) | 2018-10-23 | 2018-10-23 | Oil tank anti-theft system and method based on face recognition and fingerprint recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811235774.7A CN109398074B (en) | 2018-10-23 | 2018-10-23 | Oil tank anti-theft system and method based on face recognition and fingerprint recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109398074A CN109398074A (en) | 2019-03-01 |
CN109398074B true CN109398074B (en) | 2021-02-19 |
Family
ID=65468721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811235774.7A Active CN109398074B (en) | 2018-10-23 | 2018-10-23 | Oil tank anti-theft system and method based on face recognition and fingerprint recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109398074B (en) |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202641625U (en) * | 2012-05-08 | 2013-01-02 | 池长溪 | Automobile burglar alarm, starter of automobile burglar alarm and automobile |
CN103057518B (en) * | 2013-01-29 | 2016-01-06 | 阿坝师范高等专科学校 | Automotive anti-theft alarming system |
CN203344899U (en) * | 2013-07-05 | 2013-12-18 | 无锡商业职业技术学院 | Automobile anti-theft device |
CN103419746A (en) * | 2013-08-30 | 2013-12-04 | 瑞安市峰达汽车部件有限公司 | Automobile antitheft device basing on face and fingerprint recognition |
CN203996107U (en) * | 2014-09-03 | 2014-12-10 | 厦门市润铭电子科技有限公司 | A kind of Vehicle Anti-Theft System |
CN105518709B (en) * | 2015-03-26 | 2019-08-09 | 北京旷视科技有限公司 | The method, system and computer program product of face for identification |
CN106650574A (en) * | 2016-09-19 | 2017-05-10 | 电子科技大学 | Face identification method based on PCANet |
CN107539269A (en) * | 2017-08-11 | 2018-01-05 | 成都法线网络科技有限公司 | A kind of automotive theft proof system based on fingerprint recognition |
CN107901881A (en) * | 2018-01-02 | 2018-04-13 | 成都泰和顺信息技术有限公司 | A kind of anti-theft device of recognition of face |
-
2018
- 2018-10-23 CN CN201811235774.7A patent/CN109398074B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN109398074A (en) | 2019-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108275114B (en) | Oil tank anti-theft monitoring system | |
CN106709420B (en) | Method for monitoring driving behavior of commercial vehicle driver | |
CN107341454B (en) | Method and device for detecting obstacles in scene and electronic equipment | |
US20140375808A1 (en) | Apparatus, method, and computer readable medium for monitoring a number of passengers in an automobile | |
US6130617A (en) | Driver's eye detection method of drowsy driving warning system | |
CN109389791A (en) | A kind of detection object for vehicle is close to early warning system | |
CN111422057B (en) | Method and system for monitoring oil stealing of truck oil tank | |
EP3470274B1 (en) | Vehicle security system using sensor data | |
CN110889351A (en) | Video detection method and device, terminal equipment and readable storage medium | |
CN111599140A (en) | Vehicle rear-row living body monitoring system and method | |
CN112070039B (en) | Hash code-based vehicle collision detection method and system | |
CN107221156A (en) | The method and system that a kind of real-time monitoring is driven when intoxicated | |
CN110733461B (en) | Oil theft prevention detection system and method based on vehicle speed and hydraulic pressure change analysis | |
CN109398074B (en) | Oil tank anti-theft system and method based on face recognition and fingerprint recognition | |
CN113674311A (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
CN110329156B (en) | Method and device for identifying vehicle front information of vehicle backlight blind area | |
CN112519680A (en) | Peripheral visual field blind area detection system during starting, reversing and low-speed driving of automobile | |
US20040140885A1 (en) | Vehicle security system | |
CN109243150A (en) | A kind of vehicle early warning method and terminal | |
CN116630945A (en) | Driving distraction reminding method, device, equipment and readable storage medium | |
CN109204226B (en) | Vehicle alarm method and device | |
CN111768583A (en) | Vehicle fuel oil anti-theft method and system and vehicle | |
CN112406700B (en) | Blind area early warning system based on upper and lower binocular vision analysis range finding | |
CN214428030U (en) | Tank wagon anti-theft system | |
CN114445855A (en) | Sentinel model-based automobile fuel tank fuel stealing detection method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |