CN111797713A - License plate recognition method and photographing device - Google Patents
License plate recognition method and photographing device Download PDFInfo
- Publication number
- CN111797713A CN111797713A CN202010546400.8A CN202010546400A CN111797713A CN 111797713 A CN111797713 A CN 111797713A CN 202010546400 A CN202010546400 A CN 202010546400A CN 111797713 A CN111797713 A CN 111797713A
- Authority
- CN
- China
- Prior art keywords
- image
- license plate
- type
- target
- area corresponding
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 64
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 9
- 230000005764 inhibitory process Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a license plate recognition method and a photographing device, which relate to the field of computer graphics and image processing, and comprise the following steps: acquiring an image of a vehicle entrance; detecting an image area corresponding to an object in the image of the vehicle entrance through a multi-target detection network and identifying the type of the object; if the type of the object in the image is identified to comprise the target type, removing an image area corresponding to the target type from the image; and carrying out license plate recognition on the image. According to the embodiment of the invention, the target type object is identified, and the image area corresponding to the target type is removed from the image after the target type object is identified, so that the influence of the target object during license plate identification is avoided, and the accuracy of license plate identification is improved.
Description
Technical Field
The invention relates to the field of computer graphics and image processing, in particular to a license plate recognition method and photographing equipment.
Background
The camera is generally installed in an entrance and exit of unattended areas such as a residential quarter, a park and a parking lot, the camera is used for collecting images at the entrance and exit, license plate recognition is carried out on the images, the recognized license plate recognition is compared with a white list stored in the system in advance, and automatic opening and releasing are completed. And the parking lot white list is the vehicle with the parking qualification of the parking lot.
In the practical application process, in the monitoring process of an unmanned access, a person can place an internal vehicle license plate image shot by a mobile phone or a printed internal vehicle license plate image at the front end of a camera, and the camera is deceived to recognize the license plate by changing the angle and the distance, so that the brake is controlled through the comparison of a system white list, and vehicles pass through the unmanned area.
In the prior art, when a license plate is identified, the license plate is identified firstly, after the license plate is identified, an area around the license plate is identified, and whether the area around the license plate contains vehicles is determined, namely whether the license plate is a real license plate or a license plate which is falsely used as a white list stored in a system in advance is identified.
However, when the background is recognized in the area around the license plate, the recognition error rate is high due to the complex background condition.
For example, if someone recognizes a license plate from an image of an area surrounding the license plate captured by a mobile phone, the image captured by the mobile phone may not recognize the spoofed license plate because the image also has vehicle features. Or the size of an image region corresponding to the license plate in the image for shooting the license plate is not fixed, and particularly when the region of the license plate in the image is large, the area occupied by the region around the license plate is relatively small, and the information carried possibly is less, so that the obtained information of the region around the license plate is not comprehensive, and the recognition error is probably caused.
Disclosure of Invention
The invention provides a license plate recognition method and photographing equipment, which are used for recognizing the target type of an object and removing an image area corresponding to the target type from an image after the target type is recognized, so that the influence of the object on the license plate recognition is avoided, and the accuracy of license plate recognition is improved.
In a first aspect, an embodiment of the present invention provides a camera monitoring method, including:
acquiring an image of a vehicle entrance;
detecting an image area corresponding to an object in the image of the vehicle entrance through a multi-target detection network and identifying the type of the object;
if the type of the object in the image is detected to comprise a target type, removing an image area corresponding to the target type from the image;
and carrying out license plate recognition on the image.
According to the method, the type of the object in the image of the entrance is identified through the acquired image of the entrance of the vehicle and the multi-target detection network, the type of the image in the identified image comprises the target type, namely the type of the object which can pretend to be a white list stored in advance in the system is the target type, the image area corresponding to the target type is removed from the image to be identified, and the license plate identification is carried out on the removed image.
In one possible implementation, the types of the multi-target detection network identification at least comprise handheld electronic equipment and pedestrians.
According to the method, before the license plate recognition is carried out on the images at the vehicle entrance and exit, the interference objects of the handheld electronic equipment and the pedestrians are removed from the images, and then the license plate is recognized, so that the handheld electronic equipment of the fake license plate and the interference objects of the pedestrians are prevented from being used as real license plates in the process of recognizing the license plate, and the recognition accuracy is improved.
In one possible implementation, the multi-target detection network is obtained by:
and taking a sample picture as input, taking the target type of an object in the sample picture as output, and training a basic neural network for multiple times to obtain the multi-target detection network.
According to the method, the sample picture is used as input, the target type of the object in the sample picture is used as output, the basic neural network is trained for multiple times to obtain the multi-target detection network, the neural network is used for identification, and the identification accuracy is improved.
In one possible implementation, before removing the image region corresponding to the target type from the image, the method further includes:
if the abnormal object exists in the image of the entrance, determining an image area corresponding to the target type from a plurality of image areas in a non-maximum inhibition mode;
the abnormal object is an object of which the type is a target type and which corresponds to a plurality of image areas in the entrance image.
According to the method, when the images of the vehicle entrance and exit are identified through the multi-target detection network, the types of the objects can be identified, the image areas corresponding to the target types can also be identified, when the identified objects with the types as the target types pass through the multi-target detection network to identify the image areas, the image areas corresponding to the types most similar to the target types are selected from the image areas according to a non-maximum inhibition mode, and therefore the identification accuracy is improved.
In one possible implementation, after detecting, by the multi-target detection network, an image region corresponding to an object in the image of the vehicle entrance and exit and identifying a type of the object, the method further includes:
and if the image is detected to comprise a plurality of objects, and the types of the objects are all target types, early warning is carried out according to a preset warning mode.
According to the method, when the multi-target detection network identifies that the image comprises a plurality of objects, and the types of the objects are all target types, the situation that no vehicle passes through the vehicle entrance is indicated, and early warning is performed according to a preset warning mode, so that a manager can be reminded to confirm the condition of the vehicle entrance.
In one possible implementation, removing an image region corresponding to the target type from the image includes:
removing an image area corresponding to the target type from the image; or
And replacing the image area corresponding to the target type in the image with a preset background image.
According to the method, when the image area corresponding to the target type is removed from the image, the image area corresponding to the target type can be directly removed from the image, namely the image area of the target type is deducted from the image, license plate equipment is carried out by using the rest image, in addition, the image area corresponding to the target type of the image can be replaced by a preset background image, and the background image has no influence on license plate identification, so that the object serving as the license plate at the entrance and the exit of the vehicle can be shielded, and the accuracy of license plate identification is improved.
In a second aspect, an embodiment of the present invention provides a photographing apparatus, including: a memory and a processor:
the memory is used for storing program codes used when the photographing device runs;
the processor is configured to execute the program code to implement the following processes:
acquiring an image of a vehicle entrance;
detecting an image area corresponding to an object in the image of the vehicle entrance through a multi-target detection network and identifying the type of the object;
if the type of the object in the image is detected to comprise a target type, removing an image area corresponding to the target type from the image;
and carrying out license plate recognition on the image.
In one possible implementation, the types of the multi-target detection network identification at least comprise handheld electronic equipment and pedestrians.
In one possible implementation, the processor is specifically configured to:
and taking a sample picture as input, taking the target type of an object in the sample picture as output, and training a basic neural network for multiple times to obtain the multi-target detection network.
In one possible implementation, the processor is specifically configured to:
if the abnormal object exists in the image of the entrance, determining an image area corresponding to the target type from a plurality of image areas in a non-maximum inhibition mode;
the abnormal object is an object of which the type is a target type and which corresponds to a plurality of image areas in the entrance image.
In one possible implementation, the processor is further configured to:
and if the image is detected to comprise a plurality of objects, and the types of the objects are all target types, early warning is carried out according to a preset warning mode.
In one possible implementation, the processor is specifically configured to:
removing an image area corresponding to the target type from the image; or
And replacing the image area corresponding to the target type in the image with a preset background image.
In a third aspect, the present application further provides a computer storage medium having a computer program stored thereon, which when executed by a processing unit, implements the steps of the image capture monitoring method of the first aspect.
In addition, for technical effects brought by any one implementation manner of the second aspect to the third aspect, reference may be made to technical effects brought by different implementation manners of the first aspect, and details are not described here.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention and are not to be construed as limiting the invention.
Fig. 1 is a flowchart of a license plate recognition method according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an embodiment of the present invention for identifying a pedestrian as an object in an image using a multi-target detection network;
FIG. 3 is a schematic diagram of a handheld electronic device for recognizing the type of an object in an image using a multi-target detection network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a method for identifying a vehicle as an object in an image using a multi-target detection network according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a license plate recognition method for recognizing an image by using a multi-target detection network capable of only recognizing a target type according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a first exemplary license plate recognition process using a multi-target detection network capable of recognizing types of vehicles and targets according to an embodiment of the present disclosure;
FIG. 7 is a diagram illustrating a second exemplary embodiment of a license plate recognition process using a multi-target detection network capable of recognizing types of vehicles and targets;
FIG. 8 is a diagram illustrating a third exemplary embodiment of a license plate recognition process using a multi-target detection network capable of recognizing vehicle and target types;
FIG. 9 is a flowchart illustrating license plate recognition using a multi-target detection network capable of recognizing vehicle and target types according to an embodiment of the present invention;
FIG. 10 is a flowchart illustrating license plate recognition using a multi-target detection network that is capable of recognizing vehicle and target types, according to an embodiment of the present invention;
fig. 11 is a block diagram of a photographing apparatus according to an embodiment of the present invention;
fig. 12 is a block diagram of another photographing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.
The application scenario described in the embodiment of the present invention is for more clearly illustrating the technical solution of the embodiment of the present invention, and does not form a limitation on the technical solution provided in the embodiment of the present invention, and it can be known by a person skilled in the art that with the occurrence of a new application scenario, the technical solution provided in the embodiment of the present invention is also applicable to similar technical problems.
The term "and/or" in the embodiments of the present invention describes an association relationship of associated objects, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
In practical applications, vehicle entrance and exit management is performed for entrances and exits of unattended parking places, such as community doorways, parking lot doorways, and the like. In these places, it may happen that someone takes the white-listed license plate number of a vehicle in a parking place photographed by a mobile phone to masquerade as the vehicle entering or exiting, or takes the printed white-listed license plate number of a vehicle in a parking place to masquerade as the vehicle entering or exiting the parking place.
In the prior art, when a license plate is identified, the license plate is firstly identified, after the license plate is identified, a region around the license plate is identified, whether the region around the license plate is a vehicle or not is determined, however, when only the region around the license plate is identified in the prior art, when a camera takes a picture, the size of the license plate in the picture is unpredictable, and particularly when the license plate is large, the area occupied by the region around the license plate is small, the information which is possibly carried is small, and the identification error is easily caused.
Therefore, in the prior art, when the license plate is identified, the license plate is directly identified, so that the identification error rate is high, and the condition of falsifying the license plate is particularly easy to be confused.
According to the license plate recognition method and the photographing device provided by the embodiment of the invention, the type of the object in the image of the vehicle entrance is recognized, when the type of the object is recognized as the target type, the license plate recognition is carried out on the image of the image area corresponding to the removed target type, namely, the object which is possibly disguised as the license plate is removed, then the license plate recognition is carried out, the influence of the object of the target type during the license plate recognition is avoided, and the accuracy of the license plate recognition is improved.
The technology of the present invention is explained in detail below with reference to the accompanying drawings.
Referring to fig. 1, a license plate recognition method provided by an embodiment of the present invention is shown, including the following steps:
s100: an image of a vehicle doorway is acquired.
S101: and detecting an image area corresponding to the object in the image of the vehicle entrance and exit and identifying the type of the object through the multi-target detection network.
S102: if the type of the object in the image is detected to comprise the target type, removing an image area corresponding to the target type from the image.
S103: and carrying out license plate recognition on the image.
Wherein the target type is a type of an object which is easy to pretend as a license plate. The object types include at least pedestrians and/or handheld electronic devices. Electronic devices such as cell phones, tablet computers, electronic boards, and the like. The handheld electronic equipment is the electronic equipment held in a human hand.
Referring to fig. 2, when the collected images of the entrance and exit of the vehicle are images of the pedestrian holding the vehicle, the invention firstly identifies the object in the images, identifies the type of the object as the target type, namely, the pedestrian (the part drawn with the dotted frame in fig. 2), removes the pedestrian part and then carries out license plate identification on the images, because the pedestrian part comprises the license plate held by the pedestrian, after removing the license plate, the license plate identification on the license plate held by the pedestrian is not carried out, and the license plate held by the pedestrian is prevented from being mistaken as a real license plate.
Referring to fig. 3, when the collected images of the entrance and exit of the vehicle are images of the vehicle shot by the pedestrian holding the electronic device, the invention firstly identifies the object in the images, identifies the type of the object as the target type, namely the electronic device (the part with the dotted frame in fig. 3), removes the part of the electronic device and then carries out license plate identification on the images, and because the part of the electronic device contains the license plate shot by the electronic device, namely the fake license plate, after removing the fake license plate, the license plate identification on the part of the license plate shot by the electronic device can not be carried out, thus avoiding the situation that the license plate shot by the electronic device is mistaken as the real license plate.
Referring to fig. 4, when the images of the entrance and exit of the vehicle are collected, the present invention first identifies the object in the image, and if the type of the object does not include the target type, that is, does not include pedestrians and/or electronic devices, the present invention directly identifies the license plate of the image.
In summary, it can be seen that, before license plate recognition is performed, whether an object which is likely to falsify a license plate exists in an image is detected, if the object which is likely to falsify the license plate exists in the image, the object which is likely to falsify the license plate is removed from the image, and then license plate recognition is performed on the image, so that the situation that the object which is likely to falsify the license plate affects license plate recognition can be avoided, and the accuracy of license plate recognition is improved.
The present invention can be applied to vehicle management in an unattended parking place, specifically: the method comprises the steps of obtaining an image of a vehicle entrance and exit of an unattended parking lot, identifying the type of an object in the image of the vehicle entrance and exit through a multi-target detection network, removing an image area corresponding to a target type from the image when the type of the object in the image is identified to include the target type, identifying the license plate of the image, controlling a gate at the vehicle entrance and exit of the unattended parking lot to be opened when the identified license plate is the license plate on a white list of the parking lot, directly identifying the license plate of the image if the type of the object in the image is not identified to include the target type, comparing the image with the license plate on the white list of the parking lot after the license plate is identified, and controlling the gate at the vehicle entrance and exit of the unattended parking lot to be opened if the license plate on the white list is identified.
For the multi-target detection network of the present invention, it is possible to identify only the type of target, for example, pedestrians and handheld electronic devices. Specifically, the method comprises the following steps:
when it is detected that the type of the object in the image includes a pedestrian, an image area corresponding to the pedestrian is removed from the image, and license plate recognition is performed on the image.
When the type of the object in the image is detected to comprise the handheld electronic equipment, removing an image area corresponding to the handheld electronic equipment from the image, and then carrying out license plate recognition on the image.
When the type of the object in the image is detected to comprise the pedestrian and the handheld electronic equipment, removing an image area corresponding to the pedestrian and an image area corresponding to the handheld electronic equipment from the image, and then carrying out license plate recognition on the image.
As shown in fig. 2 to 4, when only the object type is recognized, the type of the object in the output virtual frame is a pedestrian when fig. 2 is input to the multi-target detection network, the type of the object in the output virtual frame is a handheld electronic device when fig. 3 is input to the multi-target detection network, and the output is not performed when fig. 4 is input to the multi-target detection network.
When a multi-target detection network which only identifies target types is used for identification, and a working process of license plate identification is shown in combination with fig. 5, and comprises the following steps:
s500: an image of a vehicle doorway is acquired.
S501: and detecting an image area corresponding to the object in the image of the vehicle entrance and exit and identifying the type of the object through the multi-target detection network.
S502: and if the type of the object in the image is detected to comprise the target type, removing an image area corresponding to the target type from the image, and carrying out license plate recognition on the image.
S503: and if the type of the object in the image is recognized to not comprise the target type, carrying out license plate recognition on the image.
When the multi-target detection network only recognizing the target type is used for image recognition, after an image area corresponding to the target type is removed from an image, if no vehicle exists, license plate recognition is directly sent, so that the working rate is low.
In addition, the multi-target detection network provided by the embodiment of the invention can also identify other types, such as vehicles, and the multi-target detection network can identify vehicles, pedestrians and electronic equipment.
After the image of fig. 2 with the virtual frame removed is input into the multi-target detection network, as shown in fig. 6, it is recognized that the image includes two objects, the types of the objects are pedestrian and vehicle, the virtual frame P1 is pedestrian, and the virtual frame P2 is vehicle. And then, image recognition is carried out on the image without the virtual frame P1, and in the recognition process, because the virtual frame P1 contains the license plate information, after the license plate information is removed, although the vehicle in the license plate which is falsely held by the hand of the pedestrian is recognized, the license plate information contained in the virtual frame P1 is removed, the license plate recognition of the part of the license plate which is falsely held by the hand of the pedestrian cannot be carried out, so that the accuracy of the license plate recognition is improved.
After the image with the virtual frame removed in fig. 3 is input to the multi-target detection network, as shown in fig. 7, it is detected that the image includes two objects, the types of the objects are the handheld electronic device and the vehicle, respectively, the virtual frame P3 is the handheld electronic device, and the virtual frame P4 is the vehicle. And then, carrying out license plate recognition on the image without the virtual frame P3, wherein in the recognition process, because the virtual frame P3 contains the information of the license plate, after the recognition, although the pedestrian holds the license plate of the electronic equipment in hand, namely the license plate which is falsely taken by hand, the information of the license plate is contained in the virtual frame P3 and is removed, and the license plate recognition of the part of the license plate which is falsely taken by the pedestrian holds the electronic equipment in hand can not be carried out.
After the input of fig. 4 with the virtual frame removed into the multi-target detection network, and as shown in fig. 8, it is detected that the types of the objects in the image are vehicles, respectively, and the virtual frame P5 is a vehicle. Since it is detected that the type of the object in the image does not include the target type, the image is directly recognized.
Of course, in the case of fig. 8, when the type of the object in the detected image is a vehicle and the type of the object in the detected image does not include the target type, the license plate recognition is performed on the image area corresponding to the vehicle, so that the influence of other backgrounds on the license plate recognition scene can be avoided, and the accuracy and efficiency of the license plate recognition are improved.
When the identification is performed by using the identification target type and the multi-target detection network of the vehicle, the working processes of two license plate identifications are shown in combination with fig. 9 and 10. Referring to fig. 9, an operation process of license plate recognition is shown, which includes:
s900: an image of a vehicle doorway is acquired.
S901: and detecting an image area corresponding to the object in the image of the vehicle entrance and exit and identifying the type of the object through the multi-target detection network.
S902: and if the image is detected to comprise a plurality of objects, and the types of the objects comprise the target type and the vehicle, removing an image area corresponding to the target type from the image, and carrying out license plate recognition on the image.
S903: and if the image is detected to comprise a plurality of objects, the types of the objects comprise vehicles and the types of the objects do not comprise target types, license plate recognition is carried out on the image.
S904: and if the image is detected to comprise a plurality of objects, and the types of the objects are all target types, early warning is carried out according to a preset warning mode.
Referring to fig. 10, another working process of license plate recognition is shown, which includes:
s1000: an image of a vehicle doorway is acquired.
S1001: detecting an image area corresponding to an object in an image of a vehicle entrance through a multi-target detection network and identifying the type of the object.
S1002: and if the image is detected to comprise 1 object and the type of the object is the target type, early warning is carried out according to a preset warning mode.
S1003: and if the image is detected to comprise 1 object and the type of the object is a vehicle, carrying out license plate recognition on the image.
The method comprises the steps of carrying out early warning according to a preset warning mode, specifically, generating warning information, wherein the warning information comprises a warning image, namely, the image identifying that the type of an object is only a target type is sent to a manager, so that the manager can check whether a license plate is falsely identified according to the warning image. The speaker or the loudspeaker can be arranged at the vehicle entrance and exit, when the object type is identified to be the image of the target type, the alarm voice is generated, the speaker or the loudspeaker is arranged at the vehicle entrance and exit for playing, and the pedestrian passing through the vehicle entrance and exit is warned not to pass.
For the multi-target detection network, when the image is input into the multi-target detection network, not only the type of the detected object but also the image area corresponding to the object can be detected.
In the invention, the type of the object in the image of the entrance is identified through a multi-target detection network, and the type of the object in the image is detected to be a target type and an image area corresponding to the target type.
Therefore, the image area corresponding to the target type does not need to be determined in a positioning mode after the target type is detected through the multi-target detection network.
When the classification is carried out through the multi-target detection network, the image is divided into a plurality of small areas, whether each area is a target type is detected, then the areas belonging to the same object are combined to obtain an image area corresponding to the target object, then the confidence coefficient of each type of the object is calculated, for example, when the identification types are vehicles, pedestrians and handheld electronic devices, the confidence coefficient calculation is carried out on the vehicles, the pedestrians and the handheld electronic devices respectively, and the type with the highest confidence coefficient is obtained for output. However, in the multi-object detection network, if an image is divided into small regions, the divided regions are too small, resulting in a plurality of image regions for the same object.
Based on this, an embodiment of the present invention provides a method for determining an image area corresponding to a target type, including:
if an abnormal object exists in the images of the entrance and the exit, determining an image area corresponding to the target type from the plurality of image areas in a non-maximum inhibition mode;
the abnormal object is an object whose type is a target type and corresponds to a plurality of image areas in the entrance image.
The non-maximum suppression method comprises the following steps: when the face is identified, the probability value that each image area is of the target type is identified, the maximum probability value of the image areas is determined, then the intersection ratio is calculated according to the maximum probability value and the probability value of the image areas except the image area corresponding to the maximum probability value, if the intersection ratio is larger than a preset threshold value, the intersection ratio is removed until one object corresponds to one image area.
For the neural network described above, training can be performed by:
and taking the sample picture as input, taking the target type of the object in the sample picture as output, and training the basic neural network for multiple times to obtain the multi-target detection network.
For example, when the target type is a pedestrian, a plurality of sample pictures of the pedestrian are obtained, the obtained sample pictures of the pedestrian are used as input, the pedestrian in the sample pictures is used as output, and the basic neural network is trained for multiple times to obtain the multi-target detection network.
When the target type is the handheld electronic device, a plurality of sample pictures of the handheld electronic device are obtained, the obtained sample pictures of the handheld electronic device are used as input, the handheld electronic device in the sample pictures is used as output, and the basic neural network is trained for multiple times to obtain the multi-target detection network.
When the target types are the handheld electronic device and the pedestrian, a plurality of sample pictures of the handheld electronic device and a plurality of sample pictures of the pedestrian are obtained, the obtained plurality of sample pictures of the handheld electronic device and the obtained plurality of sample pictures of the pedestrian are used as input, the pedestrian in the sample picture containing the pedestrian is used as output, the handheld electronic device in the sample picture containing the handheld electronic device is used as output, and the basic neural network is trained for multiple times to obtain the multi-target detection network.
Similarly, when the multi-target detection network can classify handheld electronic devices, pedestrians and vehicles, the training process is similar to that described above. The method comprises the steps of obtaining a plurality of sample pictures of the handheld electronic device, a plurality of sample pictures of pedestrians and a plurality of sample pictures of vehicles, taking the obtained sample pictures of the handheld electronic device, the sample pictures of the pedestrians and the sample pictures of the vehicles as input, taking the pedestrians in the sample pictures containing the pedestrians as output, taking the handheld electronic device in the sample pictures containing the handheld electronic device as output, taking the vehicles in the sample pictures containing the vehicles as output, and training a basic neural network for a plurality of times to obtain the multi-target detection network.
For different types of sample pictures, sample expansion can be performed on images in the inlet and outlet videos in various scenes, and then the collected video frames can be turned over, translated, rotated and the like.
Taking an electronic device of a handheld electronic device as an example of a mobile phone, some mobile phones or printed pictures are collected to be opposite to a camera lens, and a video image of a license plate is displayed in a full screen mode. Different hands are required to hold various mobile phones or pictures in the process of collecting samples, the distance is changed, the mobile phones are properly shaken to collect the samples, and the fake mobile phone plates of real scenes are simulated. And collecting at different point locations and different time periods to obtain the mobile phone fake plate samples under various illumination conditions in the day and at night.
The basic neural network can be yolov3 network or anchor free network.
In the practical application process, when the type of the object in the image is identified as the target type through the multi-target detection network, the image area corresponding to the target type is removed from the image, and the image analysis is carried out on the removed image. The mode of removing the image area corresponding to the target type from the image is as follows:
mode 1: and removing the image area corresponding to the target type from the image.
Mode 2: and replacing the image area corresponding to the target type in the image with a preset background image.
The preset background image can be a black image or a white image, and has a small influence on license plate recognition.
Specifically, the size of an image area corresponding to the target type is determined, a background image with the same size as the image area corresponding to the target type is obtained, and then the image area corresponding to the target type in the image is replaced by the preset background image.
When the size of the preset background image is larger than that of the image, the background image with the same size is cut out from the preset background image to replace the background image according to the size of the image area corresponding to the target type during operation.
An embodiment of the present invention provides a photographing apparatus 1100, which is shown in fig. 11 and includes: memory 1120 and processor 1110:
the memory 1120 is used for storing program codes used when the terminal device runs;
the processor 1110 is configured to execute the program code to implement the following processes:
acquiring an image of a vehicle entrance;
detecting an image area corresponding to an object in the image of the vehicle entrance through a multi-target detection network and identifying the type of the object;
if the type of the object in the image is detected to comprise a target type, removing an image area corresponding to the target type from the image;
and carrying out license plate recognition on the image.
Optionally, the types of the multi-target detection network identification at least comprise handheld electronic equipment and pedestrians.
Optionally, the processor 1110 is specifically configured to:
and taking a sample picture as input, taking the target type of an object in the sample picture as output, and training a basic neural network for multiple times to obtain the multi-target detection network.
Optionally, the processor 1110 is specifically configured to:
if the abnormal object exists in the image of the entrance, determining an image area corresponding to the target type from a plurality of image areas in a non-maximum inhibition mode;
the abnormal object is an object of which the type is a target type and which corresponds to a plurality of image areas in the entrance image.
Optionally, the processor 1110 is further configured to:
and if the image is detected to comprise a plurality of objects, and the types of the objects are all target types, early warning is carried out according to a preset warning mode.
Optionally, the processor 1110 is specifically configured to:
removing an image area corresponding to the target type from the image; or
And replacing the image area corresponding to the target type in the image with a preset background image.
In an exemplary embodiment, a storage medium comprising instructions, such as a memory comprising instructions, executable by processor 1110 to perform the above-described method is also provided. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
The photographing apparatus may also be a photographing apparatus with a communication function, so that the photographing apparatus, in addition to the above-described processor and memory, as shown in fig. 12, further includes: camera 1210, Radio Frequency (RF) circuit 1220, Wireless Fidelity (Wi-Fi) module 1230, communication interface 1240, display unit 1250, power supply 1260, processor 1270, memory 1280, and the like. Those skilled in the art will appreciate that the configuration of the photographing apparatus shown in fig. 12 does not constitute a limitation of the photographing apparatus, and the photographing apparatus provided in the embodiments of the present application may include more or less components than those shown, or combine some components, or arrange different components.
The following describes the components of the photographing apparatus 1100 in detail with reference to fig. 12:
the camera 1210 is configured to implement a shooting function of the photographing apparatus 1100, and take pictures or videos. The camera 1270 may also be used to implement a scanning function of the photographing apparatus 1100, and scan a scanned object (two-dimensional code/barcode).
The photographing apparatus 1100 of the present invention can photograph an image of a doorway of a vehicle using the camera 1210.
The photographing device 1100 may alarm in the above communication manner with a manager at a vehicle entrance when performing an early warning according to a preset alarm manner through the communication modules of the RF circuit 1220, the Wi-Fi module 1230, and the communication interface 1240.
The RF circuit 1220 may be used for receiving and transmitting data during communication. In particular, the RF circuit 1220 sends the downlink data of the base station to the processor 1270 for processing after receiving the downlink data; and in addition, sending the uplink data to be sent to the base station. Generally, the RF circuit 1220 includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like.
In addition, the RF circuitry 1220 may also communicate with networks and other electronic devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to Global System for mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.
The Wi-Fi technology belongs to a short-distance wireless transmission technology, and the photographing device 1100 can be connected with an Access Point (AP) through a Wi-Fi module 1230, so as to realize Access to a data network. The Wi-Fi module 1230 may be used for receiving and transmitting data during communication.
The photographing apparatus 1100 can be physically connected to other electronic apparatuses through the communication interface 1240. Optionally, the communication interface 1240 is connected to a communication interface of the other electronic device through a cable, so as to implement data transmission between the photographing device 1100 and the other electronic device.
In the embodiment of the present application, the photographing apparatus 1100 is capable of implementing a communication service and sending information to other contacts, so that the photographing apparatus 1100 needs to have a data transmission function, that is, the photographing apparatus 1100 needs to include a communication module therein. Although fig. 12 illustrates communication modules such as the RF circuitry 1220, the Wi-Fi module 1230, and the communication interface 1240, it is to be understood that at least one of the above components or other communication modules (e.g., bluetooth module) for enabling communication may be present in the photographing apparatus 1100 for data transmission.
For example, when the photographing apparatus 1100 is a mobile phone, the photographing apparatus 1100 may include the RF circuit 1220 and may further include the Wi-Fi module 1230; when the photographing apparatus 1100 is a computer, the photographing apparatus 1100 may include the communication interface 1240 and may further include the Wi-Fi module 1230; when the photographing apparatus 1100 is a tablet computer, the photographing apparatus 1100 may include the Wi-Fi module.
The display unit 1250 may be used to display information input by or provided to the user and various menus of the photographing apparatus 1100. The display unit 1250 is a display system of the photographing apparatus 1100, and is used for presenting an interface to realize human-computer interaction.
The display unit 1250 may include a display panel 1251. Alternatively, the Display panel 1251 may be configured by using a Liquid Crystal Display (LCD), an Organic Light-emitting diode (OLED), or the like.
The memory 1280 may be used to store software programs and modules. The processor 1270 executes various functional applications and data processing of the photographing apparatus 1100 by executing software programs and modules stored in the memory 1280, wherein the memory 1280 includes the functions of the memory 1120 in fig. 11.
Alternatively, the memory 1280 may mainly include a program storage area and a data storage area. The storage program area can store an operating system, various application programs (such as communication application), a face recognition module and the like; the storage data area may store data created according to the use of the photographing apparatus (such as various multimedia files like pictures, video files, etc., and face information templates), and the like.
Additionally, the memory 1280 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
The processor 1270 is a control center of the photographing apparatus 1100, connects various components using various interfaces and lines, and executes various functions and processes data of the photographing apparatus 1100 by running or executing software programs and/or modules stored in the memory 1280 and calling data stored in the memory 1280, thereby implementing various services based on the photographing apparatus. Processor 1270, among other things, includes the functionality of processor 1110 in fig. 11.
Optionally, the processor 1270 may include one or more processing units. Optionally, the processor 1270 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program, and the like, and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 1270.
The photographing apparatus 1100 also includes a power supply 1260 (e.g., a battery) for powering the various components. Optionally, the power supply 1260 may be logically connected to the processor 1270 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system.
The embodiment of the invention also provides a computer program product, and when the computer program product runs on the photographing device, the photographing device is enabled to execute any license plate recognition method in the embodiment of the invention.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. A license plate recognition method is characterized by comprising the following steps:
acquiring an image of a vehicle entrance;
detecting an image area corresponding to an object in the image of the vehicle entrance through a multi-target detection network and identifying the type of the object;
if the type of the object in the image is detected to comprise a target type, removing an image area corresponding to the target type from the image;
and carrying out license plate recognition on the image.
2. The license plate recognition method of claim 1, wherein the types of multi-target detection network recognition at least comprise handheld electronic devices and pedestrians.
3. The license plate recognition method of claim 1, wherein the multi-target detection network is obtained by:
and taking a sample picture as input, taking the target type of an object in the sample picture as output, and training a basic neural network for multiple times to obtain the multi-target detection network.
4. The license plate recognition method of claim 1, wherein before removing the image region corresponding to the target type from the image, the method further comprises:
if the abnormal object exists in the image of the entrance, determining an image area corresponding to the target type from a plurality of image areas in a non-maximum inhibition mode;
the abnormal object is an object of which the type is a target type and which corresponds to a plurality of image areas in the entrance image.
5. The license plate recognition method of claim 1, wherein after detecting, by a multi-target detection network, an image region corresponding to an object in the image of the vehicle entrance and exit and recognizing a type of the object, the method further comprises:
and if the image is detected to comprise a plurality of objects, and the types of the objects are all target types, early warning is carried out according to a preset warning mode.
6. The license plate recognition method of any one of claims 1 to 5, wherein removing the image area corresponding to the target type from the image comprises:
removing an image area corresponding to the target type from the image; or
And replacing the image area corresponding to the target type in the image with a preset background image.
7. A photographing apparatus, comprising: a memory and a processor:
the memory is used for storing program codes used when the photographing device runs;
the processor is configured to execute the program code to implement the following processes:
acquiring an image of a vehicle entrance;
detecting an image area corresponding to an object in the image of the vehicle entrance through a multi-target detection network and identifying the type of the object;
if the type of the object in the image is detected to comprise a target type, removing an image area corresponding to the target type from the image;
and carrying out license plate recognition on the image.
8. The photographing apparatus according to claim 7, wherein the types of the multi-object detection network recognition include at least a handheld electronic device and a pedestrian.
9. The photographing apparatus of claim 7, wherein the processor is specifically configured to:
and taking a sample picture as input, taking the target type of an object in the sample picture as output, and training a basic neural network for multiple times to obtain the multi-target detection network.
10. The photographing apparatus of claim 7, wherein the processor is specifically configured to:
if the abnormal object exists in the image of the entrance, determining an image area corresponding to the target type from a plurality of image areas in a non-maximum inhibition mode;
the abnormal object is an object of which the type is a target type and which corresponds to a plurality of image areas in the entrance image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010546400.8A CN111797713B (en) | 2020-06-16 | 2020-06-16 | License plate recognition method and photographing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010546400.8A CN111797713B (en) | 2020-06-16 | 2020-06-16 | License plate recognition method and photographing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111797713A true CN111797713A (en) | 2020-10-20 |
| CN111797713B CN111797713B (en) | 2024-08-06 |
Family
ID=72804778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010546400.8A Active CN111797713B (en) | 2020-06-16 | 2020-06-16 | License plate recognition method and photographing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111797713B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580531A (en) * | 2020-12-23 | 2021-03-30 | 深圳市捷顺科技实业股份有限公司 | Method and system for identifying and detecting true and false license plates |
| CN113192358A (en) * | 2021-04-26 | 2021-07-30 | 贵州车秘科技有限公司 | Parking management system based on thermal imaging technology in intelligent parking field and use method thereof |
| CN113627210A (en) * | 2021-08-19 | 2021-11-09 | 南京华捷艾米软件科技有限公司 | Method and device for generating bar code image, electronic equipment and storage medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201351307A (en) * | 2012-06-01 | 2013-12-16 | Bingotimes Digital Technology Co Ltd | Parking lot management control device |
| US20140307923A1 (en) * | 2013-04-11 | 2014-10-16 | International Business Machines Corporation | Determining images having unidentifiable license plates |
| CN104616381A (en) * | 2015-01-28 | 2015-05-13 | 苏州市职业大学 | Intelligent measuring and controlling access control system for automobile passage of community estate |
| WO2017091060A1 (en) * | 2015-11-27 | 2017-06-01 | Mimos Berhad | A system and method for detecting objects from image |
| CN107103774A (en) * | 2017-06-19 | 2017-08-29 | 京东方科技集团股份有限公司 | A kind of vehicle monitoring method and device for monitoring vehicle |
| CN107545416A (en) * | 2017-07-28 | 2018-01-05 | 阿里巴巴集团控股有限公司 | Refuel, refuel clearing, oiling method of payment, device and electronic equipment |
| CN107609555A (en) * | 2017-09-15 | 2018-01-19 | 北京文安智能技术股份有限公司 | Detection method of license plate, model recognizing method and relevant apparatus using it |
| CN109002820A (en) * | 2018-06-27 | 2018-12-14 | 迪蒙智慧交通（深圳）有限公司 | A kind of licence plate recognition method, device and relevant device |
| CN110443245A (en) * | 2019-08-14 | 2019-11-12 | 上海世茂物联网科技有限公司 | Localization method, device and the equipment of a kind of license plate area under unrestricted scene |
| CN110533039A (en) * | 2019-09-04 | 2019-12-03 | 深圳市捷顺科技实业股份有限公司 | A kind of true-false detection method of license plate, device and equipment |
| CN110659638A (en) * | 2019-09-24 | 2020-01-07 | 北京精英路通科技有限公司 | License plate recognition method and device, computer equipment and storage medium |
| CN110837807A (en) * | 2019-11-11 | 2020-02-25 | 内蒙古大学 | Identification method and system for fake-licensed vehicle |
| US20200090506A1 (en) * | 2018-09-19 | 2020-03-19 | National Chung-Shan Institute Of Science And Technology | License plate recognition system and license plate recognition method |
| CN110909692A (en) * | 2019-11-27 | 2020-03-24 | 北京格灵深瞳信息技术有限公司 | Abnormal license plate recognition method and device, computer storage medium and electronic equipment |
| CN110991506A (en) * | 2019-11-22 | 2020-04-10 | 高新兴科技集团股份有限公司 | Vehicle brand identification method, device, equipment and storage medium |
| CN111046746A (en) * | 2019-11-22 | 2020-04-21 | 北京精英路通科技有限公司 | License plate detection method and device |
| CN111079751A (en) * | 2019-12-16 | 2020-04-28 | 深圳市芊熠智能硬件有限公司 | Method and device for identifying authenticity of license plate, computer equipment and storage medium |
| US20200134313A1 (en) * | 2018-10-30 | 2020-04-30 | Fujitsu Limited | Detection method and detection device |
| CN111144372A (en) * | 2019-12-31 | 2020-05-12 | 上海眼控科技股份有限公司 | Vehicle detection method, device, computer equipment and storage medium |
-
2020
- 2020-06-16 CN CN202010546400.8A patent/CN111797713B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201351307A (en) * | 2012-06-01 | 2013-12-16 | Bingotimes Digital Technology Co Ltd | Parking lot management control device |
| US20140307923A1 (en) * | 2013-04-11 | 2014-10-16 | International Business Machines Corporation | Determining images having unidentifiable license plates |
| CN104616381A (en) * | 2015-01-28 | 2015-05-13 | 苏州市职业大学 | Intelligent measuring and controlling access control system for automobile passage of community estate |
| WO2017091060A1 (en) * | 2015-11-27 | 2017-06-01 | Mimos Berhad | A system and method for detecting objects from image |
| CN107103774A (en) * | 2017-06-19 | 2017-08-29 | 京东方科技集团股份有限公司 | A kind of vehicle monitoring method and device for monitoring vehicle |
| CN107545416A (en) * | 2017-07-28 | 2018-01-05 | 阿里巴巴集团控股有限公司 | Refuel, refuel clearing, oiling method of payment, device and electronic equipment |
| CN107609555A (en) * | 2017-09-15 | 2018-01-19 | 北京文安智能技术股份有限公司 | Detection method of license plate, model recognizing method and relevant apparatus using it |
| CN109002820A (en) * | 2018-06-27 | 2018-12-14 | 迪蒙智慧交通（深圳）有限公司 | A kind of licence plate recognition method, device and relevant device |
| US20200090506A1 (en) * | 2018-09-19 | 2020-03-19 | National Chung-Shan Institute Of Science And Technology | License plate recognition system and license plate recognition method |
| US20200134313A1 (en) * | 2018-10-30 | 2020-04-30 | Fujitsu Limited | Detection method and detection device |
| CN110443245A (en) * | 2019-08-14 | 2019-11-12 | 上海世茂物联网科技有限公司 | Localization method, device and the equipment of a kind of license plate area under unrestricted scene |
| CN110533039A (en) * | 2019-09-04 | 2019-12-03 | 深圳市捷顺科技实业股份有限公司 | A kind of true-false detection method of license plate, device and equipment |
| CN110659638A (en) * | 2019-09-24 | 2020-01-07 | 北京精英路通科技有限公司 | License plate recognition method and device, computer equipment and storage medium |
| CN110837807A (en) * | 2019-11-11 | 2020-02-25 | 内蒙古大学 | Identification method and system for fake-licensed vehicle |
| CN110991506A (en) * | 2019-11-22 | 2020-04-10 | 高新兴科技集团股份有限公司 | Vehicle brand identification method, device, equipment and storage medium |
| CN111046746A (en) * | 2019-11-22 | 2020-04-21 | 北京精英路通科技有限公司 | License plate detection method and device |
| CN110909692A (en) * | 2019-11-27 | 2020-03-24 | 北京格灵深瞳信息技术有限公司 | Abnormal license plate recognition method and device, computer storage medium and electronic equipment |
| CN111079751A (en) * | 2019-12-16 | 2020-04-28 | 深圳市芊熠智能硬件有限公司 | Method and device for identifying authenticity of license plate, computer equipment and storage medium |
| CN111144372A (en) * | 2019-12-31 | 2020-05-12 | 上海眼控科技股份有限公司 | Vehicle detection method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 吴健辉;张国云;邓己媛;郭龙源;袁帅;: "基于车牌识别技术的双车道一体化智能道闸系统设计", 湖南理工学院学报(自然科学版), no. 02, 15 June 2013 (2013-06-15), pages 38 - 41 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580531A (en) * | 2020-12-23 | 2021-03-30 | 深圳市捷顺科技实业股份有限公司 | Method and system for identifying and detecting true and false license plates |
| CN112580531B (en) * | 2020-12-23 | 2024-04-02 | 深圳市捷顺科技实业股份有限公司 | Identification detection method and system for true and false license plates |
| CN113192358A (en) * | 2021-04-26 | 2021-07-30 | 贵州车秘科技有限公司 | Parking management system based on thermal imaging technology in intelligent parking field and use method thereof |
| CN113627210A (en) * | 2021-08-19 | 2021-11-09 | 南京华捷艾米软件科技有限公司 | Method and device for generating bar code image, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111797713B (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111797713B (en) | License plate recognition method and photographing equipment | |
| CN103985230B (en) | A kind of Notification Method based on image, device and notice system | |
| CN106407984B (en) | Target object identification method and device | |
| US20210406523A1 (en) | Method and device for detecting living body, electronic device and storage medium | |
| CN108024065B (en) | Terminal shooting method, terminal and computer readable storage medium | |
| CN108091140B (en) | Method and device for determining fake-licensed vehicle | |
| CN105828068A (en) | Method and device for carrying out occlusion detection on camera and terminal device | |
| CN108989665A (en) | Image processing method, device, mobile terminal and computer-readable medium | |
| US20210136326A1 (en) | Multi-camera collaboration-based image processing method and video surveillance system | |
| CN110556022A (en) | Parking lot parking space indication method and device based on artificial intelligence and electronic equipment | |
| CN111539338A (en) | Pedestrian mask wearing control method, device, equipment and computer storage medium | |
| CN107566742A (en) | Image pickup method, device, storage medium and electronic equipment | |
| CN107995422A (en) | Image capturing method and device, computer equipment, computer-readable recording medium | |
| KR100948382B1 (en) | Security service method and system | |
| CN109086761A (en) | Image processing method and device, storage medium, electronic equipment | |
| CN113313115A (en) | License plate attribute identification method and device, electronic equipment and storage medium | |
| CN111062401A (en) | Stacked object identification method and device, electronic device and storage medium | |
| CN111753611A (en) | Image detection method, device and system, electronic equipment and storage medium | |
| WO2022099988A1 (en) | Object tracking method and apparatus, electronic device, and storage medium | |
| CN113888865B (en) | Electronic device and vehicle information acquisition method | |
| CN115134453B (en) | Riding information display method and electronic equipment | |
| KR20200101792A (en) | The CCTV integrated control system using black box | |
| CN114359828A (en) | Target behavior recording method, device, storage medium and electronic device | |
| CN109785617B (en) | Method for processing traffic control information | |
| CN113205069A (en) | False license plate detection method and device and computer storage medium |
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 |