CN109615928A - A kind of parking management system in coverage hole berth - Google Patents
A kind of parking management system in coverage hole berth Download PDFInfo
- Publication number
- CN109615928A CN109615928A CN201910103278.4A CN201910103278A CN109615928A CN 109615928 A CN109615928 A CN 109615928A CN 201910103278 A CN201910103278 A CN 201910103278A CN 109615928 A CN109615928 A CN 109615928A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- berth
- target
- picture
- 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
Classifications
-
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a kind of parking management system in coverage hole berth, the parking management systems, comprising: at least one camera shooting unit, main controller and at least one mounting rod or installation position;At least one described mounting rod or installation position configure in Roadside Parking berth region;At least one described camera shooting unit, is located on each mounting rod or installation position, for acquiring Roadside Parking berth area image, the parking position region includes the blind area berth of the underface vertical with each mounting rod or installation position;The main controller is used to the occupied information in each berth in Roadside Parking berth region is determined, for being managed Roadside Parking by analyzing collected Roadside Parking berth area image.By means of the invention it is possible to carry out parking management to each berth for including blind area berth, the defect of parking management can not be carried out to blind area berth by solving existing elevated video.
Description
Technical field
The present invention relates to intelligent parking management technical field more particularly to a kind of parking management systems in coverage hole berth
System.
Background technique
The parking of City-level wisdom refers to AI (Artificial Intelligence, artificial intelligence), internet, cloud
The cutting edge technologies such as calculating, big data, financial technology acquire parking space information using multiple terminal equipment, are applied to city parking position
Information collection, management, inquiry, reservation and navigation, to realize the maximization and parking service of parking stall resource utilization
It optimizes.In City-level wisdom parking management, the necessity of Roadside Parking field wisdom management is especially prominent, to improvement city
Traffic condition and parking efficiency are also more significant.
The major technique realization of Roadside Parking management at present is several based on earth magnetism, the video stake of low level road surface and elevated video
Mode, elevated video since the berth of its single device management is more, installation site is high, do not destroy road surface, scene is adaptable and
The easy advantage of the abundant evidence obtaining of parking data, it has also become each preferred Roadside Parking way to manage in big city, still, elevated video
Equipment is due to installation site height, and there are blind area berths immediately below a bar, is commonly called as " black under lamp ", in city Roadside Parking field reality
The problem that part berth can not manage can be encountered in construction.Currently, the technical solution of the management in existing elevated video blind area berth
Mainly there are several types of:
One, intersected using adjacent stems position and managed
Under this kind of mode, the blind area berth under this bar position is needed using the elevated video equipment of previous bar position come pipe
It manages, within the scope of the elevated video equipment management that the blind area berth under this bar position is incorporated into previous bar position;Which exists such as
Lower defect: needing to consider the distance between adjacent stems position when construction, guarantees the distance between two video bar positions in elevated video
In the administrative distance of equipment;However in actually construction, since trackside situation is complicated, it is frequently encountered various crossings, Wu Fabao
Card the distance between bar and bar meet above-mentioned requirements;Meanwhile for the starting bar position of trackside, then can not by previous bar position come
Manage on behalf of another the blind area berth under the starting bar position;
Two, it is detected using range sensor
Under this kind of mode, a range sensor need to be installed on this bar position, such as radar sensor, ultrasonic sensor
Deng, when have vehicle enter the blind area berth after, range sensor can detect ground level and change, then notice management
Personnel carry out being manually entered evidence obtaining;Which has following defects that range sensor vulnerable to environmental disturbances, is there is pedestrian, voluntarily
After the non-motor vehicles such as vehicle enter sensor investigative range, it may occur that the case where false triggering;Which still needs manual entry, nothing
Method realizes real wisdom unattended;
Three, using the mode of range sensor combination video
Under this kind of mode, a range sensor need to be installed on this bar position, such as radar sensor, ultrasonic sensor
Deng, when have vehicle enter the blind area berth after, range sensor can detect ground level and change, and then notify video
Backtracking process is carried out, evidence obtaining process is completed;Which, which has following defects that, still needs the range sensor to be to confirm in berth
No the case where vehicle is parked, but range sensor can not differentiate the targets such as motor vehicles, non power driven vehicle and pedestrian, it can not
Truly confirm the true use state in berth;In addition, the license plate recalled by video mode, it may be possible to other
The case where passing by one's way vehicle, can not be matched with the vehicle for being really parked in blind area berth, being easy to happen mispick card.
Summary of the invention
The embodiment of the present invention provides a kind of parking management system in coverage hole berth, can be to each including blind area berth
A berth carries out parking management, and the defect of parking management can not be carried out to blind area berth by solving existing elevated video.
The embodiment of the invention provides a kind of parking management system in coverage hole berth, the parking management system, packets
It includes: at least one camera shooting unit, main controller and at least one mounting rod or installation position;
At least one described mounting rod or installation position configure in Roadside Parking berth region;
At least one described camera shooting unit, is located on each mounting rod or installation position, stops for acquiring trackside
Vehicle berth area image, the parking position region include the blind area of the underface vertical with each mounting rod or installation position
Berth;
The main controller is used to determine Roadside Parking berth by analyzing collected Roadside Parking berth area image
The occupied information in each berth in region, for being managed to Roadside Parking.
Above-mentioned technical proposal has the following beneficial effects: by means of the invention it is possible to each berth including blind area berth
Parking management is carried out, the defect of parking management can not be carried out to blind area berth by solving existing elevated video;Meanwhile based on camera shooting
The collected Roadside Parking berth area image of unit polyphaser determines road by the way that artificial intelligence deep learning algorithm is utilized
The occupied information in each berth in side parking position region, gets rid of dependence of the parking management to traditional sensors, realizing can
Reliable, accurate, efficiently blind area berth under bar can be managed by surrounding environment influence, further, be saved
The management cost of parking management.
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 structural schematic diagram of the parking management system in coverage hole berth in the embodiment of the present invention;
Fig. 2 shows for each section positional relationship in the parking management system in coverage hole berth a kind of in one embodiment of the invention
It is intended to;
Fig. 3 is a kind of middle vehicle admission pipe of the parking management system in coverage hole berth in one embodiment of the present invention
Manage flow diagram;
Fig. 4 is a kind of vehicle appearance management of the parking management system in coverage hole berth in one embodiment of the present invention
Flow diagram;
Fig. 5 is a kind of vehicle backtracking process of the parking management system in coverage hole berth in one embodiment of the present invention
Flow diagram.
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 a kind of structural schematic diagram of the parking management system in coverage hole berth in the embodiment of the present invention,
The parking management system, comprising: at least one camera shooting unit, main controller and at least one mounting rod or installation position;
At least one described mounting rod or installation position configure in Roadside Parking berth region;
At least one described camera shooting unit, is located on each mounting rod or installation position, stops for acquiring trackside
Vehicle berth area image, the parking position region include the blind area of the underface vertical with each mounting rod or installation position
Berth;
The main controller is used to determine Roadside Parking berth by analyzing collected Roadside Parking berth area image
The occupied information in each berth in region, for being managed to Roadside Parking.
Further, at least one described mounting rod or installation position configure in Roadside Parking region, comprising:
At least one described mounting rod or installation position, configuration are sailed in the vehicle with the predetermined berth in Roadside Parking berth region
Enter end/vehicle to be driven out on the position of end at a predetermined distance.
Further, at least one described camera shooting unit, is located on each mounting rod or installation position, specific to wrap
It includes:
Each camera shooting unit includes at least two video cameras, and at least two video camera is located at the video camera
The left and right sides on mounting rod or installation position where group with trackside berth parallel direction;
Wherein, at least one camera shooting on the mounting rod or installation position with the left side of trackside berth parallel direction
Machine is the first video camera, with the mounting rod or installation position is directly vertically below starting point side parallel with trackside berth for acquiring
To left area the first parking area image;
Wherein, at least one camera shooting on the mounting rod or installation position with the right side of trackside berth parallel direction
Machine is the second video camera, with the mounting rod or installation position is directly vertically below starting point side parallel with trackside berth for acquiring
To right area the second parking area image.
Further, the main controller is used to determine road by analyzing collected Roadside Parking berth area image
The occupied information in each berth in side parking position region, comprising:
Unit is imaged for each, the main controller is based on preset frequency and images from each of current camera group
The picture of predetermined resolution is obtained in machine;
It determines the picture got in predetermined video camera, is based on the preset frequency, passes through preset vehicle detection model pair
The picture that gets from the predetermined video camera carries out the detection of vehicle target, and judges described predetermined take the photograph according to testing result
Whether the parking area of camera acquisition image range detects vehicle target;
According to judging result, the dead ship condition of the target vehicle is determined.
Further, the preset vehicle detection model is to be trained by predetermined depth learning algorithm from each video camera
The vehicle detection model that the plurality of pictures of predetermined resolution obtains is obtained in each of group video camera;
Wherein, the detection of the vehicle target includes the field detecting out for entering field detecting and/or vehicle target of vehicle target.
Optionally, described for each camera shooting unit, the main controller is based on preset frequency from current camera group
Each video camera in obtain predetermined resolution picture, further includes:
The each image cache that will acquire is in the memory in the main controller, and when recording the caching of each picture
Between;
When the cache-time of any picture is more than the predetermined cache time, the buffer address of any picture is emptied.
Further, the picture got in the predetermined video camera of the determination is based on the preset frequency, passes through predetermined vehicle
Detection model carries out the detection of vehicle target to the picture got from the predetermined video camera, and sentences according to testing result
Whether the parking area for the predetermined video camera acquisition image range of breaking detects vehicle target, comprising:
Based on the picture got from each video camera, determine that the picture and second of the first video camera got is taken the photograph
The picture of camera;
Based on the preset frequency, is determined by preset vehicle detection model and acquired in the first video camera of current camera group
Whether the second parking area of the first parking area and the second video camera of current camera group the acquisition image of image detects vehicle
Target.
Further, described based on the picture got from each video camera, determine the first video camera got
Picture and the second video camera picture, comprising:
It determines in the picture of the first video camera and the picture of the second video camera got comprising where current camera group
The picture in the blind area berth region of the vertical underface of mounting rod or installation position;
Wherein, described determined by preset vehicle detection model acquires the of image in the first video camera of current camera group
Whether the second parking area of one parking area and the second video camera of current camera group acquisition image detects vehicle target, wraps
It includes:
By preset vehicle detection model determine mounting rod where current camera group or installation position it is vertical just under
Whether vehicle target is detected in the blind area berth of side.
Further, it is detected as when entering field detecting of vehicle target when vehicle target, parking position region is examined if judging
Vehicle target is measured, it is described according to judging result, determine the dead ship condition of the target vehicle, comprising:
If parking position region detection obtains vehicle target judgement to vehicle target, by the preset vehicle detection model
Value;
According to the judgment value, determine whether the judgment value is greater than preset judgment threshold value;
If more than then confirming that the vehicle target that detects is motor vehicles, and pass through the preset vehicle detection model meter
Calculation obtains the vehicle characteristics value of the vehicle target, and determines whether there is the last vehicle that the vehicle target is calculated
Characteristic value;
If it exists, the vehicle is calculated with described in the more last vehicle characteristics value that the vehicle target is calculated
Whether the vehicle characteristics value of target is consistent;
If consistent, the more consistent number of vehicle characteristics value of the vehicle target is counted, and determines time of the statistics
Whether number is more than predetermined relatively threshold value;
If being more than, determine that the vehicle target has been parked in parking position.
Further, it is detected as when going out field detecting of vehicle target when vehicle target, if judging parking position region not
Detect vehicle target, it is described according to judging result, determine the dead ship condition of the target vehicle, comprising:
If vehicle target is not detected in parking position region, in the detection for carrying out vehicle target, it is determined whether continuous super
It crosses pre-determined number and target vehicle is not detected;
If continuing to exceed pre-determined number is not detected target vehicle, determine that the target vehicle has left parking position.
Optionally, further includes:
In the picture of the memory buffer in the main controller, determine in the given time in each of current camera group
The picture to be processed cached in a video camera;
The license plate target detection of vehicle target is carried out to the picture to be processed by preset vehicle detection model;
If detecting the license plate of vehicle target, by the vehicle mesh for detecting license plate described in the judgement of preset vehicle detection model
Whether target vehicle characteristics are consistent with the vehicle characteristics for being parked in vehicle in parking position region;
If consistent, correction process is carried out to the license plate picture for detecting vehicle target by predetermined correction algorithm;
Car license recognition is carried out by picture of the Recognition Algorithm of License Plate to the license plate of the vehicle target after the correction process;
Based on the license board information of the vehicle target recognized, the parking forensic information of the vehicle target is generated.
Wherein, the parking forensic information includes the license plate number of vehicle target, the license plate picture of vehicle target, vehicle mesh
At least one of in target entry time and the time for competiton of vehicle target.
Above-mentioned technical proposal of the embodiment of the present invention has the following beneficial effects: by means of the invention it is possible to including that blind area is moored
Each berth of position carries out parking management, and the defect of parking management can not be carried out to blind area berth by solving existing elevated video;
Meanwhile based on the camera shooting collected Roadside Parking berth area image of unit polyphaser, by the way that artificial intelligence depth is utilized
Practise algorithm, determine the occupied information in each berth in Roadside Parking berth region, get rid of parking management to traditional sensors according to
Rely, realize reliable, accurate, efficiently can not can be managed blind area berth under bar by surrounding environment influence, into
One step, save the management cost of parking management.
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 that parking management can be carried out to each berth for including blind area berth, solves existing
Elevated video can not carry out the defect of parking management to blind area berth.
As shown in Figure 1, for example, in parking management system S, including at least one camera shooting unit, main controller and at least one
A mounting rod perhaps installation position at least one mounting rod or installation position configure in Roadside Parking berth region;Wherein, it takes the photograph
The quantity of camera group and mounting rod perhaps identical each the video camera group of the quantity of installation position be located at a mounting rod or
On installation position;Each camera shooting unit, includes such as video camera A and video camera B, for acquiring Roadside Parking berth area image;
Main controller configures at least one mounting rod or installation position, which is used for according to collected Roadside Parking berth
Area image determines the occupied information in each berth in Roadside Parking berth region, for being managed to Roadside Parking.Its
In, in each mounting rod perhaps installation position parking management system camera shooting unit, main controller and mounting rod or installation
Positional relationship of the position in Roadside Parking region is as shown in Figure 1;The system structure diagram of parking management system S is as shown in Fig. 2, need
It is noted that main controller is AI terminal device, artificial intelligence platform is can be used in core calculations platform, the artificial intelligent platform
Library, computer vision library, GPU (Graphics Processing Unit, graphics processor) hardware are calculated comprising deep learning
Calculate and accelerate multiple library basic softwares such as library and multimedia processing library, include deep learning algorithm of target detection in the platform with
And Parking processing software;Image unit, as in Fig. 2 video camera A and video camera B be web camera, can export
RTSP (Real Time Streaming Protocol, real time streaming transport protocol) code stream, while network snapshots can also be passed through
Grabgraf;Interchanger is interconnected for main controller and video camera A and video camera B, 4G (Fourth Generation
Communications System, forth generation mobile communication system) router is for letter between main controller and cloud server
Breath interaction;Cloud server, for receiving, handling parking forensic information, and generation parking evidence obtaining record.
It should be noted that the quantity of main controller without limitation, can be with when the quantity of main controller is multiple in the present invention
Be arranged respectively on multiple installation positions or mounting rod according to demand, multiple main controllers can also be configured in same mounting rod or
On person installation position, it is not limited here.
In a kind of possible embodiment, at least one described mounting rod or installation position are configured in Roadside Parking area
Domain, comprising: at least one described mounting rod or installation position, configuration are sailed in the vehicle with the predetermined berth in Roadside Parking berth region
Enter end/vehicle to be driven out on the position of end at a predetermined distance.At least one described camera shooting unit, is located at each mounting rod
Or on installation position, specifically include: each camera shooting unit includes at least two video cameras, at least two video cameras difference
Positioned at where the camera shooting unit mounting rod or installation position on the left and right sides with trackside berth parallel direction.
Wherein, at least one camera shooting on the mounting rod or installation position with the left side of trackside berth parallel direction
Machine is the first video camera, with the mounting rod or installation position is directly vertically below starting point side parallel with trackside berth for acquiring
To left area the first parking area image.
Wherein, at least one camera shooting on the mounting rod or installation position with the right side of trackside berth parallel direction
Machine is the second video camera, with the mounting rod or installation position is directly vertically below starting point side parallel with trackside berth for acquiring
To right area the second parking area image.
For example, in parking management system S, at least one mounting rod or installation position, configuration with Roadside Parking berth
The vehicle in the predetermined berth in region drives into end/vehicle and is driven out on the position of end at a predetermined distance, and as shown in fig. 1, mounting rod is matched
It sets and drives into end in the vehicle with the Roadside Parking berth region berth P1, is i.e. the berth P1 left-hand end rises at a distance of the position of 1/3 berth distance
It sets;Each camera shooting unit, including at least two video cameras, video camera A and video camera B as shown in Figure 2 are located at
On mounting rod or installation position with the left and right sides of trackside berth parallel direction.
Through this embodiment, it realizes and Image Acquisition and analysis is carried out to the parking position in blind area berth, it can be accurate, fast
Fast ground is managed blind area berth.
In a kind of possible embodiment, the main controller is used for by analyzing collected Roadside Parking berth area
Area image determines the occupied information in each berth in Roadside Parking berth region, comprising: for each camera shooting unit, the master
Control device obtains the picture of predetermined resolution based on preset frequency from each of current camera group video camera;It determines predetermined
The picture got in video camera is based on the preset frequency, by preset vehicle detection model to from the predetermined video camera
In the picture that gets carry out the detection of vehicle target, and judge the predetermined video camera acquisition image range according to testing result
Parking area whether detect vehicle target;According to judging result, the dead ship condition of the target vehicle is determined.
Wherein, the preset vehicle detection model is to be imaged in unit by the training of predetermined depth learning algorithm from each
Each video camera in obtain the obtained vehicle detection model of plurality of pictures of predetermined resolution;The detection of the vehicle target
The field detecting out for entering field detecting and/or vehicle target including vehicle target.
For example, in parking management system S, unit is imaged for each, main controller is based on preset frequency, such as 2 seconds/
It is secondary, the picture of predetermined resolution is obtained from the video camera A and video camera B in camera shooting unit, as resolution ratio is 1080*1920
Picture;It is then determined that predetermined video camera, such as video camera A and/or video camera B, in the picture that gets, and based on the predetermined frequency
Rate, such as 2 seconds/time carry out vehicle target to the picture got from the predetermined video camera by preset vehicle detection model
Detection, wherein the detection of vehicle target includes the field detecting out for entering field detecting and/or vehicle target of vehicle target.
It should be noted that it will be understood by those skilled in the art that preset vehicle detection model in the present invention, is to pass through
What the picture got in deep learning image object detection algorithm training camera shooting unit obtained, the detection of deep learning image object
Algorithm, such as Caffe (Convolutional Architecture for Fast Feature Embedding, convolutional Neural net
Network frame), though it can illustrate so that certain depth learns image object detection algorithm as an example in the present invention, it is not limited here.
It is described for each camera shooting unit in a kind of possible embodiment, it is based on by the main controller predetermined
Frequency obtains the picture of predetermined resolution from each of current camera group video camera, further includes: what be will acquire is each
A image cache records the cache-time of each picture in the memory in the main controller;When the caching of any picture
When time is more than the predetermined cache time, the buffer address of any picture is emptied.
For example, imaging unit for each, main controller is based on preset frequency from when proactive in parking management system S
After the picture for obtaining predetermined resolution in each of camera group video camera, each image cache that will acquire is in main controller
In memory in, in the flash storage in main controller, and record the cache-time of each picture;When any picture
Cache-time is more than the predetermined cache time, such as 15 minutes, the buffer address of the picture is emptied, with the figure for caching subsequent acquisition
Piece realizes the circulation covering of picture, to effectively utilize the memory space of memory.
In a kind of possible embodiment, the picture got in the predetermined video camera of determination, based on described predetermined
Frequency carries out the detection of vehicle target by preset vehicle detection model to the picture got from the predetermined video camera,
And judge whether the parking area of the predetermined video camera acquisition image range detects vehicle target according to testing result, it wraps
It includes: based on the picture got from each video camera, determining the picture and the second video camera of the first video camera got
Picture;Based on the preset frequency, is determined by preset vehicle detection model and acquired in the first video camera of current camera group
Whether the second parking area of the first parking area and the second video camera of current camera group the acquisition image of image detects vehicle
Target.
Wherein, described based on the picture got from each video camera, determine the figure of the first video camera got
The picture of piece and the second video camera, comprising: determine and wrapped in the picture of the first video camera and the picture of the second video camera that get
The picture in the blind area berth region of the vertical underface of mounting rod where group containing current camera or installation position.
Wherein, described determined by preset vehicle detection model acquires the of image in the first video camera of current camera group
Whether the second parking area of one parking area and the second video camera of current camera group acquisition image detects vehicle target, wraps
It includes: being determined by preset vehicle detection model in the blind of the vertical underface of mounting rod where current camera group or installation position
Whether vehicle target is detected in area berth.
For example, in parking management system S, unit is imaged for each, main controller is based on preset frequency, such as 2 seconds/
It is secondary, the picture of predetermined resolution is obtained from the video camera A and video camera B in current camera group, if resolution ratio is 1080*
1920 picture;Based on the preset frequency, such as 2 seconds/time, determined by preset vehicle detection model in current camera group first
First parking area of video camera acquisition image and the second parking area of the second video camera of current camera group acquisition image are
It is no to detect vehicle target;When for current camera group, however, it is determined that the picture of the video camera A got and the figure of video camera B
The picture in the blind area berth region comprising the vertical underface of mounting rod where current camera group or installation position in piece, passes through
Preset vehicle detection model determines in the blind area berth of the vertical underface of mounting rod where current camera group or installation position
Inside whether detect vehicle target.
Through this embodiment, whether detection parking area that can be comprehensive has vehicle target, and avoiding can not be accurately
Detect whether blind area berth has the case where vehicle target.
In a kind of possible embodiment, it is detected as when entering field detecting of vehicle target when vehicle target, if judgement
Parking position region detection is described according to judging result to vehicle target, determines the dead ship condition of the target vehicle, comprising:
If parking position region detection obtains vehicle target judgment value to vehicle target, by the preset vehicle detection model;According to
The judgment value, determines whether the judgment value is greater than preset judgment threshold value;If more than then confirming that the vehicle target detected is
Motor vehicles, and the vehicle characteristics value of the vehicle target is calculated by the preset vehicle detection model, and determination is
The no vehicle characteristics value that the vehicle target is calculated in the presence of the last time;If it exists, more last that the vehicle is calculated
Whether the vehicle characteristics value and the vehicle characteristics value that the vehicle target is calculated of target are consistent;If consistent, statistics
The more consistent number of vehicle characteristics value of the vehicle target, and determine whether the number of the statistics is more than predetermined relatively threshold
Value;If being more than, determine that the vehicle target has been parked in parking position.
For example, example is connected, if in the first parking area of the first video camera of current camera group acquisition image and when proactive
Second parking area of the second video camera of camera group acquisition image detects vehicle target, is obtained by preset vehicle detection model
Vehicle target judgment value, if confidence value is 0.93;If preset judgment threshold value is 0.9, it is later determined that confidence value 0.93 is greater than
Preset judgment threshold value 0.9 then confirms that the vehicle target detected is motor vehicles, and is calculated by preset vehicle detection model
To the vehicle characteristics value of the vehicle target;In the detection process for carrying out vehicle target, it is determined whether there are the last times to calculate
To the vehicle characteristics value of the vehicle target;If it exists, pass through the more last vehicle target of being calculated of cosine similarity
Whether vehicle characteristics value and the vehicle characteristics value that the vehicle target is calculated in this are consistent;If consistent, the vehicle target is counted
The more consistent number of vehicle characteristics value, for example 12 times, if predetermined relatively threshold value is 10, and determine number 12 times of the statistics
More than predetermined relatively threshold value, determine that the vehicle target has been parked in parking position.The admission testing process schematic diagram of vehicle target
As shown in Figure 3.Through this embodiment, dependence of the parking management to traditional sensors is got rid of, it can simply, accurately, efficiently
Vehicle target is carried out further to greatly improve the accuracy rate of the management to parking position into field detecting.
It should be noted that those skilled in the art are it can be appreciated that cosine similarity, also known as cosine similarity, are
Their similarity is assessed by calculating the included angle cosine value of two vectors.Cosine similarity according to coordinate value, draws vector
Make in vector space, such as the most common two-dimensional space, though the present invention in can in a specific way for carry out the last calculating of comparison
Whether consistent obtain the vehicle characteristics value that the vehicle target is calculated with this in the vehicle characteristics value of the vehicle target, but herein
Without limitation.
In a kind of possible embodiment, it is detected as when going out field detecting of vehicle target when vehicle target, if judgement
Vehicle target is not detected in parking position region, described to determine the dead ship condition of the target vehicle according to judging result, packet
It includes: if vehicle target is not detected in parking position region, in the detection for carrying out vehicle target, it is determined whether continue to exceed predetermined
Target vehicle is not detected in number;If continuing to exceed pre-determined number is not detected target vehicle, determine the target vehicle from
Driving and parking berth.
For example, in parking management system S, unit is imaged for each, main controller is based on preset frequency, such as 2 seconds/
It is secondary, the picture of predetermined resolution is obtained from the video camera A and video camera B in current camera group, if resolution ratio is 1080*
1920 picture;Based on the preset frequency, such as 2 seconds/time, determined by preset vehicle detection model in current camera group first
First parking area of video camera acquisition image and the second parking area of the second video camera of current camera group acquisition image are
It is no to detect vehicle target;If vehicle target is not detected, in the detection for carrying out vehicle target, however, it is determined that continue to exceed predetermined
Number, such as 5 times, are not detected target vehicle, determine that the target vehicle has left parking position.The appearance detection stream of vehicle target
Journey schematic diagram is as shown in Figure 4.
Through this embodiment, dependence of the parking management to traditional sensors is got rid of, it can be simple, accurate, efficiently right
Vehicle target carries out out field detecting, further greatly improves the accuracy rate of the management to parking position.
In a kind of possible embodiment, the system further include: the picture of the memory buffer in the main controller
In, determine the picture to be processed cached in each video camera of current camera group in the given time;Pass through predetermined vehicle
Detection model carries out the license plate target detection of vehicle target to the picture to be processed;If detecting the license plate of vehicle target,
By preset vehicle detection model judgement described in detect license plate vehicle target vehicle characteristics whether be parked in parking pool
The vehicle characteristics of vehicle are consistent in the region of position;If consistent, by predetermined correction algorithm to the license plate for detecting vehicle target
Picture carries out correction process;Vehicle is carried out by picture of the Recognition Algorithm of License Plate to the license plate of the vehicle target after the correction process
Board identification;Based on the license board information of the vehicle target recognized, the parking forensic information of the vehicle target is generated.
Wherein, the parking forensic information includes the license plate number of vehicle target, the license plate picture of vehicle target, vehicle mesh
At least one of in target entry time and the time for competiton of vehicle target.
For example, in parking management system S, after completing the admission of vehicle target/go out field detecting, in main controller
It in the picture of flash storage caching, determines in the given time, as each in the current camera group that in 1 minute, has cached
The picture to be processed of a video camera;It is examined by the license plate target that preset vehicle detection model carries out vehicle target to picture to be processed
It surveys;If detecting the license plate of vehicle target, judge that this detects the vehicle of the vehicle target of license plate by preset vehicle detection model
Whether feature is consistent with the vehicle characteristics for being parked in vehicle in parking position region;If consistent, by predetermined correction algorithm, such as
Affine transformation or perspective transform detect that the license plate picture of vehicle target carries out correction process to this;Pass through Recognition Algorithm of License Plate
Car license recognition is carried out to the picture of the license plate of the vehicle target after correction process;License plate letter based on the vehicle target recognized
Breath, generates the parking forensic information of the vehicle target, as the license plate number information of vehicle target, the license plate picture of vehicle target are believed
The time for competiton information of breath, the entry time information of vehicle target and vehicle target.Wherein, the vehicle of parking management system S returns
Processing flow schematic diagram of tracing back is as shown in Figure 5.
Through this embodiment, the docking process of vehicle can be recalled without traditional sensors by realizing, together
When, vehicle target information is confirmed by preset vehicle detection model, can quickly and accurately carry out returning for vehicle parking process
It traces back, so that the evidence obtaining of completion information of vehicles and the acquisition of vehicle related service information further improve accurately and in time
The usage experience of user.
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 (11)
1. a kind of parking management system in coverage hole berth, which is characterized in that the parking management system, comprising: at least one
A camera shooting unit, main controller and at least one mounting rod or installation position;
At least one described mounting rod or installation position configure in Roadside Parking berth region;
At least one described camera shooting unit, is located on each mounting rod or installation position, for acquiring Roadside Parking pool
Position area image, the parking position region include the blind area pool of the underface vertical with each mounting rod or installation position
Position;
The main controller is used to determine Roadside Parking berth region by analyzing collected Roadside Parking berth area image
The occupied information in each berth, for being managed to Roadside Parking.
2. parking management system according to claim 1, which is characterized in that at least one described mounting rod or installation
Position configures in Roadside Parking region, comprising:
At least one described mounting rod or installation position, configuration are driven into the vehicle with the predetermined berth in Roadside Parking berth region
End/vehicle is driven out on the position of end at a predetermined distance.
3. parking management system according to claim 2, which is characterized in that at least one described camera shooting unit, difference position
In on each mounting rod or installation position, specifically include:
Each camera shooting unit includes at least two video cameras, and at least two video camera is located at camera shooting unit institute
Mounting rod or installation position on the left and right sides with trackside berth parallel direction;
Wherein, at least one video camera on the mounting rod or installation position with the left side of trackside berth parallel direction is
First video camera with the mounting rod or installation position is directly vertically below starting point and trackside berth parallel direction for acquiring
First parking area image of left area;
Wherein, at least one video camera on the mounting rod or installation position with the right side of trackside berth parallel direction is
Second video camera with the mounting rod or installation position is directly vertically below starting point and trackside berth parallel direction for acquiring
Second parking area image of right area.
4. parking management system according to claim 3, which is characterized in that the main controller is used to acquire by analysis
The Roadside Parking berth area image arrived, determines the occupied information in each berth in Roadside Parking berth region, comprising:
Unit is imaged for each, the main controller is based on preset frequency from each of current camera group video camera
Obtain the picture of predetermined resolution;
It determines the picture got in predetermined video camera, is based on the preset frequency, by preset vehicle detection model to from institute
It states the picture got in predetermined video camera and carries out the detection of vehicle target, and judge the predetermined video camera according to testing result
Whether the parking area of acquisition image range detects vehicle target;
According to judging result, the dead ship condition of the target vehicle is determined.
5. parking management system according to claim 4, the preset vehicle detection model is to be learnt by predetermined depth
Algorithm training obtains the vehicle that the plurality of pictures of predetermined resolution obtains from each of each camera shooting unit video camera
Detection model;
Wherein, the detection of the vehicle target includes the field detecting out for entering field detecting and/or vehicle target of vehicle target.
6. parking management system according to claim 4 or 5, which is characterized in that described for each camera shooting unit, institute
The picture that main controller obtains predetermined resolution based on preset frequency from each of current camera group video camera is stated, is also wrapped
It includes:
The each image cache that will acquire records the cache-time of each picture in the memory in the main controller;
When the cache-time of any picture is more than the predetermined cache time, the buffer address of any picture is emptied.
7. parking management system according to claim 6, which is characterized in that got in the predetermined video camera of determination
Picture, be based on the preset frequency, by preset vehicle detection model to the picture got from the predetermined video camera into
The detection of row vehicle target, and judge whether the parking area of the predetermined video camera acquisition image range is examined according to testing result
Measure vehicle target, comprising:
Based on the picture got from each video camera, the picture and the second video camera of the first video camera got are determined
Picture;
Based on the preset frequency, is determined by preset vehicle detection model and acquire image in the first video camera of current camera group
The first parking area and the second video camera of current camera group acquisition image the second parking area whether detect vehicle mesh
Mark.
8. parking management system according to claim 7, which is characterized in that described to be based on obtaining from each video camera
The picture arrived determines the picture of the first video camera got and the picture of the second video camera, comprising:
It determines in the picture of the first video camera and the picture of the second video camera got comprising installation where current camera group
The picture in the blind area berth region of the vertical underface of bar or installation position;
Wherein, described to determine that acquiring the first of image in the first video camera of current camera group stops by preset vehicle detection model
Whether the second parking area of vehicle region and the second video camera of current camera group acquisition image detects vehicle target, comprising:
It is determined by preset vehicle detection model in the vertical underface of mounting rod where current camera group or installation position
Whether vehicle target is detected in the berth of blind area.
9. parking management system according to claim 8, which is characterized in that when the vehicle target that is detected as of vehicle target
When entering field detecting, if judge parking position region detection to vehicle target, it is described according to judging result, determine the target vehicle
Dead ship condition, comprising:
If parking position region detection obtains vehicle target judgment value to vehicle target, by the preset vehicle detection model;
According to the judgment value, determine whether the judgment value is greater than preset judgment threshold value;
If more than then confirming that the vehicle target that detects is motor vehicles, and calculate by the preset vehicle detection model
To the vehicle characteristics value of the vehicle target, and determine whether there is the last vehicle characteristics that the vehicle target is calculated
Value;
If it exists, the vehicle mesh is calculated with described in the more last vehicle characteristics value that the vehicle target is calculated
Whether target vehicle characteristics value is consistent;
If consistent, the more consistent number of vehicle characteristics value of the vehicle target is counted, and the number of the determining statistics is
No is more than predetermined relatively threshold value;
If being more than, determine that the vehicle target has been parked in parking position.
10. parking management system according to claim 8, which is characterized in that be detected as vehicle target when vehicle target
When going out field detecting, if judging, vehicle target is not detected in parking position region, described according to judging result, determines the target
The dead ship condition of vehicle, comprising:
If vehicle target is not detected in parking position region, in the detection for carrying out vehicle target, it is determined whether continue to exceed pre-
Determine number and target vehicle is not detected;
If continuing to exceed pre-determined number is not detected target vehicle, determine that the target vehicle has left parking position.
11. parking management system according to claim 8, further includes:
In the picture of the memory buffer in the main controller, determination is taken the photograph in each of current camera group in the given time
The picture to be processed cached in camera;
The license plate target detection of vehicle target is carried out to the picture to be processed by preset vehicle detection model;
If detect the license plate of vehicle target, by the vehicle target for detecting license plate described in the judgement of preset vehicle detection model
Whether vehicle characteristics are consistent with the vehicle characteristics for being parked in vehicle in parking position region;
If consistent, correction process is carried out to the license plate picture for detecting vehicle target by predetermined correction algorithm;
Car license recognition is carried out by picture of the Recognition Algorithm of License Plate to the license plate of the vehicle target after the correction process;
Based on the license board information of the vehicle target recognized, the parking forensic information of the vehicle target is generated;
Wherein, the parking forensic information includes license plate picture, the vehicle target of the license plate number of vehicle target, vehicle target
At least one of in entry time and the time for competiton of vehicle target.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910103278.4A CN109615928A (en) | 2019-02-01 | 2019-02-01 | A kind of parking management system in coverage hole berth |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910103278.4A CN109615928A (en) | 2019-02-01 | 2019-02-01 | A kind of parking management system in coverage hole berth |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109615928A true CN109615928A (en) | 2019-04-12 |
Family
ID=66019498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910103278.4A Pending CN109615928A (en) | 2019-02-01 | 2019-02-01 | A kind of parking management system in coverage hole berth |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109615928A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110322726A (en) * | 2019-07-03 | 2019-10-11 | 北京精英路通科技有限公司 | A kind of semiclosed Roadside Parking management system and method based on elevated video |
CN110910655A (en) * | 2019-12-11 | 2020-03-24 | 深圳市捷顺科技实业股份有限公司 | Parking management method, device and equipment |
CN110930718A (en) * | 2019-11-22 | 2020-03-27 | 北京精英路通科技有限公司 | Parking system |
CN111405196A (en) * | 2019-12-31 | 2020-07-10 | 智慧互通科技有限公司 | Vehicle management method and system based on video splicing |
CN112766222A (en) * | 2020-12-30 | 2021-05-07 | 爱泊车美好科技有限公司 | Method and device for assisting in recognizing vehicle behaviors based on parking line |
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 |
CN114530056A (en) * | 2022-02-15 | 2022-05-24 | 超级视线科技有限公司 | Parking management method and system based on positioning information and image information |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101064065A (en) * | 2007-03-29 | 2007-10-31 | 汤一平 | Parking inducing system based on computer visual sense |
CN105788351A (en) * | 2016-04-02 | 2016-07-20 | 广州乐盈信息科技有限公司 | Intelligent parking lot management system and intelligent parking lot management method based on video images |
US20160371978A1 (en) * | 2015-06-17 | 2016-12-22 | Robert Bosch Gmbh | Management of a parking lot |
CN107845289A (en) * | 2017-12-19 | 2018-03-27 | 智慧互通科技有限公司 | A kind of Roadside Parking management and charging system based on height digital video array |
CN107945566A (en) * | 2017-11-17 | 2018-04-20 | 张慧 | Curb parking management system and method based on multiple target tracking and deep learning |
CN108109428A (en) * | 2018-01-29 | 2018-06-01 | 深圳信路通智能技术有限公司 | An a kind of bar based on image continuously more parking stalls road-surface concrete management system |
-
2019
- 2019-02-01 CN CN201910103278.4A patent/CN109615928A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101064065A (en) * | 2007-03-29 | 2007-10-31 | 汤一平 | Parking inducing system based on computer visual sense |
US20160371978A1 (en) * | 2015-06-17 | 2016-12-22 | Robert Bosch Gmbh | Management of a parking lot |
CN105788351A (en) * | 2016-04-02 | 2016-07-20 | 广州乐盈信息科技有限公司 | Intelligent parking lot management system and intelligent parking lot management method based on video images |
CN107945566A (en) * | 2017-11-17 | 2018-04-20 | 张慧 | Curb parking management system and method based on multiple target tracking and deep learning |
CN107845289A (en) * | 2017-12-19 | 2018-03-27 | 智慧互通科技有限公司 | A kind of Roadside Parking management and charging system based on height digital video array |
CN108109428A (en) * | 2018-01-29 | 2018-06-01 | 深圳信路通智能技术有限公司 | An a kind of bar based on image continuously more parking stalls road-surface concrete management system |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110322726A (en) * | 2019-07-03 | 2019-10-11 | 北京精英路通科技有限公司 | A kind of semiclosed Roadside Parking management system and method based on elevated video |
CN110930718A (en) * | 2019-11-22 | 2020-03-27 | 北京精英路通科技有限公司 | Parking system |
CN110910655A (en) * | 2019-12-11 | 2020-03-24 | 深圳市捷顺科技实业股份有限公司 | Parking management method, device and equipment |
CN111405196A (en) * | 2019-12-31 | 2020-07-10 | 智慧互通科技有限公司 | Vehicle management method and system based on video splicing |
CN112766222A (en) * | 2020-12-30 | 2021-05-07 | 爱泊车美好科技有限公司 | Method and device for assisting in recognizing vehicle behaviors based on parking line |
CN112766222B (en) * | 2020-12-30 | 2024-04-09 | 爱泊车科技有限公司 | Method and device for assisting in identifying vehicle behavior based on berth line |
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 |
CN114530056A (en) * | 2022-02-15 | 2022-05-24 | 超级视线科技有限公司 | Parking management method and system based on positioning information and image information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109615928A (en) | A kind of parking management system in coverage hole berth | |
CN106530818A (en) | Intelligent parking lot management system based on video processing technology | |
CN107945566A (en) | Curb parking management system and method based on multiple target tracking and deep learning | |
CN110491168A (en) | A kind of method and device based on wheel touchdown point detection vehicle stopped state | |
CN108417087A (en) | A kind of vehicle safety traffic system and method | |
CN107301776A (en) | Track road conditions processing and dissemination method based on video detection technology | |
CN110136447A (en) | Lane change of driving a vehicle detects and method for distinguishing is known in illegal lane change | |
CN110163107A (en) | A kind of method and device based on video frame identification Roadside Parking behavior | |
WO2021223418A1 (en) | Parking detection method and apparatus employing visual difference | |
CN110210280A (en) | A kind of over the horizon cognitive method, system, terminal and storage medium | |
CN108765976A (en) | The parallel parking information of trackside manages system and method | |
CN104021677B (en) | A kind of vehicle board turning detection method and device | |
CN108091163A (en) | A kind of Roadside Parking management system combined based on video camera with trackside fence | |
CN113066306B (en) | Management method and device for roadside parking | |
CN108198430A (en) | A kind of trackside fence parking management system based on video camera and sensor | |
CN110148300A (en) | A kind of counterfeit vehicle registration plate identification method, device and computer-readable medium | |
CN105046966A (en) | System and method for automatically detecting illegal parking behaviors in drop-off areas | |
WO2021036243A1 (en) | Method and apparatus for recognizing lane, and computing device | |
CN113033479B (en) | Berth event identification method and system based on multilayer perception | |
CN111931673B (en) | Method and device for checking vehicle detection information based on vision difference | |
CN106683400A (en) | Method and a system for obtaining evidence by capturing vehicles at traffic crossing under panoramic video detection | |
CN112597807B (en) | Violation detection system, method and device, image acquisition equipment and medium | |
CN104008659A (en) | System and method capable of accurately monitoring control effects of intersection signal controller | |
CN114694095A (en) | Method, device, equipment and storage medium for determining parking position of vehicle | |
CN106251622B (en) | Vehicle and road monitoring evidence collecting method and its system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |
|
RJ01 | Rejection of invention patent application after publication |