CN115298705A - License plate recognition method and device, electronic equipment and storage medium - Google Patents
License plate recognition method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115298705A CN115298705A CN202080095192.2A CN202080095192A CN115298705A CN 115298705 A CN115298705 A CN 115298705A CN 202080095192 A CN202080095192 A CN 202080095192A CN 115298705 A CN115298705 A CN 115298705A
- Authority
- CN
- China
- Prior art keywords
- license plate
- recognition
- plate recognition
- images
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
Abstract
A license plate recognition method, a license plate recognition device, electronic equipment and a storage medium are provided, wherein the license plate recognition method comprises the following steps: acquiring a plurality of license plate images (201) of a target vehicle; respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results (202); and fusing the plurality of license plate recognition results to determine a license plate recognition result of the target vehicle (203). Because the finally determined license plate recognition result of the target vehicle is determined by fusing the license plate recognition results, the influence of license plate false detection and license plate motion blur on the license plate recognition result can be effectively eliminated, and the accuracy of license plate recognition is greatly improved.
Description
The invention relates to the technical field of license plate recognition, in particular to a license plate recognition method and device, electronic equipment and a storage medium.
License plate Recognition is a popular application field in the field of Optical Character Recognition (OCR), and a large number of license plate Recognition solutions for parking lots and toll stations are available on the market. However, in these application scenes, the distance between the license plate and the camera is about 1 meter, and with the addition of a matched lighting system and a special camera, the imaging quality of the photographed license plate image is very high, and naturally, higher license plate recognition accuracy can be achieved.
In some practical application scenarios, the camera is sometimes far away from the vehicle or license plate (for example, more than 3 m), and the camera is a non-proprietary camera, for example, a license plate recognition system applied to a loading/unloading port of a logistics transit is used for recognizing the license plate number of a loading/unloading vehicle. In order to save cost, the license plate recognition system uses a monitoring camera of a loading and unloading port instead of a proprietary camera in the license plate recognition scheme. The monitoring camera of the loading and unloading port is generally installed at a position close to a ceiling, when a vehicle stops in place, the distance between the camera and a license plate is larger than 3 meters, and in the process of stopping and leaving the vehicle, the distance can reach more than 10 meters maximally, so that the pixel area of the license plate in a picture is too small, and the recognition challenge is brought. Secondly, complex lighting conditions of the transition, such as insufficient lighting, backlight, license plate reflection and the like, also pose a challenge to recognition. In addition, vehicles in a transition place are mainly large trucks, only the license plate at the tail of the truck can be seen when the truck loads and unloads the goods, the first row of Chinese characters and letters of the double-layer yellow license plate at the tail of the truck in the picture are too small, so that the recognition is difficult, and particularly, the Chinese characters with more strokes, such as 'gan', 'zang' and 'jaw', are adhered together, so that the recognition is more difficult. Meanwhile, the camera is arranged at a high position, so that the upper half part of the license plate of some vehicle types can be blocked by the rear bumper, and the characters in the first row cannot be recognized.
In addition, the traditional license plate recognition method comprises the steps of license plate detection, image binarization, character segmentation, character recognition and the like, because false detection exists in the license plate detection, a link for judging image quality is generally added before the image binarization, a small classification network is used for eliminating non-license plates and fuzzy license plate images, so that the traditional method comprises so many links, and a large amount of manpower is consumed in each link for data labeling and model training. In addition, the final recognition accuracy is obtained by multiplying the accuracy of each link, and as the number of links is too many and each link cannot reach 100%, the accuracy of license plate recognition has a bottleneck which is difficult to break through.
Therefore, the traditional license plate recognition method has too many recognition links and is easily influenced by environmental conditions, so that the license plate recognition accuracy is low.
The embodiment of the application provides a license plate recognition method and device, electronic equipment and a storage medium, which can effectively eliminate the influence of license plate false detection and license plate motion blur on a license plate recognition result and greatly improve the accuracy of license plate recognition.
In one aspect, the present application provides a license plate recognition method, including:
acquiring a plurality of license plate images of a target vehicle;
respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results;
and fusing the plurality of license plate recognition results to determine the license plate recognition result of the target vehicle.
In some embodiments of the present application, the performing license plate recognition on the plurality of license plate images respectively to obtain a plurality of license plate recognition results includes:
respectively taking license plate images in the license plate images as target license plate images, and extracting the characteristics of the target license plate images to obtain characteristic graphs corresponding to the license plate images;
extracting an attention map of characters in the feature map;
calculating a license plate character recognition result tensor corresponding to the target license plate image according to the attention diagram;
and determining a license plate recognition result of the target license plate image according to the license plate character recognition tensor.
In some embodiments of the present application, the extracting the features of the target license plate image to obtain a feature map corresponding to the license plate image includes:
and inputting the target license plate image into a preset convolutional neural network model, so as to extract the corresponding features of the license plate image by using the convolutional neural network model, and outputting the corresponding feature map of the target license plate image.
In some embodiments of the present application, the calculating a license plate character recognition result tensor according to the attention map includes:
weighting the attention diagram and the feature diagram to obtain a weighted diagram;
and inputting the weighted graph into a preset long-short term memory network model, and outputting a license plate character recognition result tensor corresponding to the target license plate image.
In some embodiments of the present application, the license plate character recognition tensor includes character recognition tensors of a plurality of positions, the character recognition tensor of each position includes a plurality of candidate characters, and determining the license plate recognition result of the target license plate image according to the license plate character recognition tensor includes:
analyzing the license plate character recognition tensor to obtain the confidence coefficient of each candidate character in the character recognition tensor of each position;
determining the candidate character with the highest confidence coefficient at each position according to the confidence coefficient of each candidate character in the character recognition tensor at each position;
and taking the candidate character with the highest confidence coefficient at each position as the character recognition result of the position to obtain the license plate recognition result of the target license plate image.
In some embodiments of the present application, the fusing the license plate recognition results to determine the license plate recognition result of the target vehicle includes:
fusing the plurality of license plate recognition results to obtain fused license plate recognition results;
and searching in a preset license plate database according to the fused license plate recognition result, and determining the license plate recognition result of the target vehicle.
In some embodiments of the present application, the fusing the plurality of license plate recognition results to obtain a fused license plate recognition result includes:
calculating the number of qualified characters of which the character recognition result in each license plate recognition result meets the preset confidence level requirement;
and taking N license plate recognition results with the largest number of qualified characters, and fusing the license plate recognition results to obtain a fused license plate recognition result.
In some embodiments of the present application, the acquiring multiple license plate images of a target vehicle includes:
acquiring a collected monitoring video of the target vehicle;
detecting a license plate in the monitoring video to obtain a plurality of images including the license plate;
and cutting the license plate areas in the multiple images, and normalizing the license plate areas into a preset size to obtain multiple license plate images of the target vehicle.
In some embodiments of the present application, the detecting a license plate in the surveillance video to obtain a plurality of images including the license plate includes:
and detecting the license plate in the monitoring video by adopting a multi-target detection method to obtain a plurality of images comprising the license plate.
In another aspect, the present application provides a license plate recognition apparatus, including:
the acquisition unit is used for acquiring a plurality of license plate images of the target vehicle;
the recognition unit is used for respectively recognizing the license plates of the license plate images to obtain a plurality of license plate recognition results;
and the determining unit is used for fusing the license plate recognition results and determining the license plate recognition result of the target vehicle.
In some embodiments of the present application, the identification unit is specifically configured to:
respectively taking license plate images in the license plate images as target license plate images, and extracting the characteristics of the target license plate images to obtain characteristic graphs corresponding to the license plate images;
extracting an attention diagram of characters in the feature diagram;
calculating a license plate character recognition result tensor corresponding to the target license plate image according to the attention diagram;
and determining a license plate recognition result of the target license plate image according to the license plate character recognition tensor.
In some embodiments of the present application, the identification unit is specifically configured to:
and inputting the target license plate image into a preset convolutional neural network model, so as to extract the corresponding features of the license plate image by using the convolutional neural network model, and outputting the corresponding feature map of the target license plate image.
In some embodiments of the present application, the identification unit is specifically configured to:
weighting the attention diagram and the feature diagram to obtain a weighted diagram;
and inputting the weighted graph into a preset long-short term memory network model, and outputting a license plate character recognition result tensor corresponding to the target license plate image.
In some embodiments of the present application, the license plate character recognition tensor includes a character recognition tensor of a plurality of positions, the character recognition tensor of each position includes a plurality of candidate characters, and the recognition unit is specifically configured to:
analyzing the license plate character recognition tensor to obtain the confidence coefficient of each candidate character in the character recognition tensor of each position;
determining a candidate character with the highest confidence coefficient at each position according to the confidence coefficient of each candidate character in the character recognition tensor at each position;
and taking the candidate character with the highest confidence coefficient at each position as the character recognition result of the position to obtain the license plate recognition result of the target license plate image.
In some embodiments of the present application, the determining unit is specifically configured to:
fusing the plurality of license plate recognition results to obtain fused license plate recognition results;
and searching in a preset license plate database according to the fused license plate recognition result, and determining the license plate recognition result of the target vehicle.
In some embodiments of the present application, the determining unit is specifically configured to:
calculating the number of qualified characters of which the character recognition result in each license plate recognition result meets the preset confidence level requirement;
and taking N license plate recognition results with the largest number of qualified characters, and fusing the license plate recognition results to obtain a fused license plate recognition result.
In some embodiments of the present application, the obtaining unit is specifically configured to:
acquiring a collected monitoring video of the target vehicle;
detecting a license plate in the monitoring video to obtain a plurality of images including the license plate;
and cutting license plate areas in the multiple images, and normalizing the license plate areas into a preset size to obtain multiple license plate images of the target vehicle.
In some embodiments of the present application, the obtaining unit is specifically configured to:
and detecting the license plate in the monitoring video by adopting a multi-target detection method to obtain a plurality of images comprising the license plate.
In another aspect, the present application further provides an electronic device, including:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the license plate recognition method described above.
In another aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is loaded by a processor to execute the steps in the license plate recognition method.
In the application, a plurality of license plate images of a target vehicle are obtained; respectively carrying out license plate recognition on a plurality of license plate images to obtain a plurality of license plate recognition results; and fusing the plurality of license plate recognition results to determine the license plate recognition result of the target vehicle. According to the method and the device, a plurality of license plate recognition results are obtained by recognizing a plurality of license plate images of the target vehicle, the license plate recognition results are fused, the license plate recognition result of the target vehicle is determined, and the finally determined license plate recognition result of the target vehicle is determined by fusing the license plate recognition results, so that the influences of license plate false detection and license plate motion blurring on the license plate recognition result can be effectively eliminated, and the accuracy of license plate recognition is greatly improved.
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a scene schematic diagram of a license plate recognition system according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a license plate recognition method according to an embodiment of the present invention;
FIG. 3 is a flowchart of one embodiment of step 202 in an embodiment of the present invention;
FIG. 4 is a diagram illustrating a specific scenario of a license plate recognition scenario according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of an embodiment of the present invention after overlaying an attention map with license plate artwork;
FIG. 6 is a schematic structural diagram of a license plate recognition device according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an embodiment of an electronic device in an embodiment of the present invention.
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.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes are not set forth in detail in order to avoid obscuring the description of the present invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The embodiment of the invention provides a license plate recognition method, a license plate recognition device, electronic equipment and a storage medium, which are respectively described in detail below.
Referring to fig. 1, fig. 1 is a schematic view of a license plate recognition system according to an embodiment of the present invention, where the license plate recognition system may include a monitoring device 100 and an electronic device 200, the monitoring device 100 is connected to the electronic device 20 through a network, and a license plate recognition apparatus is integrated in the electronic device 200, for example, the electronic device in fig. 1, and the monitoring device 100 may access the electronic device 200.
The electronic equipment 200 in the embodiment of the invention is mainly used for acquiring a plurality of license plate images of a target vehicle; respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results; and fusing the license plate recognition results to determine the license plate recognition result of the target vehicle.
The monitoring device 100 in the embodiment of the present invention is mainly used for shooting monitoring video images and transmitting the monitoring video images to the electronic device 200.
In this embodiment of the present invention, the electronic device 200 may be an independent server, or may be a server network or a server cluster composed of servers, for example, the electronic device 200 described in this embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). In the embodiment of the present invention, the electronic device 200 and the monitoring device 100 may implement communication through any communication manner, including but not limited to mobile communication based on third Generation Partnership project (3 gpp), long Term Evolution (LTE), worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on TCP/IP Protocol Suite (TCP/IP), user Datagram Protocol (UDP) Protocol, and the like.
It will be appreciated that the monitoring device 100 used in embodiments of the present invention may be a device that includes both receiving and transmitting hardware, i.e. a device having receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a monitoring device 100 may comprise: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display. The monitoring device 100 may specifically be a monitoring camera.
It will be understood by those skilled in the art that the application environment shown in fig. 1 is only one application scenario related to the present application, and does not constitute a limitation on the application scenario of the present application, and that other application environments may further include more or less electronic devices than those shown in fig. 1, or a network connection relationship of electronic devices, for example, only 1 electronic device and 2 monitoring devices are shown in fig. 1, and it is understood that the license plate recognition system may further include one or more other electronic devices, or/and one or more other monitoring devices connected to a network of electronic devices, and is not limited herein.
In addition, as shown in fig. 1, the license plate recognition system may further include a memory 300 for storing data, such as video data, for example, a video file collected by a monitoring device.
It should be noted that the scene schematic diagram of the license plate recognition system shown in fig. 1 is only an example, the license plate recognition system and the scene described in the embodiment of the present invention are for more clearly illustrating the technical solution of the embodiment of the present invention, and do not form a limitation on the technical solution provided in the embodiment of the present invention.
First, an embodiment of the present invention provides a license plate recognition method, where an execution subject of the license plate recognition method is a license plate recognition device, and the license plate recognition device is applied to an electronic device, and the license plate recognition method includes: acquiring a plurality of license plate images of a target vehicle; respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results; and fusing the license plate recognition results to determine the license plate recognition result of the target vehicle.
As shown in fig. 2, which is a schematic flow chart of an embodiment of a license plate recognition method according to an embodiment of the present invention, the license plate recognition method includes:
201. and acquiring a plurality of license plate images of the target vehicle.
Specifically, in some embodiments of the present invention, the acquiring multiple license plate images of the target vehicle may include: acquiring a collected monitoring video of the target vehicle; detecting a license plate in the monitoring video to obtain a plurality of images including the license plate; and cutting license plate areas in the multiple images, and normalizing the license plate areas into a preset size to obtain multiple license plate images of the target vehicle. The acquired monitoring video of the target vehicle may be a monitoring video shot by one or more monitoring devices.
Further, the detecting the license plate in the surveillance video to obtain a plurality of images including the license plate includes: and detecting the license plate in the monitoring video by adopting a multi-target detection method to obtain a plurality of images comprising the license plate. Specifically, for the monitoring video collected by the camera, an SSD (Single Shot multi box Detector) multi-target detection network model can be applied to continuously detect the license plate, and the detected license plate image is cut out from the original image and normalized to a uniform size as an image sequence for inputting the subsequent steps.
The SSD algorithm is a multi-target detection algorithm for directly predicting target classes and bounding boxes. The SSD algorithm can also achieve the same effect by synthesizing feature maps (feature maps) of different convolutional layers, and the main network structure of the SSD algorithm is VGG16.
Due to the loading and unloading port of the logistics transfer station, the license plate number of the loading and unloading vehicle can be identified. In order to save cost, a monitoring camera of a loading and unloading port is generally used in the transfer station, and a proprietary camera is not used. The monitoring camera of the loading and unloading port is generally installed at a position close to a ceiling, when a vehicle stops in place, the distance between the camera and a license plate is larger than 3 meters, and in the process of stopping and leaving the vehicle, the distance can reach more than 10 meters at most, so that the pixel area of the license plate in a picture is too small, and the recognition challenge is brought. Complex lighting conditions in transit, such as insufficient lighting, backlighting, license plate reflections, etc., also present challenges for identification. In addition, vehicles in a transit station are mainly large trucks, only the license plates at the tail of the trucks can be seen when the trucks are loaded or unloaded, the first row of Chinese characters and letters of the double-layer yellow license plates at the tail of the trucks in the picture are too small, so that the recognition is difficult, and particularly, the Chinese characters with more strokes, such as 'Gang', 'Tibetan' and 'Hubei' are stuck together, so that the recognition is more difficult. Meanwhile, the camera is arranged at a high position, so that the upper half part of the license plate of some vehicle types can be blocked by the rear bumper, and the characters in the first row cannot be recognized.
Therefore, in the embodiment of the invention, the main application scene may be a license plate number recognition scene of a loading and unloading vehicle at the loading and unloading port, the target vehicle is the loading and unloading vehicle at the loading and unloading port, the monitoring device is a monitoring device arranged at a transfer loading and unloading port, and certainly, other application scenes are not limited, such as scenes with high requirements for recognizing other license plates.
202. And respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results.
In the embodiment of the present invention, after the plurality of license plate images of the target vehicle are obtained in step 201, license plate recognition may be performed on the plurality of license plate images, respectively, to obtain a plurality of license plate recognition results. Specifically, license plate recognition is performed on each license plate image, and a license plate recognition result is obtained.
As shown in fig. 3, the performing license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results may further include:
301. and respectively taking license plate images in the license plate images as target license plate images, and extracting the characteristics of the target license plate images to obtain characteristic images corresponding to the license plate images.
Specifically, extracting the features of the target license plate image to obtain a feature map corresponding to the license plate image includes: inputting the target license plate image into a preset Convolutional Neural Network (CNN) model, extracting features corresponding to the license plate image by using the Convolutional Neural network model, and outputting a feature map corresponding to the target license plate image. The preset CNN model can be obtained after training by using a large amount of acquired license plate image data.
For example, a preset CNN model is used to extract image features, and a target license plate image is input into the preset CNN model, so that a feature map f = { f } corresponding to the target license plate image can be obtained i,j,c Where f = { f = } i,j,c And j represents the position coordinates of the feature map, and c represents the channel of the feature map.
302. And extracting the attention diagram of the characters in the feature diagram.
The attention map, namely the visual attention mask of the characters in the feature map, specifically, the attention map for extracting the characters in the feature map may adopt the following formula (1), formula (2) and formula (3):
α t ＝{α t,i,j } (1)
α t ＝soft max i,j (α t ) (3)
wherein, V α Is a predetermined vector, w s ，w f1 ，w f2 ，w f3 Updating the parameters of the weight matrix of the CNN model obtained in advance before the calculation in the training process of the CNN model s t Is the hidden state of a preset Long Short-Term Memory network (LSTM) model at the time t, e i ，e j Is a column vector obtained by performing one-hot (one-hot) encoding on the spatial coordinates i, j of the features, for example: i =1,2,3,4; j =1,2,3,4, then when i =3, j =4,
normalization by the softmax function yields an attention map (also called attention mask) alpha t ,α t Is an attention map calculated at time t, which is a matrix, alpha t,i,j Is a matrix alpha t Is a scalar quantity, i, j are the row number and column number of the matrix, respectively.
The Long Short-Term Memory network (LSTM) is a time-recurrent neural network, and is specially designed for solving the Long-Term dependence problem of the common RNN (recurrent neural network), and all RNNs have a chain form of repeated neural network modules. In standard RNNs, this repeated structure block has only one very simple structure, e.g. one tanh layer.
303. And calculating a license plate character recognition result tensor corresponding to the target license plate image according to the attention map.
In an embodiment of the present invention, the calculating a license plate character recognition result tensor according to the attention map includes: weighting the attention diagram and the feature diagram to obtain a weighted diagram; and inputting the weighted graph into a preset long-short term memory network model, and outputting a license plate character recognition result tensor corresponding to the target license plate image.
Wherein, in steps 302 and 303, the LSTM is the same, and at time t, there are three LSTM inputs: the input value of the network at the current time t, the output value of the LSTM at the previous time and the unit state at the previous time; the output of the LSTM is two: the LSTM output value at the current time t, and the cell state at the current time t. Of course these input and output values are vectors.
Input of LSTM at time t
Obtained from the following formula (4) and formula (5);
u t,c ＝∑ i,j α t,i,j f i,j,c (4)
wherein, c t-1 A one-hot coded vector u of the previous character sequence number in the target license plate image t,c Is the feature vector of the weighted graph obtained after weighted summation of the attention map and the feature graph,
for the input vector of LSTM at time t, w c 、w u1 In order to obtain the parameters of the weight matrix of the LSTM model in advance, the LSTM model is updated during training.
The state update and output of the LSTM is derived from equation (6) as follows:
wherein s is t Is the hidden state of LSTM at time t, is a column vector, o t Is the output vector of LSTM at time t, and the tensor of the character recognition result at time t is obtained by the following formula (7):
wherein the content of the first and second substances,
is the character recognition result vector at time t, u t Calculated for equation (4) to obtain t Obtained from the formula (6), w o 、w u2 Is the parameter of the weight matrix of the LSTM model acquired in advance.
304. And determining a license plate recognition result of the target license plate image according to the license plate character recognition tensor.
The determining of the license plate recognition result of the target license plate image according to the license plate character recognition tensor comprises:
(1) And analyzing the license plate character recognition tensor to obtain the confidence coefficient of each candidate character in the character recognition tensor of each position.
(2) And determining the candidate character with the highest confidence coefficient at each position according to the confidence coefficient of each candidate character in the character recognition tensor at each position.
(3) And taking the candidate character with the highest confidence coefficient at each position as the character recognition result at the position to obtain the license plate recognition result of the target license plate image.
203. And fusing the plurality of license plate recognition results to determine the license plate recognition result of the target vehicle.
The fusing the license plate recognition results to determine the license plate recognition result of the target vehicle may include:
(1) And fusing the license plate recognition results to obtain a fused license plate recognition result.
The fusing the plurality of license plate recognition results to obtain a fused license plate recognition result may further include: calculating the number of qualified characters of which the character recognition result in each license plate recognition result meets the preset confidence level requirement; and taking N license plate recognition results with the largest number of qualified characters, and fusing the license plate recognition results to obtain a fused license plate recognition result.
In the experiment, the inventor also finds the rule as follows: a) Clearly and correctly identifying characters, wherein in the confidence level Top5 candidate characters, the confidence level of Top1 characters is far higher than that of other candidate characters, for example, the confidence level of Top1 is higher than 0.9, and the sum of the confidence levels of the rest candidate characters is 0.1; b) When the character is fuzzy, the confidence of the Top5 candidate character is not opened, for example, the confidence of Top1 is 0.6, and the confidence of Top2 is 0.3.
Therefore, in the embodiment of the invention, a confidence threshold value can be set, the number of qualified characters meeting the confidence threshold value in the license plate recognition result can be calculated, and the number of qualified characters in the license plate recognition result is used as an index for license plate quality judgment. For example, the confidence threshold is 0.9, and a license plate recognition result includes 6 characters, which are sequentially distributed as 0.95,0.98,0.97,0.95,0.89, and 0.94, where the number of characters satisfying the confidence threshold is 5, that is, the number of qualified characters is 5.
In the embodiment of the invention, N license plate recognition results with the largest number of qualified characters are taken to fuse the license plate recognition results, and the fused license plate recognition results can be obtained by the following specific method:
because each license plate recognition result contains the position information of each character, based on the position information, the character alignment is carried out, then the characters of each position are voted and sequenced, and the optimal character of the position is obtained, and the method comprises the following specific steps:
1. for the position information of each character in the license plate recognition result, the vertex abscissa x and the character width can be obtained according to the following formula, and the abscissa of the center point of the character is calculated:
2. taking one of the N license plate recognition results as a reference license plate recognition result, sequentially comparing each character in the remaining N-1 license plate recognition results with the reference license plate recognition result from left to right, specifically, setting a threshold, and if the minimum value of the horizontal coordinate distances between the center point of one character and the center points of all characters of the reference license plate recognition result is smaller than the threshold, attributing the character to the corresponding reference character;
3. when all characters in the N-1 license plate recognition results are classified to the corresponding characters of the reference recognition result, character voting of each position is carried out from left to right in sequence according to the character position of the reference license plate recognition result, and it is assumed that m (C) candidate characters at a certain position exist 1 ，C 1 ...C m ) For character C i (i =1,2.. M), assuming that the number of occurrences is l, the character C i The score of (a) is:
wherein the content of the first and second substances,
is a character C i Score of (2), confidence l Is a character C i Confidence of the l-th occurrence.
4. And then, obtaining the candidate character with the highest score as the optimal character of the position, and arranging the optimal characters of all the positions according to the sequence from left to right to obtain a fused license plate recognition result.
(2) And searching in a preset license plate database according to the fused license plate recognition result, and determining the license plate recognition result of the target vehicle.
In the step (1), the plurality of license plate recognition results are fused to obtain a fused license plate recognition result, and the fused license plate recognition result may be complete license plate information or may only include a part of license plate information. For example, taking a license plate recognition scene at a transfer loading/unloading port as an example, the license plate recognition result after fusion can be matched in a vehicle database of a logistics transfer to obtain a complete license plate number.
In the embodiment of the invention, a plurality of license plate images of a target vehicle are obtained; respectively carrying out license plate recognition on a plurality of license plate images to obtain a plurality of license plate recognition results; and fusing the license plate recognition results to determine the license plate recognition result of the target vehicle. According to the embodiment of the invention, a plurality of license plate recognition results are obtained by recognizing a plurality of license plate images of the target vehicle, the plurality of license plate recognition results are fused to determine the license plate recognition result of the target vehicle, and the finally determined license plate recognition result of the target vehicle is determined by fusing the plurality of license plate recognition results, so that the influences of license plate false detection and license plate motion blur on the license plate recognition result can be effectively eliminated, and the accuracy of license plate recognition is greatly improved.
The license plate recognition scheme in the embodiment of the invention is described in combination with a specific application scenario as follows:
the traditional license plate recognition method comprises the steps of license plate detection, image binarization, character segmentation, character recognition and the like, because false detection exists in the license plate detection, a link for judging the image quality is generally added before the image binarization, a small classification network is used in the link for eliminating non-license plates and fuzzy license plate images, and the traditional method comprises so many links, so that a large amount of manpower is consumed in each link for data labeling and model training. In addition, the final identification accuracy is obtained by multiplying the accuracy of each link, and because the number of links is too many and each link cannot reach 100%, the identification accuracy has a bottleneck which is difficult to break through.
Therefore, as shown in fig. 4, in the embodiment of the present invention, image quality discrimination, image binarization, character segmentation and character recognition in the existing license plate recognition process are integrated into one deep neural network (Attention-OCR), in the Attention-OCR model training process, only the license plate number needs to be labeled, and the position of each character does not need to be labeled, so that the labeling workload is simplified, and by using the advantage of large data (collecting a large amount of data of the license plate image and the license plate number), the Attention-OCR network is sufficiently trained by using a large amount of license plate images, so that a very high accuracy can be achieved.
The Attention-OCR network structure is shown in FIG. 1 and comprises the following parts: the method comprises the steps of inputting an image sequence in the CNN, outputting a feature map corresponding to the image sequence, extracting an attention map from each feature map, inputting the attention map into the LSTM, namely a character recognition result tensor at t moment, analyzing the character recognition result tensor at t moment to obtain the confidence coefficient of each candidate character, and taking the character with the highest confidence coefficient as the character recognition result at the position. After the attention map is visualized, the map is overlaid with the original license plate image, as shown in fig. 5, wherein the small square is the attention map.
And calculating the number of qualified characters meeting the confidence threshold in the license plate recognition result, taking the number of qualified characters in the license plate recognition result as an index for judging the quality of the license plate, and fusing the license plate recognition results by taking 5 license plate recognition results with the largest number of qualified characters. And searching in a preset license plate database according to the fused license plate recognition result, and determining the license plate recognition result of the target vehicle.
In order to better implement the license plate recognition method in the embodiment of the present invention, based on the license plate recognition method, a license plate recognition apparatus is further provided in the embodiment of the present invention, as shown in fig. 6, the license plate recognition apparatus 600 includes:
an acquiring unit 601, configured to acquire multiple license plate images of a target vehicle;
the recognition unit 602 is configured to perform license plate recognition on the multiple license plate images respectively to obtain multiple license plate recognition results;
a determining unit 603, configured to fuse the multiple license plate recognition results, and determine a license plate recognition result of the target vehicle.
In some embodiments of the present application, the identifying unit 602 is specifically configured to:
respectively taking license plate images in the license plate images as target license plate images, and extracting the characteristics of the target license plate images to obtain characteristic graphs corresponding to the license plate images;
extracting an attention map of characters in the feature map;
calculating a license plate character recognition result tensor corresponding to the target license plate image according to the attention map;
and determining a license plate recognition result of the target license plate image according to the license plate character recognition tensor.
In some embodiments of the present application, the identifying unit 602 is specifically configured to:
and inputting the target license plate image into a preset convolution neural network model, extracting the features corresponding to the license plate image by using the convolution neural network model, and outputting a feature map corresponding to the target license plate image.
In some embodiments of the present application, the identifying unit 602 is specifically configured to:
weighting the attention diagram and the feature diagram to obtain a weighted diagram;
and inputting the weighted graph into a preset long-short term memory network model, and outputting a license plate character recognition result tensor corresponding to the target license plate image.
In some embodiments of the present application, the license plate character recognition tensor includes character recognition tensors at multiple positions, where the character recognition tensor at each position includes multiple candidate characters, and the recognition unit 602 is specifically configured to:
analyzing the license plate character recognition tensor to obtain the confidence coefficient of each candidate character in the character recognition tensor of each position;
determining the candidate character with the highest confidence coefficient at each position according to the confidence coefficient of each candidate character in the character recognition tensor at each position;
and taking the candidate character with the highest confidence coefficient at each position as the character recognition result of the position to obtain the license plate recognition result of the target license plate image.
In some embodiments of the present application, the determining unit 603 is specifically configured to:
fusing the plurality of license plate recognition results to obtain fused license plate recognition results;
and searching in a preset license plate database according to the fused license plate recognition result, and determining the license plate recognition result of the target vehicle.
In some embodiments of the present application, the determining unit 603 is specifically configured to:
calculating the number of qualified characters of which the character recognition result in each license plate recognition result meets the preset confidence level requirement;
and taking N license plate recognition results with the largest number of qualified characters, and fusing the license plate recognition results to obtain a fused license plate recognition result.
In some embodiments of the present application, the obtaining unit 601 is specifically configured to:
acquiring a collected monitoring video of the target vehicle;
detecting a license plate in the monitoring video to obtain a plurality of images including the license plate;
and cutting license plate areas in the multiple images, and normalizing the license plate areas into a preset size to obtain multiple license plate images of the target vehicle.
In some embodiments of the present application, the obtaining unit 601 is specifically configured to:
and detecting the license plate in the monitoring video by adopting a multi-target detection method to obtain a plurality of images comprising the license plate.
In the embodiment of the invention, a plurality of license plate images of a target vehicle are acquired through an acquisition unit 601; the recognition unit 602 performs license plate recognition on the plurality of license plate images respectively to obtain a plurality of license plate recognition results; the determining unit 603 fuses the plurality of license plate recognition results to determine a license plate recognition result of the target vehicle. According to the embodiment of the invention, a plurality of license plate recognition results are obtained by recognizing a plurality of license plate images of the target vehicle, the plurality of license plate recognition results are fused to determine the license plate recognition result of the target vehicle, and the finally determined license plate recognition result of the target vehicle is determined by fusing the plurality of license plate recognition results, so that the influences of license plate false detection and license plate motion blur on the license plate recognition result can be effectively eliminated, and the accuracy of license plate recognition is greatly improved.
An embodiment of the present invention further provides an electronic device, which integrates any one of the license plate recognition devices provided in the embodiments of the present invention, where the electronic device includes:
one or more processors;
a memory;
and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor for performing the steps of the license plate recognition method in any one of the above embodiments of the license plate recognition method.
The embodiment of the invention also provides electronic equipment which integrates any license plate recognition method provided by the embodiment of the invention. As shown in fig. 7, it shows a schematic structural diagram of an electronic device according to an embodiment of the present invention, specifically:
the electronic device may include components such as a processor 701 of one or more processing cores, memory 702 of one or more computer-readable storage media, a power supply 703, and an input unit 704. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 7 does not constitute a limitation of the electronic device and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components. Wherein:
the processor 701 is a control center of the electronic device, connects various parts of the whole electronic device by using various interfaces and lines, and performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 702 and calling data stored in the memory 702, thereby performing overall monitoring of the electronic device. Optionally, processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 701.
The memory 702 may be used to store software programs and modules, and the processor 701 executes various functional applications and data processing by operating the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs (such as a sound playing function, an image playing function, etc.) required by at least one function, and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 702 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. Accordingly, the memory 702 may also include a memory controller to provide the processor 701 with access to the memory 702.
The electronic device further includes a power source 703 for supplying power to each component, and preferably, the power source 703 may be logically connected to the processor 701 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The power supply 703 may also include any component including one or more of a dc or ac power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The electronic device may also include an input unit 704, and the input unit 704 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the electronic device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 701 in the electronic device loads the executable file corresponding to the process of one or more application programs into the memory 702 according to the following instructions, and the processor 701 runs the application program stored in the memory 702, so as to implement various functions as follows:
acquiring a plurality of license plate images of a target vehicle;
respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results;
and fusing the plurality of license plate recognition results to determine the license plate recognition result of the target vehicle.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present invention provides a computer-readable storage medium, which may include: read Only Memory (ROM), random Access Memory (RAM), magnetic or optical disks, and the like. The license plate recognition method comprises a step of identifying a license plate, a step of identifying the license plate, and a step of executing the steps of the license plate recognition method. For example, the computer program may be loaded by a processor to perform the steps of:
acquiring a plurality of license plate images of a target vehicle;
respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results;
and fusing the license plate recognition results to determine the license plate recognition result of the target vehicle.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed descriptions of other embodiments, which are not described herein again.
In a specific implementation, each unit or structure may be implemented as an independent entity, or may be combined arbitrarily to be implemented as one or several entities, and the specific implementation of each unit or structure may refer to the foregoing method embodiment, which is not described herein again.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
The license plate recognition method, the license plate recognition device, the electronic device and the storage medium provided by the embodiment of the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (20)
- A license plate recognition method comprises the following steps:acquiring a plurality of license plate images of a target vehicle;respectively carrying out license plate recognition on the plurality of license plate images to obtain a plurality of license plate recognition results;and fusing the plurality of license plate recognition results to determine the license plate recognition result of the target vehicle.
- The license plate recognition method of claim 1, wherein the performing license plate recognition on the plurality of license plate images respectively to obtain a plurality of license plate recognition results comprises:respectively taking license plate images in the license plate images as target license plate images, and extracting the characteristics of the target license plate images to obtain characteristic graphs corresponding to the license plate images;extracting an attention diagram of characters in the feature diagram;calculating a license plate character recognition result tensor corresponding to the target license plate image according to the attention diagram;and determining a license plate recognition result of the target license plate image according to the license plate character recognition tensor.
- The license plate recognition method of claim 2, wherein the extracting the target license plate image features to obtain a feature map corresponding to the license plate image comprises:and inputting the target license plate image into a preset convolutional neural network model, so as to extract the corresponding features of the license plate image by using the convolutional neural network model, and outputting the corresponding feature map of the target license plate image.
- The license plate recognition method of claim 2, wherein the calculating a license plate character recognition result tensor according to the attention map comprises:weighting the attention diagram and the feature diagram to obtain a weighted diagram;and inputting the weighted graph into a preset long-short term memory network model, and outputting a license plate character recognition result tensor corresponding to the target license plate image.
- The license plate recognition method of claim 2, wherein the license plate character recognition tensor comprises character recognition tensors of a plurality of positions, the character recognition tensor of each position comprises a plurality of candidate characters, and the determining the license plate recognition result of the target license plate image according to the license plate character recognition tensor comprises:analyzing the license plate character recognition tensor to obtain the confidence coefficient of each candidate character in the character recognition tensor of each position;determining the candidate character with the highest confidence coefficient at each position according to the confidence coefficient of each candidate character in the character recognition tensor at each position;and taking the candidate character with the highest confidence coefficient at each position as the character recognition result at the position to obtain the license plate recognition result of the target license plate image.
- The license plate recognition method of claim 1, wherein the fusing the plurality of license plate recognition results to determine the license plate recognition result of the target vehicle comprises:fusing the plurality of license plate recognition results to obtain fused license plate recognition results;and searching in a preset license plate database according to the fused license plate recognition result, and determining the license plate recognition result of the target vehicle.
- The license plate recognition method of claim 6, wherein the fusing the plurality of license plate recognition results to obtain a fused license plate recognition result comprises:calculating the number of qualified characters of which the character recognition result in each license plate recognition result meets the preset confidence level requirement;and taking N license plate recognition results with the largest number of qualified characters, and fusing the license plate recognition results to obtain a fused license plate recognition result.
- The license plate recognition method of any one of claims 1 to 7, wherein the obtaining a plurality of license plate images of the target vehicle comprises:acquiring a collected monitoring video of the target vehicle;detecting a license plate in the monitoring video to obtain a plurality of images including the license plate;and cutting the license plate areas in the multiple images, and normalizing the license plate areas into a preset size to obtain multiple license plate images of the target vehicle.
- The license plate recognition method of claim 8, wherein the detecting the license plate in the surveillance video to obtain a plurality of images including the license plate comprises:and detecting the license plate in the monitoring video by adopting a multi-target detection method to obtain a plurality of images comprising the license plate.
- A license plate recognition device, wherein the license plate recognition device comprises:the acquisition unit is used for acquiring a plurality of license plate images of the target vehicle;the recognition unit is used for respectively recognizing the license plates of the license plate images to obtain a plurality of license plate recognition results;and the determining unit is used for fusing the license plate recognition results and determining the license plate recognition result of the target vehicle.
- The license plate recognition device of claim 10, wherein the recognition unit is specifically configured to:respectively taking license plate images in the license plate images as target license plate images, and extracting the characteristics of the target license plate images to obtain characteristic graphs corresponding to the license plate images;extracting an attention map of characters in the feature map;calculating a license plate character recognition result tensor corresponding to the target license plate image according to the attention map;and determining a license plate recognition result of the target license plate image according to the license plate character recognition tensor.
- The license plate recognition device of claim 11, wherein the recognition unit is specifically configured to:and inputting the target license plate image into a preset convolutional neural network model, so as to extract the corresponding features of the license plate image by using the convolutional neural network model, and outputting the corresponding feature map of the target license plate image.
- The license plate recognition device of claim 11, wherein the recognition unit is specifically configured to:weighting the attention diagram and the feature diagram to obtain a weighted diagram;and inputting the weighted graph into a preset long-short term memory network model, and outputting a license plate character recognition result tensor corresponding to the target license plate image.
- The license plate recognition device of claim 11, wherein the license plate character recognition tensor comprises a plurality of positions of character recognition tensor, each position of character recognition tensor comprises a plurality of candidate characters, and the recognition unit is specifically configured to:analyzing the license plate character recognition tensor to obtain the confidence coefficient of each candidate character in the character recognition tensor of each position;determining a candidate character with the highest confidence coefficient at each position according to the confidence coefficient of each candidate character in the character recognition tensor at each position;and taking the candidate character with the highest confidence coefficient at each position as the character recognition result of the position to obtain the license plate recognition result of the target license plate image.
- The license plate recognition device of claim 10, wherein the determination unit is specifically configured to:fusing the plurality of license plate recognition results to obtain fused license plate recognition results;and searching in a preset license plate database according to the fused license plate recognition result, and determining the license plate recognition result of the target vehicle.
- The license plate recognition device of claim 15, wherein the determination unit is specifically configured to:calculating the number of qualified characters of which the character recognition results in each license plate recognition result meet the preset confidence level requirement;and taking N license plate recognition results with the largest number of qualified characters, and fusing the license plate recognition results to obtain a fused license plate recognition result.
- The license plate recognition device of any one of claims 10 to 16, wherein the obtaining unit is specifically configured to:acquiring a collected monitoring video of the target vehicle;detecting a license plate in the monitoring video to obtain a plurality of images including the license plate;and cutting license plate areas in the multiple images, and normalizing the license plate areas into a preset size to obtain multiple license plate images of the target vehicle.
- The license plate recognition device of claim 17, wherein the obtaining unit is specifically configured to:and detecting the license plate in the monitoring video by adopting a multi-target detection method to obtain a plurality of images comprising the license plate.
- An electronic device, wherein the electronic device comprises:one or more processors;a memory; andone or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the license plate recognition method of any of claims 1-9.
- A computer-readable storage medium, in which a computer program is stored which is loaded by a processor for performing the steps of the license plate recognition method of any one of claims 1 to 9.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/071330 WO2021138893A1 (en) | 2020-01-10 | 2020-01-10 | Vehicle license plate recognition method and apparatus, electronic device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115298705A true CN115298705A (en) | 2022-11-04 |
Family
ID=76787653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080095192.2A Pending CN115298705A (en) | 2020-01-10 | 2020-01-10 | License plate recognition method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115298705A (en) |
| WO (1) | WO2021138893A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116012833A (en) * | 2023-02-03 | 2023-04-25 | 脉冲视觉(北京)科技有限公司 | License plate detection method, device, equipment, medium and program product |
| CN116977949A (en) * | 2023-08-24 | 2023-10-31 | 北京唯行科技有限公司 | Vehicle parking inspection method, device and equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303153A (en) * | 2014-07-23 | 2016-02-03 | 中兴通讯股份有限公司 | Vehicle license plate identification method and apparatus |
| US10719743B2 (en) * | 2018-01-19 | 2020-07-21 | Arcus Holding A/S | License plate reader using optical character recognition on plural detected regions |
| CN108564088A (en) * | 2018-04-17 | 2018-09-21 | 广东工业大学 | Licence plate recognition method, device, equipment and readable storage medium storing program for executing |
| CN108830192A (en) * | 2018-05-31 | 2018-11-16 | 珠海亿智电子科技有限公司 | Vehicle and detection method of license plate under vehicle environment based on deep learning |
| CN108960189B (en) * | 2018-07-20 | 2020-11-24 | 南京旷云科技有限公司 | Image re-identification method and device and electronic equipment |
| CN110135427B (en) * | 2019-04-11 | 2021-07-27 | 北京百度网讯科技有限公司 | Method, apparatus, device and medium for recognizing characters in image |
-
2020
- 2020-01-10 WO PCT/CN2020/071330 patent/WO2021138893A1/en active Application Filing
- 2020-01-10 CN CN202080095192.2A patent/CN115298705A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116012833A (en) * | 2023-02-03 | 2023-04-25 | 脉冲视觉(北京)科技有限公司 | License plate detection method, device, equipment, medium and program product |
| CN116012833B (en) * | 2023-02-03 | 2023-10-10 | 脉冲视觉(北京)科技有限公司 | License plate detection method, device, equipment, medium and program product |
| CN116977949A (en) * | 2023-08-24 | 2023-10-31 | 北京唯行科技有限公司 | Vehicle parking inspection method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021138893A1 (en) | 2021-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110020592B (en) | Object detection model training method, device, computer equipment and storage medium | |
| CN109087510B (en) | Traffic monitoring method and device | |
| CN109035304B (en) | Target tracking method, medium, computing device and apparatus | |
| US9767570B2 (en) | Systems and methods for computer vision background estimation using foreground-aware statistical models | |
| EP3471021A1 (en) | Method for determining target intelligently followed by unmanned aerial vehicle, unmanned aerial vehicle and remote controller | |
| US20190057244A1 (en) | Method for determining target through intelligent following of unmanned aerial vehicle, unmanned aerial vehicle and remote control | |
| Ahmad et al. | Overhead view person detection using YOLO | |
| CN115797736B (en) | Training method, device, equipment and medium for target detection model and target detection method, device, equipment and medium | |
| CN115546705B (en) | Target identification method, terminal device and storage medium | |
| CN111523558A (en) | Ship shielding detection method and device based on electronic purse net and electronic equipment | |
| CN115298705A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN115063454A (en) | Multi-target tracking matching method, device, terminal and storage medium | |
| CN111767915A (en) | License plate detection method, device, equipment and storage medium | |
| CN108229494B (en) | Network training method, processing method, device, storage medium and electronic equipment | |
| CN113822144A (en) | Target detection method and device, computer equipment and storage medium | |
| CN113112479A (en) | Progressive target detection method and device based on key block extraction | |
| KR101268596B1 (en) | Foreground extraction apparatus and method using CCB and MT LBP | |
| CN111814653A (en) | Method, device, equipment and storage medium for detecting abnormal behaviors in video | |
| CN110569921A (en) | Vehicle logo identification method, system, device and computer readable medium | |
| CN110619304A (en) | Vehicle type recognition method, system, device and computer readable medium | |
| CN114429631B (en) | Three-dimensional object detection method, device, equipment and storage medium | |
| EP4332910A1 (en) | Behavior detection method, electronic device, and computer readable storage medium | |
| CN111723614A (en) | Traffic signal lamp identification method and device | |
| CN111765892B (en) | Positioning method, positioning device, electronic equipment and computer readable storage medium | |
| CN114255377A (en) | Differential commodity detection and classification method for intelligent container |
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 |