CN110163107A - A kind of method and device based on video frame identification Roadside Parking behavior - Google Patents
A kind of method and device based on video frame identification Roadside Parking behavior Download PDFInfo
- Publication number
- CN110163107A CN110163107A CN201910323229.1A CN201910323229A CN110163107A CN 110163107 A CN110163107 A CN 110163107A CN 201910323229 A CN201910323229 A CN 201910323229A CN 110163107 A CN110163107 A CN 110163107A
- Authority
- CN
- China
- Prior art keywords
- video frame
- vehicle
- video
- redefined
- parking stall
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- 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
-
- 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
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a kind of method and devices based on video frame identification Roadside Parking behavior, this method comprises: obtaining the continuous multiple video frames acquired by video equipment;Parking stall region is drawn in the first video frame, and determines the coordinate information on parking stall in the parking stall region, and first video frame is collected any video frame;It determines the second video frame, based on the parking stall region drawn, Difference Calculation is carried out to the first video frame and the second video frame, the second video frame is the adjacent latter video frame with the first video frame;Judge whether calculated result meets predetermined detection rule, if satisfied, the coordinate information based on the parking stall, detects the vehicle location in the first video frame and the second video by vehicle training pattern;Based on testing result, the Roadside Parking behavior of vehicle is determined.Through the invention, it realizes without identifying that the automatic management of Roadside Parking can be completed in license board information.
Description
Technical field
The present invention relates to intelligent parking management technical fields, more particularly to a kind of video frame that is based on to identify Roadside Parking behavior
Method and device.
Background technique
Roadside Parking management is the parking management carried out using the place of thoroughfare two sides on ground.With urban economy
Rapid development and living standards of the people continuous improvement, Urban vehicles poputation rapid growth, due to history and reality
Various reasons, most cities all suffer from motor vehicle parking space the shortage even puzzlement of wretched insufficiency.Therefore, Roadside Parking management
The important ring for becoming city parking management, by government and the extensive concern of the common people.But since Roadside Parking belongs to out
The parking of putting property, management means exist many difficult, on the one hand carry out inefficient management by artificial patrol at present, and cost compared with
It is high;On the other hand, although the installation for thering is part parking lot to carry out the equipment such as earth magnetism or electronic timepiece, for effect not to the utmost
Ideal, and there is the problems such as difficult, cumbersome and larger by environmental influence of constructing.Therefore, presently relevant industry all
Sight has focused on elevated video and has carried out in the means of Roadside Parking management.
Although the Roadside Parking management based on elevated video really have installation after be hardly damaged, capture video full apparent,
Scene is not required to the advantages that people's operation, but there is still a need for still manually check video information to record out admission movement and license plate and believe
Therefore how the operation such as breath captures pendulum the problem of going out the parking behaviors such as admission of vehicle in face of numerous practitioners automatically.
Summary of the invention
The embodiment of the present invention provides a kind of method and device based on video frame identification Roadside Parking behavior, realizes and passes through
Video information automatic identification vehicle Roadside Parking behavior, it is not necessary that Roadside Parking can be completed in the case where identifying license board information
Automatic management.
On the one hand, the embodiment of the invention provides a kind of methods based on video frame identification Roadside Parking behavior, comprising:
The continuous multiple video frames acquired by video equipment are obtained, the video equipment is for acquiring Roadside Parking region
Image information;
Parking stall region is drawn in the first video frame, and determines the coordinate information on parking stall in the parking stall region,
First video frame is collected any video frame;
Determine the second video frame, based on the parking stall region drawn, to the first video frame and the second video frame into
Row Difference Calculation, the second video frame are the adjacent latter video frame with the first video frame;
Judge whether calculated result meets predetermined detection rule, if satisfied, the coordinate information based on the parking stall, passes through
Vehicle training pattern detects the vehicle location in the first video frame and the second video;
Based on testing result, the Roadside Parking behavior of vehicle is determined.
On the other hand, the embodiment of the invention provides a kind of devices based on video frame identification Roadside Parking behavior, comprising:
First obtains module, and for obtaining the continuous multiple video frames acquired by video equipment, the video equipment is used
Image information in acquisition Roadside Parking region;
Drafting module for drawing parking stall region in the first video frame, and is determined and is stopped in the parking stall region
The coordinate information of position, first video frame are collected any video frame;
Difference Calculation module, for determining the second video frame, based on the parking stall region drawn, to the first video
Frame and the second video frame carry out Difference Calculation, and the second video frame is the adjacent latter video frame with the first video frame;
Detection module, for judging whether calculated result meets predetermined detection rule, if satisfied, based on the parking stall
Coordinate information detects the vehicle location in the first video frame and the second video by vehicle training pattern;
Determining module determines the Roadside Parking behavior of vehicle for being based on testing result.
Above-mentioned technical proposal has the following beneficial effects: through the invention, parking stall coordinate information based on drafting and stops
Parking area, can it is accurate, efficiently each video frame collected to video equipment analyzes and determines, and tied according to detection
Fruit automatically identifies the Roadside Parking behavior of the vehicle in video frame, realizes without identifying that license board information can be completed trackside and stop
The automatic management of vehicle provides the support of important technology to improve urban transportation and parking management efficiency;Further, pole
The earth improves the efficiency of management of Roadside Parking, reduces the cost of Roadside Parking management, meanwhile, improve user uses body
It tests.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of method flow diagram that Roadside Parking behavior is identified based on video frame in the embodiment of the present invention;
Fig. 2 is that elevated video equipment acquires schematic diagram in one embodiment of the present invention;
Fig. 3 is the drafting schematic diagram in parking stall region in any video frame in one embodiment of the present invention;
Fig. 4 is the schematic diagram for dividing the first units chunk in one embodiment of the present invention in any video frame;
Fig. 5 is that the vehicle in one embodiment of the present invention in video frame occurs to enter and leave the schematic diagram of parking lot behavior;
Fig. 6 is vehicle movable schematic diagram in parking area in one embodiment of the present invention;
Fig. 7 is a kind of apparatus structure schematic diagram that Roadside Parking behavior is identified based on video frame in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, for the method flow diagram for identifying Roadside Parking behavior based on video frame a kind of in the embodiment of the present invention,
Include:
101, the continuous multiple video frames acquired by video equipment are obtained, the video equipment is for acquiring Roadside Parking
The image information in region;
102, parking stall region is drawn in the first video frame, and determines the coordinate letter on parking stall in the parking stall region
Breath, first video frame are collected any video frame;
103, the second video frame is determined, based on the parking stall region drawn, to the first video frame and the second video
Frame carries out Difference Calculation, and the second video frame is the adjacent latter video frame with the first video frame;
104, judge whether calculated result meets predetermined detection rule, if satisfied, the coordinate information based on the parking stall,
The vehicle location in the first video frame and the second video is detected by vehicle training pattern;
105, it is based on testing result, determines the Roadside Parking behavior of vehicle.
Further, second video frame of determination, based on the parking stall region drawn, to the first video frame with
Second video frame carries out Difference Calculation, specifically includes:
With the units chunk of predefined size, the image of the first video frame and the second video frame is divided into multiple first units
Block, wherein each position of the first units chunk in any video frame is identical;
Based on the parking area drawn, each first units chunk comprising the parking area is determined as second
Units chunk;
Calculate separately the pixel average of each second units chunk;
Determine one-to-one second list identical with the position in the second video frame in the position in the first video frame
Position block;
Calculate separately the difference value of the pixel average of each one-to-one second units chunk.
Further, the predetermined detection rule, comprising:
Judge whether each difference value being calculated is greater than predetermined difference value threshold value;
Statistics is greater than the number of the difference value of predetermined difference value threshold value, and judges whether the number is greater than predetermined number threshold
Value;
Wherein, described to judge whether calculated result meets predetermined detection rule, it specifically includes:
If the number is greater than predetermined number threshold value, determine that calculated result meets predetermined detection rule;
If the number is less than predetermined number threshold value, determine that calculated result is unsatisfactory for predetermined detection rule.
Further, however, it is determined that calculated result is unsatisfactory for predetermined detection rule, comprising:
Step a, the second video frame of predetermined detection rule will be unsatisfactory for as the first video frame redefined, and again
Determine the second video frame, wherein the second video frame redefined is the latter view adjacent with the first video frame redefined
Frequency frame;
Difference Calculation is carried out with the second video frame redefined to the first video frame redefined, and judges to calculate knot
Whether fruit meets predetermined detection rule;
Step a is executed if not satisfied, jumping, until calculated result meets the predetermined detection rule.
Further, in the coordinate information based on the parking stall, by vehicle training pattern to the first video frame
Before the step of being detected with the vehicle location in the second video, comprising:
Obtain multiple vehicle image samples in collected Roadside Parking region;
The multiple vehicle image sample is labeled and is instructed by the deep learning method based on convolutional neural networks
Practice, obtains vehicle training pattern.
Further, the coordinate information based on the parking stall, by vehicle training pattern to the first video frame and
After the step of vehicle location in second video is detected, comprising:
The vehicle location and parking stall position that will test in result carry out coordinate pair ratio, acquire the matter of vehicle rectangular area
The heart;
Vehicle of the mass center in parking stall is calculated, and the information of the vehicle by mass center in parking stall is recorded to testing result
In.
Further, described to be based on testing result, determine the Roadside Parking behavior of vehicle, comprising:
Based on testing result, determine whether the first video frame and the mass center situation of vehicle in the second video are consistent;
If consistent, determine the vehicle in the first video frame and the second video without Roadside Parking behavior;
If inconsistent, there are Roadside Parking behaviors for the vehicle for determining in the first video frame of vehicle and the second video;
Wherein, the mass center situation of the vehicle includes mass center in parking stall and mass center is not any one of in parking stall
Situation.
Optionally, after the step of vehicle in first video frame of determination and the second video is without Roadside Parking behavior,
Further include:
It jumps and executes step a, until completing the calculating to each video frame.
Optionally, the vehicle in first video frame of determining vehicle and the second video the step of there are Roadside Parking behaviors it
Afterwards, further includes:
Step m, the second video frame of Roadside Parking behavior will be present as the first video frame redefined, and again really
Fixed second video frame, wherein the second video frame redefined is the latter video adjacent with the first video frame redefined
Frame;
By vehicle training pattern to the vehicle in the first video frame redefined and the second video frame redefined
It is detected position;
Based on testing result, if the mass center of the first video frame redefined and vehicle in the second video frame redefined
Situation is inconsistent, jumps and executes step m, until the first video frame redefined and vehicle in the second video frame redefined
Mass center situation it is consistent.
As shown in fig. 7, for a kind of apparatus structure schematic diagram for identifying Roadside Parking behavior based on video frame, comprising:
First obtains module 71, for obtaining the continuous multiple video frames acquired by video equipment, the video equipment
For acquiring the image information in Roadside Parking region;
Drafting module 72 for drawing parking stall region in the first video frame, and determines and stops in the parking stall region
The coordinate information of parking stall, first video frame are collected any video frame;
Difference Calculation module 73, based on the parking stall region drawn, is regarded for determining the second video frame to first
Frequency frame and the second video frame carry out Difference Calculation, and the second video frame is the adjacent latter video frame with the first video frame;
Detection module 74, for judging whether calculated result meets predetermined detection rule, if satisfied, being based on the parking stall
Coordinate information, the vehicle location in the first video frame and the second video is detected by vehicle training pattern;
Determining module 75 determines the Roadside Parking behavior of vehicle for being based on testing result.
Further, the Difference Calculation module, is specifically used for
With the units chunk of predefined size, the image of the first video frame and the second video frame is divided into multiple first units
Block, wherein each position of the first units chunk in any video frame is identical;
Based on the parking area drawn, each first units chunk comprising the parking area is determined as second
Units chunk;
Calculate separately the pixel average of each second units chunk;
Determine one-to-one second list identical with the position in the second video frame in the position in the first video frame
Position block;
Calculate separately the difference value of the pixel average of each one-to-one second units chunk.
Further, the predetermined detection rule, comprising:
Judge whether each difference value being calculated is greater than predetermined difference value threshold value;
Statistics is greater than the number of the difference value of predetermined difference value threshold value, and judges whether the number is greater than predetermined number threshold
Value;
Wherein, the detection module, is specifically used for
If the number is greater than predetermined number threshold value, determine that calculated result meets predetermined detection rule;
If the number is less than predetermined number threshold value, determine that calculated result is unsatisfactory for predetermined detection rule.
Further, if the detection module determines that calculated result is unsatisfactory for predetermined detection rule, comprising:
First redefines unit, for that will be unsatisfactory for the second video frame of predetermined detection rule as redefined
One video frame, and redefine the second video frame, wherein the second video frame redefined is and the first video for redefining
The adjacent latter video frame of frame;
Difference Calculation unit, for carrying out difference with the second video frame redefined to the first video frame redefined
It calculates, and judges whether calculated result meets predetermined detection rule;
First jump-transfer unit, for if not satisfied, jumping execution first redefines unit, until calculated result meets institute
State predetermined detection rule.
Further, comprising:
Second obtains module, for obtaining multiple vehicle image samples in collected Roadside Parking region;
Training module, for by the deep learning method based on convolutional neural networks to the multiple vehicle image sample
It is labeled and trains, obtain vehicle training pattern.
Further, comprising:
Contrast module carrying out coordinate pair ratio for will test the vehicle location in result and parking stall position, acquiring vehicle
The mass center of rectangular area;
Computing module, for calculating vehicle of the mass center in parking stall, and the information of the vehicle by mass center in parking stall
Record is into testing result.
Further, the determining module, comprising:
First determination unit determines the mass center feelings of vehicle in the first video frame and the second video for being based on testing result
Whether shape is consistent;
Second determination unit, if determining the vehicle in the first video frame and the second video without Roadside Parking row for consistent
For;
Third determination unit, if there are tracksides for the vehicle for determining in the first video frame of vehicle and the second video for inconsistent
Parking behavior;
Wherein, the mass center situation of the vehicle includes mass center in parking stall and mass center is not any one of in parking stall
Situation.
Optionally, second determination unit, is also used to
It jumps execution described first and redefines unit, until completing the calculating to each video frame.
Optionally, the third determination unit, further includes:
Second redefines unit, for the second video frame of Roadside Parking behavior to will be present as first redefined
Video frame, and redefine the second video frame, wherein the second video frame redefined is and the first video frame for redefining
Adjacent latter video frame;
Detection unit, for passing through vehicle training pattern to the first video frame redefined and the second view redefined
Vehicle location in frequency frame is detected;
Second jump-transfer unit, for being based on testing result, if the first video frame redefined and redefine second
The mass center situation of vehicle is inconsistent in video frame, jumps execution described second and redefines unit, until redefine first
Video frame is consistent with the mass center situation of vehicle in the second video frame redefined.
Above-mentioned technical proposal of the embodiment of the present invention has the following beneficial effects: through the invention, the parking stall based on drafting
Coordinate information and parking stall region, can it is accurate, efficiently each video frame collected to video equipment analyzes and determines,
And the Roadside Parking behavior of the vehicle in video frame is automatically identified according to testing result, it realizes without identifying license board information i.e.
The automatic management of achievable Roadside Parking provides the branch of important technology to improve urban transportation and parking management efficiency
It holds;Further, the efficiency of management of Roadside Parking is greatly improved, the cost of Roadside Parking management is reduced, meanwhile, it improves
The usage experience of user.
Above-mentioned technical proposal of the embodiment of the present invention is described in detail below in conjunction with application example:
Application example of the present invention is intended to realize by video information automatic identification vehicle Roadside Parking behavior without identification
The automatic management of Roadside Parking can be completed in license board information.
For example, in the section for acquiring Roadside Parking regional image information by elevated video, by parking management system A,
Obtain continuous multiple video frames of the image information in the Roadside Parking region acquired by video equipment;By collected any view
Frequency frame is determined as the first video frame, such as frame video frame, and parking stall region is drawn in frame video frame, determines parking stall area
The coordinate information on parking stall in domain;By the adjacent latter video frame with frame video frame, i.e. frame video frame, it is determined as second
Video frame carries out Difference Calculation to frame video frame and frame video frame based on the parking stall region drawn;Judgement calculates knot
Whether fruit meets predetermined detection rule, if satisfied, the coordinate information based on parking stall, by vehicle training pattern to frame video
Frame is detected with the vehicle location in frame video frame.
It should be noted that as shown in Fig. 2, acquiring schematic diagram for elevated video in the present embodiment.Existing video camera is general
The frequency acquisition of per second more than ten or tens frames can be reached, so intensive acquisition, on the one hand, image passes to backstage and located
It manages, real-time requirement is not achieved in performance;On the other hand, within the so short time, the variation of interframe is front and back consecutive frame
Very little, it can be ignored, since the embodiment in the present invention will detect the vehicle situation of change on the parking stall of interframe,
It needs to sample successive video frames, the video frame detected in the embodiment of the present invention is all the video frame through over-sampling;This
Successive video frames in inventive embodiments can be the successive video frames of predetermined certain time interval, and 5 seconds continuous is divided into as between
Video frame.
In a possible embodiment, the second video frame is determined in step 103, based on the parking stall area drawn
Domain carries out Difference Calculation to the first video frame and the second video frame, specifically includes: with the units chunk of predefined size, by the first view
Frequency frame and the image of the second video frame are divided into multiple first units chunks, wherein each first units chunk is in any video frame
In position it is identical;Based on the parking area drawn, each first units chunk comprising the parking area is determined
For the second units chunk;Calculate separately the pixel average of each second units chunk;Determine position in the first video frame with
Identical one-to-one second units chunk in position in second video frame;Calculate separately each one-to-one second unit
The difference value of the pixel average of block.
Wherein, the predetermined detection rule, comprising: judge whether each difference value being calculated is greater than predetermined difference value threshold
Value;Statistics is greater than the number of the difference value of predetermined difference value threshold value, and judges whether the number is greater than predetermined number threshold value.
Wherein, described to judge whether calculated result meets predetermined detection rule, it specifically includes: making a reservation for if the number is greater than
Number threshold value determines that calculated result meets predetermined detection rule;If the number is less than predetermined number threshold value, calculated result is determined
It is unsatisfactory for predetermined detection rule.
For example, in parking management system A, if the first video frame is frame video frame, the second video frame is determined, as the
The image of first video frame and the second video frame then with the units chunk of predefined size, is divided into multiple first by frame video frame
Units chunk, e.g., the size of every frame is 1920px (width) × 1080px (height) in the video frame acquired in the embodiment of the present invention,
In, px is pixel, is started respectively from the upper left angle point (0,0) of frame video frame and frame video frame, respectively transversely and longitudinal
Straight line is drawn by side length of a, frame video frame and the respective whole image of frame video frame are divided into many sides by straight cuts
The small square block of a length of a, generally takes a=16px;Wherein, position phase of each first units chunk in any video frame
Together;Based on the parking area drawn, each first units chunk comprising parking area is determined as the second units chunk, such as Fig. 3
It is shown, it is the drafting schematic diagram in parking stall region in any video frame;As shown in figure 4, calculate constituent parts block whether with drawn in Fig. 3
The parking stall region of system overlaps, i.e., whether constituent parts block is located in parking stall, is only retained according to calculated result with parking area
There is the constituent parts block of overlapping region, it is assumed that there is n units chunk to be located in parking area, then the number of the second units chunk is n, is passed through
Following formula one calculates separately the pixel average of each second units chunk:
Wherein, a be fritter side length, for place pixel value, for k-th of fritter region;
It is then determined that in the first video frame, the current position in frame video frame in the second video frame, be currently the
Identical one-to-one second units chunk in position in frame video frame;It is calculated separately by following formula two each
The difference value of the pixel average of a one-to-one second units chunk:
... ... ... ... ... ... (formula two)
Wherein, EkFor the difference of corresponding kth fritter average value in two consecutive frames, mkFor the mean pixel of k-th of fritter
Value, i are the kth fritter on the i-th frame.
Then, according to calculated result, judge whether each difference value being calculated is greater than predetermined difference value threshold value;Statistics is big
In the number of the difference value of predetermined difference value threshold value, and judge whether the number is greater than predetermined number threshold value;If more than determining to calculate
As a result meet predetermined detection rule;If being less than, determine that calculated result is unsatisfactory for predetermined detection rule.
Through this embodiment, can quickly and accurately determine in continuous adjacent two video frame in parking area
Information of vehicles, and calculated by difference, it can be accurately determined whether vehicle has occurred road in continuous adjacent two video frame
Side parking behavior greatly improves the detection efficiency of Roadside Parking behavior.
In a possible embodiment, however, it is determined that calculated result is unsatisfactory for predetermined detection rule, comprising: step a, will not
Meet the second video frame of predetermined detection rule as the first video frame redefined, and redefine the second video frame,
In, the second video frame redefined is the latter video frame adjacent with the first video frame redefined;To what is redefined
First video frame carries out Difference Calculation with the second video frame redefined, and judges whether calculated result meets predetermined detection rule
Then;Step a is executed if not satisfied, jumping, until calculated result meets the predetermined detection rule.
For example, in parking management system A, the pre- parking area drawn in video frame, as chosen in successive video frames
Any frame image draws the parking stall region in the frame image, with a certain vertex (x on parking stall0, y0) it is used as starting point,
Boundary mapping polygon along parking stall, and record each vertex (x of polygon1, y1)、(x2, y2)、(x3, y3), it eventually forms
The polygon of closure, the polygon of the closure are the parking area drawn;Wherein, video equipment is for acquiring Roadside Parking area
The image information in domain;Obtain the continuous multiple video frames acquired by video equipment;Collected frame video frame is determined as
First video frame, and parking stall region is drawn in frame video frame, determine the coordinate information on parking stall in the region of parking stall;It will
Frame video frame is determined as the second video frame, based on the parking stall region drawn, to frame video frame and frame video frame into
Row Difference Calculation;Judge whether calculated result meets predetermined detection rule, if not satisfied, executing step a, step a is that will be discontented with
First video frame of sufficient predetermined detection rule is currently frame video frame as the first video frame redefined, and again really
Fixed second video frame, wherein the second video frame redefined be with the first video frame for redefining, be currently frame video
The adjacent latter video frame of frame, i.e. frame video frame;To the first video frame redefined, i.e., currently for frame video frame with again
The second video frame newly determined currently carries out Difference Calculation for frame video frame, and it is predetermined to judge whether calculated result meets
Detected rule;Step a is executed if not satisfied, jumping, until calculated result meets predetermined detection rule.
Through this embodiment, stopping in continuous adjacent multiple video frames two-by-two can be quickly and accurately determined
Information of vehicles in region, and by Difference Calculation, it can be accurately determined whether vehicle has occurred in multiple video frame
Roadside Parking behavior not only greatly improves the detection efficiency of Roadside Parking behavior, and further greatly improves inspection
Survey the accuracy rate of Roadside Parking behavior.
In a possible embodiment, in the coordinate information based on the parking stall, pass through vehicle training pattern
Before the step of being detected to the vehicle location in the first video frame and the second video, comprising: obtain collected trackside and stop
Multiple vehicle image samples in vehicle region;By the deep learning method based on convolutional neural networks to the multiple vehicle figure
Decent is labeled and trains, and obtains vehicle training pattern.
For example, pre-acquiring passes through in the collected Roadside Parking region of elevated video equipment in parking management system A
Multiple vehicle image samples;Multiple vehicle image sample is marked by the deep learning method based on convolutional neural networks
Note and training, obtain vehicle training pattern.
It should be noted that those skilled in the art are it can be appreciated that convolutional neural networks (Convolutional
Neural Networks, CNN) it is a kind of comprising convolutional calculation and with the feedforward neural network of depth structure
(Feedforward Neural Networks) is one of the representative algorithm of deep learning (deep learning).This implementation
The specific step that multiple vehicle image sample is labeled and is trained by the deep learning method of convolutional neural networks in example
Suddenly it repeats no more.
In a possible embodiment, in the coordinate information based on the parking stall, pass through vehicle training pattern
After the step of being detected to the vehicle location in the first video frame and the second video, comprising: will test the vehicle in result
Position and parking stall position carry out coordinate pair ratio, acquire the mass center of vehicle rectangular area;Vehicle of the mass center in parking stall is calculated,
And the information of the vehicle by mass center in parking stall is recorded into testing result.
For example, in parking management system A, by vehicle training pattern to the first video frame, such as current first video frame
It is detected, is obtained for the vehicle location in frame video frame for frame video frame and the second video, such as current second video frame
Testing result, then, the vehicle location and parking stall position that will test in result carry out coordinate pair ratio, acquire vehicle rectangular area
Mass center, i.e. the central point of rectangular area;Vehicle of the calculating mass center in parking stall, and the vehicle by mass center in parking stall
Information is recorded into testing result.
Through this embodiment, it realizes without identifying that license board information can be by the increase of vehicle in parking stall in video frame
Or reduce and judge going out, entering the parking behaviors such as parking lot for vehicle, greatly improve the detection efficiency of Roadside Parking behavior.
In a possible embodiment, step 105 is based on testing result, determines the Roadside Parking behavior of vehicle, comprising:
Based on testing result, determine whether the first video frame and the mass center situation of vehicle in the second video are consistent;If consistent, first is determined
Vehicle in video frame and the second video is without Roadside Parking behavior;If inconsistent, determine in the first video frame of vehicle and the second video
Vehicle there are Roadside Parking behaviors;Wherein, the mass center situation of the vehicle includes that mass center is not stopping in parking stall with mass center
Any situation in parking stall.
Wherein, after the step of vehicle in first video frame of determination and the second video is without Roadside Parking behavior, also
It include: to jump to execute step a, until completing the calculating to each video frame.
Wherein, the vehicle in first video frame of determining vehicle and the second video the step of there are Roadside Parking behaviors it
Afterwards, further includes: the second video frame of Roadside Parking behavior step m, will be present as the first video frame redefined, and again
Determine the second video frame, wherein after the second video frame redefined is adjacent with first video frame redefined
One video frame;By vehicle training pattern to the vehicle in the first video frame redefined and the second video frame redefined
It is detected position;Based on testing result, if vehicle in the first video frame redefined and the second video frame redefined
Mass center situation it is inconsistent, jump and execute step m, until the first video frame for redefining and the second video frame redefined
The mass center situation of middle vehicle is consistent.
For example, connecting example in parking management system A, it is based on testing result, determines the first video frame, such as current first
Video frame be frame video frame and the second video, as current second video frame be frame video frame in vehicle mass center situation whether
Unanimously;Wherein, the mass center situation of vehicle include mass center in parking stall and mass center not in parking stall in any situation;If
Unanimously, determine that the vehicle in the first video frame and the second video without Roadside Parking behavior, then, jumps and executes step a, until complete
The calculating of pairs of each video frame;If inconsistent, there are Roadside Parkings for the vehicle for determining in the first video frame of vehicle and the second video
Behavior executes step m as shown in figure 5, then: the second video frame of Roadside Parking behavior will be present as the redefined
One video frame, if current second video frame is frame video frame, the first video frame redefined is frame video frame, is laid equal stress on
It is new to determine the second video frame, for example frame video frame, wherein the second video frame redefined is and the first view for redefining
The adjacent latter video frame of frequency frame;By vehicle training pattern to the first video frame redefined and the second view redefined
Vehicle location in frequency frame is detected;Based on testing result, if the first video frame redefined and redefine second
The mass center situation of vehicle is inconsistent in video frame, jumps and executes step m, until the first video frame for redefining with redefine
The second video frame in vehicle mass center situation it is consistent, vehicle as shown in FIG. 6 is movable in parking area, but the vehicle not into
Row goes out the movement of admission, at this time, it is believed that vehicle is in stable state after variation after a period of time, can be used as result and sentences
Disconnected foundation.Assuming that frame and the vehicle in parking stall in frame video frame are unchanged, then compare in frame and frame video frame
Final result of the variation of vehicle as parking behavior in parking stall.If having vehicle in the parking stall of two video frames or all not having
There is vehicle, final result is without parking behaviors such as discrepancy parking stalls;If there is vehicle in frame parking stall in frame parking stall
There is no vehicle, is then judged as that parking stall has vehicle to be driven out to;If there is no vehicle in frame parking stall and having vehicle in frame parking stall
, then it is judged as that parking stall has vehicle to drive into, is then then transferred to step a calculates next before and after frames i.e. frame and frame each second
The difference of units chunk.
It through this embodiment, can be for the vehicle that parking behavior occurs in continuous adjacent two frame, after adjacent
Continuous multiframe is further to be detected, until detecting the case where vehicle is in stable state, realizes the various parkings to vehicle
Behavior can complete detection, further increase the accuracy rate of detection, meanwhile, also can be in continuous adjacent two frame
The vehicle that parking behavior does not occur is detected based on adjacent subsequent multiframe is further, so that the information for passing through continuous multiple frames
It determines the Roadside Parking behavior of vehicle, greatly improves the accuracy rate of detection.
The embodiment of the invention provides a kind of devices based on video frame identification Roadside Parking behavior, and above-mentioned mention may be implemented
The embodiment of the method for confession, concrete function realize the explanation referred in embodiment of the method, and details are not described herein.
It should be understood that the particular order or level of the step of during disclosed are the examples of illustrative methods.Based on setting
Count preference, it should be appreciated that in the process the step of particular order or level can be in the feelings for the protection scope for not departing from the disclosure
It is rearranged under condition.Appended claim to a method is not illustratively sequentially to give the element of various steps, and not
It is to be limited to the particular order or level.
In above-mentioned detailed description, various features are combined together in single embodiment, to simplify the disclosure.No
This published method should be construed to reflect such intention, that is, the embodiment of theme claimed needs to compare
The more features of the feature clearly stated in each claim.On the contrary, as appended claims is reflected
Like that, the present invention is in the state fewer than whole features of disclosed single embodiment.Therefore, appended claims
It is hereby expressly incorporated into detailed description, wherein each claim is used as alone the individual preferred embodiment of the present invention.
For can be realized any technical staff in the art or using the present invention, above to disclosed embodiment into
Description is gone.To those skilled in the art;The various modifications mode of these embodiments will be apparent from, and this
The General Principle of text definition can also be suitable for other embodiments on the basis of not departing from the spirit and scope of the disclosure.
Therefore, the disclosure is not limited to embodiments set forth herein, but most wide with principle disclosed in the present application and novel features
Range is consistent.
Description above includes the citing of one or more embodiments.Certainly, in order to describe above-described embodiment and description portion
The all possible combination of part or method is impossible, but it will be appreciated by one of ordinary skill in the art that each implementation
Example can do further combinations and permutations.Therefore, embodiment described herein is intended to cover fall into the appended claims
Protection scope in all such changes, modifications and variations.In addition, with regard to term used in specification or claims
The mode that covers of "comprising", the word is similar to term " includes ", just as " including " solved in the claims as transitional word
As releasing.In addition, the use of any one of specification in claims term "or" being to indicate " non-exclusionism
Or ".
Those skilled in the art will also be appreciated that the various illustrative components, blocks that the embodiment of the present invention is listed
(illustrative logical block), unit and step can by electronic hardware, computer software, or both knot
Conjunction is realized.For the replaceability (interchangeability) for clearly showing that hardware and software, above-mentioned various explanations
Property component (illustrative components), unit and step universally describe their function.Such function
It can be that the design requirement for depending on specific application and whole system is realized by hardware or software.Those skilled in the art
Can be can be used by various methods and realize the function, but this realization is understood not to for every kind of specific application
Range beyond protection of the embodiment of the present invention.
Various illustrative logical blocks or unit described in the embodiment of the present invention can by general processor,
Digital signal processor, specific integrated circuit (ASIC), field programmable gate array or other programmable logic devices, discrete gate
Or transistor logic, discrete hardware components or above-mentioned any combination of design carry out implementation or operation described function.General place
Managing device can be microprocessor, and optionally, which may be any traditional processor, controller, microcontroller
Device or state machine.Processor can also be realized by the combination of computing device, such as digital signal processor and microprocessor,
Multi-microprocessor, one or more microprocessors combine a digital signal processor core or any other like configuration
To realize.
The step of method described in the embodiment of the present invention or algorithm can be directly embedded into hardware, processor execute it is soft
The combination of part module or the two.Software module can store in RAM memory, flash memory, ROM memory, EPROM storage
Other any form of storaging mediums in device, eeprom memory, register, hard disk, moveable magnetic disc, CD-ROM or this field
In.Illustratively, storaging medium can be connect with processor, so that processor can read information from storaging medium, and
It can be to storaging medium stored and written information.Optionally, storaging medium can also be integrated into the processor.Processor and storaging medium can
To be set in asic, ASIC be can be set in user terminal.Optionally, processor and storaging medium also can be set in
In different components in the terminal of family.
In one or more exemplary designs, above-mentioned function described in the embodiment of the present invention can be in hardware, soft
Part, firmware or any combination of this three are realized.If realized in software, these functions be can store and computer-readable
On medium, or it is transferred on a computer readable medium in the form of one or more instructions or code forms.Computer readable medium includes electricity
Brain storaging medium and convenient for so that computer program is allowed to be transferred to from a place telecommunication media in other places.Storaging medium can be with
It is that any general or special computer can be with the useable medium of access.For example, such computer readable media may include but
It is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disc storages, disk storage or other magnetic storage devices or other
What can be used for carry or store with instruct or data structure and it is other can be by general or special computer or general or specially treated
The medium of the program code of device reading form.In addition, any connection can be properly termed computer readable medium, example
Such as, if software is to pass through a coaxial cable, fiber optic cables, double from a web-site, server or other remote resources
Twisted wire, Digital Subscriber Line (DSL) are defined with being also contained in for the wireless way for transmitting such as example infrared, wireless and microwave
In computer readable medium.The disk (disk) and disk (disc) includes compress disk, radium-shine disk, CD, DVD, floppy disk
And Blu-ray Disc, disk is usually with magnetic replicate data, and disk usually carries out optically replicated data with laser.Combinations of the above
Also it may be embodied in computer readable medium.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (18)
1. a kind of method based on video frame identification Roadside Parking behavior characterized by comprising
The continuous multiple video frames acquired by video equipment are obtained, the video equipment is used to acquire the figure in Roadside Parking region
As information;
Parking stall region is drawn in the first video frame, and determines the coordinate information on parking stall in the parking stall region, it is described
First video frame is collected any video frame;
Determine the second video frame, based on the parking stall region drawn, it is poor to carry out to the first video frame and the second video frame
Divide and calculate, the second video frame is the adjacent latter video frame with the first video frame;
Judge whether calculated result meets predetermined detection rule, if satisfied, the coordinate information based on the parking stall, passes through vehicle
Training pattern detects the vehicle location in the first video frame and the second video;
Based on testing result, the Roadside Parking behavior of vehicle is determined.
2. the method according to claim 1, wherein the second video frame of the determination, described in having drawn
Parking stall region carries out Difference Calculation to the first video frame and the second video frame, specifically includes:
With the units chunk of predefined size, the image of the first video frame and the second video frame is divided into multiple first units chunks,
In, each position of the first units chunk in any video frame is identical;
Based on the parking area drawn, each first units chunk comprising the parking area is determined as the second unit
Block;
Calculate separately the pixel average of each second units chunk;
It determines in one-to-one second units chunk identical with the position in the second video frame of the position in the first video frame;
Calculate separately the difference value of the pixel average of each one-to-one second units chunk.
3. the method according to claim 1, wherein the predetermined detection is regular, comprising:
Judge whether each difference value being calculated is greater than predetermined difference value threshold value;
Statistics is greater than the number of the difference value of predetermined difference value threshold value, and judges whether the number is greater than predetermined number threshold value;
Wherein, described to judge whether calculated result meets predetermined detection rule, it specifically includes:
If the number is greater than predetermined number threshold value, determine that calculated result meets predetermined detection rule;
If the number is less than predetermined number threshold value, determine that calculated result is unsatisfactory for predetermined detection rule.
4. according to the method described in claim 3, if it is determined that calculated result is unsatisfactory for predetermined detection rule, comprising:
Step a, the second video frame of predetermined detection rule will be unsatisfactory for as the first video frame redefined, and redefined
Second video frame, wherein the second video frame redefined is the latter video frame adjacent with the first video frame redefined;
Difference Calculation is carried out with the second video frame redefined to the first video frame redefined, and judges that calculated result is
It is no to meet predetermined detection rule;
Step a is executed if not satisfied, jumping, until calculated result meets the predetermined detection rule.
5. method according to claim 1-4, which is characterized in that in the coordinate letter based on the parking stall
Before the step of ceasing, being detected by vehicle training pattern to the vehicle location in the first video frame and the second video, comprising:
Obtain multiple vehicle image samples in collected Roadside Parking region;
The multiple vehicle image sample is labeled and is trained by the deep learning method based on convolutional neural networks, is obtained
To vehicle training pattern.
6. according to the method described in claim 5, it is characterized in that, the coordinate information based on the parking stall, passes through vehicle
After the step of training pattern detects the vehicle location in the first video frame and the second video, comprising:
The vehicle location and parking stall position that will test in result carry out coordinate pair ratio, acquire the mass center of vehicle rectangular area;
Vehicle of the mass center in parking stall is calculated, and the information of the vehicle by mass center in parking stall is recorded into testing result.
7. according to the method described in claim 6, it is characterized in that, it is described be based on testing result, determine the Roadside Parking of vehicle
Behavior, comprising:
Based on testing result, determine whether the first video frame and the mass center situation of vehicle in the second video are consistent;
If consistent, determine the vehicle in the first video frame and the second video without Roadside Parking behavior;
If inconsistent, there are Roadside Parking behaviors for the vehicle for determining in the first video frame of vehicle and the second video;
Wherein, the mass center situation of the vehicle include mass center in parking stall and mass center not in parking stall in any feelings
Shape.
8. the method according to the description of claim 7 is characterized in that the vehicle in the first video frame of the determination and the second video
After the step of without Roadside Parking behavior, further includes:
It jumps and executes step a, until completing the calculating to each video frame.
9. the method according to the description of claim 7 is characterized in that the vehicle in first video frame of determining vehicle and the second video
After the step of there are Roadside Parking behaviors, further includes:
Step m, the second video frame of Roadside Parking behavior will be present as the first video frame redefined, and redefine
Two video frames, wherein the second video frame redefined is the latter video frame adjacent with the first video frame redefined;
By vehicle training pattern to the vehicle location in the first video frame redefined and the second video frame redefined
It is detected;
Based on testing result, if the mass center situation of the first video frame redefined and vehicle in the second video frame redefined
It is inconsistent, it jumps and executes step m, until the matter of the first video frame redefined and vehicle in the second video frame redefined
Mood shape is consistent.
10. a kind of device based on video frame identification Roadside Parking behavior characterized by comprising
First obtains module, and for obtaining the continuous multiple video frames acquired by video equipment, the video equipment is for adopting
Collect the image information in Roadside Parking region;
Drafting module for drawing parking stall region in the first video frame, and determines parking stall in the parking stall region
Coordinate information, first video frame are collected any video frame;
Difference Calculation module, for determining the second video frame, based on the parking stall region drawn, to the first video frame with
Second video frame carries out Difference Calculation, and the second video frame is the adjacent latter video frame with the first video frame;
Detection module, for judging whether calculated result meets predetermined detection rule, if satisfied, the coordinate based on the parking stall
Information detects the vehicle location in the first video frame and the second video by vehicle training pattern;
Determining module determines the Roadside Parking behavior of vehicle for being based on testing result.
11. device according to claim 10, which is characterized in that the Difference Calculation module is specifically used for
With the units chunk of predefined size, the image of the first video frame and the second video frame is divided into multiple first units chunks,
In, each position of the first units chunk in any video frame is identical;
Based on the parking area drawn, each first units chunk comprising the parking area is determined as the second unit
Block;
Calculate separately the pixel average of each second units chunk;
It determines in one-to-one second units chunk identical with the position in the second video frame of the position in the first video frame;
Calculate separately the difference value of the pixel average of each one-to-one second units chunk.
12. device according to claim 10, which is characterized in that the predetermined detection rule, comprising:
Judge whether each difference value being calculated is greater than predetermined difference value threshold value;
Statistics is greater than the number of the difference value of predetermined difference value threshold value, and judges whether the number is greater than predetermined number threshold value;
Wherein, the detection module, is specifically used for
If the number is greater than predetermined number threshold value, determine that calculated result meets predetermined detection rule;
If the number is less than predetermined number threshold value, determine that calculated result is unsatisfactory for predetermined detection rule.
13. device according to claim 12, if the detection module determines that calculated result is unsatisfactory for predetermined detection rule,
Include:
First redefines unit, for that will be unsatisfactory for the second video frame of predetermined detection rule as the first view redefined
Frequency frame, and redefine the second video frame, wherein the second video frame redefined is and the first video frame phase for redefining
Adjacent latter video frame;
Difference Calculation unit, by being carried out based on difference to the first video frame redefined with the second video frame redefined
It calculates, and judges whether calculated result meets predetermined detection rule;
First jump-transfer unit, for if not satisfied, jumping execution first redefines unit, until calculated result meet it is described pre-
Determine detected rule.
14. the described in any item devices of 0-13 according to claim 1 characterized by comprising
Second obtains module, for obtaining multiple vehicle image samples in collected Roadside Parking region;
Training module, for being carried out by the deep learning method based on convolutional neural networks to the multiple vehicle image sample
Mark and training, obtain vehicle training pattern.
15. device according to claim 14 characterized by comprising
Contrast module carrying out coordinate pair ratio for will test the vehicle location in result and parking stall position, acquiring vehicle rectangle
The mass center in region;
Computing module, for calculating vehicle of the mass center in parking stall, and the information record of the vehicle by mass center in parking stall
Into testing result.
16. device according to claim 15, which is characterized in that the determining module, comprising:
First determination unit determines that the mass center situation of vehicle in the first video frame and the second video is for being based on testing result
It is no consistent;
Second determination unit, if determining the vehicle in the first video frame and the second video without Roadside Parking behavior for consistent;
Third determination unit, if there are Roadside Parkings for the vehicle for determining in the first video frame of vehicle and the second video for inconsistent
Behavior;
Wherein, the mass center situation of the vehicle include mass center in parking stall and mass center not in parking stall in any feelings
Shape.
17. device according to claim 16, which is characterized in that second determination unit is also used to jump execution institute
It states first and redefines unit, until completing the calculating to each video frame.
18. device according to claim 16, which is characterized in that the third determination unit, further includes:
Second redefines unit, for the second video frame of Roadside Parking behavior to will be present as the first video redefined
Frame, and redefine the second video frame, wherein the second video frame redefined is adjacent with the first video frame redefined
Latter video frame;
Detection unit, for passing through vehicle training pattern to the first video frame redefined and the second video frame redefined
In vehicle location detected;
Second jump-transfer unit, for being based on testing result, if the first video frame redefined and the second video redefined
The mass center situation of vehicle is inconsistent in frame, jumps execution described second and redefines unit, until the first video redefined
Frame is consistent with the mass center situation of vehicle in the second video frame redefined.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910323229.1A CN110163107B (en) | 2019-04-22 | 2019-04-22 | Method and device for recognizing roadside parking behavior based on video frames |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910323229.1A CN110163107B (en) | 2019-04-22 | 2019-04-22 | Method and device for recognizing roadside parking behavior based on video frames |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110163107A true CN110163107A (en) | 2019-08-23 |
CN110163107B CN110163107B (en) | 2021-06-29 |
Family
ID=67639800
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910323229.1A Active CN110163107B (en) | 2019-04-22 | 2019-04-22 | Method and device for recognizing roadside parking behavior based on video frames |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110163107B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110517506A (en) * | 2019-08-26 | 2019-11-29 | 重庆同济同枥信息技术有限公司 | Method, apparatus and storage medium based on traffic video image detection Parking |
CN110688902A (en) * | 2019-08-30 | 2020-01-14 | 智慧互通科技有限公司 | Method and device for detecting vehicle area in parking space |
CN111178185A (en) * | 2019-12-17 | 2020-05-19 | 北京智芯原动科技有限公司 | High-level roadside parking detection method and device based on video |
CN111292353A (en) * | 2020-01-21 | 2020-06-16 | 成都恒创新星科技有限公司 | Parking state change identification method |
CN111476169A (en) * | 2020-04-08 | 2020-07-31 | 智慧互通科技有限公司 | Complex scene roadside parking behavior identification method based on video frames |
CN111739043A (en) * | 2020-04-13 | 2020-10-02 | 北京京东叁佰陆拾度电子商务有限公司 | Parking space drawing method, device, equipment and storage medium |
CN112766206A (en) * | 2021-01-28 | 2021-05-07 | 深圳市捷顺科技实业股份有限公司 | High-order video vehicle detection method and device, electronic equipment and storage medium |
CN113012467A (en) * | 2021-02-23 | 2021-06-22 | 中国联合网络通信集团有限公司 | Parking control method and device |
CN113052141A (en) * | 2021-04-26 | 2021-06-29 | 超级视线科技有限公司 | Method and device for detecting parking position of vehicle |
WO2021223418A1 (en) * | 2020-04-26 | 2021-11-11 | 智慧互通科技有限公司 | Parking detection method and apparatus employing visual difference |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1921590A1 (en) * | 2005-08-30 | 2008-05-14 | Matsushita Electric Industrial Co., Ltd. | Parking position search assisting apparatus, method and program |
CN102637360A (en) * | 2012-04-01 | 2012-08-15 | 长安大学 | Video-based road parking event detection method |
CN103325259A (en) * | 2013-07-09 | 2013-09-25 | 西安电子科技大学 | Illegal parking detection method based on multi-core synchronization |
CN105513371A (en) * | 2016-01-15 | 2016-04-20 | 昆明理工大学 | Expressway illegal parking detection method based on kernel density estimation |
CN106204643A (en) * | 2016-07-01 | 2016-12-07 | 湖南源信光电科技有限公司 | Multi-object tracking method based on multiple features combining Yu Mean Shift algorithm |
CN106384532A (en) * | 2015-07-31 | 2017-02-08 | 富士通株式会社 | Video data analysis method and apparatus thereof, and parking space monitoring system |
CN106504580A (en) * | 2016-12-07 | 2017-03-15 | 深圳市捷顺科技实业股份有限公司 | A kind of method for detecting parking stalls and device |
CN107404653A (en) * | 2017-05-23 | 2017-11-28 | 南京邮电大学 | A kind of Parking quick determination method of HEVC code streams |
-
2019
- 2019-04-22 CN CN201910323229.1A patent/CN110163107B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1921590A1 (en) * | 2005-08-30 | 2008-05-14 | Matsushita Electric Industrial Co., Ltd. | Parking position search assisting apparatus, method and program |
CN102637360A (en) * | 2012-04-01 | 2012-08-15 | 长安大学 | Video-based road parking event detection method |
CN103325259A (en) * | 2013-07-09 | 2013-09-25 | 西安电子科技大学 | Illegal parking detection method based on multi-core synchronization |
CN106384532A (en) * | 2015-07-31 | 2017-02-08 | 富士通株式会社 | Video data analysis method and apparatus thereof, and parking space monitoring system |
CN105513371A (en) * | 2016-01-15 | 2016-04-20 | 昆明理工大学 | Expressway illegal parking detection method based on kernel density estimation |
CN106204643A (en) * | 2016-07-01 | 2016-12-07 | 湖南源信光电科技有限公司 | Multi-object tracking method based on multiple features combining Yu Mean Shift algorithm |
CN106504580A (en) * | 2016-12-07 | 2017-03-15 | 深圳市捷顺科技实业股份有限公司 | A kind of method for detecting parking stalls and device |
CN107404653A (en) * | 2017-05-23 | 2017-11-28 | 南京邮电大学 | A kind of Parking quick determination method of HEVC code streams |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110517506A (en) * | 2019-08-26 | 2019-11-29 | 重庆同济同枥信息技术有限公司 | Method, apparatus and storage medium based on traffic video image detection Parking |
CN110688902B (en) * | 2019-08-30 | 2022-02-11 | 智慧互通科技股份有限公司 | Method and device for detecting vehicle area in parking space |
CN110688902A (en) * | 2019-08-30 | 2020-01-14 | 智慧互通科技有限公司 | Method and device for detecting vehicle area in parking space |
CN111178185A (en) * | 2019-12-17 | 2020-05-19 | 北京智芯原动科技有限公司 | High-level roadside parking detection method and device based on video |
CN111292353A (en) * | 2020-01-21 | 2020-06-16 | 成都恒创新星科技有限公司 | Parking state change identification method |
CN111292353B (en) * | 2020-01-21 | 2023-12-19 | 成都恒创新星科技有限公司 | Parking state change identification method |
CN111476169A (en) * | 2020-04-08 | 2020-07-31 | 智慧互通科技有限公司 | Complex scene roadside parking behavior identification method based on video frames |
CN111476169B (en) * | 2020-04-08 | 2023-11-07 | 智慧互通科技股份有限公司 | Complex scene road side parking behavior identification method based on video frame |
WO2021203717A1 (en) * | 2020-04-08 | 2021-10-14 | 智慧互通科技有限公司 | Method for recognizing roadside parking behavior in complex scenario on basis of video frames |
CN111739043A (en) * | 2020-04-13 | 2020-10-02 | 北京京东叁佰陆拾度电子商务有限公司 | Parking space drawing method, device, equipment and storage medium |
CN111739043B (en) * | 2020-04-13 | 2023-08-08 | 北京京东叁佰陆拾度电子商务有限公司 | Parking space drawing method, device, equipment and storage medium |
US11398092B2 (en) | 2020-04-26 | 2022-07-26 | Intelligent Inter Connection Technology Co., Ltd. | Parking detection method and device based on visual difference |
WO2021223418A1 (en) * | 2020-04-26 | 2021-11-11 | 智慧互通科技有限公司 | Parking detection method and apparatus employing visual difference |
CN112766206A (en) * | 2021-01-28 | 2021-05-07 | 深圳市捷顺科技实业股份有限公司 | High-order video vehicle detection method and device, electronic equipment and storage medium |
CN112766206B (en) * | 2021-01-28 | 2024-05-28 | 深圳市捷顺科技实业股份有限公司 | High-order video vehicle detection method and device, electronic equipment and storage medium |
CN113012467A (en) * | 2021-02-23 | 2021-06-22 | 中国联合网络通信集团有限公司 | Parking control method and device |
CN113052141A (en) * | 2021-04-26 | 2021-06-29 | 超级视线科技有限公司 | Method and device for detecting parking position of vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN110163107B (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110163107A (en) | A kind of method and device based on video frame identification Roadside Parking behavior | |
CN110717433A (en) | Deep learning-based traffic violation analysis method and device | |
CN101631237B (en) | Video monitoring data storing and managing system | |
CN107301776A (en) | Track road conditions processing and dissemination method based on video detection technology | |
CN110491168A (en) | A kind of method and device based on wheel touchdown point detection vehicle stopped state | |
CN106530818A (en) | Intelligent parking lot management system based on video processing technology | |
CN109615928A (en) | A kind of parking management system in coverage hole berth | |
CN101216996A (en) | A method for monitoring vehicle offences by video | |
CN107590999A (en) | A kind of traffic state judging method based on bayonet socket data | |
CN106169253A (en) | Parking lot based on parking difficulty idle condition Forecasting Methodology and system | |
CN110032947A (en) | A kind of method and device that monitor event occurs | |
CN102890866A (en) | Traffic flow speed estimation method based on multi-core support vector regression machine | |
CN105023300A (en) | Parking lot management system based on big data | |
CN105373774A (en) | Method for detecting physical punishment behaviors of kindergarten teachers on children | |
CN104008659B (en) | A kind of system and method precisely monitoring intersection signal control device control effects | |
CN111445700B (en) | Regional running and stopping vehicle monitoring method based on license plate identification data | |
CN113205689A (en) | Multi-dimension-based roadside parking admission event judgment method and system | |
CN109766743A (en) | A kind of intelligent bionic policing system | |
CN111159625A (en) | Urban green wave coordination effect evaluation system | |
CN104318760A (en) | Crossing violation behavior intelligent detection method and system based on analog model | |
CN108682154B (en) | Road congestion detection system based on deep learning analysis of traffic flow state change | |
CN109920253A (en) | Parking charge method and system based on vehicle regular visit | |
CN109325445A (en) | A kind of method and device of Car license recognition classification | |
CN115027497B (en) | Target vehicle cut-in intention prediction method and readable storage medium | |
CN103996308B (en) | A kind of system and method for energy Real-Time Monitoring intersection signal control effect |
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 | ||
CB02 | Change of applicant information |
Address after: 075000 ten building, phase 1, airport economic and Technological Development Zone, Zhangjiakou, Hebei Applicant after: Smart intercommunication Technology Co.,Ltd. Address before: 075000 ten building, phase 1, airport economic and Technological Development Zone, Zhangjiakou, Hebei Applicant before: INTELLIGENT INTERCONNECTION TECHNOLOGIES Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |