CN115578862B - Traffic flow conversion method, device, computing equipment and storage medium - Google Patents
Traffic flow conversion method, device, computing equipment and storage medium Download PDFInfo
- Publication number
- CN115578862B CN115578862B CN202211322259.9A CN202211322259A CN115578862B CN 115578862 B CN115578862 B CN 115578862B CN 202211322259 A CN202211322259 A CN 202211322259A CN 115578862 B CN115578862 B CN 115578862B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- traffic
- human
- flow
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- 230000002194 synthesizing effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 230000004044 response Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000013145 classification model Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 5
- 238000000926 separation method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a traffic flow conversion method, a device, a computing device and a storage medium, which relate to the technical field of road traffic monitoring and comprise the following steps: the road condition data set is constructed according to road section traffic videos, the road condition data set comprises a pedestrian and vehicle traffic label, the pedestrian and vehicle traffic and M vehicle traffic corresponding to M vehicle types one by one, the pedestrian and vehicle traffic is converted into standard vehicle traffic respectively, the equivalent value of the pedestrian and vehicle corresponding to the influence of the standard vehicle type on the traffic is quantized uniformly, the comparability of the two standard vehicle traffic is guaranteed, the two standard vehicle traffic is synthesized according to the pedestrian and vehicle traffic label, the pedestrian and vehicle traffic is comprehensively measured, and the accuracy of measuring the traffic is improved.
Description
Technical Field
The invention relates to the technical field of road traffic monitoring, in particular to a traffic flow conversion method, a traffic flow conversion device, a traffic flow conversion computing device and a traffic flow storage medium.
Background
In a unit time, the number of traffic participants passing through a certain place or a certain section of a road is traffic flow, and the traffic participants can include motor vehicles, non-motor vehicles and pedestrians, accordingly, the traffic flow can be specifically any one of the motor vehicle traffic flow, the non-motor vehicle traffic flow and the human flow, under the condition that no special explanation exists, the traffic flow generally refers to the motor vehicle traffic flow, and can be used as a judgment basis of traffic congestion conditions so as to support a traffic signal system to make traffic control actions, and also can provide quantitative guidance basis for traffic change trend and road construction planning, so that it is particularly important to accurately measure the traffic flow.
Some roads (such as crossroads and small roads in cities) often face conditions of mixed traffic of people and vehicles and mixed traffic of various vehicles of different types, pedestrians have longer time and smaller space than the time required by the vehicles to occupy the road, the time and space required by the various vehicles of different types (such as bicycles, household automobiles and buses) are also different, the capability of driving and the vehicles to pass through the road is far different, the traffic flow and the traffic flow are usually monitored separately, for example, natural quantity statistics is carried out on pedestrian targets or/and moving vehicle targets in road traffic videos to obtain the traffic flow or/and the traffic flow, and the traffic flow and the pedestrian targets and the traffic flow are incomparable, and the traffic flow is not good in accuracy whether the traffic flow or the traffic flow is directly used as the traffic flow.
Disclosure of Invention
The present invention aims to solve at least some technical problems in the related art, and to achieve the above objects, the present invention provides a traffic flow conversion method, a device, a computing device, and a storage medium.
In a first aspect, the present invention provides a traffic flow conversion method, including:
constructing a road condition data set suitable for indicating the road section to bear the traffic condition of people and vehicles during video shooting according to the road section traffic video, wherein the road condition data set comprises people and vehicles passing labels, people flow and M vehicle flows corresponding to M vehicle types one by one, and M is a positive integer;
distributing M preset vehicle conversion coefficients to M vehicle flows one by one to form a pairing sequence, and carrying out weighted summation on the pairing sequence to obtain a standard vehicle flow;
multiplying a preset human-vehicle conversion coefficient by the human flow to obtain another standard vehicle flow;
and integrating the two standard traffic flows according to the man-vehicle passing labels.
Optionally, constructing a road condition dataset adapted to instruct a road section to withstand traffic conditions of people and vehicles during video capturing according to the road section traffic video includes:
carrying out classification tracking on the road section traffic videos to obtain a human track information set and M vehicle track information sets corresponding to M vehicle types one by one;
dividing the number of tracks of the person track information sets with the video shooting duration of the road section traffic video to obtain the traffic flow, and dividing the number of tracks of each vehicle track information set with the video shooting duration to obtain the corresponding traffic flow;
carrying out road type identification on one frame in the road section traffic video;
and generating the pedestrian and vehicle passing label according to the identified road type, the human track information set and the M vehicle track information sets, and combining the pedestrian and vehicle passing label, the pedestrian flow and the M vehicle flow to form the road condition data set.
Optionally, generating the passenger-vehicle pass tag according to the identified road type, the passenger-track information set, and the M vehicle-track information sets includes:
analyzing the human track information set and the M vehicle track information sets through a preset motion mode analysis model to obtain a human-vehicle motion mode;
and forming the man-vehicle movement mode and the road type into the man-vehicle passing tag.
Alternatively, one of the standard traffic flows is expressed as:
wherein beta is i Representing the preset vehicle conversion coefficient T adapted to the ith vehicle model i-c Representing the preset vehicle conversion coefficient beta i Is set in the vehicle flow rate;
the other of the standard traffic flows is expressed as: alpha X T p Wherein T is p And the flow of people is represented, and alpha represents the preset conversion coefficient of the passenger and the vehicle.
Optionally, the preset human-vehicle conversion coefficient is greater than 0.3 and less than 0.5.
Optionally, integrating the two standard traffic flows according to the man-vehicle pass tag includes:
checking whether the passenger-vehicle mixed attribute exists in the passenger-vehicle passing label;
if yes, adding the two standard traffic flows to obtain total traffic flow;
and if not, forming the two standard traffic flows into a traffic flow array.
Optionally, after integrating two standard traffic flows according to the man-vehicle passing tag, the method further includes:
presenting the aggregate traffic flow or the traffic flow array on a user interface;
when the total traffic flow is presented, two standard traffic flows are combined into the traffic flow array in response to an input traffic flow switching instruction, and then the total traffic flow is switched into the traffic flow array on the user interface.
In a second aspect, the present invention provides a traffic flow conversion device comprising:
the road condition data construction module is used for constructing a road condition data set suitable for indicating the road section to bear the traffic condition of people and vehicles during video shooting according to the road section traffic video, wherein the road condition data set comprises a people and vehicle passing label, the traffic volume and M traffic volumes corresponding to M vehicle types one by one, and M is a positive integer;
the vehicle flow normalization module is used for distributing M preset vehicle conversion coefficients to M vehicle flows one by one to form a pairing sequence, and carrying out weighted summation processing on the pairing sequence to obtain a standard vehicle flow; the method comprises the steps of carrying out a first treatment on the surface of the
The pedestrian flow standardization module is used for multiplying a preset pedestrian and vehicle conversion coefficient with the pedestrian flow to obtain another standard vehicle flow;
and the traffic flow synthesis module is used for synthesizing the two standard traffic flows according to the man-vehicle traffic labels.
In a third aspect, the present invention provides a computing device comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the traffic flow conversion method according to the first aspect when executing the computer program.
In a fourth aspect, the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the traffic flow conversion method according to the first aspect.
By using the traffic flow conversion method, the traffic flow conversion device, the calculation equipment and the storage medium, the traffic flow and the traffic flow which are in accordance with the actual road conditions are respectively converted into the standard traffic flow, the equivalent value of the traffic flow, which is equivalent to the influence of the standard vehicle type, of the traffic is uniformly quantized, the comparability of the two standard traffic flows is ensured, furthermore, the traffic flow is comprehensively measured by taking the traffic label as the basis of integrating the two standard traffic flows, and the accuracy of measuring the traffic flow is improved.
Drawings
Fig. 1 is a flow chart of a traffic flow conversion method according to an embodiment of the invention;
FIG. 2 is a schematic flow chart of S1 in FIG. 1;
FIG. 3 is a schematic representation of an image representing a road including overpass in accordance with an embodiment of the present invention;
FIGS. 4 and 5 are schematic diagrams illustrating two passenger-vehicle separation modes according to embodiments of the present invention;
FIG. 6 is a schematic diagram of an image representing an intersection in accordance with an embodiment of the present invention;
FIG. 7 is a schematic diagram of a hybrid mode of a man-vehicle according to an embodiment of the invention;
FIG. 8 is a flow chart of another traffic flow conversion method according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a user interface according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a traffic flow conversion device according to an embodiment of the invention;
FIG. 11 is a schematic circuit diagram of a computing device according to an embodiment of the invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the drawings, wherein like reference numerals in different drawings denote like or similar elements unless otherwise indicated. It is noted that the implementations described in the following exemplary examples do not represent all implementations of the invention. They are merely examples of apparatus and methods consistent with aspects of the present disclosure as detailed in the claims and the scope of the invention is not limited thereto. Features of the various embodiments of the invention may be combined with each other without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Referring to fig. 1, a traffic flow conversion method according to an embodiment of the present invention includes S1 to S3.
S1, constructing a road condition data set suitable for indicating the road section to bear the traffic condition of people and vehicles in the video shooting period according to the road section traffic video, wherein the road condition data set comprises people and vehicles passing labels, people flow and M vehicle flows corresponding to M vehicle types one by one, and M is a positive integer.
In the embodiment of the invention, in the urban rush hour or other periods, the high-definition camera installed on the road side supporting rod can be called on line through the server or the traffic signal central control computer, so that the high-definition camera shoots a certain road section in a fixed direction, the unmanned aerial vehicle can also drive the high-definition camera, and the high-definition camera shoots a certain road section to generate road section traffic videos, and of course, road section traffic videos can also be generated in other modes.
In the embodiment of the invention, the high-definition camera can send the road traffic video to some computing devices such as a server or/and a traffic signal central control computer in real time, the traffic signal central control computer can download the road traffic video from the server, and of course, the road traffic video can also be prestored in other computing devices such as a portable computer in an offline mode.
In the embodiment of the invention, a human-vehicle classification model, a road classification model and a vehicle classification model can be trained in advance, for example, a human-vehicle classification model based on a multi-granularity perception SVM can be used for classifying pedestrians, vehicles and others, various road classification models based on frequency spectrums, cluster groups and machine learning algorithms can be used for classifying roads including overpasses, cross roads, small roads, sidewalks and the like, various vehicle classification models based on a CSPPeleNetSE network and a support vector machine can be used for classifying vehicles such as bicycles, electric vehicles, automobiles and trucks and the like, and the classification models belong to the prior art, and the embodiment of the invention does not limit a classification mode facing human-vehicle-road under the condition of no conflict.
S2, M preset vehicle conversion coefficients are allocated to M vehicle flows one by one to form a pairing sequence, and the pairing sequence is subjected to weighted summation processing to obtain a standard vehicle flow; and multiplying the preset human-vehicle conversion coefficient by the human flow to obtain another standard vehicle flow.
| Traffic participants | Conversion coefficient |
| Pedestrian | 0.4 |
| Bicycle with wheel | 1 |
| Two-wheel motorcycle | 2 |
| Mini car | 3 |
| Small passenger car or truck with load capacity less than 3t | 5 |
| Small bus | 6 |
| 640 type single-section bus or truck with load capacity less than 9t | 10 |
| 650-type single-section bus or truck with 9-15 t loading capacity | 15 |
| Double-deck bus | 18 |
| Articulated buses or trucks with a load capacity greater than 15t | 20 |
In the embodiment of the invention, the conversion coefficients corresponding to pedestrians and various vehicle types can be pre-stored in the list form as shown above, the embodiment of the invention does not limit the vehicle types displayed in the list and the bicycles as standard vehicle types, and of course, new vehicle types can be added or eliminated from the list, and other vehicle types except the bicycles can be set as standard vehicle types, for example, each conversion coefficient is multiplied by 0.2, so that the small passenger car is used as the standard vehicle type.
In the embodiment of the invention, the road condition data set may further include pedestrian labels and M vehicle type labels, the conversion coefficient searched in the list according to the pedestrian labels is a preset human-vehicle conversion coefficient, the conversion coefficient searched in the list according to each vehicle type label is a corresponding preset vehicle conversion coefficient, the preset vehicle conversion coefficient and the corresponding vehicle flow can be stored in the same row or the same column of the two-dimensional matrix, and finally the two-dimensional matrix forms a pairing sequence of M rows and 2 columns or 2 columns and M rows, and the pairing sequence may also be in a data set or other forms.
S3, integrating two standard traffic flows according to the passenger-vehicle traffic labels.
By using the traffic flow conversion method, the traffic flow and the traffic flow which are in accordance with the actual road conditions are respectively converted into the standard traffic flow, the equivalent value of the traffic flow, which is equivalent to the influence of the standard vehicle type, of the traffic is uniformly quantized, the comparability of the two standard traffic flows is ensured, furthermore, the traffic label is used as the basis for synthesizing the two standard traffic flows, the traffic flow is comprehensively measured, and the accuracy of measuring the traffic flow is improved.
Alternatively, referring to fig. 2, S1 includes S11 to S14.
S11, carrying out human-vehicle classification tracking on the road section traffic video to obtain a human track information set and M vehicle track information sets corresponding to M vehicle types one by one.
In the embodiment of the invention, a target detection algorithm yolov5 and a multi-target tracking algorithm deepsort can be combined to construct and pre-train a human-vehicle recognition model, pedestrian targets and various vehicle targets in road section traffic videos can be tracked and counted in a classified manner through the human-vehicle recognition model, and the human-vehicle recognition model belongs to the prior art, and considers human-vehicle classification efficiency and accuracy; when outputting a person track record suitable for uniquely characterizing each pedestrian walking route from the person-vehicle recognition model, storing each person track record into a first list, and finally enabling the first list to form a person track information set; when outputting the vehicle track records which are suitable for uniquely representing each vehicle driving route from the human-vehicle identification model, each vehicle track record can be stored in a corresponding second list, and finally M second lists named as M vehicle types form M vehicle track information sets.
Taking a person track record as an example, the record form may be: track_person_10= [ (x) 1 ，y 1 ，a 1 ，h 1 ，v 1 )，…，(x i ，y i ，a i ，h i ，v i )，…，(x N ，y N ，a N ，h N ，v N )]Wherein person_10 is a tag for uniquely identifying the walking route of the 10 th pedestrian target in the road section traffic video, X i And Y is equal to i Together representing the ith track point of the 10 th pedestrian target in the road section traffic video, wherein the track point can be the center point of the tracking frame, a i 、h i V i The aspect ratio, the height and the speed of the 10 th pedestrian target at the ith track point are sequentially expressed, wherein the aspect ratio can be the ratio of the height to the width of the tracking frame, i is more than or equal to 1 and less than or equal to N, and N represents the frame number of the road section traffic video.
It should be noted that each person track record and each car track record may be set in a unified form, where the unified form may be a data set or a multidimensional matrix or other forms, for example, for the kth bicycle, a two-dimensional matrix of 2 rows and N columns is named by track_bicycle_k, and corresponding track points are stored in each column of the two-dimensional matrix, which is not described herein again.
And S12, dividing the number of tracks of the person track information sets by the video shooting time to obtain the traffic flow, and dividing the number of tracks of each vehicle track information set by the video shooting time to obtain the corresponding traffic flow.
In the embodiment of the invention, the track_person can be counted to obtain the track number, or the label with the largest value can be directly determined in the human track information set, and the value in the label is determined to be the total track number, for example, in the human track information set, all labels are arranged according to the ascending or descending order of the value, the label with the largest value is arranged at the first position or the last position, and 15 is the total track number under the condition that the label with the largest value is track_person_10, so that the label searching mode is more efficient than the counting mode, and the track number of each vehicle track information set and the track number of the human track information set can be uniformly acquired.
S13, identifying the road type of one frame in the road section traffic video.
In the embodiment of the invention, the frame of the road section traffic video can be extracted, and when the road section traffic video is played to a certain frame of image, the played image is captured to obtain an image to be recognized, wherein the image to be recognized expresses an overpass-containing road as shown in fig. 3, and the image to be recognized expresses an intersection as shown in fig. 6; the image to be identified can be identified by a road type identification method such as CN202210880954.0 to determine which road segment is a crossing road or a overpass road including a overpass, or the image to be identified expressing a street can be identified by a road type identification method such as CN202010953644.8 to determine which road segment is a road of a diversion of people and vehicles and a road of a mix of people and vehicles.
And S14, generating a pedestrian and vehicle passing label according to the identified road type, the pedestrian and vehicle track information set and the M vehicle track information sets, and combining the pedestrian and vehicle passing label, the pedestrian flow and the M vehicle flow to form a road condition data set.
In the embodiment of the invention, all track points in the human track information set can be marked on the blank image, and all track points in the M vehicle track information sets can be marked on the blank image to form a human-vehicle track map; performing cluster analysis on the human-vehicle track diagram to determine whether the human track family is mixed with or separated from the vehicle track family; if the human track family and the vehicle track family are mixed and the road type is a human-vehicle mixed road type, setting a human-vehicle passing label as' the human-vehicle follows the design requirement of the human-vehicle mixed road; if the human track group is separated from the vehicle track group and the road type is a human-vehicle split road type, setting the human-vehicle passing label as 'the human-vehicle is required to pass following the human-vehicle split road design'.
Under some road conditions, even if a pavement is arranged on a road section such as a cross road, an electric vehicle, a bicycle and the like often travel on the pavement along with pedestrians, vehicles, trucks and the like also pass through the pavement, the mixed traveling condition of the vehicles and the like often occurs, the same situation also occurs on a street, the pavement is usually arranged on two sides of a lane, isolation measures are not adopted between the pavement and the lane, the consistency of the traffic condition of the vehicles and the type of the road is considered, and the accuracy of the traffic label of the vehicles is promoted.
Optionally, S14 includes: analyzing the human track information set and the M vehicle track information sets through a preset motion mode analysis model to obtain a human-vehicle motion mode; the man-car movement mode and the road type are combined into the man-car passing tag.
In the embodiment of the invention, a clustering algorithm such as K-means or DBSCAN can be pre-constructed and trained to be used as a preset motion mode analysis model, and the motion modes of the human and the vehicle can be divided into two types, namely a human-vehicle mixed mode for expressing the mixture of a human track group and a vehicle track group and a human-vehicle separation mode for expressing the separation of the human track group and the vehicle track group, and of course, the motion modes of the human and the vehicle can be other modes or further subdivided.
Illustratively, on fig. 4, 5 and 7, the human track family is shown in dashed form and the vehicle track family is shown in solid form; under the condition that a high-definition camera shoots a road with an overpass along the direction of a lane line, extracting a frame of image from a road section traffic video as an image to be identified (see fig. 3), wherein the image to be identified presents a horizontal effect, correspondingly, a human track group and a vehicle track group are separated and distributed in a T shape (see fig. 4), and a human-vehicle passing label can be set as a human-vehicle track in a T-shaped separation mode, namely, the road type is a human-vehicle diversion type; under the condition that the high-definition camera aerial photographs the overpass-containing road along the overlooking direction, the image to be recognized presents overlooking effect, correspondingly, the human track family is separated from the vehicle track family and distributed in a cross shape (see figure 5), and the human-vehicle passing labels can be set as 'the human-vehicle track is in a cross-shaped separation mode-the road type is a human-vehicle diversion type'; under the condition that the high-definition camera aerial photographs the crossing road along the oblique direction, the image to be recognized presents an aerial oblique effect (see fig. 6), correspondingly, the human track groups and the vehicle track groups are mixed and distributed in a grid disc (see fig. 7), and the human-vehicle passing labels can be set as a human-vehicle track in a grid disc mixed mode, namely, the road type is a human-vehicle mixed type.
By means of the motion mode analysis model, the human-vehicle motion mode is analyzed and combined with the road type, and the method has the advantages of simplicity and high efficiency, so that the human-vehicle passing label can take the two aspects of the human-vehicle passing condition and the road design requirement into account, and the comprehensiveness and the accuracy of the human-vehicle passing label are improved.
Alternatively, a standard traffic flow is expressed as:
wherein beta is i Representing a preset vehicle conversion coefficient adapted to an ith vehicle model, T i-c Representing the pairing to a preset vehicle conversion coefficient beta i Is provided.
Another standard traffic flow is expressed as: alpha X T p Wherein T is p The flow of people is represented, and alpha represents a preset conversion coefficient of the people and the vehicles.
In the embodiment of the invention, the preset human conversion coefficient and all vehicle conversion coefficients can be put into the weighted summation model in advance, when M traffic flows are input into the weighted summation model, the human flow and other traffic flows are set to be zero, and when only the human flow is input into the weighted summation model, all the traffic flows are set to be zero so as to respectively represent two standard traffic flows, thereby taking the simplicity and the accuracy into consideration.
Optionally, the preset human-vehicle conversion coefficient is greater than 0.3 and less than 0.5, for example, the preset human-vehicle conversion coefficient may be 0.45 or other values, which provides a reasonable value range.
In the embodiment of the present invention, the preset human-vehicle conversion coefficient may be an empirical value, or may be calculated by the formula three (a Vehicle with a frame ×V Human body )/(A Human body ×V Vehicle with a frame ) Obtaining, wherein A Vehicle with a frame Representing the floor area of a standard vehicle, V Human body Indicating the walking speed of a person, A Human body Representing the floor area of a person, V Vehicle with a frame Representing the running speed of a standard bicycle, for example, the floor space of a normal bicycle may be 0.6 square meter, the running speed of an adult may be 1 meter per second, the projected area of an adult may be 0.36 square meter, and the running speed of a normal bicycle may be 4.5 meters per second, whereby the preset human-to-vehicle conversion factor is about 0.37.
Optionally, referring to fig. 8, the traffic flow conversion method according to another embodiment of the present invention, S3 includes: checking whether the personnel-vehicle passing label has the personnel-vehicle mixing attribute or not; if yes, adding the two standard traffic flows to obtain total traffic flow; if not, the two standard traffic flows are combined into a traffic flow array.
In the embodiment of the invention, the man-vehicle passing label is compared with a preset mixed word, if the man-vehicle passing label contains the mixed word, the man-vehicle passing label is reflected to be in the man-vehicle mixed attribute, the two standard traffic flows are synthesized in an addition mode, otherwise, the man-vehicle passing label is reflected to be in the man-vehicle split attribute, the two standard traffic flows are synthesized in an array mode, the total traffic flow or the traffic flow array is taken as a traffic flow result, and the traffic flow result can be sent to a traffic signal central control computer, an intelligent automobile and the like by a server, or can be sent to the server by the traffic signal central control computer, the intelligent automobile and the like, so that the traffic flow result is finely managed according to different traffic conditions, and the singleness of the traffic flow result is avoided.
Optionally, referring to fig. 8, further includes: s4, presenting the aggregate traffic flow or the traffic flow array on a user interface; s5, when the total traffic flow is presented, responding to the input traffic flow switching instruction, and after the two standard traffic flows are formed into a traffic flow array, switching the total traffic flow into the traffic flow array on the user interface so as to facilitate the user to distinguish the two traffic flow results.
In the embodiment of the invention, the traffic signal central control computer or the intelligent automobile and the like are provided with a display, and the display can present a user interface shown in fig. 9, wherein the user interface comprises the following fields of' total traffic flow: 72 bicycles per minute "and a graphic control on the left side of the aforementioned field, the graphic control being provided as a toggle icon represented in double-arrow cycles; the user clicks the graphic control once, namely inputs a traffic flow switching instruction once, and the field' aggregate traffic flow: 72 bicycles per minute "disappeared", and the field "traffic flow array: TF (TF) Vehicle with a frame TF =50 bicycles per minute Human body 22 bikes per minute "are presented in the field vanishing area, where TF Vehicle with a frame Represents standard traffic flow corresponding to M traffic flows, TF Human body Representing a standard traffic flow corresponding to the traffic flow; the user clicks once again the graphic control and once again inputs the traffic flow switching fingerLet, field "traffic flow array: TF (TF) Vehicle with a frame TF =50 bicycles per minute Human body =22 bicycles per minute "disappeared", field "aggregate traffic flow: 72 bicycles per minute "are presented in the field disappearing area.
Referring to fig. 10, a traffic flow conversion device according to another embodiment of the present invention includes: the road condition data construction module is used for constructing a road condition data set suitable for indicating the road section to bear the traffic condition of people and vehicles in the video shooting period according to the road section traffic video, wherein the road condition data set comprises a people and vehicles passing label, the traffic quantity and M traffic quantities corresponding to M vehicle types one by one, and M is a positive integer; the vehicle flow standardization module is used for distributing M preset vehicle conversion coefficients to M vehicle flows one by one to form a pairing sequence, and carrying out weighted summation processing on the pairing sequence to obtain a standard vehicle flow; the pedestrian flow standardization module is used for multiplying a preset pedestrian and vehicle conversion coefficient by the pedestrian flow to obtain another standard vehicle flow; and the traffic flow synthesis module is used for synthesizing two standard traffic flows according to the man-vehicle traffic labels.
Referring to fig. 11, a computing device according to another embodiment of the present invention includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the traffic flow conversion method when executing the computer program, and where the processor may be connected to the memory through a universal serial bus. It is understood that the foregoing computing device may be a server or a terminal device.
A non-transitory computer-readable storage medium of another embodiment of the present invention has stored thereon a computer program which, when executed by a processor, implements the above-described traffic flow conversion method.
In general, the computer instructions to implement the methods of the present invention may be carried in any combination of one or more computer-readable storage media. The non-transitory computer-readable storage medium may include any computer-readable medium, except the signal itself in temporary propagation.
The computer readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer program code for carrying out operations of the present invention may be written in one or more programming languages, or combinations thereof, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" language or similar programming languages, particularly the Python language suitable for neural network computing and TensorFlow, pyTorch-based platform frameworks may be used. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or to an external computer (for example, through the Internet using an Internet service provider).
The traffic flow conversion device, the computing device and the storage medium can be referred to the specific description of the traffic flow conversion method and the beneficial effects thereof, and are not repeated here.
While embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (9)
1. A traffic flow conversion method, comprising:
constructing a road condition data set suitable for indicating the road section to bear the traffic condition of people and vehicles during video shooting according to the road section traffic video, wherein the road condition data set comprises people and vehicles passing labels, people flow and M vehicle flows corresponding to M vehicle types one by one, and M is a positive integer;
distributing M preset vehicle conversion coefficients to M vehicle flows one by one to form a pairing sequence, and carrying out weighted summation on the pairing sequence to obtain a standard vehicle flow;
multiplying a preset human-vehicle conversion coefficient by the human flow to obtain another standard vehicle flow;
synthesizing two standard traffic flows according to the man-vehicle passing labels;
the construction of the road condition data set suitable for indicating the road section to bear the traffic condition of people and vehicles during video shooting according to the road section traffic video comprises the following steps:
carrying out classification tracking on the road section traffic videos to obtain a human track information set and M vehicle track information sets corresponding to M vehicle types one by one;
carrying out road type identification on one frame in the road section traffic video;
analyzing a human-vehicle movement mode according to the human track information set and the M vehicle track information sets;
if the human-vehicle movement mode expresses that the human track family and the vehicle track family are mixed and the road type is a human-vehicle mixed type, setting the human-vehicle passing tag with the human-vehicle mixed attribute;
and if the human-vehicle movement mode expresses that the human track group is separated from the vehicle track group and the road type is a human-vehicle shunting type, setting the human-vehicle passing tag with the human-vehicle shunting attribute.
2. The traffic flow conversion method according to claim 1, wherein constructing a road condition data set adapted to indicate that a road section is subjected to a traffic condition during video capturing from a road section traffic video further comprises:
dividing the number of tracks of the person track information sets with the video shooting duration of the road section traffic video to obtain the traffic flow, and dividing the number of tracks of each vehicle track information set with the video shooting duration to obtain the corresponding traffic flow;
and combining the pedestrian and vehicle passing tag, the pedestrian flows and the M vehicle flows to form the road condition data set.
3. The traffic flow conversion method according to claim 1, wherein one of the standard traffic flows is expressed as:
wherein beta is i Representing the preset vehicle conversion coefficient T adapted to the ith vehicle model i-c Representing the preset vehicle conversion coefficient beta i Is set in the vehicle flow rate;
the other of the standard traffic flows is expressed as: alpha X T p Wherein T is p And the flow of people is represented, and alpha represents the preset conversion coefficient of the passenger and the vehicle.
4. The traffic flow conversion method according to claim 1, wherein the preset human-vehicle conversion coefficient is greater than 0.3 and less than 0.5.
5. The traffic flow converting method according to any one of claims 1-4, wherein integrating two of said standard traffic flows according to said man-vehicle pass tag comprises:
checking whether the passenger-vehicle mixed attribute exists in the passenger-vehicle passing label;
if yes, adding the two standard traffic flows to obtain total traffic flow;
and if not, forming the two standard traffic flows into a traffic flow array.
6. The traffic flow converting method according to claim 5, further comprising, after integrating two of said standard traffic flows according to said man-vehicle pass tag:
presenting the aggregate traffic flow or the traffic flow array on a user interface;
when the total traffic flow is presented, two standard traffic flows are combined into the traffic flow array in response to an input traffic flow switching instruction, and then the total traffic flow is switched into the traffic flow array on the user interface.
7. A traffic flow conversion device, comprising:
the road condition data construction module is used for constructing a road condition data set suitable for indicating the road section to bear the traffic condition of people and vehicles during video shooting according to the road section traffic video, wherein the road condition data set comprises a people and vehicle passing label, the traffic volume and M traffic volumes corresponding to M vehicle types one by one, and M is a positive integer;
the vehicle flow normalization module is used for distributing M preset vehicle conversion coefficients to M vehicle flows one by one to form a pairing sequence, and carrying out weighted summation processing on the pairing sequence to obtain a standard vehicle flow;
the pedestrian flow standardization module is used for multiplying a preset pedestrian and vehicle conversion coefficient with the pedestrian flow to obtain another standard vehicle flow;
the traffic flow synthesis module is used for synthesizing two standard traffic flows according to the man-vehicle traffic labels;
the road condition data construction module is specifically configured to:
carrying out classification tracking on the road section traffic videos to obtain a human track information set and M vehicle track information sets corresponding to M vehicle types one by one;
carrying out road type identification on one frame in the road section traffic video;
analyzing a human-vehicle movement mode according to the human track information set and the M vehicle track information sets;
if the human-vehicle movement mode expresses that the human track family and the vehicle track family are mixed and the road type is a human-vehicle mixed type, setting the human-vehicle passing tag with the human-vehicle mixed attribute;
and if the human-vehicle movement mode expresses that the human track group is separated from the vehicle track group and the road type is a human-vehicle shunting type, setting the human-vehicle passing tag with the human-vehicle shunting attribute.
8. A computing device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the traffic flow conversion method of any of claims 1-6 when the computer program is executed.
9. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the traffic flow conversion method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211322259.9A CN115578862B (en) | 2022-10-26 | 2022-10-26 | Traffic flow conversion method, device, computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211322259.9A CN115578862B (en) | 2022-10-26 | 2022-10-26 | Traffic flow conversion method, device, computing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115578862A CN115578862A (en) | 2023-01-06 |
| CN115578862B true CN115578862B (en) | 2023-09-19 |
Family
ID=84587832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211322259.9A Active CN115578862B (en) | 2022-10-26 | 2022-10-26 | Traffic flow conversion method, device, computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115578862B (en) |
Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101577054A (en) * | 2009-02-27 | 2009-11-11 | 北京中星微电子有限公司 | Control method of traffic signal lamp and system |
| JP2010097488A (en) * | 2008-10-17 | 2010-04-30 | Toyota Motor Corp | Peripheral monitoring device |
| JP2011095959A (en) * | 2009-10-29 | 2011-05-12 | Sumitomo Electric Ind Ltd | Traffic signal control system and signal control apparatus |
| CN102741884A (en) * | 2010-07-27 | 2012-10-17 | 松下电器产业株式会社 | Mobile body detection device and mobile body detection method |
| CN102819764A (en) * | 2012-07-18 | 2012-12-12 | 郑州金惠计算机系统工程有限公司 | Method for counting pedestrian flow from multiple views under complex scene of traffic junction |
| CN103020624A (en) * | 2011-09-23 | 2013-04-03 | 杭州海康威视系统技术有限公司 | Intelligent marking, searching and replaying method and device for surveillance videos of shared lanes |
| CN103164968A (en) * | 2011-12-15 | 2013-06-19 | 西安大昱光电科技有限公司 | Intelligence traffic signal lamp controlling system based on traffic flow |
| WO2015089867A1 (en) * | 2013-12-17 | 2015-06-25 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method |
| CN104933710A (en) * | 2015-06-10 | 2015-09-23 | 华南理工大学 | Intelligent analysis method of store people stream track on the basis of surveillance video |
| CN105427343A (en) * | 2015-11-18 | 2016-03-23 | 中国科学院信息工程研究所 | Moving target detecting and tracking method based on DM8148 development board |
| CN105488519A (en) * | 2015-11-13 | 2016-04-13 | 同济大学 | Video classification method based on video scale information |
| JP2016162409A (en) * | 2015-03-05 | 2016-09-05 | 沖電気工業株式会社 | Image processing device, image processing system, image processing method and program |
| CN106652494A (en) * | 2015-11-03 | 2017-05-10 | 中国移动通信集团公司 | Traffic light control method and device |
| CN107622678A (en) * | 2017-10-18 | 2018-01-23 | 冯迎安 | A kind of intelligent traffic control system and its method based on image procossing |
| CN108986465A (en) * | 2018-07-27 | 2018-12-11 | 深圳大学 | A kind of method of vehicle Flow Detection, system and terminal device |
| CN109919072A (en) * | 2019-02-28 | 2019-06-21 | 桂林电子科技大学 | Fine vehicle type recognition and flow statistics method based on deep learning and trajectory tracking |
| CN110473412A (en) * | 2019-09-12 | 2019-11-19 | 杭州京安交通工程设施有限公司 | A kind of controlling system of traffic light |
| CN111445699A (en) * | 2020-04-13 | 2020-07-24 | 黑龙江工程学院 | Intersection traffic conflict discrimination method based on real-time vehicle track |
| CN112017209A (en) * | 2020-09-07 | 2020-12-01 | 图普科技（广州）有限公司 | Regional crowd trajectory determination method and device |
| CN113420618A (en) * | 2021-06-04 | 2021-09-21 | 哈尔滨工业大学（深圳） | Signal intersection standard vehicle accurate conversion method, device and system |
| WO2021189009A1 (en) * | 2020-03-19 | 2021-09-23 | Nvidia Corporation | Future trajectory predictions in multi-actor environments for autonomous machine applications |
| KR20210117637A (en) * | 2020-03-19 | 2021-09-29 | 주식회사 아이오라이트 | Method for video monitoring for vehicle and human auto detection based on deep learning and Data transmission method using the same |
| CN115158320A (en) * | 2022-08-11 | 2022-10-11 | 小米汽车科技有限公司 | Vehicle control method and device, vehicle and readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017054311A (en) * | 2015-09-09 | 2017-03-16 | 株式会社デンソー | Object detection apparatus |
| US20210049772A1 (en) * | 2018-07-16 | 2021-02-18 | Accel Robotics Corporation | Automated store that tracks shoppers who exit a vehicle |
| US11276179B2 (en) * | 2019-12-18 | 2022-03-15 | Zoox, Inc. | Prediction on top-down scenes based on object motion |
-
2022
- 2022-10-26 CN CN202211322259.9A patent/CN115578862B/en active Active
Patent Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010097488A (en) * | 2008-10-17 | 2010-04-30 | Toyota Motor Corp | Peripheral monitoring device |
| CN101577054A (en) * | 2009-02-27 | 2009-11-11 | 北京中星微电子有限公司 | Control method of traffic signal lamp and system |
| JP2011095959A (en) * | 2009-10-29 | 2011-05-12 | Sumitomo Electric Ind Ltd | Traffic signal control system and signal control apparatus |
| CN102741884A (en) * | 2010-07-27 | 2012-10-17 | 松下电器产业株式会社 | Mobile body detection device and mobile body detection method |
| CN103020624A (en) * | 2011-09-23 | 2013-04-03 | 杭州海康威视系统技术有限公司 | Intelligent marking, searching and replaying method and device for surveillance videos of shared lanes |
| CN103164968A (en) * | 2011-12-15 | 2013-06-19 | 西安大昱光电科技有限公司 | Intelligence traffic signal lamp controlling system based on traffic flow |
| CN102819764A (en) * | 2012-07-18 | 2012-12-12 | 郑州金惠计算机系统工程有限公司 | Method for counting pedestrian flow from multiple views under complex scene of traffic junction |
| WO2015089867A1 (en) * | 2013-12-17 | 2015-06-25 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method |
| JP2016162409A (en) * | 2015-03-05 | 2016-09-05 | 沖電気工業株式会社 | Image processing device, image processing system, image processing method and program |
| CN104933710A (en) * | 2015-06-10 | 2015-09-23 | 华南理工大学 | Intelligent analysis method of store people stream track on the basis of surveillance video |
| CN106652494A (en) * | 2015-11-03 | 2017-05-10 | 中国移动通信集团公司 | Traffic light control method and device |
| CN105488519A (en) * | 2015-11-13 | 2016-04-13 | 同济大学 | Video classification method based on video scale information |
| CN105427343A (en) * | 2015-11-18 | 2016-03-23 | 中国科学院信息工程研究所 | Moving target detecting and tracking method based on DM8148 development board |
| CN107622678A (en) * | 2017-10-18 | 2018-01-23 | 冯迎安 | A kind of intelligent traffic control system and its method based on image procossing |
| CN108986465A (en) * | 2018-07-27 | 2018-12-11 | 深圳大学 | A kind of method of vehicle Flow Detection, system and terminal device |
| CN109919072A (en) * | 2019-02-28 | 2019-06-21 | 桂林电子科技大学 | Fine vehicle type recognition and flow statistics method based on deep learning and trajectory tracking |
| CN110473412A (en) * | 2019-09-12 | 2019-11-19 | 杭州京安交通工程设施有限公司 | A kind of controlling system of traffic light |
| WO2021189009A1 (en) * | 2020-03-19 | 2021-09-23 | Nvidia Corporation | Future trajectory predictions in multi-actor environments for autonomous machine applications |
| KR20210117637A (en) * | 2020-03-19 | 2021-09-29 | 주식회사 아이오라이트 | Method for video monitoring for vehicle and human auto detection based on deep learning and Data transmission method using the same |
| CN111445699A (en) * | 2020-04-13 | 2020-07-24 | 黑龙江工程学院 | Intersection traffic conflict discrimination method based on real-time vehicle track |
| CN112017209A (en) * | 2020-09-07 | 2020-12-01 | 图普科技（广州）有限公司 | Regional crowd trajectory determination method and device |
| CN113420618A (en) * | 2021-06-04 | 2021-09-21 | 哈尔滨工业大学（深圳） | Signal intersection standard vehicle accurate conversion method, device and system |
| CN115158320A (en) * | 2022-08-11 | 2022-10-11 | 小米汽车科技有限公司 | Vehicle control method and device, vehicle and readable storage medium |
Non-Patent Citations (7)
| Title |
|---|
| 一级公路交通安全设施人性化设置分析;郑少鹏;胡刚;汤永华;陈怀勇;罗春荣;胡澄宇;李薇;;公路交通科技(应用技术版)(第04期);全文 * |
| 单目视频中无标记人体运动动作轨迹实时提取方法;闫晓明;;周口师范学院学报(第02期);全文 * |
| 基于人工蜂群算法的运动目标检测方法;陈雷;张立毅;郭艳菊;刘婷;李锵;;计算机工程与应用(第21期);全文 * |
| 基于社会力的自动驾驶汽车行人轨迹预测模型;杨文彦;张希;陈浩;金文强;;公路交通科技(第08期);全文 * |
| 基于运动轨迹采集的混合交通特性研究;吕剑;史其信;杨新苗;;武汉理工大学学报(交通科学与工程版)(第01期);全文 * |
| 机非混行道路交通改善方法研究;邵海鹏;杨晓光;董海倩;;城市交通(第01期);全文 * |
| 采用多组单应约束和马尔可夫随机场的运动目标检测算法;崔智高;李艾华;冯国彦;;计算机辅助设计与图形学学报(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115578862A (en) | 2023-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Moers et al. | The exid dataset: A real-world trajectory dataset of highly interactive highway scenarios in germany | |
| Bock et al. | The ind dataset: A drone dataset of naturalistic road user trajectories at german intersections | |
| Yang et al. | Top-view trajectories: A pedestrian dataset of vehicle-crowd interaction from controlled experiments and crowded campus | |
| CN109520744B (en) | Driving performance testing method and device for automatic driving vehicle | |
| Cai et al. | Deep learning-based video system for accurate and real-time parking measurement | |
| Breuer et al. | openDD: A large-scale roundabout drone dataset | |
| JP2021503106A (en) | Methods and systems for determining the presence or absence of target road equipment at intersections | |
| CN108389421B (en) | Parking lot accurate induction system and method based on image re-identification | |
| CN109711009B (en) | Unmanned automobile performance evaluation method and device, electronic equipment and medium | |
| CN106097717B (en) | Signalized intersections based on the fusion of two class floating car datas are averaged transit time method of estimation | |
| US11756417B2 (en) | Method, apparatus, and system for detecting road incidents | |
| CN112116263B (en) | Traffic intersection risk level assessment method and device, electronic equipment and storage medium | |
| Guo et al. | Automated analysis of pedestrian walking behaviour at a signalised intersection in China | |
| KR20230012953A (en) | Machine learning-based framework for drivable surface annotation | |
| Pi et al. | Visual recognition for urban traffic data retrieval and analysis in major events using convolutional neural networks | |
| Zheng et al. | A deep learning–based approach for moving vehicle counting and short-term traffic prediction from video images | |
| Darwhekar et al. | Computer vision based intelligent traffic management system | |
| CN115578862B (en) | Traffic flow conversion method, device, computing equipment and storage medium | |
| CN113420618A (en) | Signal intersection standard vehicle accurate conversion method, device and system | |
| CN117830354A (en) | Track acquisition method, track acquisition device, computer equipment and storage medium | |
| CN114492544B (en) | Model training method and device and traffic incident occurrence probability evaluation method and device | |
| CN117409569A (en) | Intelligent traffic system and method based on big data | |
| Ammourah et al. | Introduction to the Third Generation Simulation Dataset: Data Collection and Trajectory Extraction | |
| CN109255953A (en) | Movable vehicle distribution methods of exhibiting and system based on region | |
| Kutsch et al. | TUMDOT–MUC: Data Collection and Processing of Multimodal Trajectories Collected by Aerial Drones |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Gong Zhiqun Inventor after: Xu Feng Inventor after: Yang Shiting Inventor after: Zhang Dongliang Inventor after: Gao Wei Inventor before: Gong Zhiqun Inventor before: Xu Feng Inventor before: Yang Shiting Inventor before: Zhang Dongliang Inventor before: Gao Wei |
|
| CB03 | Change of inventor or designer information |