CN110490127A - Close rule recognition methods and device, storage medium, electronic device in position - Google Patents
Close rule recognition methods and device, storage medium, electronic device in position Download PDFInfo
- Publication number
- CN110490127A CN110490127A CN201910755330.4A CN201910755330A CN110490127A CN 110490127 A CN110490127 A CN 110490127A CN 201910755330 A CN201910755330 A CN 201910755330A CN 110490127 A CN110490127 A CN 110490127A
- Authority
- CN
- China
- Prior art keywords
- stop position
- target
- target vehicle
- image
- specified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000004590 computer program Methods 0.000 claims description 19
- 230000007613 environmental effect Effects 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 235000014676 Phragmites communis Nutrition 0.000 description 1
- 241000669244 Unaspis euonymi Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the present disclosure provides a kind of position and closes rule recognition methods and device, storage medium, electronic device, the described method includes: passing through the image that the image capture device installed on target vehicle acquires target vehicle position in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs；According to the target stop position of image recognition target vehicle；By judging whether target stop position is located at specified docks, determine whether target stop position is to close rule stop position.Solve the problems, such as can not precisely identify whether shared vehicle stopping place is suitable in the prior art.
Description
Technical field
This disclosure relates to which technical field of data processing, closes rule recognition methods and device in particular to a kind of position, deposits
Storage media, electronic device.
Background technique
The shared vehicles of market circulation at present, generally by its internal global positioning system (Global installed
Positioning System, referred to as GPS) or Inertial Measurement Unit (Inertial Measurement Unit, referred to as
IMU stop position) is identified.But this recognition methods precision is not high, can not precisely identify whether the shared vehicles are stopped
In suitable place.
For in the related technology, can not precisely identify the whether suitable problem in shared vehicle stopping place, at present still
There is not reasonable solution.
Summary of the invention
The embodiment of the present disclosure provides a kind of position and closes rule recognition methods and device, storage medium, electronic device, at least
Solve the problems, such as can not precisely identify whether shared vehicle stopping place is suitable in the related technology.
According to one embodiment of the disclosure, a kind of position conjunction rule recognition methods is provided, comprising: detecting for referring to
In the case where showing the stop instruction that target vehicle has been stopped, set by the Image Acquisition installed on the target vehicle
The standby image for acquiring the target vehicle position；Identify that the target of the target vehicle is stopped according to described image
By position；By judging whether the target stop position is located at specified docks, whether the target stop position is determined
Stop position is advised to close.
Optionally, the target stop position that the target vehicle is identified according to described image includes: to extract institute
State the first characteristics of image in image；The first image feature is inputted into the first location model, to identify that the target is stopped
Position.
Optionally, after the target stop position for identifying the target vehicle according to described image, further includes: root
The environmental parameter of the target stop position is identified according to described image, wherein the environmental parameter includes at least following one: week
Whether side is blocked with the presence or absence of building, periphery whether there is communal facility, be located in the range of the specified docks.
Optionally, described by judging whether the target stop position is located at specified docks, determine the target
It includes: when the environmental parameter of the target stop position meets preset rule that whether stop position, which is conjunction rule stop position,
When, determine that the target stop position is located at the specified docks, and then determine that the target stop position is to close rule to stop
By position；When the environmental parameter of the target stop position is unsatisfactory for preset rule, determine that the target stops position
It sets and is not located at the specified docks, and then determine that the target stop position is irregularity stop position.
Optionally, the determination target stop position be irregularity stop position after, the method also includes: hold
The operation of row at least one of: the irregularity stop position is sent to server；Information warning is sent, wherein the police
Show that information stops position for prompting the target stop position for irregularity stop position, and for target described in tip distance
Set the specified docks in specified range.
Optionally, the image capture device by installing on the target vehicle acquires the target traffic work
The image of tool position includes: the video image and/or photograph for acquiring target vehicle position within a predetermined period of time
Picture, wherein the target vehicle is the shared vehicles.
According to another embodiment of the present disclosure, a kind of position conjunction rule recognition methods is additionally provided, comprising: detecting use
In the case where the stop instruction that instruction target vehicle has been stopped, adopted by the image installed on the target vehicle
Collection equipment acquires the image of the target vehicle position；Described image is sent to server, so that the service
Device identifies the target stop position of the target vehicle according to described image；Receive the target that the server returns
Stop position；By judging whether the target stop position is located at specified docks, determine that the target stop position is
It is no to advise stop position to close.
According to another embodiment of the present disclosure, a kind of position conjunction rule recognition methods is additionally provided, comprising: obtain target and hand over
The image that logical tool is sent, wherein described image is the target vehicle in the case where detecting stop instruction, is passed through
The image of the target vehicle position for the image capture device acquisition installed on the target vehicle, it is described
Stop instruction is used to indicate the target vehicle and has stopped；The target of the target vehicle is identified according to described image
Stop position；The target stop position that will identify that is sent to the target vehicle, so that the target traffic work
Tool judges whether the target stop position is located at specified docks, and determines whether the target stop position is to close rule
Stop position.
Optionally, the target stop position that the target vehicle is identified according to described image includes: to extract institute
State the second characteristics of image in image；Second characteristics of image is inputted into the second location model, to identify that the target is stopped
Position.
According to another embodiment of the present disclosure, a kind of position conjunction rule identification device is additionally provided, comprising: the first acquisition mould
Block, for passing through the target traffic in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image capture device installed on tool acquires the image of the target vehicle position；First identification module, is used for
The target stop position of the target vehicle is identified according to described image；First determining module, for by described in judgement
Whether target stop position is located at specified docks, determines whether the target stop position is to close rule stop position.
According to another embodiment of the present disclosure, a kind of position conjunction rule identification device is additionally provided, comprising: the second acquisition mould
Block, for passing through the target traffic in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image capture device installed on tool acquires the image of the target vehicle position；First sending module, is used for
Described image is sent to server, so that the server identifies that the target of the target vehicle is stopped according to described image
By position；Receiving module, the target stop position returned for receiving the server；Second determining module, for leading to
It crosses and judges whether the target stop position is located at specified docks, determine whether the target stop position is to close rule to stop
Position.
According to another embodiment of the present disclosure, a kind of position conjunction rule identification device is additionally provided, comprising: module is obtained,
For obtaining the image of target vehicle transmission, wherein described image is that the target vehicle is detecting that stop refers to
In the case where order, where the target vehicle acquired by the image capture device installed on the target vehicle
The image of position, the stop instruction are used to indicate the target vehicle and have stopped；Second identification module, for according to institute
State the target stop position of target vehicle described in image recognition；Second sending module, the target for will identify that
Stop position is sent to the target vehicle so that the target vehicle judge the target stop position whether position
In specified docks, and determine whether the target stop position is to close rule stop position.
According to another embodiment of the present disclosure, a kind of storage medium is additionally provided, meter is stored in the storage medium
Calculation machine program, wherein the computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
According to another embodiment of the present disclosure, a kind of electronic device, including memory and processor are additionally provided, it is special
Sign is, computer program is stored in the memory, and the processor is arranged to run the computer program to hold
Step in row any of the above-described embodiment of the method.
Rule recognition methods and device, storage medium, electronic device are closed by the position that the embodiment of the present disclosure provides, is being detected
In the case where being used to indicate the stop instruction that target vehicle has been stopped, adopted by the image installed on target vehicle
Collect the image of equipment acquisition target vehicle position；According to the target stop position of image recognition target vehicle；
By judging whether target stop position is located at specified docks, determine whether target stop position is to close rule stop position,
Then the image that the image capture device carried by target vehicle acquires position is identified, according in image
The content of display intuitively determines whether current stop position meets the rule of specified docks, and then determines whether to close rule
Position solves the problems, such as can not precisely identify whether shared vehicle stopping place is suitable, improves needle in the prior art
To the precision of shared vehicle stopping position identification.
Detailed description of the invention
Attached drawing described herein is used to provide further understanding of the disclosure, constitutes part of this application, this public affairs
The illustrative embodiments and their description opened do not constitute the improper restriction to the disclosure for explaining the disclosure.In the accompanying drawings:
Fig. 1 is the hardware configuration frame that the mobile terminal of rule recognition methods is closed in a kind of optional position of the embodiment of the present disclosure
Figure；
Fig. 2 is that the flow chart of rule recognition methods is closed in a kind of optional position of the embodiment of the present disclosure；
Fig. 3 is that the flow chart of rule recognition methods is closed in the optional position of another kind of the embodiment of the present disclosure；
Fig. 4 is that the flow chart of rule recognition methods is closed in the optional position of another kind of the embodiment of the present disclosure；
Fig. 5 is that the flow chart of rule recognition methods is closed in the optional position of another kind of the embodiment of the present disclosure；
Fig. 6 is the structural block diagram that rule identification device is closed according to a kind of optional position of the embodiment of the present disclosure；
Fig. 7 is the structural block diagram that rule identification device is closed according to the optional position of another kind of the embodiment of the present disclosure；
Fig. 8 is the structural block diagram that rule identification device is closed according to the optional position of another kind of the embodiment of the present disclosure.
Specific embodiment
The disclosure is described in detail below with reference to attached drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
It should be noted that the specification and claims of the disclosure and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.
Embodiment 1
Rule recognition methods embodiment is closed in position provided by the embodiment of the present application one can be in mobile terminal, terminal
Or it is executed in similar arithmetic unit.For running on mobile terminals, Fig. 1 is that a kind of position of the embodiment of the present disclosure is closed
Advise the hardware block diagram of the mobile terminal of recognition methods.As shown in Figure 1, mobile terminal 10 may include one or more (Fig. 1
In only show one) (processor 102 can include but is not limited to Micro-processor MCV or programmable logic device to processor 102
The processing unit of FPGA etc.) and memory 104 for storing data, optionally, above-mentioned mobile terminal can also include being used for
The transmission device 106 and input-output equipment 108 of communication function.It will appreciated by the skilled person that shown in FIG. 1
Structure is only to illustrate, and does not cause to limit to the structure of above-mentioned mobile terminal.For example, mobile terminal 10, which may also include, compares Fig. 1
Shown in more perhaps less component or with the configuration different from shown in Fig. 1.
Memory 104 can be used for storing computer program, for example, the software program and module of application software, such as this public affairs
The corresponding computer program of acquisition methods of the scheduled throughput in embodiment is opened, processor 102 is stored in storage by operation
Computer program in device 104 realizes above-mentioned method thereby executing various function application and data processing.Memory
104 may include high speed random access memory, may also include nonvolatile memory, and such as one or more magnetic storage device dodges
It deposits or other non-volatile solid state memories.In some instances, memory 104 can further comprise relative to processor
102 remotely located memories, these remote memories can pass through network connection to mobile terminal 10.The example of above-mentioned network
Including but not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Transmitting device 106 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of mobile terminal 10 provide.In an example, transmitting device 106 includes a Network adaptation
Device (Network Interface Controller, referred to as NIC), can be connected by base station with other network equipments to
It can be communicated with internet.In an example, transmitting device 106 can for radio frequency (Radio Frequency, referred to as
RF) module is used to wirelessly be communicated with internet.
The embodiment of the present disclosure provides a kind of position conjunction rule recognition methods.Fig. 2 is that one kind of the embodiment of the present disclosure is optional
The flow chart of rule recognition methods is closed in position, as shown in Fig. 2, this method comprises:
Step S202 passes through mesh in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image for the image capture device acquisition target vehicle position installed on the mark vehicles；
Step S204, according to the target stop position of image recognition target vehicle；
Step S206 determines that target stop position is by judging whether target stop position is located at specified docks
It is no to advise stop position to close.
Led to by the above method in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
Cross the image for the image capture device acquisition target vehicle position installed on target vehicle；According to image recognition
The target stop position of target vehicle；By judging whether target stop position is located at specified docks, target is determined
Whether stop position is to close rule stop position, i.e., acquires position by the image capture device that target vehicle carries
Then image is identified, intuitively determine whether current stop position meets specified stop area according to the content shown in image
The rule in domain, and then determine whether that shared vehicle stopping can not precisely be identified in the prior art by solving to close and advise position
The whether suitable problem in place improves the precision for shared vehicle stopping position identification.
Optionally, the target vehicle in the embodiment of the present disclosure can include but is not limited to arbitrarily share the vehicles,
For example, shared bicycle, shared automobile, shared electric vehicle, shared scooter etc..
Optionally, in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs, pass through target
The image for the image capture device acquisition target vehicle position installed on the vehicles can be by following steps reality
Existing: after user terminates using target vehicle, instruction is stopped in triggering, and stop instruction herein can be user and hand over target
Automatic trigger after logical tool stops working or locks can also actively be triggered by user.The single-chip microcontroller being arranged inside target vehicle
Or chip, after detecting stop instruction, triggers the image capture device installed on target vehicle and taken pictures or recorded a video, this
The camera lens at place can be set to wide-angle lens or the deeper camera lens of the depth of field, acquire the image information of surrounding enviroment as much as possible.
Optionally, it can be realized by following steps according to the target stop position of image recognition target vehicle:
S1 extracts the first characteristics of image in image；
First characteristics of image is inputted the first location model, to identify target stop position by S2.
The first location model herein can be any two sorting algorithms model.Its sensing inputted as target vehicle
Device data, the GPS data of the image including but not limited to shot and current stop position export as sentencing between 0 to 1
Determine result.It should be noted that pass through that the first location model exports as a result, can be the target stop position identified,
It can be the judging result whether target stop position is located at specified docks, be also possible to whether target stop position is conjunction
The judging result for advising stop position can also export probability value or target of the target stop position positioned at specified docks and stop
It is the probability value for closing rule stop position by position, conjunction rule stop position, this public affairs is then judged whether it is according to obtained probability value
Embodiment is opened not limit this.
The first location model herein can by support vector machines (Support Vector Machine, referred to as
SVM) the realization of algorithm: preparation training data first, i.e., it is known it is reasonable or unreasonable park photo and its judgement, scheming
Feature detection is carried out as in, and using detection methods such as such as harris, DOG, feature describing word is being extracted to feature locations, such as
SIFT, Brief etc., the feature description of every picture construction bag of words (Bag of words), corresponding its determine as a result, using svm
It is corresponding with judgement that training returns out feature.When obtaining a new picture every time, feature extraction is carried out to picture first, is then made
Conjunction rule stand is determine whether with the classifier of SVM.The advantage of Svm algorithm is that operation is very fast, therefore is suitble to hand in target
Logical tool interior operation, committed memory is smaller, and operation is fast, can obtain a result in time.
Wherein, Harris Corner Detection principle is to calculate grey scale change value in the picture using mobile window, wherein closing
Key process includes being converted into gray level image, calculating difference image, Gaussian smoothing, calculate local extremum, confirmation angle point.DOG
(Difference of Gaussian) is the method for gray level image enhancing and Corner Detection.SIFT, i.e. scale invariant feature become
(Scale-invariant feature transform, referred to as SIFT) is changed, is retouched for one kind of field of image processing
It states.This description has scale invariability, can detect key point in the picture, is a kind of local feature description's.BRIEF is
In the article of one in 2010 entitled " BRIEF:Binary Robust Independent Elementary Features "
It proposes, BRIEF is that the characteristic point having detected that is described, it is a kind of binary-coded description, has abandoned utilization
The conventional method of area grayscale histogram Expressive Features point greatly accelerates the speed of feature descriptor foundation, while also pole
The big time for reducing characteristic matching.
Bag of words (Bag-of-words model) are to be simplified under natural language processing and information retrieval (IR)
Expression model, in information retrieval, Bag of words model assumes for a text, ignore its word order and grammer,
It is only regarded as a set of words, or perhaps a combination of word by syntax, and the appearance of each word is independent in text
, whether occur independent of other words, selects a vocabulary not by the shadow of previous sentence in any one position in other words
It is loud and independent choice.
Bag of words describes to have in every one kind it is to be understood that assuming to have 5 class images to indicate the feature of image
10 width images, being divided into patch to every piece image first in this way (can be rigidity segmentation to be also possible to be based on key as SIFT
Point detection), in this way, each image just indicates that each patch is indicated with a feature vector by many patch,
, it is assumed that being indicated with Sift, piece image might have hundreds and thousands of a patch, the dimension of each patch feature vector for we
Number 128.Next building Bag of words model, it is assumed that the Size of Dictionary dictionary is 100, that is, has 100 words.That
All patch can be clustered with K-means algorithm, k=100 obtains each when k-means being waited to restrain
Cluster last mass center, then this 100 mass centers (dimension 128) are exactly 100 words of dictionary Reed, dictionary creation is completed.
After dictionary creation is complete, the histogram h that the initial value of 100 bin is 0 is first initialized.Every piece image has many patch,
These patch and the distance with each mass center are calculated again, look at that each patch is nearest from which mass center, then directly
Corresponding bin just adds 1 in side figure h, after all patches of diagram picture then have been calculated, has just obtained a bin=
100 histogram, is then normalized, and indicates diagram picture with the vector of this 100 dimension.All images are calculated and are completed
Later, so that it may carry out taxonomic clustering training and predict.
Whether rationally the first location model herein can also realize by convolutional neural networks, first preparing pictures and its
The judgement parked as a result, design convolutional neural networks, such as vgg, resnet, mobilenet etc., finally extract network
Judgement label head whether feature correspondence one is parked rationally, returns out the predicted value between 0 to 1.
Rationally determine to be a classical image classification problem due to parking, i.e. corresponding one of image whether two points
Class determine as a result, can be used there are many more other, general machine learning method determined that the embodiment of the present disclosure is to this
It is not construed as limiting.
Optionally, it can also be realized by following steps according to the target stop position of image recognition target vehicle:
Server is sent an image to, so that server identifies the target stop position of target vehicle in image.
It should be noted that identifying to image can be carried out by following three kinds of modes:
1, the algorithm a0 affixed one's name to by target vehicle internal body determines whether reasonable stand, obtains determining knot
Fruit d0.
2. image is uploaded to cloud server by wireless network, rational stop is determine whether by algorithm a1 beyond the clouds
Position is put, obtains determining d1.
3. image is observed by the naked eye under the auxiliary information of GPS by backstage user, with reference to preset rules, judgement is
No is rational position, result d2.
Wherein, algorithm a0 and algorithm a1 can be used by machine learning algorithm realize, including above-mentioned SVM algorithm and volume
Product neural network model, the embodiment of the present disclosure are not construed as limiting this.In order to preferably match application scenarios, algorithm a0 be can choose
Arithmetic speed is fast and the algorithm not high to required precision, algorithm a1 can choose arithmetic speed compared with the slow but higher algorithm of precision.
It can choose different decision procedures according to different business scenario demands.For example, when stand is unreasonable then
It can not normally return the car when terminating stroke, determine to guarantee quickly to provide as a result, can be made with employing mode 1 using result d0
Judgement.When user it is one or many it is unreasonable park target vehicle, need statistical data to decide whether to reduce its credit rating
When, accuracy rate height but slow mode 2 can be used, judged using result d1.When user thinks orderly shutdown,
But when being determined as that the dispute of unreasonable parking determines, human assistance judgement can be carried out with employing mode 3, be made and being sentenced using result d2
It is disconnected.
Wherein result d2 is generally more accurate, but quantity is few, and at high cost, decision rule needs to determine by experience.Example
Such as do not determine that person first has to determine the region that scooter is parked by GPS, using map, personal experience etc., is obtaining the region just
(such as region is specified in roadside) and the improper judgment basis parked often are parked, then by where target vehicle in image
Position, determined.
In the algorithm of mode 1 and mode 2, the true value that result d2 is used as verifying can be used, carry out machine learning
Training, pass through continuous data accumulation, improve d0 and d1 accuracy.
Two kinds of d0 and d1 as a result, due to computing resource difference, can also there is a situation where that d1 is more accurate compared with d0, it is general same
When consider that the result of d0, d1 are done and determined, but when difficult or when delay is larger there are network, can also only use the result of d0.
D0, d1's as a result, further comprising the confidence level to judgement in above-mentioned steps.It can be determined according to the confidence level of d0
The result of d1 whether is waited to be judged.When the confidence level of d1 is relatively low, result d2 can be obtained by artificial judgment, thus
It is easier to provide with understanding of the machine learning for difficult scene.
Optionally, after the target stop position according to image recognition target vehicle, further includes: known according to image
The environmental parameter of other target stop position, wherein environmental parameter includes at least following one: periphery hides with the presence or absence of building
Whether gear, periphery whether there is communal facility, are located in the range of specified docks；The environmental parameter of target stop position is full
When foot is preset regular, determine that the mark stop position is located at specified docks.
Optionally, described by judging whether the target stop position is located at specified docks, determine the target
It includes: by judging whether the environmental parameter of the target stop position meets in advance that whether stop position, which is conjunction rule stop position,
The rule of setting, determines whether the target stop position is located at the specified docks；When the target stop position
When environmental parameter meets preset rule, determine that the target stop position is located at the specified docks, and then really
The fixed target stop position is to close rule stop position；When the environmental parameter of the target stop position be unsatisfactory for it is preset
It when regular, determines that the target stop position is not located at the specified docks, and then determines that the target stop position is
Irregularity stop position.
Optionally, the determination target stop position be irregularity stop position after, the method also includes: hold
The operation of row at least one of: the irregularity stop position is sent to server；Information warning is sent, wherein the police
Show that information stops position for prompting the target stop position for irregularity stop position, and for target described in tip distance
Set the specified docks in specified range.
If surrounding enviroment darkness is narrow, it may illustrate that stop position in more hidden place, belongs to stopping for irregularity
By position.If docks are broad bright, but periphery does not have any communal facility, may illustrate that stop position is excessively remote,
Also belong to the stop position of irregularity.
Stop range can also be marked off according to GPS data, docks can be set with pre-set specified docks
More eye-catching mark is set, as long as target vehicle, which rests within the scope of specified docks, to be detected by GPS, i.e.,
Make can't detect, can also be identified by the mark for including in image.
It should be noted that information warning can be directly sent to the client of user by target vehicle, herein
Client can be the client for the linking objective vehicles, is also possible to target vehicle and sends information warning to
Server, the client of user is sent to by server, and the embodiment of the present disclosure does not limit this.
Alternately through the image capture device acquisition target vehicle position installed on target vehicle
Image includes: the video image and/or photograph image for acquiring target vehicle position within a predetermined period of time, wherein
Target vehicle is the shared vehicles.
Fig. 3 is that the flow chart of rule recognition methods is closed in a kind of another optional position of the embodiment of the present disclosure, as shown in figure 3, should
Method includes:
Step S302 passes through mesh in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image for the image capture device acquisition target vehicle position installed on the mark vehicles；
Step S304, sends an image to server, so that target of the server according to image recognition target vehicle
Stop position；
Step S306 receives the target stop position that server returns；
Step S308 determines that target stop position is by judging whether target stop position is located at specified docks
It is no to advise stop position to close.
Fig. 4 is that the flow chart of rule recognition methods is closed in the optional position of another kind of the embodiment of the present disclosure, as shown in figure 4, should
Method includes:
Step S402 obtains the image that target vehicle is sent, wherein image is that target vehicle stops detecting
In the case where instruction, pass through the target vehicle position for the image capture device acquisition installed on target vehicle
Image, stop instruction and be used to indicate target vehicle and stopped；
Step S404, according to the target stop position of image recognition target vehicle；
Step S406, the target stop position that will identify that is sent to target vehicle, so that target vehicle is sentenced
Whether disconnected target stop position is located at specified docks, and determines whether institute's target stop position is to close rule stop position.
It optionally, include: the second figure extracted in image according to the target stop position of image recognition target vehicle
As feature；The second characteristics of image of institute is inputted into the second location model, to identify target stop position.The second location model herein
Algorithm identical with the first location model can be used, the content having been noted above is not repeated herein.It should be noted that logical
It crosses that the second location model exports as a result, can be the target stop position identified, whether is also possible to target stop position
Judging result positioned at specified docks is also possible to whether target stop position is the judging result for closing rule stop position,
That is, image recognition processes and the deterministic process of conjunction rule stop position can be executed in server side, the embodiment of the present disclosure is to this
Without limitation.If the second location model exports the result is that " whether target stop position is located at the judgement knot of specified docks
This result is directly sent to target vehicle by fruit ", if the output of the second location model is the result is that " target stop position is
The no judging result to close rule stop position ", directly sends target vehicle for this result, the second location model can also be defeated
Target stop position is located at the probability value of specified docks out or target stop position is the probability value for closing rule stop position,
Then the probability value of output is sent to target vehicle.
Interactive process between target vehicle and server in order to better understand is illustrated in conjunction with Fig. 5.Figure
5 be the flow chart that rule recognition methods is closed according to the optional position of another kind of the embodiment of the present disclosure, as shown in figure 5, this method packet
It includes:
S501 triggers a stop for target vehicle 52 by user 50 and instructs；
S502 after target vehicle 52 receives stop instruction, acquires mesh using the image capture device of itself installation
Mark the image of vehicles position；
S503, target vehicle 52 send an image to server 54；
S504, server 54 is according to the target stop position of image recognition target vehicle 52；
S505, the target stop position that server 54 will identify that are sent to target vehicle 52；
S506, target vehicle 52 determine target by judging whether target stop position is located at specified docks
Whether stop position is to close rule stop position；
S507 after target vehicle 52 identifies result, can stop position if it is closing to advise to user 50 1 feedbacks
It sets, executes and stop instruction, complete the process for using of stop and the target end vehicles, if it is irregularity stop position, then
Stop instruction, the i.e. not process for using of the target end vehicles are not executed, and prompt information can be issued the user with, prompts to use
The current stop position irregularity in family, and docks specified nearby are provided.
A kind of position conjunction rule identification device is additionally provided in the embodiment of the present disclosure, which closes for realizing above-mentioned position and advise
Recognition methods embodiment and preferred embodiment, the descriptions that have already been made will not be repeated.As used below, term " mould
The combination of the software and/or hardware of predetermined function may be implemented in block ".Although device described in following embodiment is preferably with soft
Part is realized, but the realization of the combination of hardware or software and hardware is also that may and be contemplated.
Fig. 6 is the structural block diagram that rule identification device is closed according to a kind of optional position of the embodiment of the present disclosure, such as Fig. 6 institute
Show, which includes:
First acquisition module 602, for detecting the feelings for being used to indicate the stop instruction that target vehicle has been stopped
Under condition, the image of target vehicle position is acquired by the image capture device installed on target vehicle；
First identification module 604, for the target stop position according to image recognition target vehicle；
First determining module 606, for determining target by judging whether target stop position is located at specified docks
Whether stop position is to close rule stop position.
Optionally, the first identification module 604 includes: the first extraction unit, for extracting the first characteristics of image in image；
First input unit, for the first characteristics of image to be inputted the first location model, to identify target stop position.
Optionally, the first identification module 604 includes: transmission unit, for sending an image to server, so that server
Identify the target stop position of target vehicle in image.
Optionally, described device further include: third identification module, for the environment according to image recognition target stop position
Parameter, wherein environmental parameter includes at least following one: periphery is blocked with the presence or absence of building, periphery is set with the presence or absence of public
It applies, whether be located in the range of specified docks；Third determining module meets for the environmental parameter when target stop position
When preset rule, determine that target stop position is located at specified docks.
Optionally, the first determining module 606 is also used to: when the environmental parameter satisfaction of the target stop position is preset
Rule when, determine that the target stop position is located at the specified docks, and then determine that the target stop position is
Close rule stop position；When the environmental parameter of the target stop position is unsatisfactory for preset rule, the target is determined
Stop position is not located at the specified docks, and then determines that the target stop position is irregularity stop position.
Optionally, described device further include: execution module, for executing the operation of at least one of: not conforming to described
Rule stop position is sent to server；Information warning is sent, wherein the information warning is for prompting the target stop position
For irregularity stop position, and for the specified docks in target stop position specified range described in tip distance.
Optionally, the first acquisition module 602 includes: acquisition unit, for acquiring target traffic work within a predetermined period of time
Have the video image and/or photograph image of position, wherein target vehicle is the shared vehicles.
Fig. 7 is the structural block diagram that rule identification device is closed according to the optional position of another kind of the embodiment of the present disclosure, such as Fig. 7 institute
Show, which includes:
Second acquisition module 702, for detecting the feelings for being used to indicate the stop instruction that target vehicle has been stopped
Under condition, the image of target vehicle position is acquired by the image capture device installed on target vehicle；
First sending module 704, for sending an image to server, so that server is according to image recognition target traffic
The target stop position of tool；
Receiving module 706, for receiving the target stop position of server return；
Second determining module 708, for determining target by judging whether target stop position is located at specified docks
Whether stop position is to close rule stop position.
Fig. 8 is the structural block diagram that rule identification device is closed according to a kind of optional position of the embodiment of the present disclosure, such as Fig. 8 institute
Show, which includes:
Module 802 is obtained, for obtaining the image of target vehicle transmission, wherein image is that target vehicle exists
In the case where detecting stop instruction, pass through the target vehicle for the image capture device acquisition installed on target vehicle
The image of position, stop instruction are used to indicate target vehicle and have stopped；
Second identification module 804, for the target stop position according to image recognition target vehicle；
Second sending module 806, the target stop position for will identify that are sent to the target vehicle, so that
Target vehicle judges whether the target stop position is located at specified docks, and whether determines target stop position
Stop position is advised to close.
Optionally, the second identification module 804 includes: the second extraction unit, for extracting the second characteristics of image in image；
Second input unit, for the second characteristics of image to be inputted the second location model, to identify target stop position.Herein second
Algorithm identical with the first location model can be used in location model, and the content having been noted above is not repeated herein.
Embodiment of the disclosure additionally provides a kind of storage medium, is stored with computer program in the storage medium, wherein
The computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program:
S1 passes through target traffic in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image for the image capture device acquisition target vehicle position installed on tool；
S2, according to the target stop position of image recognition target vehicle；
S3 determines whether target stop position is conjunction by judging whether target stop position is located at specified docks
Advise stop position.
Optionally, in the present embodiment, above-mentioned storage medium may be also configured to store for executing following steps
Computer program:
S11 passes through the target in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image capture device installed on the vehicles acquires the image of the target vehicle position；
Described image is sent to server by S12, so that the server identifies the target traffic according to described image
The target stop position of tool；
S13 receives the target stop position that the server returns；
S14 determines the target stop position by judging whether the target stop position is located at specified docks
It whether is to close rule stop position.
Optionally, in the present embodiment, above-mentioned storage medium may be also configured to store for executing following steps
Computer program:
S21 obtains the image that target vehicle is sent, wherein image is that target vehicle is detecting that stop refers to
In the case where order, pass through the figure for the target vehicle position that the image capture device installed on target vehicle acquires
Picture, stop instruction are used to indicate target vehicle and have stopped；
S22, according to the target stop position of image recognition target vehicle；
S23, the target stop position that will identify that is sent to the target vehicle, so that the target traffic
Tool judges whether the target stop position is located at specified docks, and determines whether the target stop position is conjunction
Advise stop position.
Optionally, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk, read-only memory (Read-
Only Memory, referred to as ROM), it is random access memory (Random Access Memory, referred to as RAM), mobile hard
The various media that can store computer program such as disk, magnetic or disk.
Embodiment of the disclosure additionally provides a kind of electronic device, including memory and processor, stores in the memory
There is computer program, which is arranged to run computer program to execute the step in any of the above-described embodiment of the method
Suddenly.
Optionally, above-mentioned electronic device can also include transmission device and input-output equipment, wherein the transmission device
It is connected with above-mentioned processor, which connects with above-mentioned processor.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
S1 passes through target traffic in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image for the image capture device acquisition target vehicle position installed on tool；
S2, according to the target stop position of image recognition target vehicle；
S3 determines whether target stop position is conjunction by judging whether target stop position is located at specified docks
Advise stop position.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
S11 passes through the target in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
The image capture device installed on the vehicles acquires the image of the target vehicle position；
S12 sends an image to server, so that the server identifies the target vehicle according to described image
Target stop position；
S13 receives the target stop position that server returns；
S14 determines whether target stop position is conjunction by judging whether target stop position is located at specified docks
Advise stop position.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
S21 obtains the image that target vehicle is sent, wherein image is that target vehicle is detecting that stop refers to
In the case where order, pass through the figure for the target vehicle position that the image capture device installed on target vehicle acquires
Picture, stop instruction are used to indicate target vehicle and have stopped；
S22, according to the target stop position of image recognition target vehicle；
S23, the target stop position that will identify that are sent to the target vehicle, so that target vehicle judges
Whether target stop position is located at specified docks, and determines whether target stop position is to close rule stop position.
Specific example in the present embodiment can refer to example described in above-described embodiment and optional embodiment, this
Details are not described herein for embodiment.
Obviously, those skilled in the art should be understood that each module of the above-mentioned disclosure or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
It is performed by computing device in the storage device, and in some cases, it can be to be different from shown in sequence execution herein
Out or description the step of, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or
Step is fabricated to single integrated circuit module to realize.It is combined in this way, the disclosure is not limited to any specific hardware and software.
The foregoing is merely preferred embodiment of the present disclosure, are not limited to the disclosure, for the skill of this field
For art personnel, the disclosure can have various modifications and variations.It is all within the principle of the disclosure, it is made it is any modification, etc.
With replacement, improvement etc., should be included within the protection scope of the disclosure.
Claims (14)
1. rule recognition methods is closed in a kind of position characterized by comprising
In the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs, pass through the target vehicle
The image capture device of upper installation acquires the image of the target vehicle position；
The target stop position of the target vehicle is identified according to described image；
By judging whether the target stop position is located at specified docks, determine whether the target stop position is conjunction
Advise stop position.
2. the method according to claim 1, wherein described identify the target vehicle according to described image
Target stop position include:
Extract the first characteristics of image in described image；
The first image feature is inputted into the first location model, to identify the target stop position.
3. the method according to claim 1, wherein identifying the target vehicle according to described image
After target stop position, further includes:
The environmental parameter of the target stop position is identified according to described image, wherein the environmental parameter includes at least following
One of: periphery is blocked with the presence or absence of building, periphery whether there is communal facility, whether is located at the model of the specified docks
In enclosing.
4. according to the method described in claim 3, it is characterized in that, described by judging whether the target stop position is located at
Specified docks determine whether the target stop position is to close rule stop position to include:
When the environmental parameter of the target stop position meets preset rule, determine that the target stop position is located at
The specified docks, and then determine that the target stop position is to close rule stop position；
When the environmental parameter of the target stop position is unsatisfactory for preset rule, the target stop position is determined not
Positioned at the specified docks, and then determine that the target stop position is irregularity stop position.
5. according to the method described in claim 4, it is characterized in that, the determination target stop position is irregularity stop
After position, the method also includes: execute the operation of at least one of:
The irregularity stop position is sent to server；
Information warning is sent, wherein the information warning is irregularity stop position for prompting the target stop position, with
And for the specified docks in target stop position specified range described in tip distance.
6. method according to any one of claims 1 to 5, which is characterized in that described by the target vehicle
The image that the image capture device of installation acquires the target vehicle position includes:
The video image and/or photograph image of target vehicle position are acquired within a predetermined period of time, wherein the mesh
Marking the vehicles is the shared vehicles.
7. rule recognition methods is closed in a kind of position characterized by comprising
In the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs, pass through the target vehicle
The image capture device of upper installation acquires the image of the target vehicle position；
Described image is sent to server, so that the server identifies the mesh of the target vehicle according to described image
Mark stop position；
Receive the target stop position that the server returns；
By judging whether the target stop position is located at specified docks, determine whether the target stop position is conjunction
Advise stop position.
8. rule recognition methods is closed in a kind of position characterized by comprising
Obtain the image that target vehicle is sent, wherein described image is that the target vehicle is detecting that stop refers to
In the case where order, where the target vehicle acquired by the image capture device installed on the target vehicle
The image of position, the stop instruction are used to indicate the target vehicle and have stopped；
The target stop position of the target vehicle is identified according to described image；
The target stop position that will identify that is sent to the target vehicle, so that the target vehicle judges
Whether the target stop position is located at specified docks, and determines whether the target stop position is to close rule to stop position
It sets.
9. according to the method described in claim 8, it is characterized in that, described identify the target vehicle according to described image
Target stop position include:
Extract the second characteristics of image in described image；
Second characteristics of image is inputted into the second location model, to identify the target stop position.
10. rule identification device is closed in a kind of position characterized by comprising
First acquisition module, for leading in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
Cross the image that the image capture device installed on the target vehicle acquires the target vehicle position；
First identification module, for identifying the target stop position of the target vehicle according to described image；
First determining module, for determining the mesh by judging whether the target stop position is located at specified docks
Whether mark stop position is to close rule stop position.
11. rule identification device is closed in a kind of position characterized by comprising
Second acquisition module, for leading in the case where detecting that being used to indicate the stop that target vehicle has been stopped instructs
Cross the image that the image capture device installed on the target vehicle acquires the target vehicle position；
First sending module, for described image to be sent to server, so that the server identifies institute according to described image
State the target stop position of target vehicle；
Receiving module, the target stop position returned for receiving the server；
Second determining module, for determining the mesh by judging whether the target stop position is located at specified docks
Whether mark stop position is to close rule stop position.
12. rule identification device is closed in a kind of position characterized by comprising
Module is obtained, for obtaining the image of target vehicle transmission, wherein described image is that the target vehicle exists
In the case where detecting stop instruction, pass through the target for the image capture device acquisition installed on the target vehicle
The image of vehicles position, the stop instruction are used to indicate the target vehicle and have stopped；
Second identification module, for identifying the target stop position of the target vehicle according to described image；
Second sending module, the target stop position for will identify that is sent to the target vehicle, so that institute
It states target vehicle and judges whether the target stop position is located at specified docks, and determine that the target stops position
Whether set is to close rule stop position.
13. a kind of storage medium, which is characterized in that be stored with computer program in the storage medium, wherein the computer
Program is arranged to execute method described in any one of claim 1 to 9 when operation.
14. a kind of electronic device, including memory and processor, which is characterized in that be stored with computer journey in the memory
Sequence, the processor are arranged to run the computer program to execute side described in any one of claim 1 to 9
Method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910755330.4A CN110490127A (en) | 2019-08-15 | 2019-08-15 | Close rule recognition methods and device, storage medium, electronic device in position |
| PCT/CN2020/109344 WO2021027944A1 (en) | 2019-08-15 | 2020-08-14 | Position compliance recognition method and apparatus, storage medium and electronic apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910755330.4A CN110490127A (en) | 2019-08-15 | 2019-08-15 | Close rule recognition methods and device, storage medium, electronic device in position |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110490127A true CN110490127A (en) | 2019-11-22 |
Family
ID=68551311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910755330.4A Pending CN110490127A (en) | 2019-08-15 | 2019-08-15 | Close rule recognition methods and device, storage medium, electronic device in position |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110490127A (en) |
| WO (1) | WO2021027944A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111559732A (en) * | 2020-04-28 | 2020-08-21 | 哈工大机器人(中山)有限公司 | Automobile fuel tank position and angle identification method and system based on 2D vision |
| WO2021027944A1 (en) * | 2019-08-15 | 2021-02-18 | 纳恩博（常州）科技有限公司 | Position compliance recognition method and apparatus, storage medium and electronic apparatus |
| CN113781792A (en) * | 2021-09-06 | 2021-12-10 | 腾讯科技（深圳）有限公司 | Parking detection system, method and related equipment |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358863A (en) * | 2021-11-23 | 2022-04-15 | 摩拜(北京)信息技术有限公司 | Shared vehicle returning processing method and device and shared vehicle |
| CN114463632A (en) * | 2022-01-14 | 2022-05-10 | 摩拜(北京)信息技术有限公司 | Shared vehicle returning processing method and device and shared vehicle |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103366598A (en) * | 2013-07-15 | 2013-10-23 | 广州市浩云安防科技股份有限公司 | Vehicle in-place parking detection system and detecting method |
| CN106504565A (en) * | 2017-01-03 | 2017-03-15 | 上海量明科技发展有限公司 | The decision method of shared vehicle parking position, apparatus and system |
| CN106898024A (en) * | 2017-04-12 | 2017-06-27 | 上海量明科技发展有限公司 | Shared vehicle parking monitoring and managing method, system and device |
| CN107491765A (en) * | 2017-08-29 | 2017-12-19 | 张羽 | A kind of shared bicycle and its parking identification device and system |
| US20180068564A1 (en) * | 2016-09-05 | 2018-03-08 | Panasonic Intellectual Property Corporation Of America | Parking position identification method, parking position learning method, parking position identification system, parking position learning device, and non-transitory recording medium for recording program |
| CN108266033A (en) * | 2016-12-30 | 2018-07-10 | 现代自动车株式会社 | Automatic parking system and automatic stop process |
| CN109993789A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视数字技术股份有限公司 | A kind of the separated of shared bicycle stops determination method, device and camera |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130066829A (en) * | 2011-12-13 | 2013-06-21 | 한국전자통신연구원 | Parking lot management system based on cooperation of intelligence cameras |
| CN106779971A (en) * | 2017-01-03 | 2017-05-31 | 上海量明科技发展有限公司 | Charging method, client and system under shared vehicle assistance state |
| CN106601011B (en) * | 2017-01-03 | 2023-04-18 | 上海量明科技发展有限公司 | Shared vehicle and method, device and system for judging parking position of shared vehicle |
| CN106781445B (en) * | 2017-02-13 | 2023-09-12 | 上海量明科技发展有限公司 | Information output method, client and system of shared vehicle |
| CN106871860B (en) * | 2017-04-12 | 2024-01-30 | 上海量明科技发展有限公司 | Method and system for judging parking direction of shared bicycle and shared bicycle |
| CN107067357B (en) * | 2017-04-12 | 2023-05-23 | 上海量明科技发展有限公司 | Shared vehicle parking supervision method and system and shared vehicle |
| CN110490127A (en) * | 2019-08-15 | 2019-11-22 | 北京致行慕远科技有限公司 | Close rule recognition methods and device, storage medium, electronic device in position |
-
2019
- 2019-08-15 CN CN201910755330.4A patent/CN110490127A/en active Pending
-
2020
- 2020-08-14 WO PCT/CN2020/109344 patent/WO2021027944A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103366598A (en) * | 2013-07-15 | 2013-10-23 | 广州市浩云安防科技股份有限公司 | Vehicle in-place parking detection system and detecting method |
| US20180068564A1 (en) * | 2016-09-05 | 2018-03-08 | Panasonic Intellectual Property Corporation Of America | Parking position identification method, parking position learning method, parking position identification system, parking position learning device, and non-transitory recording medium for recording program |
| CN108266033A (en) * | 2016-12-30 | 2018-07-10 | 现代自动车株式会社 | Automatic parking system and automatic stop process |
| CN106504565A (en) * | 2017-01-03 | 2017-03-15 | 上海量明科技发展有限公司 | The decision method of shared vehicle parking position, apparatus and system |
| CN106898024A (en) * | 2017-04-12 | 2017-06-27 | 上海量明科技发展有限公司 | Shared vehicle parking monitoring and managing method, system and device |
| CN107491765A (en) * | 2017-08-29 | 2017-12-19 | 张羽 | A kind of shared bicycle and its parking identification device and system |
| CN109993789A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视数字技术股份有限公司 | A kind of the separated of shared bicycle stops determination method, device and camera |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021027944A1 (en) * | 2019-08-15 | 2021-02-18 | 纳恩博（常州）科技有限公司 | Position compliance recognition method and apparatus, storage medium and electronic apparatus |
| CN111559732A (en) * | 2020-04-28 | 2020-08-21 | 哈工大机器人(中山)有限公司 | Automobile fuel tank position and angle identification method and system based on 2D vision |
| CN113781792A (en) * | 2021-09-06 | 2021-12-10 | 腾讯科技（深圳）有限公司 | Parking detection system, method and related equipment |
| CN113781792B (en) * | 2021-09-06 | 2023-11-24 | 腾讯科技（深圳）有限公司 | Parking detection system, method and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021027944A1 (en) | 2021-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110490127A (en) | Close rule recognition methods and device, storage medium, electronic device in position | |
| Wali et al. | An automatic traffic sign detection and recognition system based on colour segmentation, shape matching, and svm | |
| CN107944450B (en) | License plate recognition method and device | |
| CN102007499B (en) | Detecting facial expressions in digital images | |
| Baran et al. | A smart camera for the surveillance of vehicles in intelligent transportation systems | |
| US20170213081A1 (en) | Methods and systems for automatically and accurately detecting human bodies in videos and/or images | |
| JP2020504358A (en) | Image-based vehicle damage evaluation method, apparatus, and system, and electronic device | |
| Zeeshan Zia et al. | Explicit occlusion modeling for 3d object class representations | |
| WO2019177732A1 (en) | Real-to-synthetic image domain transfer | |
| CN113688851B (en) | Data labeling method and device and fine granularity identification method and device | |
| CN105321350A (en) | Method and device for detection of fake plate vehicles | |
| CN112052815B (en) | Behavior detection method and device and electronic equipment | |
| CN113155173B (en) | Perception performance evaluation method and device, electronic device and storage medium | |
| Bell et al. | A novel system for nighttime vehicle detection based on foveal classifiers with real-time performance | |
| CN112418360B (en) | Convolutional neural network training method, pedestrian attribute identification method and related equipment | |
| CN109063790B (en) | Object recognition model optimization method and device and electronic equipment | |
| Zhang et al. | Vehicle classification with confidence by classified vector quantization | |
| Sikirić et al. | Image representations on a budget: Traffic scene classification in a restricted bandwidth scenario | |
| CN111814562A (en) | Vehicle identification method, vehicle identification model training method and related device | |
| Agarwal et al. | Vehicle Characteristic Recognition by Appearance: Computer Vision Methods for Vehicle Make, Color, and License Plate Classification | |
| Chughtai et al. | Traffic Surveillance System: Robust Multiclass Vehicle Detection and Classification | |
| Tian et al. | Design of Intelligent Parking Management System Based on License Plate Recognition. | |
| WO2020001263A1 (en) | Parking space recognition | |
| Pan et al. | A hybrid deep learning algorithm for the license plate detection and recognition in vehicle-to-vehicle communications | |
| CN108831158A (en) | It disobeys and stops monitoring method, device and electric terminal |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210205 Address after: Floor 16 and 17, block a, building 3, chuangyangang, Changzhou science and Education City, No.18, middle Changwu Road, Wujin District, Changzhou City, Jiangsu Province, 213000 Applicant after: NINEBOT (CHANGZHOU) TECH Co.,Ltd. Address before: 100086 No.161, 6 / F, block B, building 1, No.38, Zhongguancun Street, Haidian District, Beijing Applicant before: BEIJING ZHIXING MUYUAN TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191122 |