CN109147341B - Violation vehicle detection method and device - Google Patents
Violation vehicle detection method and device Download PDFInfo
- Publication number
- CN109147341B CN109147341B CN201811075372.5A CN201811075372A CN109147341B CN 109147341 B CN109147341 B CN 109147341B CN 201811075372 A CN201811075372 A CN 201811075372A CN 109147341 B CN109147341 B CN 109147341B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- frame image
- information
- image
- vehicles
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention proposes a kind of violation vehicle detection method and device, and wherein method includes: the monitoring video flow for obtaining non-parking area；For every frame image therein, the information of vehicles that image detection obtains each vehicle is carried out；Information of vehicles in frame image is compared with the information of vehicles of previous frame image in monitoring video flow, determines the same vehicle in frame image and previous frame image, and setting flag；For each vehicle in frame image, according to the information of vehicles of vehicle in the information of vehicles and previous frame image of vehicle in frame image, it is determined whether caching frame image, when determining caching frame image, by frame image buffer storage into the corresponding image library of vehicle；For each vehicle, according to the corresponding image library of vehicle, determine whether vehicle is violation vehicle, amount of images to be treated when so as to reduce determining violation vehicle improves the detection efficiency of violation vehicle under the premise of ensuring accuracy in detection.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of violation vehicle detection method and device.
Background technique
Current violation vehicle detection method is mainly the monitoring video flow for obtaining non-parking area, for monitor video
Every frame image in stream carries out image detection to image, the parameter information of each vehicle in image is obtained, according in every frame image
The parameter information of each vehicle, it is determined whether there are violation vehicles.In the above method, need to carry out detection acquisition to every frame image
Vehicle parameter information, heavy workload reduce the detection efficiency of violation vehicle.
Summary of the invention
The present invention is directed to solve at least some of the technical problems in related technologies.
For this purpose, the first purpose of this invention is to propose a kind of violation vehicle detection method, for solving the prior art
Middle detection efficiency is poor, problem at high cost.
Second object of the present invention is to propose a kind of violation vehicle detection device.
Third object of the present invention is to propose another violation vehicle detection device.
Fourth object of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
5th purpose of the invention is to propose a kind of computer program product.
In order to achieve the above object, first aspect present invention embodiment proposes a kind of violation vehicle detection method, comprising:
Obtain the monitoring video flow of non-parking area；
For every frame image in the monitoring video flow, image detection is carried out to the frame image, obtains the frame figure
The information of vehicles of each vehicle as in；
The information of vehicles of information of vehicles and previous frame image in the monitoring video flow in the frame image is compared
It is right, determine the same vehicle in the frame image and the previous frame image, and identical mark is set for the same vehicle
Note；
For each vehicle in the frame image, according to the information of vehicles of vehicle described in the frame image and it is described before
The information of vehicles of vehicle described in one frame image, it is determined whether the frame image is cached, it, will when determining the caching frame image
The frame image buffer storage is into the corresponding image library of the vehicle；
For each vehicle, according to the corresponding image library of the vehicle, determine whether the vehicle is violation vehicle.
Further, the information of vehicles includes the location information and dimension information of vehicle；
The information of vehicles of information of vehicles and previous frame image in the monitoring video flow in the frame image is compared
It is right, determine the same vehicle in the frame image and the previous frame image, comprising:
The information of vehicles of information of vehicles and previous frame image in the monitoring video flow in the frame image is compared
It is right, judge that the frame image is less than first threshold with whether there is corresponding dimension information difference in the previous frame image, and
Corresponding location information difference is less than two information of vehicles of second threshold；
If it exists, by the corresponding vehicle of described two information of vehicles, it is determined as same vehicle.
Further, for each vehicle in the frame image, believed according to the vehicle of vehicle described in the frame image
The information of vehicles of breath and vehicle described in the previous frame image, it is determined whether cache the frame image, comprising:
For each vehicle in the frame image, calculate vehicle described in the frame image information of vehicles and it is described before
Similarity between the information of vehicles of vehicle described in one frame image；
According to the similarity, the caching probability of the frame image is determined；
According to the caching probability, it is determined whether cache the frame image.
Further, when determining the caching frame image, by the frame image buffer storage to the corresponding image of the vehicle
In library, comprising:
When determining the caching frame image, the topography in the frame image including the vehicle is obtained；
Topography including the vehicle is cached in the corresponding image library of the vehicle.
Further, the information of vehicles includes the location information of vehicle；
For each vehicle in the frame image, according to the information of vehicles of vehicle described in the frame image and it is described before
The information of vehicles of vehicle described in one frame image, it is determined whether before caching the frame image, further includes:
For the frame image, obtain each in the location information and previous frame image of each vehicle in the frame image
The location information of a vehicle；
For the location information of each vehicle in the previous frame image, the corresponding position range in the frame image is judged
It is interior to whether there is vehicle；
If vehicle is not present within the scope of the corresponding position in the frame image, by vehicle described in the previous frame image
Image cover within the scope of the corresponding position in the frame image.
Further, for each vehicle, according to the corresponding image library of the vehicle, determine whether the vehicle is violating the regulations
Vehicle, comprising:
For each vehicle, each frame image in corresponding image library is obtained；
According to each frame image and corresponding acquisition time, judge the stoppage of vehicle non-parking area when
Between whether be more than preset time threshold；
If the stoppage of vehicle is more than preset time threshold in the time of non-parking area, it is determined that the vehicle is violating the regulations
Vehicle.
Further, described to be directed to each vehicle, according to the corresponding image library of the vehicle, determine the vehicle whether be
After violation vehicle, further includes:
When the vehicle is violation vehicle, image successively is carried out to each image in the corresponding image library of the vehicle
Detection obtains the parameter information and confidence level of vehicle described in described image；
When there are the parameter informations or the corresponding image of the vehicle that corresponding confidence level is greater than default confidence threshold value
When having carried out the amount of images of image recognition in library and being greater than preset quantity threshold value, by the maximum parameter information of corresponding confidence level,
It is determined as the parameter information of the vehicle.
The violation vehicle detection method of the embodiment of the present invention, by the monitoring video flow for obtaining non-parking area；For prison
Every frame image in video flowing is controlled, image detection is carried out to frame image, the information of vehicles of each vehicle in getting frame image；By frame
Information of vehicles in image is compared with the information of vehicles of previous frame image in monitoring video flow, determines frame image and former frame
Same vehicle in image, and identical label is set for same vehicle；For each vehicle in frame image, according to frame figure
As in vehicle information of vehicles and previous frame image in vehicle information of vehicles, it is determined whether caching frame image, determine cache
When frame image, by frame image buffer storage into the corresponding image library of vehicle；For each vehicle, according to the corresponding image library of vehicle,
Determine whether vehicle is violation vehicle, and amount of images to be treated, reduces work when so as to reduce determining violation vehicle
It measures, under the premise of ensuring accuracy in detection, improves the detection efficiency of violation vehicle.
In order to achieve the above object, second aspect of the present invention embodiment proposes a kind of violation vehicle detection device, comprising:
Module is obtained, for obtaining the monitoring video flow of non-parking area；
Detection module, for carrying out image detection to the frame image for every frame image in the monitoring video flow,
Obtain the information of vehicles of each vehicle in the frame image；
Comparison module, for by the vehicle of the information of vehicles in the frame image and previous frame image in the monitoring video flow
Information is compared, and determines the same vehicle in the frame image and the previous frame image, and be directed to the same vehicle
Identical label is set；
Buffer process module, each vehicle for being directed in the frame image, according to vehicle described in the frame image
Information of vehicles and the previous frame image described in vehicle information of vehicles, it is determined whether the frame image is cached, in determination
When caching the frame image, by the frame image buffer storage into the corresponding image library of the vehicle；
Determining module, for being directed to each vehicle, according to the corresponding image library of the vehicle, determine the vehicle whether be
Violation vehicle.
Further, the information of vehicles includes the location information and dimension information of vehicle；
The comparison module is specifically used for,
The information of vehicles of information of vehicles and previous frame image in the monitoring video flow in the frame image is compared
It is right, judge that the frame image is less than first threshold with whether there is corresponding dimension information difference in the previous frame image, and
Corresponding location information difference is less than two information of vehicles of second threshold；
If it exists, by the corresponding vehicle of described two information of vehicles, it is determined as same vehicle.
Further, the buffer process module is specifically used for,
For each vehicle in the frame image, calculate vehicle described in the frame image information of vehicles and it is described before
Similarity between the information of vehicles of vehicle described in one frame image；
According to the similarity, the caching probability of the frame image is determined；
According to the caching probability, it is determined whether cache the frame image.
Further, the buffer process module is specifically used for,
When determining the caching frame image, the topography in the frame image including the vehicle is obtained；
Topography including the vehicle is cached in the corresponding image library of the vehicle.
Further, the information of vehicles includes the location information of vehicle；
The device further include: judgment module and image processing module；
The acquisition module is also used to obtain the location information of each vehicle in the frame image for the frame image,
And in previous frame image each vehicle location information；
The judgment module judges the frame figure for the location information for each vehicle in the previous frame image
It whether there is vehicle within the scope of corresponding position as in；
Described image processing module, when for vehicle to be not present within the scope of the corresponding position in the frame image, by institute
The image for stating vehicle described in previous frame image covers within the scope of the corresponding position in the frame image.
Further, the determining module is specifically used for,
For each vehicle, each frame image in corresponding image library is obtained；
According to each frame image and corresponding acquisition time, judge the stoppage of vehicle non-parking area when
Between whether be more than preset time threshold；
If the stoppage of vehicle is more than preset time threshold in the time of non-parking area, it is determined that the vehicle is violating the regulations
Vehicle.
Further, the acquisition module is also used to when the vehicle is violation vehicle, successively corresponding to the vehicle
Image library in each image carry out image detection, obtain described image described in vehicle parameter information and confidence level；
The determining module is also used to be greater than the parameter information for presetting confidence threshold value there are corresponding confidence level, or
When having carried out the amount of images of image recognition in the corresponding image library of vehicle described in person greater than preset quantity threshold value, set corresponding
The maximum parameter information of reliability, is determined as the parameter information of the vehicle.
The violation vehicle detection device of the embodiment of the present invention, by the monitoring video flow for obtaining non-parking area；For prison
Every frame image in video flowing is controlled, image detection is carried out to frame image, the information of vehicles of each vehicle in getting frame image；By frame
Information of vehicles in image is compared with the information of vehicles of previous frame image in monitoring video flow, determines frame image and former frame
Same vehicle in image, and identical label is set for same vehicle；For each vehicle in frame image, according to frame figure
As in vehicle information of vehicles and previous frame image in vehicle information of vehicles, it is determined whether caching frame image, determine cache
When frame image, by frame image buffer storage into the corresponding image library of vehicle；For each vehicle, according to the corresponding image library of vehicle,
Determine whether vehicle is violation vehicle, and amount of images to be treated, reduces work when so as to reduce determining violation vehicle
It measures, under the premise of ensuring accuracy in detection, improves the detection efficiency of violation vehicle.
In order to achieve the above object, third aspect present invention embodiment proposes another violation vehicle detection device, comprising: deposit
Reservoir, processor and storage are on a memory and the computer program that can run on a processor, which is characterized in that the processing
Device realizes violation vehicle detection method as described above when executing described program.
To achieve the goals above, fourth aspect present invention embodiment proposes a kind of computer-readable storage of non-transitory
Medium is stored thereon with computer program, which realizes violation vehicle detection method as described above when being executed by processor.
To achieve the goals above, fifth aspect present invention embodiment proposes a kind of computer program product, when described
When instruction processing unit in computer program product executes, violation vehicle detection method as described above is realized.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is a kind of flow diagram of violation vehicle detection method provided in an embodiment of the present invention；
Fig. 2 is a kind of structural schematic diagram of violation vehicle detection device provided in an embodiment of the present invention；
Fig. 3 is the structural schematic diagram of another violation vehicle detection device provided in an embodiment of the present invention；
Fig. 4 is the structural schematic diagram of another violation vehicle detection device provided in an embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings the violation vehicle detection method and device of the embodiment of the present invention are described.
Fig. 1 is a kind of flow diagram of violation vehicle detection method provided in an embodiment of the present invention.As shown in Figure 1, should
Detection method includes the following steps for violation vehicle:
S101, the monitoring video flow for obtaining non-parking area.
The executing subject of violation vehicle detection method provided by the invention is violation vehicle detection device, violation vehicle detection
Device is specifically as follows the software etc. installed on hardware device, such as terminal device, background server etc. or hardware device.
Violation vehicle detection device can be connect with the camera for monitoring each non-parking area, or it is corresponding with camera after
The connection of platform server, obtains the monitoring video flow for the non-parking area that camera is shot.
S102, for every frame image in monitoring video flow, image detection carried out to frame image, it is each in getting frame image
The information of vehicles of vehicle.
In the present embodiment, every frame image in monitoring video flow can be inputted into the first image detection model, obtain first
The information of vehicles of each vehicle of image detection model output.Wherein, the first image detection model for example can be depth convolution
Neural network model.The training process of first image detection model for example can be, acquisition largely includes the image of vehicle, and
The location information and dimension information of vehicle in image are labeled, training sample data are obtained；Using training sample data
The first initial image detection model is trained, trained first image detection model is obtained.Wherein, in information of vehicles
It may include the location information and dimension information of vehicle.The location information of vehicle refers to the position of vehicle in the picture.Vehicle
Dimension information for example may include in following information any one or it is a variety of: height of car, vehicle width, Vehicle length
Deng.
S103, the information of vehicles in frame image is compared with the information of vehicles of previous frame image in monitoring video flow,
It determines the same vehicle in frame image and previous frame image, and identical label is set for same vehicle.
In the present embodiment, the process that violation vehicle detection device executes step 103 is specifically as follows, by the vehicle in frame image
Information is compared with the information of vehicles of previous frame image in monitoring video flow, in judgment frame image and previous frame image whether
There are corresponding dimension information differences to be less than first threshold, and corresponding location information difference is less than two vehicles of second threshold
Information；If it exists, by the corresponding vehicle of two information of vehicles, it is determined as same vehicle.
Specifically, for each information of vehicles in frame image, by each vehicle in the information of vehicles and previous frame image
Information is compared, obtain the dimension information difference between each information of vehicles in the information of vehicles and previous frame image with
And location information difference；Corresponding dimension information difference is obtained less than first threshold, and corresponding location information difference is less than the
The information of vehicles of two threshold values；By the corresponding vehicle of information of vehicles vehicle corresponding with the information of vehicles in frame image, it is determined as
Same vehicle.
S104, for each vehicle in frame image, according in frame image in the information of vehicles and previous frame image of vehicle
The information of vehicles of vehicle, it is determined whether caching frame image, it is when determining caching frame image, frame image buffer storage is corresponding to vehicle
In image library.
In the present embodiment, for each vehicle in frame image, violation vehicle detection device can be according to vehicle in frame image
Information of vehicles and previous frame image in vehicle information of vehicles, between the information of vehicles for determining vehicle described in two field pictures
Difference, when differing greatly, by frame image buffer storage into the corresponding image library of vehicle.
In the present embodiment, violation vehicle detection device is according to vehicle in the information of vehicles and previous frame image of vehicle in frame image
Information of vehicles, it is determined whether the process of caching frame image is specifically as follows, and for each vehicle in frame image, calculates frame
Similarity in image in the information of vehicles and previous frame image of vehicle between the information of vehicles of vehicle；According to similarity, determine
The caching probability of frame image；According to caching probability, it is determined whether caching frame image.Wherein, according to similarity, frame image is determined
The formula for caching probability can be as shown in following formula (1).
Wherein, P indicates caching probability；N indicates preset cache amount of images；N indicates that default longest caches frame number；R is indicated
Similarity.
In the present embodiment, when caching probability greater than predetermined probabilities threshold value, caching frame image is determined；When caching probability is less than
When equal to predetermined probabilities threshold value, not caching frame image is determined.In the present embodiment, if caching probability is greater than predetermined probabilities threshold value,
Determining frame image, there are the vehicles that corresponding similarity is greater than certain similarity threshold with previous frame image, so that it is determined that the vehicle
It is in motion process, therefore, it is necessary to caching frame images.If caching probability is less than or equal to predetermined probabilities threshold value, it is determined that frame
There is no the vehicles that corresponding similarity is greater than certain similarity threshold with previous frame image for image, it is determined that frame image is with before
One frame image is compared, and move vehicle is not present, and there is only parking vehicle or vehicle is not present, therefore, there is no need to caching frame figure
Picture.So as to which when non-parking area vehicle location occurs mobile, corresponding frame image is cached, so that it is guaranteed that violating the regulations
The accuracy of vehicle detection.
Further, frame image buffer storage specifically may be used by violation vehicle detection device to the process in the corresponding image library of vehicle
Think, includes the topography of vehicle when determining caching frame image, in getting frame image；Topography including vehicle is delayed
It is stored in the corresponding image library of vehicle.Wherein, when determining caching frame image, violation vehicle detection device can be from frame image
The topography including the vehicle is obtained, removal includes the topography of other vehicles, only by the topography including the vehicle
It is cached in the corresponding image library of vehicle, so that the amount of storage of image library is reduced, and in post-collection vehicle parameter information, into
One step reduces workload, improves the detection efficiency of violation vehicle.
Further, on the basis of the above embodiments, when the vehicle in frame image is blocked, this may be can't detect
Vehicle obtains the car information less than the vehicle, therefore, in order to reduce the vehicle fleet size for leaking identification in step 103, information of vehicles
In may include vehicle location information；Before step 104, the method can with the following steps are included: be directed to frame image,
In getting frame image in the location information and previous frame image of each vehicle each vehicle location information；For former frame
The location information of each vehicle in image whether there is vehicle within the scope of the corresponding position in judgment frame image；If in frame image
Corresponding position within the scope of be not present vehicle, then the image of vehicle in previous frame image is covered to the corresponding position in frame image
In range.Wherein, corresponding position range can be according to the movement speed of non-parking area vehicle and the time of consecutive frame image
Difference is determined.
In the present embodiment, for the location information of vehicle each in previous frame image, due to adopting between consecutive frame image
The collection time difference is very short, therefore, the information of vehicles present in previous frame image, one within the scope of the corresponding position of the frame image
As there are corresponding information of vehicles；If corresponding information of vehicles is not present within the scope of the corresponding position of the frame image, it is determined that
Vehicle within the scope of corresponding position is identified by leakage, therefore, the image of vehicle in previous frame image can be covered in frame image
Corresponding position within the scope of.Wherein, when specific covering, the characteristic information of vehicle in available previous frame image；To frame image
It is detected, obtains the characteristic information within the scope of corresponding position, specific covering position is determined according to characteristic information, and then carry out
Covering further increases the detection efficiency of violation vehicle to reduce the vehicle fleet size of leakage identification.
S105, determine whether vehicle is violation vehicle according to the corresponding image library of vehicle for each vehicle.
In the present embodiment, the process that violation vehicle detection device executes step 105 is specifically as follows, for each vehicle,
Obtain each frame image in corresponding image library；According to each frame image and corresponding acquisition time, stoppage of vehicle is judged
It whether is more than preset time threshold in the time of non-parking area；If stoppage of vehicle is when the time of non-parking area is more than default
Between threshold value, it is determined that vehicle is violation vehicle.
Further, after step 105, the method can using the following steps are included: when vehicle is violation vehicle,
Image detection successively is carried out to each image in the corresponding image library of vehicle, obtains the parameter information of vehicle in image, and
Confidence level；When in parameter information or the corresponding image library of vehicle for being greater than default confidence threshold value there are corresponding confidence level
When having carried out the amount of images of image recognition greater than preset quantity threshold value, the maximum parameter information of corresponding confidence level determines
For the parameter information of the vehicle.
In the present embodiment, violation vehicle detection device can successively be inputted each image in the corresponding image library of vehicle
Second image detection model obtains the parameter information and confidence level of each vehicle of the second image detection model output.Wherein,
Confidence level indicates integrity degree and the accuracy of the parameter information got.In the present embodiment, the second image detection model for example may be used
Think depth convolutional neural networks model.The training process of second image detection model for example can be that acquisition largely includes
The image of vehicle, and the parameter information and confidence level of each vehicle in image are obtained, obtain training sample data；Using training sample
Notebook data is trained the second initial image detection model, obtains trained second image detection model.
The violation vehicle detection method of the embodiment of the present invention, by the monitoring video flow for obtaining non-parking area；For prison
Every frame image in video flowing is controlled, image detection is carried out to frame image, the information of vehicles of each vehicle in getting frame image；By frame
Information of vehicles in image is compared with the information of vehicles of previous frame image in monitoring video flow, determines frame image and former frame
Same vehicle in image, and identical label is set for same vehicle；For each vehicle in frame image, according to frame figure
As in vehicle information of vehicles and previous frame image in vehicle information of vehicles, it is determined whether caching frame image, determine cache
When frame image, by frame image buffer storage into the corresponding image library of vehicle；For each vehicle, according to the corresponding image library of vehicle,
Determine whether vehicle is violation vehicle, amount of images to be treated when determining violation vehicle is acquired so as to reduce, is reduced
Workload under the premise of ensuring accuracy in detection improves the detection efficiency of violation vehicle.
Fig. 2 is a kind of structural schematic diagram of violation vehicle detection device provided in an embodiment of the present invention.As shown in Fig. 2, packet
It includes: obtaining module 21, detection module 22, comparison module 23, buffer process module 24 and determining module 25.
Wherein, module 21 is obtained, for obtaining the monitoring video flow of non-parking area；
Detection module 22, for carrying out image inspection to the frame image for every frame image in the monitoring video flow
It surveys, obtains the information of vehicles of each vehicle in the frame image；
Comparison module 23, for by the information of vehicles in the frame image and previous frame image in the monitoring video flow
Information of vehicles is compared, and determines the same vehicle in the frame image and the previous frame image, and be directed to the identical vehicle
The identical label of setting；
Buffer process module 24, each vehicle for being directed in the frame image, according to vehicle described in the frame image
Information of vehicles and the previous frame image described in vehicle information of vehicles, it is determined whether the frame image is cached, true
When caching the frame image surely, by the frame image buffer storage into the corresponding image library of the vehicle；
Determining module 25, for whether determining the vehicle according to the corresponding image library of the vehicle for each vehicle
For violation vehicle.
Violation vehicle detection device provided by the invention is specifically as follows hardware device, such as terminal device, background service
The software etc. installed on device etc. or hardware device.Violation vehicle detection device can with for monitoring each non-parking area
Camera connection, or background server corresponding with camera connection obtains the non-parking area that shoots of camera
Monitoring video flow.
