CN115719465A - Vehicle detection method, apparatus, device, storage medium, and program product - Google Patents
Vehicle detection method, apparatus, device, storage medium, and program product Download PDFInfo
- Publication number
- CN115719465A CN115719465A CN202211497780.6A CN202211497780A CN115719465A CN 115719465 A CN115719465 A CN 115719465A CN 202211497780 A CN202211497780 A CN 202211497780A CN 115719465 A CN115719465 A CN 115719465A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- detection
- model
- determining
- area
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 334
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 95
- 238000000034 method Methods 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 238000013526 transfer learning Methods 0.000 claims 2
- 239000000126 substance Substances 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 230000005012 migration Effects 0.000 description 3
- 238000013508 migration Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012015 optical character recognition Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The present disclosure provides a vehicle detection method, apparatus, device, storage medium, and program product, which relate to the technical field of data processing, and in particular, to the technical field of big data, artificial intelligence, and intelligent transportation. The specific implementation scheme is as follows: determining a vehicle area according to the input image data, wherein the vehicle area represents an area where the vehicle is located and displayed by the image data; and determining vehicle detection data according to the vehicle region, wherein the vehicle detection data comprises at least one of: the vehicle detection method comprises the following steps of vehicle attributes, vehicle license plate numbers, violation detection results, vehicle running tracks and vehicle flow detection results, wherein the vehicle attributes represent physical characteristics of vehicles.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, particularly to the field of big data, artificial intelligence, and intelligent transportation technologies, and in particular, to a vehicle detection method, apparatus, device, storage medium, and program product.
Background
Vehicles, as a general vehicle, have various demands such as daily management. With the development of computer technology and internet technology, the related technology can assist vehicle detection and the like.
Disclosure of Invention
The present disclosure provides a vehicle detection method, apparatus, device, storage medium, and program product.
According to an aspect of the present disclosure, there is provided a vehicle detection method including: determining a vehicle area according to the input image data, wherein the vehicle area represents an area where the vehicle is located and displayed by the image data; and determining vehicle detection data according to the vehicle region, wherein the vehicle detection data comprises at least one of: the vehicle detection method comprises the following steps of vehicle attributes, vehicle license plate numbers, violation detection results, vehicle running tracks and vehicle flow detection results, wherein the vehicle attributes represent physical characteristics of vehicles.
According to another aspect of the present disclosure, there is provided a vehicle detection apparatus including: the device comprises a vehicle area determining module and a vehicle detection data determining module. And the vehicle area determining module is used for determining a vehicle area according to the input image data, wherein the vehicle area represents an area where the vehicle is located and displayed by the image data. A vehicle detection data determination module for determining vehicle detection data based on the vehicle region, wherein the vehicle detection data comprises at least one of: the vehicle detection method comprises the following steps of vehicle attributes, vehicle license plate numbers, violation detection results, vehicle running tracks and vehicle flow detection results, wherein the vehicle attributes represent physical characteristics of vehicles.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor and a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods of the embodiments of the disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program, the computer program being stored on at least one of a readable storage medium and an electronic device, the computer program being stored on at least one of the readable storage medium and the electronic device, the computer program, when executed by a processor, implementing the method of an embodiment of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 schematically illustrates a system architecture diagram of a vehicle detection method and apparatus according to an embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow chart of a vehicle detection method according to an embodiment of the disclosure;
FIG. 3 schematically illustrates a schematic diagram of a vehicle detection method according to another embodiment of the present disclosure;
fig. 4 schematically shows a schematic diagram of obtaining a vehicle license plate number according to a vehicle detection method according to still another embodiment of the present disclosure;
fig. 5 schematically shows a specific example of displaying a vehicle attribute of a vehicle license number license and a vehicle color in the time-series video frame Img;
FIG. 6 schematically illustrates a block diagram of a vehicle detection device according to an embodiment of the present disclosure; and
fig. 7 schematically shows a block diagram of an electronic device that can implement the vehicle detection method of the embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.).
Fig. 1 schematically shows a system architecture of a vehicle detection method and apparatus according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.
As shown in fig. 1, a system architecture 100 according to this embodiment may include clients 101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between clients 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
A user may use clients 101, 102, 103 to interact with server 105 over network 104 to receive or send messages, etc. Various messaging client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (examples only) may be installed on the clients 101, 102, 103.
The server 105 may be a server that provides various services, such as a back-office management server (for example only) that provides support for websites browsed by users using the clients 101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the client. In addition, the server 105 may also be a cloud server, i.e., the server 105 has a cloud computing function.
It should be noted that the vehicle detection method provided by the embodiment of the present disclosure may be executed by the server 105. Accordingly, the vehicle detection apparatus provided by the embodiment of the present disclosure may be disposed in the server 105. The vehicle detection method provided by the embodiments of the present disclosure may also be performed by a server or server cluster that is different from the server 105 and is capable of communicating with the clients 101, 102, 103 and/or the server 105. Accordingly, the vehicle detection device provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the clients 101, 102, 103 and/or the server 105.
In one example, the server 105 may acquire image data input from the clients 101, 102, 103 through the network 104, perform vehicle detection on the image data, and determine a vehicle detection result.
It should be understood that the number of clients, networks, and servers in FIG. 1 is merely illustrative. There may be any number of clients, networks, and servers, as desired for an implementation.
It should be noted that in the technical solution of the present disclosure, the processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user are all in compliance with the regulations of the relevant laws and regulations, and do not violate the customs of the public order.
In the technical scheme of the disclosure, before the personal information of the user is obtained or collected, the authorization or the consent of the user is obtained.
The embodiment of the present disclosure provides a vehicle detection method, and a vehicle detection method according to an exemplary embodiment of the present disclosure is described below with reference to fig. 2 to 5 in conjunction with the system architecture of fig. 1. The vehicle detection method of the embodiment of the present disclosure may be performed by the server 105 shown in fig. 1, for example.
FIG. 2 schematically shows a flow chart of a vehicle detection method according to an embodiment of the disclosure.
As shown in fig. 2, the vehicle detection method 200 of the embodiment of the present disclosure may include, for example, operations S210 to S220.
In operation S210, a vehicle region is determined according to the input image data.
Illustratively, the input image data may be received from the terminals 101, 102, 103, for example. The image data may be captured by an image capturing device such as a camera for a road, for example.
The vehicle region represents a region where the vehicle is located where the image data is displayed.
For example, the vehicle region can be marked with a detection frame.
In operation S220, vehicle detection data is determined according to the vehicle region.
The vehicle detection data includes at least one of: the vehicle attribute, the vehicle license number, the violation detection result, the vehicle running track and the traffic flow detection result.
The vehicle attributes characterize physical characteristics of the vehicle.
Illustratively, the vehicle attributes may include, for example, a color of the vehicle, a model of the vehicle, and the like.
According to the vehicle detection method disclosed by the embodiment of the disclosure, the vehicle area is determined according to the input image data, so that the area, in which the vehicle is displayed, in the image data can be positioned from the input image data, and the vehicle detection data can be accurately determined based on the vehicle area.
According to the vehicle detection method of the embodiment of the present disclosure, the passing vehicle detection data includes at least one of: the vehicle attribute, the vehicle license number, the violation detection result, the vehicle running track and the traffic flow detection result can realize multifunctional and comprehensive vehicle detection. For example, at least one of the vehicle attribute, the vehicle license number, the violation detection result, the vehicle running track and the traffic flow detection result can basically cover the vehicle detection requirements under various scenes, and the vehicle detection efficiency is higher.
FIG. 3 schematically shows a schematic diagram of a vehicle detection method 300 according to another embodiment of the present disclosure.
In the case where there is one input image data, for example, a vehicle attribute and a vehicle license number can be determined. In the case where the input image data is plural or the input image data includes plural time-series video frames, the above five types of vehicle detection results of the vehicle attribute, the vehicle license number, the violation detection result, the vehicle running track, and the traffic flow detection result can be determined.
As shown in fig. 3, a vehicle detection method 300 according to another embodiment of the present disclosure utilizes a specific example that can be implemented using the following embodiments to determine vehicle detection data according to a vehicle region.
Exemplarily, determining the vehicle detection data includes at least one of operations S321 to S325, for example, according to the vehicle region. In the example of fig. 3, a specific example in which the determination of the vehicle detection data includes, for example, operations S321 to S325 according to the vehicle region is schematically shown.
In operation S321, vehicle attributes 303 are determined according to the vehicle region 302.
As shown in fig. 3, a specific example of determining the vehicle attribute according to the vehicle region in operation S321 may be implemented, for example, by using the following embodiment: the vehicle region 302 is detected according to the vehicle attribute detection model M2, and the vehicle attribute 303 is obtained.
Illustratively, the vehicle property detection model may include, for example: the PaddlePaddle-an Lightweight CPU conditional Neural Network, PP-LCNet, is a Lightweight Convolutional Neural Network.
The PP-LCNet can improve the accuracy of vehicle attribute detection under the condition of keeping delay unchanged. And the PP-LCNet is lighter, has higher vehicle attribute detection speed and vehicle attribute detection accuracy, has lower memory requirement, and is suitable for vehicle detection in more scenes.
In operation S322, a vehicle license number 305 is determined based on the vehicle region 302.
As shown in fig. 3, a specific example of determining the vehicle license number 305 according to the vehicle region 302, for example, of operation S322 may be implemented by using the following embodiment.
In operation S326, the vehicle region 302 is detected according to the vehicle license plate detection model M3, resulting in the vehicle license plate region 304.
Illustratively, the vehicle license plate inspection model may include, for example: the PaddlePaddle-Optical Character registration version 3_ det is PP-OCRv3_ det.
The PP-OCRv3_ det has a large-receptive-field pixel aggregation network structure, a teacher model mutual learning strategy and a characteristic pyramid structure of a residual error attention mechanism, and can efficiently and accurately detect the vehicle license plate.
In operation S327, the vehicle license region 304 is detected according to the character recognition model M4, and the vehicle license number 305 is obtained.
Illustratively, the Character Recognition model M4 may include, for example, a Paddlepaddle-Optical Character Recognition version 3_ rec, i.e., PP-OCRv3_ rec.
PP-OCRv3_ rec is a lightweight text recognition network, the accuracy of vehicle license number recognition can be improved by replacing a recurrent neural network RNN with a small-scale high-precision Chinese scene text recognition model SVTR _ Tiny, and meanwhile, the speed of vehicle license number detection can be improved by utilizing an attention-directed CTC training strategy, a data augmentation strategy for mining character context information, a self-supervised pre-training model, a combined mutual learning strategy and a non-labeled data mining scheme, so that a lightweight character recognition model M4 with high character recognition accuracy and high speed is provided.
In operation S323, a violation detection result 306 is determined based on the vehicle license number and the vehicle region of the plurality of time-series video frames.
The violation detection result relates to a vehicle violation and a vehicle license number associated with the violation. In some cases, the violation behavior of the vehicle needs to be determined from consecutive behaviors in the time dimension, and thus the violation detection result is associated with multiple time-series video frames.
Illustratively, a specific example of determining the violation detection result according to the vehicle license number and the vehicle area of a plurality of time-series video frames can be implemented by using the following embodiments, for example: a vehicle identification associated with the license plate region of the vehicle is determined. And aiming at any one vehicle identifier, determining the illegal parking detection result of the vehicle according to the vehicle area of the illegal parking area and the vehicle identifier and the illegal parking time threshold.
The violation detection results include violation parking detection results.
For example, the vehicle identifier may be obtained by marking a vehicle area of the input image data, for example, a corresponding vehicle identifier may be marked in each vehicle area of the initial input image data, and the vehicle identifiers of subsequent time-series video frames may be synchronized through vehicle tracking, for example, the same vehicle identifier may be associated, or a vehicle identifier may be added, deleted, and the like.
For example, the illegal parking area and the illegal parking time threshold may be pre-configured according to a specific scenario, for example.
It should be noted that the vehicle identification may be used to uniquely identify the vehicle, and the vehicle identification may be the same as or different from the vehicle license number.
The illegal parking is a common type of illegal parking detection, and the vehicle detection method disclosed by the embodiment of the disclosure can cover the conventional illegal parking detection function by detecting the illegal parking.
In operation S324, a vehicle movement trajectory 307 is determined according to the vehicle regions of the plurality of time-series video frames.
As shown in fig. 3, for example, the following embodiment may be utilized to implement the specific example of determining the vehicle movement track 307 for the vehicle regions of the plurality of time-series video frames of operation S324: and detecting the vehicle areas 302 of a plurality of time sequence video frames according to the vehicle tracking model M5 to obtain a vehicle running track 307.
Illustratively, the vehicle tracking model M5 may include, for example: observation-Central SORT: the Rethronking SORT for Robust Multi-Object Tracking, namely OC-SORT, is a Multi-target Tracking algorithm.
The OC-SORT is suitable for the conditions that a model in multi-target tracking is sensitive to target overlapping and nonlinear motion and high frame rate video is needed, vehicle tracking can be carried out simply and on line in real time, and meanwhile the OC-SORT has the characteristic of robustness in the process of target overlapping and nonlinear motion.
In operation S325, the traffic flow detection result 308 is determined according to the vehicle running track 307 and the vehicle area.
Illustratively, the following embodiments can be used to realize specific examples of determining the traffic flow detection result according to the vehicle running track and the vehicle area: and determining the traffic flow detection result in the corresponding direction according to the number of the vehicle areas and the direction of the vehicle running track.
For example, in some scenarios, the vehicle flow detection needs to be accurate to the direction of vehicle travel. According to the vehicle detection method disclosed by the embodiment of the disclosure, the vehicle flow detection result in the corresponding direction can be accurately determined through the number of the vehicle areas and the direction of the vehicle running track.
According to the vehicle detection method disclosed by the embodiment of the disclosure, through the operation, for example, the vehicle attribute, the vehicle license number, the violation detection result, the vehicle running track and the traffic flow detection result can be automatically determined, and multifunctional and all-scene vehicle detection is realized.
According to the vehicle detection method disclosed by the embodiment of the disclosure, high-dimensional input image data can be handled through the corresponding deep learning model, and corresponding detection can be accurately carried out by utilizing the expression capability of deep learning.
According to the vehicle detection method disclosed by the embodiment of the disclosure, through the vehicle attribute detection model such as PP-LCNet, the vehicle license plate detection model such as PP-OCRv3_ det, the character recognition model such as PP-OCRv3_ rec and the vehicle tracking model such as OC-SORT, technical model selection is not needed by related users, and the usability is higher.
In some scenes, data and model magnitude related to realizing multifunctional and full-scene vehicle detection need hardware equipment with large memory and high performance, according to the vehicle detection method disclosed by the embodiment of the disclosure, the specific deep learning model has the advantages of light weight, high detection accuracy, high detection speed and the like, the memory and performance requirements on the hardware equipment can be reduced under the condition of realizing multifunctional and full-scene vehicle detection, and the method has higher adaptability with the hardware equipment.
In addition, according to the vehicle detection method of the embodiment of the disclosure, the pipeline operation can be systematically performed, and at least one type of vehicle detection result which is output can be obtained through the corresponding operation with respect to the input image data. For example, the violation detection result may be determined based on a vehicle detection result of the type of a vehicle license number, and the traffic detection result may also be determined based on a vehicle detection result of the type of a vehicle running trajectory. The vehicle detection method and the vehicle detection device can provide multiple vehicle detections under the condition that the vehicle detection results comprise vehicle attributes, vehicle license numbers, violation detection results, vehicle running tracks and vehicle flow detection results, do not need corresponding users to carry out logic building of corresponding detection functions or adaptive adjustment of corresponding deep learning models, and have higher vehicle detection efficiency.
Fig. 4 schematically shows a schematic diagram of obtaining a vehicle license plate number according to a vehicle detection method according to still another embodiment of the present disclosure.
As shown in fig. 4, according to a vehicle detecting method according to another embodiment of the present disclosure, the following embodiment can be used to detect a vehicle license plate region according to a character recognition model, so as to obtain a specific example of a vehicle license plate number.
In operation S471, a vehicle identifier 402 associated with the license plate region 401 is determined.
Detecting the vehicle license number requires that the vehicle license area be predetermined and associated with a vehicle identification, e.g., a vehicle appears in multiple time-sequential video frames and a corresponding vehicle identification needs to be associated with the vehicle for detecting the vehicle license number of the vehicle.
In operation S472, a vehicle license plate region of the time-series video frame 403 having the vehicle identifier 402 is detected according to the character recognition model, resulting in a candidate vehicle license plate number 404.
In operation S473, the largest number of candidate vehicle license numbers having the same value is determined as vehicle license number 405.
The following description will be given taking an example in which a certain vehicle C1 is displayed in a total of X time-series video frames from the time-series video frame P1 to the time-series video frame PX. For example, in some cases, the candidate vehicle license number detected by some time series video frames is wrong due to different angles of the vehicle C1 in different time series video frames, occlusion, and the like.
According to the vehicle detection method of the embodiment of the disclosure, by determining the vehicle identifier related to the vehicle license plate region, the vehicle license plate region of the time sequence video frame with the vehicle identifier can be uniquely determined based on the vehicle identifier, by detecting the vehicle license plate region of the time sequence video frame with the vehicle identifier according to the character recognition model, candidate vehicle license plate numbers are obtained, and the maximum number of candidate vehicle license plate numbers with the same value is determined as the vehicle license plate number, so that the vehicle license plate number detection accuracy can be improved.
In the example of fig. 4, candidate vehicle license plate numbers detected from the vehicle license plate region of each time-series video frame are schematically shown, for example, the candidate vehicle license plate number N1 corresponding to the time-series video frame P1 is 12345, the candidate vehicle license plate number N3 corresponding to the time-series video frame P3 is 12845, and in the case where the number of candidate vehicle license plate numbers having a value of 12345 is the largest, the candidate vehicle license plate number 12345 may be determined as the vehicle license plate number 405.
Illustratively, according to the vehicle detection method of the further embodiment of the present disclosure, the specific example of determining the vehicle detection data according to the vehicle area can be implemented by using the following embodiments, for example: in response to the vehicle detection data selection instruction, vehicle detection data matching the vehicle detection data selection instruction is determined according to the vehicle area.
For example, the vehicle detection data selection instruction may be determined by a person having a vehicle detection requirement, for example.
According to the vehicle detection method, vehicle detection data are further selected, vehicle detection data matched with the vehicle detection data selection instruction can be determined according to the vehicle area, selection and configuration of the vehicle detection data are supported, flexibility is high, and the vehicle detection method can be suitable for more application scenes of vehicle detection.
Illustratively, according to a vehicle detection method of a further embodiment of the present disclosure, a specific example of determining a vehicle region from input image data may be implemented, for example, with the following embodiments: according to a plurality of continuous time sequence video frames, a first target time sequence video frame of a plurality of sequentially spaced M video frames is determined. And detecting the target time sequence video frame to obtain a vehicle area.
M is a positive integer greater than 1. Illustratively, M may take on a value within an integer numerical range of 2-12, for example.
Under the condition that the input image data comprises a plurality of time sequence video frames, the interval time between the time sequence video frames is short, the difference between the adjacent time sequence video frames is small, the detection of each time sequence video frame in sequence has a large amount of calculation, time and storage cost, and the accuracy of vehicle detection is not obviously improved.
According to the vehicle detection method, the first target time sequence video frames of the M video frames sequentially spaced are determined according to the plurality of continuous time sequence video frames, the number of the time sequence video frames needing to be detected for the vehicle area can be reduced, the vehicle area can be obtained by detecting the target time sequence video frames, the calculation power consumption can be reduced, the calculation time and the storage capacity can be saved, and the vehicle detection efficiency is higher.
For example, in the case that the vehicle detection data includes the vehicle running track, since the vehicle running track has higher time correlation, in order to ensure the accuracy of the vehicle running track, for example, M having a lower value may be taken. M may take the value 2, for example.
Illustratively, the vehicle detection method according to still another embodiment of the present disclosure, for example, may further include: and responding to a structure adjusting instruction aiming at the target model, and adjusting the structure of the target model to obtain an adjusted target model.
The target model includes at least one of a target detection model, a vehicle attribute detection model, a vehicle license plate detection model, a character recognition model, and a vehicle tracking model.
The deep learning model has a structure such as a head network (head), a backbone network (backbone), and the like.
According to the vehicle detection method disclosed by the embodiment of the disclosure, the structure of the target model is also supported to be selected, the structure of the target model is adjusted in response to the structure adjustment instruction aiming at the target model, the adjusted target model can be obtained, the structure selection and configuration of the target network are supported, the flexibility is higher, and more application scenes of vehicle detection can be adapted.
Illustratively, according to the vehicle detection method of the further embodiment of the present disclosure, the target detection model is trained by using a common training set and a business training set.
The generic training set characterizes a training set for target detection, and the business training set characterizes a training set for vehicle detection.
Illustratively, the generic training set may be acquired, for example, at an open-source training sample platform.
The target detection model is used for target detection, targets may include various object targets, and for the vehicle region detection of the embodiment of the present disclosure, adaptive model training is required, which relates to training samples related to vehicles such as road driving. These training samples are costly to the relevant personnel or entities having vehicle detection requirements.
According to the vehicle detection method disclosed by the embodiment of the disclosure, the target detection model obtained by training through the general training set and the business training set can be directly used without building a model and a training model, and the technical threshold of related personnel or entities with vehicle detection requirements can be reduced.
According to the vehicle detection method disclosed by the embodiment of the invention, the target detection model obtained by training through the universal training set and the business training set can be directly suitable for the application scene of vehicle detection, relevant personnel or entities with vehicle detection requirements are not required to obtain the training set relevant to the vehicle for adaptive model training, and the vehicle detection cost can be reduced.
Illustratively, according to the vehicle detection method of the further embodiment of the present disclosure, the target detection model is obtained by performing model fine-tuning according to the common training set and the business training set.
Fine-tune model tuning, or fine-tune, can be understood as a method of tuning a model to bridge such distribution shifts over data closer to the target data distribution.
Model fine-tuning may include, for example: and pre-training a target detection model, namely a source model, in a source training set. A new target detection model is created that replicates all the model designs and their parameters on the source model except the output layer. It is assumed that the new target detection model parameters contain knowledge learned from the source training set and that these knowledge are also applicable to the target training set. It is also assumed that the output layers of the source model are closely related to the labels of the source training set. An output layer with the output size of the category number of the target training set can be added to the new target detection model, and the model parameters of the layer are initialized randomly. A new object detection model may be trained on the training set of objects. The output layer can be trained from scratch, and the parameters of the remaining layers are derived based on the parameter tuning of the source model.
Illustratively, model refinement may be used, for example, where different training sets are applied for object detection model training.
For example, for a training set with a small amount of data but very high data similarity, the output categories of the last layers or the final classification layer of the target detection model may be modified.
For example, for a training set with a small amount of data but low similarity, the initial k layers of the pre-trained target detection model may be frozen, and the remaining (n-k) layers trained here.
According to the vehicle detection method disclosed by the embodiment of the disclosure, the target detection model obtained by carrying out model fine adjustment according to the general training set and the business training set has better performance, can accurately and efficiently carry out vehicle region detection, and has higher vehicle detection efficiency.
For example, the object detection model may include: paddlePaddle-an Evolved version of YoLO, i.e., PP-Yoloe.
Under the condition that the target detection model comprises PP-YOLOE, model training convergence can be accelerated and downstream task generalization can be improved through the PP-YOLOE.
Illustratively, according to a vehicle detection method of yet another embodiment of the present disclosure, the vehicle property detection model is trained by using a data enhancement training set.
The data enhancement training set is obtained by carrying out data enhancement processing on the training set of the vehicle attribute detection model.
Data enhancement may be understood as a method of generating new training data for existing data to extend an original training set.
According to the vehicle detection method of the embodiment of the disclosure, since the data enhancement training set is obtained by performing data enhancement processing on the training set of the vehicle attribute detection model, the cost of data acquisition and data labeling of the training set of the vehicle attribute detection model is lower, the imbalance of the training set is reduced, the generalization of the vehicle attribute detection model obtained by training the data enhancement training set is better, the accuracy of vehicle attribute detection is higher,
illustratively, according to a vehicle detection method of a further embodiment of the present disclosure, the vehicle attribute detection model is obtained by migration learning of a student model using a teacher model.
Illustratively, the teacher model is more complex in structure and the model parameters are more voluminous in scale, for example, than the student model.
According to the vehicle detection method disclosed by the embodiment of the disclosure, the vehicle attribute detection model obtained by transferring and learning the student model by using the teacher model is lighter, the vehicle attribute detection accuracy of the teacher model can be achieved, and the vehicle attribute detection efficiency is higher.
Illustratively, according to a vehicle detection method of yet another embodiment of the present disclosure, the training set of the vehicle attribute detection model includes target label samples, and the target label samples are labeled training samples obtained by detecting unlabeled samples by using a teacher model.
One difficult problem with the use of correlation models for technicians or entities having vehicle detection requirements is: how this model applies to the current vertical class scene. For example, the correlation model is suitable for a wide range of application scenarios, and the performance and detection accuracy of the model may be greatly reduced in a specific application scenario. And secondary training is required, and the cost for acquiring and labeling the training samples is high.
According to the vehicle detection method disclosed by the embodiment of the disclosure, the teacher model is utilized to detect the unlabeled sample to obtain the labeled training sample, the initial unlabeled sample can be automatically labeled by combining the teacher model, and the labor cost for labeling related labels can be saved. Through the training set of the vehicle attribute detection model comprising the target label sample, the vehicle attribute detection model which is more accurate and more suitable for the current application scene can be obtained.
For example, the rest of the object models may be obtained by migration learning from the teacher model to the student model, and the corresponding labeled training samples of the object models may also be labeled by unlabeled samples through the teacher model.
As shown in fig. 5, a vehicle detection method according to still another embodiment of the present disclosure may further include: the vehicle detection data is displayed in time-series video frames.
In the example of fig. 5, a specific example of displaying a vehicle attribute of the vehicle license number license and the vehicle color in the time-series video frame Img is schematically shown. In the example of fig. 5, a vehicle zone Z1 and a vehicle license plate zone Z2 are also schematically shown.
According to the vehicle detection method of the embodiment of the disclosure, by displaying the vehicle detection data in the time-series video frame, the vehicle detection data can be displayed in a visual manner when the relevant person watches the time-series video frame.
Illustratively, according to the vehicle detection method of the further embodiment of the present disclosure, for example, configurations such as a saving position, an obtaining position, and the like of various parameters and data, such as a path configuration supporting input image data, an operating device configuration of the vehicle detection method of the embodiment of the present disclosure, and the like, are also possible.
Fig. 6 schematically shows a block diagram of a vehicle detection apparatus according to an embodiment of the present disclosure.
As shown in fig. 6, the vehicle detection 600 of the embodiment of the present disclosure includes, for example, a vehicle region determination module 610 and a vehicle detection data determination module 620.
A vehicle region determining module 610, configured to determine a vehicle region according to the input image data, where the vehicle region represents a region where the vehicle displayed by the image data is located; and
a vehicle detection data determination module 620 configured to determine vehicle detection data according to the vehicle region, wherein the vehicle detection data includes at least one of: the vehicle detection method comprises the following steps of vehicle attributes, vehicle license plate numbers, violation detection results, vehicle running tracks and vehicle flow detection results, wherein the vehicle attributes represent physical characteristics of vehicles.
Illustratively, the image data comprises a plurality of time-sequential video frames; the vehicle detection data determination module includes at least one of the following.
And the vehicle attribute determining submodule is used for determining the vehicle attribute according to the vehicle area.
And the vehicle license number determining submodule is used for determining the vehicle license number according to the vehicle area.
And the violation detection result determining submodule is used for determining a violation detection result according to the vehicle license number and the vehicle areas of the plurality of time sequence video frames.
And the vehicle running track determining submodule is used for determining the vehicle running track according to the vehicle areas of the plurality of time sequence video frames.
And the traffic flow detection result determining submodule is used for determining a traffic flow detection result according to the vehicle running track and the vehicle area.
Illustratively, the vehicle zone determination module includes: and the vehicle area first determining submodule is used for detecting the input image data according to the target detection model to obtain a vehicle area.
The vehicle attribute determination sub-module includes: and the vehicle attribute determining unit is used for detecting the vehicle area according to the vehicle attribute detection model to obtain the vehicle attribute.
The vehicle license number determination submodule includes: the vehicle license plate region determining unit is used for detecting the vehicle region according to the vehicle license plate detection model to obtain a vehicle license plate region; and the vehicle license number determining unit is used for detecting the vehicle license area according to the character recognition model to obtain the vehicle license number.
The violation detection result determination submodule includes: a vehicle identification determination unit for determining a vehicle identification associated with the license plate region of the vehicle; and the illegal parking detection result determining unit is used for determining the illegal parking detection result of the vehicle according to the vehicle area of the illegal parking area and the vehicle identification and the illegal parking time threshold, wherein the illegal parking detection result comprises the illegal parking detection result.
The vehicle running track determination submodule includes: and the vehicle running track determining unit is used for detecting the vehicle areas of the time sequence video frames according to the vehicle tracking model to obtain the vehicle running track.
The traffic flow detection result determination submodule includes: and the traffic flow detection result determining unit is used for determining the traffic flow detection result in the corresponding direction according to the number of the vehicle areas and the direction of the vehicle running track.
Illustratively, the vehicle license plate number determination unit includes: a vehicle identification determination subunit for determining a vehicle identification associated with the license plate region of the vehicle; the candidate vehicle license number determining subunit is used for detecting the vehicle license area of the time sequence video frame with the vehicle identification according to the character recognition model to obtain a candidate vehicle license number; a vehicle license number determination subunit operable to determine a maximum number of candidate vehicle license numbers having the same value as the vehicle license number.
Illustratively, the vehicle zone determination module includes: the first target time sequence video frame determining submodule is used for determining a plurality of first target time sequence video frames which are sequentially spaced by M video frames according to a plurality of continuous time sequence video frames, wherein M is a positive integer larger than 1; and the vehicle area second determining submodule is used for detecting the target time sequence video frame to obtain a vehicle area.
Illustratively, the vehicle detection data determination module includes: and the selection module is used for responding to the vehicle detection data selection instruction and determining the vehicle detection data matched with the vehicle detection data selection instruction according to the vehicle area.
Exemplarily, the method further comprises the following steps: the adjusting module is used for responding to a structure adjusting instruction aiming at the target model and adjusting the structure of the target model to obtain the adjusted target model, wherein the target model comprises at least one of a target detection model, a vehicle attribute detection model, a vehicle license plate detection model, a character recognition model and a vehicle tracking model.
Illustratively, the target detection model is trained using a generic training set and a business training set, wherein the generic training set characterizes the training set for target detection, and the business training set characterizes the training set for vehicle detection.
Illustratively, the target detection model is obtained by performing model fine-tuning according to the common training set and the business training set.
Illustratively, the vehicle attribute detection model is obtained by training with a data enhancement training set, and the data enhancement training set is obtained by performing data enhancement processing on the training set of the vehicle attribute detection model.
Illustratively, the vehicle attribute detection model is obtained by migration learning of a student model using a teacher model.
Illustratively, the training set of the vehicle attribute detection model includes target label samples, which are labeled training samples obtained by detecting unlabeled samples using the teacher model.
Illustratively, the object detection model includes: the vehicle license plate detection model comprises a PaddlePaddlePaddleLight CPU conditional Neural Network, the vehicle license plate detection model comprises a PaddlePaddlePaddleLight CPU conditional Neural Network 3_ det, the Character Recognition model comprises a PaddlePaddlePaddledPaddledPaddledPaddleWriter registration 3_ rec, and the vehicle tracking model comprises an Observation-Central SORT: resetting SORT for debug Multi-Object Tracking.
Exemplarily, the method further comprises the following steps: and the display module is used for displaying the vehicle detection data in the time sequence video frame.
It should be understood that the embodiments of the apparatus part of the present disclosure correspond to the embodiments of the method part of the present disclosure, and the technical problems to be solved and the technical effects to be achieved also correspond to the same or similar, which are not repeated herein.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the device 700 comprises a computing unit 701, which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, causes the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (31)
1. A vehicle detection method, comprising:
determining a vehicle area according to the input image data, wherein the vehicle area represents an area where a vehicle is located and displayed by the image data; and
determining vehicle detection data from the vehicle region, wherein the vehicle detection data comprises at least one of: the vehicle detection method comprises the following steps of vehicle attributes, vehicle license plate numbers, violation detection results, vehicle running tracks and vehicle flow detection results, wherein the vehicle attributes represent physical characteristics of a vehicle.
2. The method of claim 1, wherein the image data comprises a plurality of time-sequential video frames; the determining vehicle detection data according to the vehicle region comprises at least one of:
determining the vehicle attribute according to the vehicle region;
determining the vehicle license number according to the vehicle region;
determining the violation detection result according to the vehicle license number and the vehicle regions of the plurality of time sequence video frames;
determining the vehicle running track according to the vehicle areas of the plurality of time sequence video frames; and
and determining the traffic flow detection result according to the vehicle running track and the vehicle area.
3. The method of claim 2, wherein,
the determining a vehicle region according to the input image data includes:
detecting the input image data according to a target detection model to obtain the vehicle area;
the determining the vehicle attribute according to the vehicle region includes:
detecting the vehicle area according to a vehicle attribute detection model to obtain the vehicle attribute;
the determining the vehicle license number according to the vehicle region includes:
detecting the vehicle region according to a vehicle license plate detection model to obtain a vehicle license plate region;
detecting the vehicle license plate area according to a character recognition model to obtain the vehicle license plate number;
the determining the violation detection result according to the vehicle license number and the vehicle region of the plurality of time-series video frames includes:
determining a vehicle identification associated with the vehicle license plate region;
for any one vehicle identifier, determining an illegal parking detection result of the vehicle according to the vehicle area of the illegal parking area and the vehicle identifier and an illegal parking time threshold, wherein the illegal parking detection result comprises the illegal parking detection result;
the determining the vehicle trajectory for the vehicle region of the plurality of time-series video frames comprises:
detecting the vehicle areas of the time sequence video frames according to a vehicle tracking model to obtain the vehicle running track;
the determining the traffic flow detection result according to the vehicle running track and the vehicle area comprises:
and determining the traffic flow detection result in the corresponding direction according to the number of the vehicle areas and the direction of the vehicle running track.
4. The method of claim 3, wherein the detecting the vehicle license plate region according to a character recognition model to obtain the vehicle license plate number comprises:
determining a vehicle identification associated with the vehicle license plate region;
detecting the vehicle license plate area of the time sequence video frame with the vehicle identification according to the character recognition model to obtain a candidate vehicle license plate number;
determining a maximum number of the candidate vehicle license numbers having the same value as the vehicle license number.
5. The method of any of claims 2-4, wherein the determining a vehicle region from the input image data comprises:
determining a plurality of first target time sequence video frames which are sequentially spaced by M video frames according to a plurality of continuous time sequence video frames, wherein M is a positive integer greater than 1;
and detecting the target time sequence video frame to obtain the vehicle area.
6. The method of any one of claims 1-4, wherein the determining vehicle detection data from vehicle zones comprises:
in response to a vehicle detection data selection instruction, determining the vehicle detection data matched with the vehicle detection data selection instruction according to the vehicle area.
7. The method of claim 3, further comprising:
and responding to a structure adjustment instruction aiming at a target model, and adjusting the structure of the target model to obtain an adjusted target model, wherein the target model comprises at least one of the target detection model, the vehicle attribute detection model, the vehicle license plate detection model, the character recognition model and the vehicle tracking model.
8. The method of claim 3, wherein the target detection model is trained using a generic training set and a business training set, wherein the generic training set characterizes the training set for target detection and the business training set characterizes the training set for vehicle detection.
9. The method of claim 8, wherein the object detection model is model-refined from the generic training set and the business training set.
10. The method of claim 3, wherein the vehicle attribute detection model is trained using a data-enhanced training set, the data-enhanced training set being obtained by performing data enhancement processing on a training set of the vehicle attribute detection model.
11. The method of claim 3, wherein the vehicle attribute detection model is a result of transfer learning of a student model using a teacher model.
12. The method of claim 11, wherein the training set of vehicle attribute detection models comprises target label exemplars that are labeled training exemplars detected on unlabeled exemplars with the teacher model.
13. The method of claim 3, wherein the object detection model comprises: the vehicle license plate detection model comprises a Paddlepacker registration version 3_ det, the Character Recognition model comprises a Paddlepacker registration version 3_ rec, and the vehicle tracking model comprises an Observation-Central SORT: retking SORT for Robust Multi-Obj ect Tracking.
14. The method of any of claims 2-4, further comprising:
displaying the vehicle detection data in the time-series video frame.
15. A vehicle detection device comprising:
the vehicle area determining module is used for determining a vehicle area according to the input image data, wherein the vehicle area represents an area where a vehicle is located and displayed by the image data; and
a vehicle detection data determination module to determine vehicle detection data based on the vehicle region, wherein the vehicle detection data includes at least one of: the vehicle detection method comprises the following steps of vehicle attributes, vehicle license plate numbers, violation detection results, vehicle running tracks and vehicle flow detection results, wherein the vehicle attributes represent physical characteristics of a vehicle.
16. The apparatus of claim 15, wherein the image data comprises a plurality of time-sequential video frames; the vehicle detection data determination module includes at least one of:
the vehicle attribute determining submodule is used for determining the vehicle attribute according to the vehicle area;
a vehicle license number determination submodule for determining the vehicle license number based on the vehicle region;
a violation detection result determination sub-module, configured to determine the violation detection result according to the vehicle license number and the vehicle area of the plurality of time-series video frames;
the vehicle running track determining submodule is used for determining the vehicle running track according to the vehicle areas of the time sequence video frames; and
and the traffic flow detection result determining submodule is used for determining the traffic flow detection result according to the vehicle running track and the vehicle area.
17. The apparatus of claim 16, wherein,
the vehicle region determination module includes:
the vehicle area first determining submodule is used for detecting the input image data according to a target detection model to obtain a vehicle area;
the vehicle attribute determination sub-module includes:
the vehicle attribute determining unit is used for detecting the vehicle area according to a vehicle attribute detection model to obtain the vehicle attribute;
the vehicle license number determination sub-module includes:
the vehicle license plate region determining unit is used for detecting the vehicle region according to the vehicle license plate detection model to obtain a vehicle license plate region;
the vehicle license number determining unit is used for detecting the vehicle license area according to a character recognition model to obtain the vehicle license number;
the violation detection result determination sub-module includes:
a vehicle identification determination unit for determining a vehicle identification associated with the vehicle license plate region;
the illegal parking detection result determining unit is used for determining the illegal parking detection result of the vehicle according to the vehicle area of the illegal parking area, which is associated with the vehicle identification, and the illegal parking time threshold value aiming at any one vehicle identification, wherein the illegal parking detection result comprises the illegal parking detection result;
the vehicle running track determining submodule comprises:
the vehicle running track determining unit is used for detecting the vehicle areas of the time sequence video frames according to a vehicle tracking model to obtain the vehicle running track;
the traffic flow detection result determination submodule includes:
and the traffic flow detection result determining unit is used for determining the traffic flow detection result in the corresponding direction according to the number of the vehicle areas and the direction of the vehicle running track.
18. The apparatus of claim 17, wherein the vehicle license number determination unit comprises:
a vehicle identification determination subunit operable to determine a vehicle identification associated with the vehicle license plate region;
a candidate vehicle license number determination subunit, configured to detect the vehicle license area of the time-series video frame with the vehicle identifier according to the character recognition model, so as to obtain a candidate vehicle license number;
a vehicle license number determination subunit operable to determine a maximum number of the candidate vehicle license numbers having the same value as the vehicle license number.
19. The apparatus of any of claims 16-18, wherein the vehicle zone determination module comprises:
the first target time sequence video frame determining submodule is used for determining a plurality of first target time sequence video frames which are sequentially spaced by M video frames according to a plurality of continuous time sequence video frames, wherein M is a positive integer larger than 1;
and the vehicle area second determining submodule is used for detecting the target time sequence video frame to obtain the vehicle area.
20. The apparatus of any of claims 15-18, wherein the vehicle detection data determination module comprises:
the selection module is used for responding to a vehicle detection data selection instruction and determining the vehicle detection data matched with the vehicle detection data selection instruction according to the vehicle area.
21. The apparatus of claim 17, further comprising:
the adjusting module is configured to adjust a structure of a target model in response to a structure adjustment instruction for the target model to obtain an adjusted target model, where the target model includes at least one of the target detection model, the vehicle attribute detection model, the vehicle license plate detection model, the character recognition model, and the vehicle tracking model.
22. The apparatus of claim 17, wherein the target detection model is trained using a generic training set and a business training set, wherein the generic training set characterizes the training set for target detection and the business training set characterizes the training set for vehicle detection.
23. The apparatus of claim 22, wherein the object detection model is fine-tuned according to the generic training set and the business training set.
24. The apparatus of claim 17, wherein the vehicle attribute detection model is trained using a data-enhanced training set that is data-enhanced from a training set of the vehicle attribute detection model.
25. The apparatus of claim 17, wherein the vehicle attribute detection model is a result of transfer learning of a student model using a teacher model.
26. The apparatus of claim 25, wherein the training set of vehicle attribute detection models comprises target label exemplars that are labeled training exemplars detected on unlabeled exemplars with the teacher model.
27. The apparatus of claim 17, wherein the object detection model comprises: the vehicle license plate detection model comprises a PaddlePaddlePad-an illuminated weight CPU conditional Neural Network, the vehicle license plate detection model comprises a PaddlePaddlePad-an illuminated weight registration version 3_ det, the Character Recognition model comprises a PaddlePad-Optical Character registration version 3_ rec, and the vehicle tracking model comprises an observer-central SORT: resetting SORT for Robust Multi-Object Tracking.
28. The apparatus of any of claims 2-4, further comprising:
and the display module is used for displaying the vehicle detection data in the time sequence video frame.
29. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-14.
30. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-14.
31. A computer program product comprising a computer program stored on at least one of a readable storage medium and an electronic device, the computer program, when executed by a processor, implementing the method according to any one of claims 1-14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497780.6A CN115719465B (en) | 2022-11-24 | 2022-11-24 | Vehicle detection method, device, apparatus, storage medium, and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497780.6A CN115719465B (en) | 2022-11-24 | 2022-11-24 | Vehicle detection method, device, apparatus, storage medium, and program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115719465A true CN115719465A (en) | 2023-02-28 |
| CN115719465B CN115719465B (en) | 2023-11-03 |
Family
ID=85256681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211497780.6A Active CN115719465B (en) | 2022-11-24 | 2022-11-24 | Vehicle detection method, device, apparatus, storage medium, and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115719465B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778589A (en) * | 2016-12-09 | 2017-05-31 | 厦门大学 | A kind of masked method for detecting human face of robust based on modified LeNet |
| CN109359676A (en) * | 2018-10-08 | 2019-02-19 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating vehicle damage information |
| WO2020155763A1 (en) * | 2019-01-28 | 2020-08-06 | 平安科技（深圳）有限公司 | Ocr recognition method and electronic device thereof |
| CN112861701A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Illegal parking identification method and device, electronic equipment and computer readable medium |
| CN112861706A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Road state monitoring method, device, equipment and storage medium |
| CN112990295A (en) * | 2021-03-10 | 2021-06-18 | 中国互联网络信息中心 | Semi-supervised graph representation learning method and device based on migration learning and deep learning fusion |
| CN113887418A (en) * | 2021-09-30 | 2022-01-04 | 北京百度网讯科技有限公司 | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium |
| CN114005095A (en) * | 2021-10-29 | 2022-02-01 | 北京百度网讯科技有限公司 | Vehicle attribute identification method and device, electronic equipment and medium |
| CN114261338A (en) * | 2021-12-08 | 2022-04-01 | 阿波罗智联(北京)科技有限公司 | Vehicle detection method and device and automatic driving vehicle |
| US20220335728A1 (en) * | 2021-04-14 | 2022-10-20 | Thinkware Corporation | Electronic device, method, and computer readable storage medium for detection of vehicle appearance |
| CN115359471A (en) * | 2022-07-15 | 2022-11-18 | 北京百度网讯科技有限公司 | Image processing and joint detection model training method, device, equipment and storage medium |
-
2022
- 2022-11-24 CN CN202211497780.6A patent/CN115719465B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778589A (en) * | 2016-12-09 | 2017-05-31 | 厦门大学 | A kind of masked method for detecting human face of robust based on modified LeNet |
| CN109359676A (en) * | 2018-10-08 | 2019-02-19 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating vehicle damage information |
| WO2020155763A1 (en) * | 2019-01-28 | 2020-08-06 | 平安科技（深圳）有限公司 | Ocr recognition method and electronic device thereof |
| CN112861701A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Illegal parking identification method and device, electronic equipment and computer readable medium |
| CN112861706A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Road state monitoring method, device, equipment and storage medium |
| CN112990295A (en) * | 2021-03-10 | 2021-06-18 | 中国互联网络信息中心 | Semi-supervised graph representation learning method and device based on migration learning and deep learning fusion |
| US20220335728A1 (en) * | 2021-04-14 | 2022-10-20 | Thinkware Corporation | Electronic device, method, and computer readable storage medium for detection of vehicle appearance |
| CN113887418A (en) * | 2021-09-30 | 2022-01-04 | 北京百度网讯科技有限公司 | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium |
| CN114005095A (en) * | 2021-10-29 | 2022-02-01 | 北京百度网讯科技有限公司 | Vehicle attribute identification method and device, electronic equipment and medium |
| CN114261338A (en) * | 2021-12-08 | 2022-04-01 | 阿波罗智联(北京)科技有限公司 | Vehicle detection method and device and automatic driving vehicle |
| CN115359471A (en) * | 2022-07-15 | 2022-11-18 | 北京百度网讯科技有限公司 | Image processing and joint detection model training method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115719465B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113435529B (en) | Model pre-training method, model training method and image processing method | |
| CN111598164A (en) | Method and device for identifying attribute of target object, electronic equipment and storage medium | |
| CN113836925B (en) | Training method and device for pre-training language model, electronic equipment and storage medium | |
| JP2023527100A (en) | Event detection method, device, electronic device, readable storage medium, and computer program | |
| CN114428677B (en) | Task processing method, processing device, electronic equipment and storage medium | |
| CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
| CN112200067A (en) | Intelligent video event detection method, system, electronic equipment and storage medium | |
| CN113657483A (en) | Model training method, target detection method, device, equipment and storage medium | |
| CN112348104A (en) | Counterfeit program identification method, apparatus, device and storage medium | |
| CN111160410A (en) | Object detection method and device | |
| CN116578925B (en) | Behavior prediction method, device and storage medium based on feature images | |
| CN114090601B (en) | Data screening method, device, equipment and storage medium | |
| Mandal et al. | Improving it support by enhancing incident management process with multi-modal analysis | |
| CN113051911B (en) | Method, apparatus, device, medium and program product for extracting sensitive words | |
| CN113657596B (en) | Method and device for training model and image recognition | |
| CN115719465B (en) | Vehicle detection method, device, apparatus, storage medium, and program product | |
| CN113963186A (en) | Training method of target detection model, target detection method and related device | |
| CN114417974A (en) | Model training method, information processing method, device, electronic device and medium | |
| CN113989720A (en) | Target detection method, training method, device, electronic equipment and storage medium | |
| CN114120180A (en) | Method, device, equipment and medium for generating time sequence nomination | |
| CN111768007A (en) | Method and apparatus for mining data | |
| CN114445711B (en) | Image detection method, image detection device, electronic equipment and storage medium | |
| CN114677691B (en) | Text recognition method, device, electronic equipment and storage medium | |
| CN116186549B (en) | Model training method, device, equipment and medium | |
| CN114724090B (en) | Training method of pedestrian re-identification model, and pedestrian re-identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |