CN110175533A - Overpass traffic condition method of real-time, device, terminal and storage medium - Google Patents
Overpass traffic condition method of real-time, device, terminal and storage medium Download PDFInfo
- Publication number
- CN110175533A CN110175533A CN201910377112.1A CN201910377112A CN110175533A CN 110175533 A CN110175533 A CN 110175533A CN 201910377112 A CN201910377112 A CN 201910377112A CN 110175533 A CN110175533 A CN 110175533A
- Authority
- CN
- China
- Prior art keywords
- overpass
- image
- target image
- threshold value
- lane line
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
A kind of overpass traffic condition method of real-time, it include: the target image first obtained when having vehicle on overpass bridge floor, lane line in recognition target image, then using the objective contour in adjacent two lane line regions in YOLO algorithm of target detection detection target image, judge whether the number of objective contour is greater than predetermined number threshold value, when the number for determining objective contour is more than or equal to the predetermined number threshold value, the result that congestion event has occurred on overpass is exported.The present invention also provides a kind of overpass traffic condition real-time monitoring device, terminal and storage mediums.The present invention is with the computer vision and the sense of hearing of artificial intelligence deep learning, the artificial 7*24 hour strict intelligence warning free of discontinuities on duty of substitution, it is ensured that the routine safety of overpass, solve the problems, such as it is traditional passively check non-timely, it is incomprehensive.
Description
Technical field
The present invention relates to technical field of video monitoring, and in particular to a kind of overpass traffic condition method of real-time, dress
It sets, terminal and storage medium.
Background technique
With China's expanding economy and social progress, urban motor vehicle is skyrocketed through, in order to alleviate urban transportation
Problem, China have built many urban viaducts, and traffic power is doubled or even several times by setting up for overpass.Due to height
Bridge formation vehicle flowrate is big, and maintenance cost is high, and it is more severe that traffic accident influence occurs, thus monitoring system is provided on overpass to friendship
Logical situation is measured in real time.
Traditional overpass monitoring system mainly passively judges the detection of traffic accident, for example, by patrolman
The scene judgement of member, or judge section with the presence or absence of traffic accident, Huo Zheyi by the analysis statistics to the section volume of traffic
By driver and conductor's active telephone call.Although the timed patrol of patrol is found past when accident it can be found that accident information
Toward longer time is had occurred that, not in time;By the great variety of the section volume of traffic come traffic when analyzing traffic accident
Through deteriorating, accident has tended to occur the long period;Alarm driver information communication has some setbacks, and can not be accurately positioned real discovery field and tool
The traffic condition of body.
Therefore, it is necessary to propose it is a kind of monitoring in time, broad covered area, can be confirmed in time after the accident it is overhead
The technical solution of bridge traffic condition monitoring.
Summary of the invention
In view of the foregoing, it is necessary to propose a kind of overpass traffic condition method of real-time, device, terminal and storage
Medium, can with the computer vision and the sense of hearing of artificial intelligence deep learning, solve that tradition passively checks non-timely, it is incomplete
Face property problem, and effective HD image foundation is provided for vehicle management department.
The first aspect of the present invention provides a kind of overpass traffic condition method of real-time, which comprises
Obtain target image when having vehicle on overpass bridge floor;
Identify the lane line in the target image;
Objective contour in the target image in adjacent two lane line regions is detected using YOLO algorithm of target detection;
Judge whether the number of the objective contour is greater than predetermined number threshold value;
When the number for determining the objective contour is more than or equal to the predetermined number threshold value, exports and sent out on overpass
The result of congestion event is given birth to.
Preferably, the lane line in the identification target image includes:
Background image when obtaining on overpass bridge floor without vehicle;
Detect the lane line in the background image;
Obtain position coordinates of the lane line in the background image;
The region that the position coordinates are corresponded in the target image is determined as the lane line.
Preferably, the predetermined number threshold value is determining in the following manner:
In the case where smooth traffic, every preset time period acquisition one has image when vehicle, and it is to be measured to obtain multiple
Image;
Profile in multiple described testing images is detected using YOLO algorithm of target detection;
Count the total number of the profile in all testing images;
The mean number that profile is determined according to the total number of the profile, as the predetermined number threshold value.
Preferably, described after the number for judging the objective contour is more than or equal to the predetermined number threshold value
Method further include:
Former frame target image and a later frame target image are subjected to difference processing, obtain difference image;
Judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
When the characteristic value for judging the difference image is less than the default characteristic threshold value, then exports on overpass and have occurred
Serious congestion event.
Preferably, adjacent two lane line regions in the target image are detected using YOLO algorithm of target detection described
Before interior objective contour, the method also includes:
Illumination or contrast normalized are carried out to the target image;
Noise reduction process is carried out to multiple images after carrying out the normalized using bilateral filtering algorithm.
Preferably, when the number for determining the objective contour is less than the predetermined number threshold value, the method also includes:
There is no the results of congestion event on output overpass.
Preferably, after the result of congestion event having occurred on the output overpass, the method also includes:
To vehicle management, department sends a warning message;
The driver on the vehicle in overpass pre-determined distance sends a warning message simultaneously.
The second aspect of the present invention provides a kind of overpass traffic condition real-time monitoring device, and described device includes:
Module is obtained, there is target image when vehicle on overpass bridge floor for obtaining;
Identification module, for identification lane line in the target image;
Detection module, for detecting adjacent two lane line regions in the target image using YOLO algorithm of target detection
Interior objective contour;
Judgment module, for judging whether the number of the objective contour is greater than predetermined number threshold value;
Output module, for when determine the objective contour number be more than or equal to the predetermined number threshold value when,
The result of congestion event has occurred on output overpass.
The third aspect of the present invention provides a kind of terminal, and the terminal includes processor, and the processor is deposited for executing
The overpass traffic condition method of real-time is realized when the computer program stored in reservoir.
The fourth aspect of the present invention provides a kind of computer readable storage medium, deposits on the computer readable storage medium
Computer program is contained, the computer program realizes the overpass traffic condition real-time monitoring side when being executed by processor
Method.
In conclusion overpass traffic condition method of real-time, device, terminal and storage medium of the present invention,
First obtain target image when having vehicle on overpass bridge floor;Identify the lane line in the target image;Using YOLO target
Detection algorithm detects the objective contour in the target image in adjacent two lane line regions;Judge of the objective contour
Whether number is greater than predetermined number threshold value;When the number for determining the objective contour is more than or equal to the predetermined number threshold value
When, export the result that congestion event has occurred on overpass.With the computer vision and the sense of hearing of artificial intelligence deep learning, substitution
Artificial 7*24 hours strict intelligence warning free of discontinuities on duty, it is ensured that the routine safety of overpass.Solves traditional passive inspection
Problem non-timely, incomprehensive, and provide effective HD image foundation for vehicle management department.
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
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the flow chart for the overpass traffic condition method of real-time that the embodiment of the present invention one provides.
Fig. 2 is the structure chart of overpass traffic condition real-time monitoring device provided by Embodiment 2 of the present invention.
Fig. 3 is the structural schematic diagram for the terminal that the embodiment of the present invention three provides.
The present invention that the following detailed description will be further explained with reference to the above drawings.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying example, the present invention will be described in detail.It should be noted that in the absence of conflict, the embodiment of the present invention and embodiment
In feature can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment is only
It is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Embodiment one
Fig. 1 is the flow chart for the overpass traffic condition method of real-time that the embodiment of the present invention one provides.
In the present embodiment, the overpass traffic condition method of real-time can be applied in terminal, for needing
The terminal for carrying out overpass traffic condition real-time monitoring, can directly integrate overhead provided by method of the invention at the terminal
The function of bridge traffic condition real-time monitoring, or with Software Development Kit (Software Development Kit, SKD)
Form is run in the terminal.
As shown in Figure 1, the overpass traffic condition method of real-time is related to technical field of video monitoring, it is applied to height
This special scenes on bridge formation, the overpass traffic condition method of real-time specifically includes following steps, according to difference
Demand, the sequence of step can change in the flow chart, certain to can be omitted.
S11: target image when having vehicle on overpass bridge floor is obtained.
In the present embodiment, target figure when having vehicle on overpass bridge floor is obtained using high-definition digital image capture device
Picture.
High speed continuous shooting digital photo technologies can be used, by high-definition digital image capture device quickly to the overpass
Bridge floor carries out continuous shooting to obtain multiple high-definition digital images.Especially during vehicle driving, need to connect using high speed
Digital photo technologies are clapped, the image of multiple vehicles is obtained, or video flowing is acquired by high-definition digital image capture device, passes through
The every frame extracted in video flowing obtains multiple images, so as in the next steps can be comprehensive by multiple successional images
Conjunction identifies whether the vehicle on overpass bridge floor gets congestion.
The high-definition digital image capture device may include that at least two high definition cameras, the high definition camera is mounted on height
On at least one support frame being arranged on bridge formation bridge floor, the region of two high definition cameras shooting can be opposite.That is, a high definition phase
Machine obtains the image on the overpass bridge floor in a driving direction or video and is sent to Streaming Media storage device, another height
Clear camera obtains image on the overpass bridge floor in another driving direction or video and is sent to Streaming Media storage device.
Certainly in other embodiments, the high definition camera can also have other installation sites, as long as can clearly obtain
Take the clear image on overpass bridge floor.
High-definition digital image capture device in the present embodiment can be fixedly disposed on the support frame of the overpass,
It is also possible on the support frame for being rotatably arranged on the overpass.The high-definition digital image capture device of rotation setting can rotate
Obtain the image or video on the overpass bridge floor on two different directions, function is equal to fixed and shoot using two
The function of contrary high-definition digital image capture device.Thus, in the present embodiment, mainly with fixed high-definition digital image
It is illustrated for acquisition equipment.For the high-definition digital image capture device of rotation setting, then by when static for the first time
An image is obtained, an image is obtained when second of same position static, is analyzed in conjunction with the image obtained twice, really
Determine the event that traffic congestion whether has occurred on overpass.
High-definition digital image capture device can be monitored by technologies such as dedicated video optical transmitter and receiver, cable networks to overpass
The indoor video analytics server of room sends the high-definition image of acquisition, so that vehicle management department passes through indoor video at any time
Analysis server grasps the traffic conditions on overpass.
S12: the lane line in the target image is identified.
In the present embodiment, after getting target image, the lane line in recognition target image is needed, convenient for subsequent to phase
Region between adjacent two lane lines carries out emphasis monitoring.
Preferably, the lane line in the identification target image includes:
121) background image when obtaining on overpass bridge floor without vehicle.
In the present embodiment, when on overpass bridge floor without any vehicle, the acquisition of high-definition digital image capture device is first passed through
One image, as background image;Or from image when being intercepted in video on a vertical frame dimension bridge formation bridge floor without any vehicle, as
Background image.
It should be understood that only including background information in the background image, for example, the lane information on bridge floor, sky
Information etc., and do not include the foreground information of any vehicle.
122) lane line in the background image is detected.
In the present embodiment, line segment detector (Line Segment Detector, LSD) algorithm can be used to the back
Scape image carries out straight-line detection.It should be noted that other algorithms can also be used to the background image in the present embodiment
Carry out straight-line detection, it is not limited to line segment detector algorithm, for example, using the line detection algorithm based on hough feature.Institute
Stating line segment detector is a kind of straight-line detection partitioning algorithm, it can obtain the detection knot of subpixel accuracy within the linear time
Fruit.The input of line segment detector algorithm is image, and output is a series of line segmentation result.The target of line segment detector algorithm
It is straight profile local in detection image.Straight line inspection is carried out to the background image by using line segment detector algorithm
It surveys, so that it may detect the lane line in the background image.
123) position coordinates of the lane line in the background image are obtained.
In the present embodiment, can using the upper left corner of background image as coordinate origin, with a height of ordinate of background image, with
The width of background image is abscissa, establishes rectangular coordinate system.
After establishing rectangular coordinate system, lane line region described in background image in the rectangular coordinate system is obtained
All position coordinates.
Since lane line has apparent color identifier, thus lane can be obtained according to the color attribute of lane line itself
Then all pixels point of line region obtains position coordinates of all pixels point in rectangular coordinate system.
The picture annotation tool that open source software can be used, is manually labeled the lane line in background image, for example,
Mark the frame of lane line in background image.The all pixels point in marked frame is obtained, all pixels point is then obtained
Position coordinates in rectangular coordinate system.
124) region that the position coordinates are corresponded in the target image is determined as the lane line.
In the present embodiment, due to image when background image is on overpass without vehicle, there is figure when vehicle on overpass
It seem this prospect of vehicle to be increased on the basis of background image, and the camera site of high-definition digital image capture device is solid
Calmly, i.e. the size of background image and the target image is identical, and the lane line in background image is in target image
Lane line, thus directly the position coordinates of the lane line region in the background image can be determined as in target image
Lane line region position coordinates.
Specifically, using the upper left corner of target image as coordinate origin, with a height of ordinate of target image, with target image
Width be abscissa, establish rectangular coordinate system.
After establishing rectangular coordinate system, had picture at position coordinates described in target image is obtained in the rectangular coordinate system
Vegetarian refreshments, the region where all pixels point are the region where the lane line in target image.
S13: the target in the target image in adjacent two lane line regions is detected using YOLO algorithm of target detection
Profile.
In the present embodiment, the region between two adjacent lane lines is the region of vehicle driving, is examined using YOLO target
Method of determining and calculating detects the objective contour in adjacent two lane line regions.YOLO (You Only Look Once:Better,
Faster, Stronger) algorithm of target detection is fast multi-target detection algorithm, it can detect multiple targets simultaneously, and use
The form frame of rectangle frame has selected the contour area of each target.YOLO algorithm of target detection is the prior art, and the present invention is herein
It is not described in detail.
Preferably, adjacent two lane line regions in the target image are detected using YOLO algorithm of target detection described
Before interior objective contour, the method also includes:
The target image is pre-processed.
In the present embodiment, the pretreatment may include: to carry out at illumination or contrast normalization to the target image
Reason;Noise reduction process is carried out to multiple images after carrying out the normalized using bilateral filtering algorithm.
What it is due to monitoring is fortune on the overpass of round-the-clock (different periods, different light intensity, Different climate feature)
Row state after pre-processing to target image, can solve returning for the contrast of image under different periods, different illumination conditions
One changes, and highlights so that the feature of identification division required in image be optimized, remaining is not needed to the feature of identification division
Weakening treatment is carried out, to improve using the vehicle in YOLO algorithm of target detection detection target image in adjacent two lane line regions
Contour area.
The bilateral filtering algorithm can effectively remove noise, for example, generated by high-definition digital image capture device
Salt-pepper noise, meanwhile, also there is good edge details holding capacity.Treatment process about bilateral filtering algorithm is existing skill
Art, in this not go into detail by the present invention.
It should be noted that in the present embodiment, without carrying out image grayscale normalized, i.e. mesh to the target image
Logo image is color image by pretreated target image.
It is described that phase in the pretreated target image is detected using YOLO algorithm of target detection after pretreatment
Objective contour in adjacent two lane line regions.
S14: judge whether the number of the objective contour is greater than predetermined number threshold value.
In the present embodiment, detect that multiple contour areas, multiple contour area are vehicle by YOLO algorithm of target detection
Contour area.The number of the corresponding objective contour of contour area is counted, then judges whether the number is greater than and presets
Number threshold value, determine congestion event whether has occurred on overpass according to the result of judgement.
Preferably, the predetermined number threshold value is determining in the following manner:
141) in the case where smooth traffic, every preset time period acquisition one has image when vehicle, obtains multiple
Testing image;
142) profile in multiple described testing images is detected using YOLO algorithm of target detection;
143) total number of the profile in all testing images is counted;
144) mean number that profile is determined according to the total number of the profile, as the predetermined number threshold value.
, can be in the case where the smooth traffic on overpass in the present embodiment, shooting one in every preset time period
There is image when vehicle, the contour area then occurred in detection image, the contour area finally counted in all images corresponds to
Profile total number, a mean number is calculated, as the critical value of event of whether getting congestion on assessment overpass,
The predetermined number threshold value thereby determined that is more accurate, more can intuitively judge the traffic condition on overpass.
Certainly, in other embodiments, the overpass smooth traffic feelings of system acquisition can also be monitored by conventional traffic
Average vehicle flow under condition.Then after detecting the profile in multiple described testing images using YOLO algorithm of target detection, system
The total number for counting the profile in all testing images, current vehicle flowrate is calculated according to total number, relatively more current
Vehicle flowrate and average vehicle flow between size relation, to determine the traffic condition on overpass.
The predetermined number is held when the number for judging the objective contour is more than or equal to the predetermined number threshold value
Row S15;Otherwise, when the number for judging the objective contour is less than the predetermined number threshold value, S16 is executed.
S15: the result of congestion event has occurred on output overpass.
In the present embodiment, detect that the objective contour number on overpass is greater than using YOLO algorithm of target detection determining
Or when being equal to predetermined number threshold value, it is believed that the vehicle on overpass is more, then exports and congestion event has occurred on overpass
As a result.
In other embodiments, due to predetermined number threshold value be according to smooth traffic on overpass in the case where count flat
Equal vehicle number thus detects that the objective contour number on overpass is greater than or waits by comparing YOLO algorithm of target detection
When average traffic number, it is believed that the more conclusion of vehicle on overpass can more be bonded actual conditions.
S16: there is no the results of congestion event on output overpass.
In the present embodiment, there is pedestrian in determining target image, there is train, and the current fortune of train in the second target image
When row state is dead ship condition, that is, determine within the yellow safety line on overpass bridge floor there is pedestrian, though there are column on train rail
Vehicle but for halted state, the scene that corresponding train waiting pedestrian gets on the bus, such situation thinks that pedestrian crosses yellow safety line category
In normal behaviour, the result that cross-lane occurs without pedestrian is exported.
Further, after the number of the judgement objective contour is greater than predetermined number threshold value, the method is also
Include:
1) former frame target image and a later frame target image are subjected to difference processing, obtain difference image;
In the present embodiment, available continuous multiple frames target image, and two frame target image of front and back is subjected to difference processing.
Each pixel in former frame target image is subjected to difference processing with the corresponding pixel in a later frame target image,
Difference image can be obtained.
2) judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
In the present embodiment, the characteristic value of difference image can be calculated, for example, variance, mean value or comentropy, histogram
Deng.Then the size relation between judging characteristic value and default characteristic threshold value.
It should be understood that the variance of difference image should be calculated if pre-set characteristic threshold value is variance yields;Together
Reason should calculate the histogram of difference image if pre-set characteristic threshold value is histogram.
3) it when the characteristic value for judging the difference image is less than the default characteristic threshold value, then exports on overpass and occurs
Serious congestion event.
It is easily understood that if the vehicle that is, on overpass is slack or moves when serious congestion event has occurred
It is dynamic very slowly so that using almost indifference between the front and back two field pictures of high-definition digital image capture device shooting, to preceding
After one frame target image and a later frame target image carry out difference processing, the obtained pixel value in difference image is largely 0,
Then the characteristic value of calculated difference image is necessarily smaller than pre-set characteristic threshold value.If there is no serious congestion events
When, i.e., the vehicle on overpass is between normal movement, the front and back two field pictures using the shooting of high-definition digital image capture device
Difference can be larger, after carrying out difference processing to former frame target image and a later frame target image, in obtained difference image
Pixel value the case where be not in most of being 0, then the characteristic value of calculated difference image is necessarily greater than or is equal to pre-
The characteristic threshold value being first arranged.
Further, after the result of congestion event having occurred on the output overpass, the method also includes:
To vehicle management, department sends a warning message;
Meanwhile the driver on the vehicle in overpass pre-determined distance sends a warning message.
In the present embodiment, when congestion event has occurred on finding overpass, to vehicle management, department sends a warning message
While send a warning message to the driver on the vehicle in overpass pre-determined distance.It sends and accuses to vehicle management department
Alert information, the staff convenient for vehicle management department in time discongest traffic, avoid the generation of second accident;In addition,
It sends a warning message to other drivers of overpass just to be driven towards, to prompt other drivers to change route, avoids on overpass
Traffic congestion causes endless loop.Play the dual congested in traffic effect discongested on overpass.
In conclusion overpass traffic condition method of real-time of the present invention, first obtaining on overpass bridge floor has vehicle
When target image, by detect without vehicle when background image in lane line determine the lane line in target image, into
And the contour area in target image in adjacent two lane lines is detected by YOLO algorithm of target detection, judging adjacent two
When the number of the corresponding objective contour of contour area in lane line is more than predetermined number threshold value, it is believed that gathered around on overpass
Stifled event.With the computer vision and the sense of hearing of artificial intelligence deep learning, artificial 7*24 hours on duty of substitution free of discontinuities strict
Intelligence warning, it is ensured that the routine safety of overpass.Solve tradition passively check non-timely, it is incomprehensive, cause traffic
The problem of accident rescue is not in time and accident information is issued not in time, and effective height is provided for vehicle management department
Clear image foundation.
Embodiment two
Fig. 2 is the structure chart of overpass traffic condition real-time monitoring device provided by Embodiment 2 of the present invention.
In some embodiments, the overpass traffic condition real-time monitoring device 20 may include multiple by program code
Functional module composed by section.The program code of each program segment in the overpass traffic condition real-time monitoring device 20 can
To be stored in the memory of terminal, and as performed by least one described processor, with execution (being detailed in Fig. 1 description) to presence
Overpass traffic condition is measured in real time.
In the present embodiment, the overpass traffic condition real-time monitoring device 20, run on overpass this is specific
Scene, the function according to performed by it can be divided into multiple functional modules.The functional module may include: acquisition mould
Block 201, identification module 202, detection module 203, preprocessing module 204, judgment module 205, the first output module 206, second
Output module 207 and sending module 208.The so-called module of the present invention refers to that one kind can be performed by least one processor simultaneously
And the series of computation machine program segment of fixed function can be completed, storage is in memory.In the present embodiment, about each mould
The function of block will be described in detail in subsequent embodiment.
Module 201 is obtained, there is target image when vehicle on overpass bridge floor for obtaining.
In the present embodiment, target figure when having vehicle on overpass bridge floor is obtained using high-definition digital image capture device
Picture.
High speed continuous shooting digital photo technologies can be used, by high-definition digital image capture device quickly to the overpass
Bridge floor carries out continuous shooting to obtain multiple high-definition digital images.Especially during vehicle driving, need to connect using high speed
Digital photo technologies are clapped, the image of multiple vehicles is obtained, or video flowing is acquired by high-definition digital image capture device, passes through
The every frame extracted in video flowing obtains multiple images, so as in the next steps can be comprehensive by multiple successional images
Conjunction identifies whether the vehicle on overpass bridge floor gets congestion.
The high-definition digital image capture device may include that at least two high definition cameras, the high definition camera is mounted on height
On at least one support frame being arranged on bridge formation bridge floor, the region of two high definition cameras shooting can be opposite.That is, a high definition phase
Machine obtains the image on the overpass bridge floor in a driving direction or video and is sent to Streaming Media storage device, another height
Clear camera obtains image on the overpass bridge floor in another driving direction or video and is sent to Streaming Media storage device.
Certainly in other embodiments, the high definition camera can also have other installation sites, as long as can clearly obtain
Take the clear image on overpass bridge floor.
High-definition digital image capture device in the present embodiment can be fixedly disposed on the support frame of the overpass,
It is also possible on the support frame for being rotatably arranged on the overpass.The high-definition digital image capture device of rotation setting can rotate
Obtain the image or video on the overpass bridge floor on two different directions, function is equal to fixed and shoot using two
The function of contrary high-definition digital image capture device.Thus, in the present embodiment, mainly with fixed high-definition digital image
It is illustrated for acquisition equipment.For the high-definition digital image capture device of rotation setting, then by when static for the first time
An image is obtained, an image is obtained when second of same position static, is analyzed in conjunction with the image obtained twice, really
Determine the event that traffic congestion whether has occurred on overpass.
High-definition digital image capture device can be monitored by technologies such as dedicated video optical transmitter and receiver, cable networks to overpass
The indoor video analytics server of room sends the high-definition image of acquisition, so that vehicle management department passes through indoor video at any time
Analysis server grasps the traffic conditions on overpass.
Identification module 202, for identification lane line in the target image.
In the present embodiment, after getting target image, the lane line in recognition target image is needed, convenient for subsequent to phase
Region between adjacent two lane lines carries out emphasis monitoring.
Preferably, the identification module 202 identifies that the lane line in the target image includes:
121) background image when obtaining on overpass bridge floor without vehicle.
In the present embodiment, when on overpass bridge floor without any vehicle, the acquisition of high-definition digital image capture device is first passed through
One image, as background image;Or from image when being intercepted in video on a vertical frame dimension bridge formation bridge floor without any vehicle, as
Background image.
It should be understood that only including background information in the background image, for example, the lane information on bridge floor, sky
Information etc., and do not include the foreground information of any vehicle.
122) lane line in the background image is detected.
In the present embodiment, line segment detector (Line Segment Detector, LSD) algorithm can be used to the back
Scape image carries out straight-line detection.It should be noted that other algorithms can also be used to the background image in the present embodiment
Carry out straight-line detection, it is not limited to line segment detector algorithm, for example, using the line detection algorithm based on hough feature.Institute
Stating line segment detector is a kind of straight-line detection partitioning algorithm, it can obtain the detection knot of subpixel accuracy within the linear time
Fruit.The input of line segment detector algorithm is image, and output is a series of line segmentation result.The target of line segment detector algorithm
It is straight profile local in detection image.By using line segment detector line segment detector algorithm to the background image into
Row straight-line detection, so that it may detect the lane line in the background image.
123) position coordinates of the lane line in the background image are obtained.
In the present embodiment, can using the upper left corner of background image as coordinate origin, with a height of ordinate of background image, with
The width of background image is abscissa, establishes rectangular coordinate system.
After establishing rectangular coordinate system, lane line region described in background image in the rectangular coordinate system is obtained
All position coordinates.
Since lane line has apparent color identifier, thus lane can be obtained according to the color attribute of lane line itself
Then all pixels point of line region obtains position coordinates of all pixels point in rectangular coordinate system.
The picture annotation tool that open source software can be used, is manually labeled the lane line in background image, for example,
Mark the frame of lane line in background image.The all pixels point in marked frame is obtained, all pixels point is then obtained
Position coordinates in rectangular coordinate system.
124) region that the position coordinates are corresponded in the target image is determined as the lane line.
In the present embodiment, due to image when background image is on overpass without vehicle, there is figure when vehicle on overpass
It seem this prospect of vehicle to be increased on the basis of background image, and the camera site of high-definition digital image capture device is solid
Calmly, i.e. the size of background image and the target image is identical, and the lane line in background image is in target image
Lane line, thus directly the position coordinates of the lane line region in the background image can be determined as in target image
Lane line region position coordinates.
Specifically, using the upper left corner of target image as coordinate origin, with a height of ordinate of target image, with target image
Width be abscissa, establish rectangular coordinate system.
After establishing rectangular coordinate system, had picture at position coordinates described in target image is obtained in the rectangular coordinate system
Vegetarian refreshments, the region where all pixels point are the region where the lane line in target image.
Detection module 203, for detecting adjacent two lane lines in the target image using YOLO algorithm of target detection
Objective contour in region.
In the present embodiment, the region between two adjacent lane lines is the region of vehicle driving, is examined using YOLO target
Method of determining and calculating detects the objective contour in adjacent two lane line regions.YOLO (You Only Look Once:Better,
Faster, Stronger) algorithm of target detection is fast multi-target detection algorithm, it can detect multiple targets simultaneously, and use
The form frame of rectangle frame has selected the contour area of each target.YOLO algorithm of target detection is the prior art, and the present invention is herein
It is not described in detail.
Preferably, it is detected adjacent two in the target image in the detection module 203 using YOLO algorithm of target detection
Before objective contour in lane line region, the overpass traffic condition real-time monitoring device 20 further include:
Preprocessing module 204, for being pre-processed to the target image.
In the present embodiment, the pretreatment may include: to carry out at illumination or contrast normalization to the target image
Reason;Noise reduction process is carried out to multiple images after carrying out the normalized using bilateral filtering algorithm.
What it is due to monitoring is fortune on the overpass of round-the-clock (different periods, different light intensity, Different climate feature)
Row state after pre-processing to target image, can solve returning for the contrast of image under different periods, different illumination conditions
One changes, and highlights so that the feature of identification division required in image be optimized, remaining is not needed to the feature of identification division
Weakening treatment is carried out, to improve using the vehicle in YOLO algorithm of target detection detection target image in adjacent two lane line regions
Contour area.
The bilateral filtering algorithm can effectively remove noise, for example, generated by high-definition digital image capture device
Salt-pepper noise, meanwhile, also there is good edge details holding capacity.Treatment process about bilateral filtering algorithm is existing skill
Art, in this not go into detail by the present invention.
It should be noted that in the present embodiment, without carrying out image grayscale normalized, i.e. mesh to the target image
Logo image is color image by pretreated target image.
It is described that phase in the pretreated target image is detected using YOLO algorithm of target detection after pretreatment
Objective contour in adjacent two lane line regions.
Judgment module 205, for judging whether the number of the objective contour is greater than predetermined number threshold value.
In the present embodiment, detect that multiple contour areas, multiple contour area are vehicle by YOLO algorithm of target detection
Contour area.The number of the corresponding objective contour of contour area is counted, then judges whether the number is greater than and presets
Number threshold value, determine congestion event whether has occurred on overpass according to the result of judgement.
Preferably, the predetermined number threshold value is determining in the following manner:
141) in the case where smooth traffic, every preset time period acquisition one has image when vehicle, obtains multiple
Testing image;
142) profile in multiple described testing images is detected using YOLO algorithm of target detection;
143) total number of the profile in all testing images is counted;
144) mean number that profile is determined according to the total number of the profile, as the predetermined number threshold value.
, can be in the case where the smooth traffic on overpass in the present embodiment, shooting one in every preset time period
There is image when vehicle, the contour area then occurred in detection image, the contour area finally counted in all images corresponds to
Profile total number, a mean number is calculated, as the critical value of event of whether getting congestion on assessment overpass,
The predetermined number threshold value thereby determined that is more accurate, more can intuitively judge the traffic condition on overpass.
Certainly, in other embodiments, the overpass smooth traffic feelings of system acquisition can also be monitored by conventional traffic
Average vehicle flow under condition.Then after detecting the profile in multiple described testing images using YOLO algorithm of target detection, system
The total number for counting the profile in all testing images, current vehicle flowrate is calculated according to total number, relatively more current
Vehicle flowrate and average vehicle flow between size relation, to determine the traffic condition on overpass.
First output module 206, for when the number of the determining objective contour of the judgment module 205 is greater than or waits
When the predetermined number threshold value, the result that congestion event has occurred on overpass is exported.
In the present embodiment, detect that the objective contour number on overpass is greater than using YOLO algorithm of target detection determining
Or when being equal to predetermined number threshold value, it is believed that the vehicle on overpass is more, then exports and congestion event has occurred on overpass
As a result.
In other embodiments, due to predetermined number threshold value be according to smooth traffic on overpass in the case where count flat
Equal vehicle number thus detects that the objective contour number on overpass is greater than or waits by comparing YOLO algorithm of target detection
When average traffic number, it is believed that the more conclusion of vehicle on overpass can more be bonded actual conditions.
Second output module 207 is also used to determine the number of the objective contour less than described when the judgment module 205
When predetermined number threshold value, there is no the results of congestion event on output overpass.
In the present embodiment, there is pedestrian in determining target image, there is train, and the current fortune of train in the second target image
When row state is dead ship condition, that is, determine within the yellow safety line on overpass bridge floor there is pedestrian, though there are column on train rail
Vehicle but for halted state, the scene that corresponding train waiting pedestrian gets on the bus, such situation thinks that pedestrian crosses yellow safety line category
In normal behaviour, the result that cross-lane occurs without pedestrian is exported.
Further, the judgment module 205 judge the objective contour number be greater than predetermined number threshold value after,
The overpass traffic condition real-time monitoring device 20 further include:
1) former frame target image and a later frame target image are subjected to difference processing, obtain difference image;
In the present embodiment, available continuous multiple frames target image, and two frame target image of front and back is subjected to difference processing.
Each pixel in former frame target image is subjected to difference processing with the corresponding pixel in a later frame target image,
Difference image can be obtained.
2) judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
In the present embodiment, the characteristic value of difference image can be calculated, for example, variance, mean value or comentropy, histogram
Deng.Then the size relation between judging characteristic value and default characteristic threshold value.
It should be understood that the variance of difference image should be calculated if pre-set characteristic threshold value is variance yields;Together
Reason should calculate the histogram of difference image if pre-set characteristic threshold value is histogram.
3) it when the characteristic value for judging the difference image is less than the default characteristic threshold value, then exports on overpass and occurs
Serious congestion event.
It is easily understood that if the vehicle that is, on overpass is slack or moves when serious congestion event has occurred
It is dynamic very slowly so that using almost indifference between the front and back two field pictures of high-definition digital image capture device shooting, to preceding
After one frame target image and a later frame target image carry out difference processing, the obtained pixel value in difference image is largely 0,
Then the characteristic value of calculated difference image is necessarily smaller than pre-set characteristic threshold value.If there is no serious congestion events
When, i.e., the vehicle on overpass is between normal movement, the front and back two field pictures using the shooting of high-definition digital image capture device
Difference can be larger, after carrying out difference processing to former frame target image and a later frame target image, in obtained difference image
Pixel value the case where be not in most of being 0, then the characteristic value of calculated difference image is necessarily greater than or is equal to pre-
The characteristic threshold value being first arranged.
Further, after the result of congestion event having occurred on first output module 206 output overpass, institute
State overpass traffic condition real-time monitoring device 20 further include:
Sending module 208, for sending a warning message to vehicle management department;
The sending module 208 is also used to the driver simultaneously on the vehicle in overpass pre-determined distance and sends announcement
Alert information.
In the present embodiment, when congestion event has occurred on finding overpass, to vehicle management, department sends a warning message
While send a warning message to the driver on the vehicle in overpass pre-determined distance.It sends and accuses to vehicle management department
Alert information, the staff convenient for vehicle management department in time discongest traffic, avoid the generation of second accident, in addition,
It sends a warning message to other drivers of overpass just to be driven towards, to prompt other drivers to change route, avoids on overpass
Traffic congestion causes endless loop.Play the dual congested in traffic effect discongested on overpass.
In conclusion overpass traffic condition real-time monitoring device of the present invention is first obtained using the technology of image procossing
Target image when having vehicle on overpass bridge floor is taken, the lane line in background image when by detecting without vehicle determines target
Lane line in image, and then the profile region in target image in adjacent two lane lines is detected by YOLO algorithm of target detection
Domain is recognized when the number for judging the corresponding objective contour of contour area in adjacent two lane lines is more than predetermined number threshold value
For congestion event has occurred on overpass.With the computer vision and the sense of hearing of artificial intelligence deep learning, artificial 7* on duty is substituted
Strict intelligence warning free of discontinuities in 24 hours, it is ensured that the routine safety of overpass.Solve tradition passively check non-timely,
It is incomprehensive, cause traffic accident rescue not in time and accident information publication not in time the problem of, and be vehicle management portion
Door provides effective HD image foundation.
Embodiment three
As shown in fig.3, the structural schematic diagram of the terminal provided for the embodiment of the present invention three.In present pre-ferred embodiments
In, the terminal 3 includes memory 31, at least one processor 32, at least one communication bus 33 and transceiver 34.
It will be understood by a person skilled in the art that the structure of the terminal shown in Fig. 3 does not constitute the restriction of the embodiment of the present invention,
Either bus topology, be also possible to star structure, the terminal 3 can also include than illustrate it is more or fewer other
Hardware perhaps software or different component layouts.
In some embodiments, the terminal 3 includes that one kind can be automatic to carry out according to the instruction for being previously set or storing
Numerical value calculates and/or the terminal of information processing, and hardware includes but is not limited to microprocessor, specific integrated circuit, programmable gate
Array, digital processing unit and embedded device etc..The terminal 3 may also include customer equipment, and the customer equipment includes but not
Human-computer interaction can be carried out by modes such as keyboard, mouse, remote controler, touch tablet or voice-operated devices with client by being limited to any one
Electronic product, for example, personal computer, tablet computer, smart phone, digital camera etc..
It should be noted that the terminal 3 is only for example, other electronic products that are existing or being likely to occur from now on such as may be used
It is adapted to the present invention, should also be included within protection scope of the present invention, and is incorporated herein by reference.
In some embodiments, the memory 31 is used to store program code and various data, such as is mounted on described
Overpass traffic condition real-time monitoring device 20 in terminal 3, and in the operational process of terminal 3 realize high speed, it is automatically complete
At the access of program or data.The memory 31 includes read-only memory (Read-Only Memory, ROM), random storage
Device (Random Access Memory, RAM), programmable read only memory (Programmable Read-Only Memory,
PROM), Erasable Programmable Read Only Memory EPROM (Erasable Programmable Read-Only Memory, EPROM), one
Secondary programmable read only memory (One-time Programmable Read-Only Memory, OTPROM), electronics erasing type
Can make carbon copies read-only memory (Electrically-Erasable Programmable Read-Only Memory, EEPROM),
CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic
Tape storage or any other the computer-readable medium that can be used in carrying or storing data.
In some embodiments, at least one described processor 32 can be made of integrated circuit, such as can be by single
The integrated circuit of encapsulation is formed, and is also possible to be made of the integrated circuit that multiple identical functions or different function encapsulate, be wrapped
Include one or more central processing unit (Central Processing unit, CPU), microprocessor, digital processing chip,
The combination etc. of graphics processor and various control chips.At least one described processor 32 is the control core of the terminal 3
(Control Unit) is stored in using all parts of various interfaces and the entire terminal 3 of connection by running or executing
Program or module in the memory 31, and the data being stored in the memory 31 are called, to execute terminal 3
Various functions and processing data, such as execute the function of overpass traffic condition real-time monitoring.
In some embodiments, at least one communication bus 33 is arranged to realize the memory 31 and described
Connection communication between at least one processor 32 etc..
Although being not shown, the terminal 3 can also include the power supply (such as battery) powered to all parts, it is preferred that
Power supply can be logically contiguous by electric power controller and at least one described processor 32, to pass through electric power controller reality
The functions such as now management charging, electric discharge and power managed.Power supply can also include one or more direct current or alternating current
The random components such as source, recharging device, power failure detection circuit, power adapter or inverter, power supply status indicator.
The terminal 3 can also include multiple sensors, bluetooth module, Wi-Fi module etc., and details are not described herein.
It should be appreciated that the embodiment is only purposes of discussion, do not limited by this structure in patent claim.
The above-mentioned integrated unit realized in the form of software function module, can store and computer-readable deposit at one
In storage media.Above-mentioned software function module is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, terminal or the network equipment etc.) or processor (processor) execute each reality of the present invention
Apply the part of the method.
In a further embodiment, in conjunction with Fig. 2, the operation of the terminal 3 is can be performed at least one described processor 32
Device and the types of applications program of installation (overpass traffic condition real-time monitoring device 20 as mentioned), program code etc.,
For example, above-mentioned modules.
Program code is stored in the memory 31, and at least one described processor 32 can call the memory 31
The program code of middle storage is to execute relevant function.For example, modules described in Fig. 2 are stored in the memory 31
In program code, and as performed by least one described processor 32, to realize the function of the modules to reach
The purpose of overpass traffic condition real-time monitoring.
In one embodiment of the invention, the memory 31 stores multiple instruction, the multiple instruction by it is described extremely
Few performed function to realize overpass traffic condition real-time monitoring of a processor 32.
Specifically, at least one described processor 32 can refer to the corresponding implementation of Fig. 1 to the concrete methods of realizing of above-metioned instruction
The description of correlation step in example, this will not be repeated here.
In several embodiments provided by the present invention, it should be understood that disclosed device, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the module
It divides, only a kind of logical function partition, there may be another division manner in actual implementation.
The module as illustrated by the separation member may or may not be physically separated, aobvious as module
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of the modules therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
It, can also be in addition, each functional module in each embodiment of the present invention can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds software function module.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " is not excluded for other units or, odd number is not excluded for plural number.The multiple units stated in device claim
Or device can also be implemented through software or hardware by a unit or device.The first, the second equal words are used to indicate name
Claim, and does not indicate any particular order.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. a kind of overpass traffic condition method of real-time, which is characterized in that the described method includes:
Obtain target image when having vehicle on overpass bridge floor;
Identify the lane line in the target image;
Objective contour in the target image in adjacent two lane line regions is detected using YOLO algorithm of target detection;
Judge whether the number of the objective contour is greater than predetermined number threshold value;
When the number for determining the objective contour is more than or equal to the predetermined number threshold value, exports and had occurred on overpass
The result of congestion event.
2. the method as described in claim 1, which is characterized in that described to identify that the lane line in the target image includes:
Background image when obtaining on overpass bridge floor without vehicle;
Detect the lane line in the background image;
Obtain position coordinates of the lane line in the background image;
The region that the position coordinates are corresponded in the target image is determined as the lane line.
3. the method as described in claim 1, which is characterized in that the predetermined number threshold value is determining in the following manner:
In the case where smooth traffic, every preset time period acquisition one has image when vehicle, obtains multiple testing images;
Profile in multiple described testing images is detected using YOLO algorithm of target detection;
Count the total number of the profile in all testing images;
The mean number that profile is determined according to the total number of the profile, as the predetermined number threshold value.
4. the method as described in claim 1, which is characterized in that be more than or equal to institute in the number for judging the objective contour
After stating predetermined number threshold value, the method also includes:
Former frame target image and a later frame target image are subjected to difference processing, obtain difference image;
Judge whether the characteristic value of the difference image is greater than default characteristic threshold value;
When the characteristic value for judging the difference image is less than the default characteristic threshold value, then exports and had occurred on overpass seriously
Congestion event.
5. the method as described in claim 1, which is characterized in that detect the target using YOLO algorithm of target detection described
Before objective contour in image in adjacent two lane line regions, the method also includes:
Illumination or contrast normalized are carried out to the target image;
Noise reduction process is carried out to multiple images after carrying out the normalized using bilateral filtering algorithm.
6. the method as described in claim 1, which is characterized in that when the number for determining the objective contour is less than described default
When number threshold value, the method also includes:
There is no the results of congestion event on output overpass.
7. the method as described in any one of claim 1 to 6, which is characterized in that had occurred on the output overpass
After the result of congestion event, the method also includes:
To vehicle management, department sends a warning message;
The driver on the vehicle in overpass pre-determined distance sends a warning message simultaneously.
8. a kind of overpass traffic condition real-time monitoring device, which is characterized in that described device includes:
Module is obtained, there is target image when vehicle on overpass bridge floor for obtaining;
Identification module, for identification lane line in the target image;
Detection module, for being detected in the target image in adjacent two lane line regions using YOLO algorithm of target detection
Objective contour;
Judgment module, for judging whether the number of the objective contour is greater than predetermined number threshold value;
Output module, for determining that the number of the objective contour is more than or equal to the predetermined number when the judgment module
When threshold value, the result that congestion event has occurred on overpass is exported.
9. a kind of terminal, which is characterized in that the terminal includes processor, and the processor is used to execute to store in memory
The overpass traffic condition method of real-time as described in any one of claim 1 to 7 is realized when computer program.
10. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
It is, the overpass traffic shape as described in any one of claim 1 to 7 is realized when the computer program is executed by processor
Condition method of real-time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910377112.1A CN110175533A (en) | 2019-05-07 | 2019-05-07 | Overpass traffic condition method of real-time, device, terminal and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910377112.1A CN110175533A (en) | 2019-05-07 | 2019-05-07 | Overpass traffic condition method of real-time, device, terminal and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110175533A true CN110175533A (en) | 2019-08-27 |
Family
ID=67690545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910377112.1A Pending CN110175533A (en) | 2019-05-07 | 2019-05-07 | Overpass traffic condition method of real-time, device, terminal and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110175533A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111028510A (en) * | 2019-12-20 | 2020-04-17 | 汤勤 | Comprehensive emergency management platform architecture for cloud computing |
CN111523482A (en) * | 2020-04-24 | 2020-08-11 | 深圳市商汤科技有限公司 | Lane congestion detection method and apparatus, electronic device, and storage medium |
CN111652940A (en) * | 2020-04-30 | 2020-09-11 | 平安国际智慧城市科技股份有限公司 | Target abnormity identification method and device, electronic equipment and storage medium |
CN113657551A (en) * | 2021-09-01 | 2021-11-16 | 陕西工业职业技术学院 | Robot grabbing posture task planning method for sorting and stacking multiple targets |
CN113819910A (en) * | 2019-09-29 | 2021-12-21 | 百度在线网络技术(北京)有限公司 | Method and device for identifying overpass zone in vehicle navigation |
CN115311869A (en) * | 2022-07-29 | 2022-11-08 | 重庆长安汽车股份有限公司 | Road event obtaining method and system based on intelligent network connection automobile computing power sharing and automobile |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106327863A (en) * | 2015-07-06 | 2017-01-11 | 北京文安智能技术股份有限公司 | Method, device and system for detection and early warning of vehicle congestion |
CN106652445A (en) * | 2016-11-15 | 2017-05-10 | 成都通甲优博科技有限责任公司 | Road traffic accident judging method and device |
CN107945523A (en) * | 2017-11-27 | 2018-04-20 | 北京华道兴科技有限公司 | A kind of road vehicle detection method, DETECTION OF TRAFFIC PARAMETERS method and device |
CN108875600A (en) * | 2018-05-31 | 2018-11-23 | 银江股份有限公司 | A kind of information of vehicles detection and tracking method, apparatus and computer storage medium based on YOLO |
CN109087517A (en) * | 2018-09-19 | 2018-12-25 | 山东大学 | Intelligent signal lamp control method and system based on big data |
CN109241938A (en) * | 2018-09-27 | 2019-01-18 | 深圳金三立视频科技股份有限公司 | Congestion in road detection method and terminal |
-
2019
- 2019-05-07 CN CN201910377112.1A patent/CN110175533A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106327863A (en) * | 2015-07-06 | 2017-01-11 | 北京文安智能技术股份有限公司 | Method, device and system for detection and early warning of vehicle congestion |
CN106652445A (en) * | 2016-11-15 | 2017-05-10 | 成都通甲优博科技有限责任公司 | Road traffic accident judging method and device |
CN107945523A (en) * | 2017-11-27 | 2018-04-20 | 北京华道兴科技有限公司 | A kind of road vehicle detection method, DETECTION OF TRAFFIC PARAMETERS method and device |
CN108875600A (en) * | 2018-05-31 | 2018-11-23 | 银江股份有限公司 | A kind of information of vehicles detection and tracking method, apparatus and computer storage medium based on YOLO |
CN109087517A (en) * | 2018-09-19 | 2018-12-25 | 山东大学 | Intelligent signal lamp control method and system based on big data |
CN109241938A (en) * | 2018-09-27 | 2019-01-18 | 深圳金三立视频科技股份有限公司 | Congestion in road detection method and terminal |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113819910A (en) * | 2019-09-29 | 2021-12-21 | 百度在线网络技术(北京)有限公司 | Method and device for identifying overpass zone in vehicle navigation |
CN111028510A (en) * | 2019-12-20 | 2020-04-17 | 汤勤 | Comprehensive emergency management platform architecture for cloud computing |
CN111028510B (en) * | 2019-12-20 | 2020-11-13 | 海安荔弘科技有限公司 | Comprehensive emergency management platform architecture for cloud computing |
CN111523482A (en) * | 2020-04-24 | 2020-08-11 | 深圳市商汤科技有限公司 | Lane congestion detection method and apparatus, electronic device, and storage medium |
CN111652940A (en) * | 2020-04-30 | 2020-09-11 | 平安国际智慧城市科技股份有限公司 | Target abnormity identification method and device, electronic equipment and storage medium |
CN111652940B (en) * | 2020-04-30 | 2024-06-04 | 平安国际智慧城市科技股份有限公司 | Target abnormality recognition method, target abnormality recognition device, electronic equipment and storage medium |
CN113657551A (en) * | 2021-09-01 | 2021-11-16 | 陕西工业职业技术学院 | Robot grabbing posture task planning method for sorting and stacking multiple targets |
CN113657551B (en) * | 2021-09-01 | 2023-10-20 | 陕西工业职业技术学院 | Robot grabbing gesture task planning method for sorting and stacking multiple targets |
CN115311869A (en) * | 2022-07-29 | 2022-11-08 | 重庆长安汽车股份有限公司 | Road event obtaining method and system based on intelligent network connection automobile computing power sharing and automobile |
CN115311869B (en) * | 2022-07-29 | 2023-07-18 | 重庆长安汽车股份有限公司 | Road event acquisition method and system based on intelligent network-connected automobile calculation force sharing and automobile |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110175533A (en) | Overpass traffic condition method of real-time, device, terminal and storage medium | |
US20240233387A1 (en) | Scenario recreation through object detection and 3d visualization in a multi-sensor environment | |
WO2020248386A1 (en) | Video analysis method and apparatus, computer device and storage medium | |
Osman et al. | Intelligent traffic management system for cross section of roads using computer vision | |
KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
CN110991224B (en) | Pedestrian red light running detection method and device based on image recognition and related equipment | |
CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
CN106384532A (en) | Video data analysis method and apparatus thereof, and parking space monitoring system | |
CN107886055A (en) | A kind of retrograde detection method judged for direction of vehicle movement | |
CN108363953B (en) | Pedestrian detection method and binocular monitoring equipment | |
CN111931726B (en) | Traffic light detection method, device, computer storage medium and road side equipment | |
CN110070061A (en) | A kind of passengers quantity projectional technique and device | |
US11727580B2 (en) | Method and system for gathering information of an object moving in an area of interest | |
CN110263623A (en) | Train climbs monitoring method, device, terminal and storage medium | |
CN113936465A (en) | Traffic incident detection method and device | |
CN114677848B (en) | Perception early warning system, method, device and computer program product | |
CN110263622A (en) | Train fire monitoring method, apparatus, terminal and storage medium | |
KR101736431B1 (en) | System and Method for Smart Traffic Monitoring Using Multiple Image | |
CN105262984B (en) | A kind of detector with fixing device | |
CN114596704B (en) | Traffic event processing method, device, equipment and storage medium | |
CN115272924A (en) | Treatment system based on modularized video intelligent analysis engine | |
JP7203277B2 (en) | Method and apparatus for monitoring vehicle license plate recognition rate and computer readable storage medium | |
CN114972731A (en) | Traffic light detection and identification method and device, moving tool and storage medium | |
CN114549444A (en) | Cross-camera target detection and tracking system and method | |
CN106355925A (en) | Method and device for achieving evaluation of control effect of intersection signal machine by using internet |
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 |