In the present embodiment, every frame image in monitoring video flow can be inputted into the first image detection model, obtain first
The information of vehicles of each vehicle of image detection model output.Wherein, the first image detection model for example can be depth convolution
Neural network model.The training process of first image detection model for example can be, acquisition largely includes the image of vehicle, and
The location information and dimension information of vehicle in image are labeled, training sample data are obtained；Using training sample data
The first initial image detection model is trained, trained first image detection model is obtained.Wherein, in information of vehicles
It may include the location information and dimension information of vehicle.The location information of vehicle refers to the position of vehicle in the picture.Vehicle
Dimension information for example may include in following information any one or it is a variety of: height of car, vehicle width, Vehicle length
Deng.
Further, on the basis of the above embodiments, comparison module 23 is specifically used for, by the information of vehicles in frame image
Be compared with the information of vehicles of previous frame image in monitoring video flow, in judgment frame image and previous frame image with the presence or absence of pair
The dimension information difference answered is less than first threshold, and corresponding location information difference is less than two information of vehicles of second threshold；
If it exists, by the corresponding vehicle of two information of vehicles, it is determined as same vehicle.
Specifically, for each information of vehicles in frame image, by each vehicle in the information of vehicles and previous frame image
Information is compared, obtain the dimension information difference between each information of vehicles in the information of vehicles and previous frame image with
And location information difference；Corresponding dimension information difference is obtained less than first threshold, and corresponding location information difference is less than the
The information of vehicles of two threshold values；By the corresponding vehicle of information of vehicles vehicle corresponding with the information of vehicles in frame image, it is determined as
Same vehicle.
Further, on the basis of the above embodiments, buffer process module 24 specifically can be used for, in frame image
Each vehicle, calculate frame image in vehicle information of vehicles and the information of vehicles of vehicle in previous frame image between it is similar
Degree；According to similarity, the caching probability of frame image is determined；According to caching probability, it is determined whether caching frame image.
In the present embodiment, when caching probability greater than predetermined probabilities threshold value, caching frame image is determined；When caching probability is less than
When equal to predetermined probabilities threshold value, not caching frame image is determined.In the present embodiment, if caching probability is greater than predetermined probabilities threshold value,
Determining frame image, there are the vehicles that corresponding similarity is greater than certain similarity threshold with previous frame image, so that it is determined that the vehicle
It is in motion process, therefore, it is necessary to caching frame images.If caching probability is less than or equal to predetermined probabilities threshold value, it is determined that frame
There is no the vehicles that corresponding similarity is greater than certain similarity threshold with previous frame image for image, it is determined that frame image is with before
One frame image is compared, and move vehicle is not present, and there is only parking vehicle or vehicle is not present, therefore, there is no need to caching frame figure
Picture.So as to which when non-parking area vehicle location occurs mobile, corresponding frame image is cached, so that it is guaranteed that violating the regulations
The accuracy of vehicle detection.
Further, on the basis of the above embodiments, buffer process module 24 specifically can be used for, and determine caching frame
It include the topography of vehicle when image, in getting frame image；Topography including vehicle is cached to the corresponding figure of vehicle
As in library.Wherein, when determining caching frame image, violation vehicle detection device can be obtained from frame image including the vehicle
Topography, removal include the topography of other vehicles, and it is corresponding that the topography including the vehicle is only cached to vehicle
In image library, to reduce the amount of storage of image library, and in post-collection vehicle parameter information, it is further reduced workload,
Improve the detection efficiency of violation vehicle.
Further, on the basis of the above embodiments, determining module 25 specifically can be used for, and for each vehicle, obtain
Take each frame image in corresponding image library；According to each frame image and corresponding acquisition time, judge that stoppage of vehicle exists
Whether the time of non-parking area is more than preset time threshold；If stoppage of vehicle is more than preset time in the time of non-parking area
Threshold value, it is determined that vehicle is violation vehicle.
Further, on the basis of the above embodiments, the acquisition module 21 is also used in the vehicle be vehicle violating the regulations
When, successively in the corresponding image library of the vehicle each image carry out image detection, obtain described image described in vehicle
Parameter information and confidence level；
The determining module 25 is also used to be greater than the parameter information for presetting confidence threshold value there are corresponding confidence level,
It, will be corresponding or when having carried out the amount of images of image recognition in the corresponding image library of the vehicle and being greater than preset quantity threshold value
The maximum parameter information of confidence level, is determined as the parameter information of the vehicle.
In the present embodiment, violation vehicle detection device can successively be inputted each image in the corresponding image library of vehicle
Second image detection model obtains the parameter information and confidence level of each vehicle of the second image detection model output.Wherein,
Confidence level indicates integrity degree and the accuracy of the parameter information got.In the present embodiment, the second image detection model for example may be used
Think depth convolutional neural networks model.The training process of second image detection model for example can be that acquisition largely includes
The image of vehicle, and the parameter information and confidence level of each vehicle in image are obtained, obtain training sample data；Using training sample
Notebook data is trained the second initial image detection model, obtains trained second image detection model.
The violation vehicle detection device of the embodiment of the present invention, by the monitoring video flow for obtaining non-parking area；For prison
Every frame image in video flowing is controlled, image detection is carried out to frame image, the information of vehicles of each vehicle in getting frame image；By frame
Information of vehicles in image is compared with the information of vehicles of previous frame image in monitoring video flow, determines frame image and former frame
Same vehicle in image, and identical label is set for same vehicle；For each vehicle in frame image, according to frame figure
As in vehicle information of vehicles and previous frame image in vehicle information of vehicles, it is determined whether caching frame image, determine cache
When frame image, by frame image buffer storage into the corresponding image library of vehicle；For each vehicle, according to the corresponding image library of vehicle,
Determine whether vehicle is violation vehicle, and amount of images to be treated, reduces work when so as to reduce determining violation vehicle
It measures, under the premise of ensuring accuracy in detection, improves the detection efficiency of violation vehicle.
Further, when the vehicle in frame image is blocked, the vehicle may be can't detect, obtained less than the vehicle
Car information, therefore, in order to reduce the vehicle fleet size of leakage identification, in conjunction with reference Fig. 3, on the basis of embodiment shown in Fig. 2, vehicle
It may include the location information of vehicle in information；The device can also include: judgment module 26 and image processing module
27。
Wherein, the acquisition module 21 is also used to obtain the position of each vehicle in the frame image for the frame image
The location information of each vehicle in confidence breath and previous frame image；
The judgment module 26 judges the frame for the location information for each vehicle in the previous frame image
It whether there is vehicle within the scope of corresponding position in image；
Described image processing module 27 will when for vehicle to be not present within the scope of the corresponding position in the frame image
The image of vehicle described in the previous frame image covers within the scope of the corresponding position in the frame image.
Wherein, corresponding position range can be according to the movement speed of non-parking area vehicle and the time of consecutive frame image
Difference is determined.
In the present embodiment, for the location information of vehicle each in previous frame image, due to adopting between consecutive frame image
The collection time difference is very short, therefore, the information of vehicles present in previous frame image, one within the scope of the corresponding position of the frame image
As there are corresponding information of vehicles；If corresponding information of vehicles is not present within the scope of the corresponding position of the frame image, it is determined that
Vehicle within the scope of corresponding position is identified by leakage, therefore, the image of vehicle in previous frame image can be covered in frame image
Corresponding position within the scope of.Wherein, when specific covering, the characteristic information of vehicle in available previous frame image；To frame image
It is detected, obtains the characteristic information within the scope of corresponding position, specific covering position is determined according to characteristic information, and then carry out
Covering further increases the detection efficiency of violation vehicle to reduce the vehicle fleet size of leakage identification.
Fig. 4 is the structural schematic diagram of another violation vehicle detection device provided in an embodiment of the present invention.The violation vehicle
Detection device includes:
Memory 1001, processor 1002 and it is stored in the calculating that can be run on memory 1001 and on processor 1002
Machine program.
Processor 1002 realizes the violation vehicle detection method provided in above-described embodiment when executing described program.
Further, violation vehicle detection device further include:
Communication interface 1003, for the communication between memory 1001 and processor 1002.
Memory 1001, for storing the computer program that can be run on processor 1002.
Memory 1001 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-
Volatile memory), a for example, at least magnetic disk storage.
Processor 1002 realizes violation vehicle detection method described in above-described embodiment when for executing described program.
If memory 1001, processor 1002 and the independent realization of communication interface 1003, communication interface 1003, memory
1001 and processor 1002 can be connected with each other by bus and complete mutual communication.The bus can be industrial standard
Architecture (Industry Standard Architecture, referred to as ISA) bus, external equipment interconnection
(Peripheral Component, referred to as PCI) bus or extended industry-standard architecture (Extended Industry
Standard Architecture, referred to as EISA) bus etc..The bus can be divided into address bus, data/address bus, control
Bus processed etc..Only to be indicated with a thick line in Fig. 4, it is not intended that an only bus or a type of convenient for indicating
Bus.
Optionally, in specific implementation, if memory 1001, processor 1002 and communication interface 1003, are integrated in one
It is realized on block chip, then memory 1001, processor 1002 and communication interface 1003 can be completed mutual by internal interface
Communication.
Processor 1002 may be a central processing unit (Central Processing Unit, referred to as CPU), or
Person is specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC) or quilt
It is configured to implement one or more integrated circuits of the embodiment of the present invention.
The present invention also provides a kind of non-transitorycomputer readable storage mediums, are stored thereon with computer program, the journey
Violation vehicle detection method as described above is realized when sequence is executed by processor.
The present invention also provides a kind of computer program products, when the instruction processing unit in the computer program product executes
When, realize violation vehicle detection method as described above.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing custom logic function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.Such as, if realized with hardware in another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized: have for data-signal is realized the logic gates of logic function from
Logic circuit is dissipated, the specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
The embodiment of the present invention is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as to limit of the invention
System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of the invention
Type.
Claims (8)
1. a kind of violation vehicle detection method characterized by comprising
Obtain the monitoring video flow of non-parking area；
For every frame image in the monitoring video flow, image detection is carried out to the frame image, is obtained in the frame image
The information of vehicles of each vehicle；The information of vehicles includes: location information and dimension information；
Information of vehicles in the frame image is compared with the information of vehicles of previous frame image in the monitoring video flow, really
Same vehicle in the fixed frame image and the previous frame image, and identical label is set for the same vehicle；
For each vehicle in the frame image, according to the information of vehicles of vehicle described in the frame image and the former frame
The information of vehicles of vehicle described in image, it is determined whether the frame image is cached, it, will be described when determining the caching frame image
Frame image buffer storage is into the corresponding image library of the vehicle；
For each vehicle, according to the corresponding image library of the vehicle, determine whether the vehicle is violation vehicle；
For each vehicle in the frame image, according to the information of vehicles of vehicle described in the frame image and the former frame
The information of vehicles of vehicle described in image, it is determined whether cache the frame image, comprising:
For each vehicle in the frame image, calculate vehicle described in the frame image information of vehicles and the former frame
Similarity between the information of vehicles of vehicle described in image；
According to the similarity, the caching probability of the frame image is determined；Wherein, similarity is higher, and caching probability is smaller；
According to the caching probability, it is determined whether cache the frame image；
For each vehicle, according to the corresponding image library of the vehicle, determine whether the vehicle is violation vehicle, comprising:
For each vehicle, each frame image in corresponding image library is obtained；
According to each frame image and corresponding acquisition time, judge that the stoppage of vehicle is in the time of non-parking area
No is more than preset time threshold；
If the stoppage of vehicle is more than preset time threshold in the time of non-parking area, it is determined that the vehicle is vehicle violating the regulations
.
2. the method according to claim 1, wherein the information of vehicles includes the location information and size of vehicle
Information；
Information of vehicles in the frame image is compared with the information of vehicles of previous frame image in the monitoring video flow, really
Same vehicle in the fixed frame image and the previous frame image, comprising:
Information of vehicles in the frame image is compared with the information of vehicles of previous frame image in the monitoring video flow, is sentenced
The frame image that breaks with whether there is corresponding dimension information difference in the previous frame image is less than first threshold, and corresponding
Location information difference is less than two information of vehicles of second threshold；
If it exists, by the corresponding vehicle of described two information of vehicles, it is determined as same vehicle.
3. the method according to claim 1, wherein determine cache the frame image when, by the frame image
It is cached in the corresponding image library of the vehicle, comprising:
When determining the caching frame image, the topography in the frame image including the vehicle is obtained；
Topography including the vehicle is cached in the corresponding image library of the vehicle.
4. the method according to claim 1, wherein the information of vehicles includes the location information of vehicle；
For each vehicle in the frame image, according to the information of vehicles of vehicle described in the frame image and the former frame
The information of vehicles of vehicle described in image, it is determined whether before caching the frame image, further includes:
For the frame image, each vehicle in the location information and previous frame image of each vehicle is obtained in the frame image
Location information；
For the location information of each vehicle in the previous frame image, judge be within the scope of the corresponding position in the frame image
It is no that there are vehicles；
If vehicle is not present within the scope of the corresponding position in the frame image, by the figure of vehicle described in the previous frame image
As covering within the scope of the corresponding position in the frame image.
5. the method according to claim 1, wherein it is described be directed to each vehicle, it is corresponding according to the vehicle
Image library, after determining whether the vehicle is violation vehicle, further includes:
When the vehicle is violation vehicle, image inspection successively is carried out to each image in the corresponding image library of the vehicle
It surveys, obtains the parameter information and confidence level of vehicle described in described image；
When in parameter information or the corresponding image library of the vehicle for being greater than default confidence threshold value there are corresponding confidence level
When having carried out the amount of images of image recognition greater than preset quantity threshold value, the maximum parameter information of corresponding confidence level determines
For the parameter information of the vehicle.
6. a kind of violation vehicle detection device characterized by comprising
Module is obtained, for obtaining the monitoring video flow of non-parking area；
Detection module, for carrying out image detection to the frame image, obtaining for every frame image in the monitoring video flow
The information of vehicles of each vehicle in the frame image；The information of vehicles includes: location information and dimension information；
Comparison module, for believing the vehicle of previous frame image in the information of vehicles and the monitoring video flow in the frame image
Breath is compared, and determines the same vehicle in the frame image and the previous frame image, and be arranged for the same vehicle
Identical label；
Buffer process module, each vehicle for being directed in the frame image, according to the vehicle of vehicle described in the frame image
The information of vehicles of vehicle described in information and the previous frame image, it is determined whether cache the frame image, cached determining
When the frame image, by the frame image buffer storage into the corresponding image library of the vehicle；
Determining module, for determining whether the vehicle is violating the regulations according to the corresponding image library of the vehicle for each vehicle
Vehicle；
The buffer process module is specifically used for,
For each vehicle in the frame image, calculate vehicle described in the frame image information of vehicles and the former frame
Similarity between the information of vehicles of vehicle described in image；
According to the similarity, the caching probability of the frame image is determined；Wherein, similarity is higher, and caching probability is smaller；
According to the caching probability, it is determined whether cache the frame image；
The determining module is specifically used for,
For each vehicle, each frame image in corresponding image library is obtained；
According to each frame image and corresponding acquisition time, judge that the stoppage of vehicle is in the time of non-parking area
No is more than preset time threshold；
If the stoppage of vehicle is more than preset time threshold in the time of non-parking area, it is determined that the vehicle is vehicle violating the regulations
.
7. a kind of violation vehicle detection device characterized by comprising
Memory, processor and storage are on a memory and the computer program that can run on a processor, which is characterized in that institute
It states when processor executes described program and realizes such as violation vehicle detection method as claimed in any one of claims 1 to 5.
8. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the program quilt
Such as violation vehicle detection method as claimed in any one of claims 1 to 5 is realized when processor executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075372.5A CN109147341B (en) | 2018-09-14 | 2018-09-14 | Violation vehicle detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075372.5A CN109147341B (en) | 2018-09-14 | 2018-09-14 | Violation vehicle detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109147341A CN109147341A (en) | 2019-01-04 |
| CN109147341B true CN109147341B (en) | 2019-11-22 |
Family
ID=64825505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811075372.5A Active CN109147341B (en) | 2018-09-14 | 2018-09-14 | Violation vehicle detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109147341B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948436B (en) * | 2019-02-01 | 2020-12-08 | 深兰科技（上海）有限公司 | Method and device for monitoring vehicles on road |
| CN110020608A (en) * | 2019-03-15 | 2019-07-16 | 北京筑梦园科技有限公司 | A kind of vehicle identification method, equipment, system and parking charge system |
| CN112017441B (en) * | 2019-05-28 | 2022-03-08 | 浙江宇视科技有限公司 | Vehicle traffic behavior detection method, device, equipment and storage medium |
| CN110491132B (en) * | 2019-07-11 | 2022-04-08 | 平安科技（深圳）有限公司 | Vehicle illegal parking detection method and device based on video frame picture analysis |
| CN112309134B (en) * | 2019-07-29 | 2022-12-16 | 富士通株式会社 | Vehicle speed detection method and device |
| CN110491135B (en) * | 2019-08-20 | 2021-10-22 | 深圳市商汤科技有限公司 | Method and related device for detecting illegal parking |
| CN113378602A (en) * | 2020-03-10 | 2021-09-10 | 顺丰科技有限公司 | Method and device for detecting illegal stacking of articles, server and storage medium |
| CN113012439B (en) * | 2021-03-29 | 2022-06-21 | 北京百度网讯科技有限公司 | Vehicle detection method, device, equipment and storage medium |
| CN112991742B (en) * | 2021-04-21 | 2021-08-20 | 四川见山科技有限责任公司 | Visual simulation method and system for real-time traffic data |
| CN112990114B (en) * | 2021-04-21 | 2021-08-10 | 四川见山科技有限责任公司 | Traffic data visualization simulation method and system based on AI identification |
| CN114359875B (en) * | 2022-03-17 | 2022-05-17 | 成都考拉悠然科技有限公司 | Vehicle effective snapshot method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11272987A (en) * | 1998-03-25 | 1999-10-08 | Fuji Electric Co Ltd | Automatic detection and notification system for illegal parking vehicle |
| CN103093194A (en) * | 2013-01-07 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Breach of regulation vehicle detection method and device based on videos |
| CN103116985A (en) * | 2013-01-21 | 2013-05-22 | 信帧电子技术（北京）有限公司 | Detection method and device of parking against rules |
| CN105046966A (en) * | 2015-05-08 | 2015-11-11 | 天津大学 | System and method for automatically detecting illegal parking behaviors in drop-off areas |
| CN105809975A (en) * | 2016-05-30 | 2016-07-27 | 北京精英智通科技股份有限公司 | Abnormal parking judgment method and abnormal parking judgment device |
| CN106127143A (en) * | 2016-06-23 | 2016-11-16 | 昆明理工大学 | A kind of highway parking offense detection method |
| CN107305627A (en) * | 2016-04-22 | 2017-10-31 | 杭州海康威视数字技术股份有限公司 | A kind of automobile video frequency monitoring method, server and system |
| CN108305466A (en) * | 2018-03-13 | 2018-07-20 | 北京智芯原动科技有限公司 | Roadside Parking detection method and device based on vehicle characteristics analysis |
-
2018
- 2018-09-14 CN CN201811075372.5A patent/CN109147341B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11272987A (en) * | 1998-03-25 | 1999-10-08 | Fuji Electric Co Ltd | Automatic detection and notification system for illegal parking vehicle |
| CN103093194A (en) * | 2013-01-07 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Breach of regulation vehicle detection method and device based on videos |
| CN103116985A (en) * | 2013-01-21 | 2013-05-22 | 信帧电子技术（北京）有限公司 | Detection method and device of parking against rules |
| CN105046966A (en) * | 2015-05-08 | 2015-11-11 | 天津大学 | System and method for automatically detecting illegal parking behaviors in drop-off areas |
| CN107305627A (en) * | 2016-04-22 | 2017-10-31 | 杭州海康威视数字技术股份有限公司 | A kind of automobile video frequency monitoring method, server and system |
| CN105809975A (en) * | 2016-05-30 | 2016-07-27 | 北京精英智通科技股份有限公司 | Abnormal parking judgment method and abnormal parking judgment device |
| CN106127143A (en) * | 2016-06-23 | 2016-11-16 | 昆明理工大学 | A kind of highway parking offense detection method |
| CN108305466A (en) * | 2018-03-13 | 2018-07-20 | 北京智芯原动科技有限公司 | Roadside Parking detection method and device based on vehicle characteristics analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109147341A (en) | 2019-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109147341B (en) | Violation vehicle detection method and device | |
| WO2019105342A1 (en) | Method and apparatus for detecting fake license plates of vehicles, readable storage medium, and electronic device | |
| CN111862228B (en) | Occlusion detection method, system, computer device and readable storage medium | |
| CN112330601A (en) | Parking detection method, device, equipment and medium based on fisheye camera | |
| US8687063B2 (en) | Method for predicting lane line and lane departure warning system using the same | |
| CN109670383B (en) | Video shielding area selection method and device, electronic equipment and system | |
| CN107633237B (en) | Image background segmentation method, device, equipment and medium | |
| CN110276258A (en) | A kind of method and system identifying vehicle appearance | |
| CN112633255B (en) | Target detection method, device and equipment | |
| CN107748882B (en) | Lane line detection method and device | |
| CN112328822B (en) | Picture pre-marking method and device and terminal equipment | |
| CN107333107A (en) | Monitor image pickup method, device and its equipment | |
| CN111860590B (en) | License plate voting method, license plate voting device, computer equipment and storage medium | |
| US20140037141A1 (en) | Method for evaluating a plurality of time-offset pictures, device for evaluating pictures, and monitoring system | |
| CN110298302B (en) | Human body target detection method and related equipment | |
| CN116363495A (en) | Scene change detection method, device, computer equipment and storage medium | |
| CN112654999B (en) | Method and device for determining labeling information | |
| CN110796129A (en) | Text line region detection method and device | |
| CN109766799B (en) | Parking space recognition model training method and device and parking space recognition method and device | |
| CN116051373A (en) | Image stitching method, image stitching device and terminal equipment | |
| CN112188283B (en) | Method, device and equipment for cutting video and storage medium | |
| CN111738185B (en) | Target identification method, device and equipment | |
| CN112818918B (en) | Living body detection method, living body detection device, electronic equipment and storage medium | |
| CN112906651B (en) | Target detection method and device | |
| CN112016514B (en) | Traffic sign recognition method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |