Traffic data visualization method and apparatus, electronic device, and medium

Abstract

The present disclosure relates to a traffic data visualization method, device, electronic equipment, computer readable storage medium and computer program product. The method comprises: obtaining a first traffic data set of a traffic participant, each traffic data in the first traffic data set comprising a plurality of attribute fields; obtaining an additional attribute field of the traffic data in the first traffic data set and an additional attribute value of the additional attribute field according to an attribute value of the attribute field, thereby obtaining a second traffic data set; determining a traffic data subset from the second traffic data set in response to a search request, each traffic data in the traffic data subset having an attribute value or an additional attribute value satisfying the search request; generating target information according to the traffic data subset; and visualizing the target information.

Description

Technical Field

[0001] This disclosure relates to the field of computers, and particularly to the field of data visualization technology, specifically to a traffic data visualization method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of urban and intercity transportation, traffic conditions are becoming increasingly complex. Current traffic studies typically require the analysis and processing of traffic flow data. Traffic data, containing the spatiotemporal distribution characteristics of traffic flow, is a crucial basis for analyzing road capacity, traffic management, traffic flow prediction, and traffic accident detection. Given the diverse nature of current traffic data, it is essential to efficiently and comprehensively visualize and present this data to better support traffic decision-making.

[0003] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0004] According to one aspect of this disclosure, a traffic data visualization method is provided, comprising: acquiring a first traffic dataset of traffic participants, each traffic data item in the first traffic dataset including multiple attribute fields; obtaining additional attribute fields and additional attribute values ​​of the traffic data in the first traffic dataset based on the attribute values ​​of the attribute fields, thereby obtaining a second traffic dataset; in response to a search request, determining a subset of traffic data from the second traffic dataset, each traffic data item in the subset having attribute values ​​or additional attribute values ​​that satisfy the search request; generating target information based on the traffic data subset; and performing visualization processing on the target information.

[0005] According to another aspect of this disclosure, a traffic data visualization apparatus is provided, comprising: an acquisition unit configured to acquire a first traffic dataset of traffic participants, wherein each traffic data item in the first traffic dataset includes multiple attribute fields; a derivation unit configured to obtain additional attribute fields and additional attribute values ​​of the traffic data in the first traffic dataset based on the attribute values ​​of the attribute fields, thereby obtaining a second traffic dataset; a search unit configured to determine a subset of traffic data from the second traffic dataset in response to a search request, wherein each traffic data item in the subset of traffic data has an attribute value or additional attribute value that satisfies the search request; an extraction unit configured to generate target information based on the subset of traffic data; and a visualization unit configured to perform visualization processing on the target information.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the methods described in this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods described in this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described in this disclosure.

[0009] According to one or more embodiments of this disclosure, traffic data mining is achieved by deriving one or more additional attribute values ​​based on the original traffic attribute values; and by using these additional attributes as redundancy of the original traffic attribute values, the traffic dynamics of various traffic participants can be displayed in a multi-dimensional and multi-faceted manner, thereby displaying the various indicator data required for traffic planning in a more targeted and directional way.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0012] Figure 1This is a flowchart illustrating a traffic data visualization method according to an exemplary embodiment;

[0013] Figure 2 This is a flowchart illustrating the determination of the relative position with respect to a fixed reference object according to an exemplary embodiment;

[0014] Figure 3a and 3b These are schematic diagrams showing images containing multiple traffic participants according to exemplary embodiments;

[0015] Figure 4 This is a schematic diagram illustrating a trajectory map formed in map data according to an exemplary embodiment;

[0016] Figure 5 This is a schematic diagram illustrating a heat map formed in map data according to an exemplary embodiment;

[0017] Figure 6 This is a structural block diagram illustrating a traffic data visualization device according to an exemplary embodiment; and

[0018] Figure 7 This is a structural block diagram illustrating an exemplary computing device that can be applied to exemplary embodiments. Detailed Implementation

[0019] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0021] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0022] Current traffic condition studies typically require the visualization of traffic data to intuitively present the spatiotemporal distribution characteristics of traffic flow. Given the diverse types of traffic, the lack of a unified data visualization method or platform leads to data and application barriers between various traffic departments or applications, creating numerous information silos and hindering the realization of the value of big data. Furthermore, visualization operations are usually based on raw traffic data, which directly reduces the accuracy of traffic decisions and makes it difficult to perceive the corresponding spatiotemporal distribution characteristics in a multi-dimensional and multi-faceted manner, resulting in low visualization efficiency and a lack of data dimensionality.

[0023] Embodiments of this disclosure provide a traffic data visualization method 100. For example... Figure 1 As shown, method 100 includes: step 110, obtaining a first traffic dataset of traffic participants, wherein each traffic data in the first traffic dataset includes multiple attribute fields; step 120, obtaining additional attribute fields and additional attribute values ​​of the traffic data in the first traffic dataset based on the attribute values ​​of the attribute fields, thereby obtaining a second traffic dataset; step 130, in response to a search request, determining a subset of traffic data from the second traffic dataset, wherein each traffic data in the subset of traffic data has attribute values ​​or additional attribute values ​​that satisfy the search request; step 140, generating target information based on the subset of traffic data; and step 150, visualizing the target information.

[0024] According to embodiments of this disclosure, traffic data mining is achieved by deriving one or more additional attribute values ​​based on the original traffic attribute values; and by using these additional attributes as redundancy of the original traffic attribute values, the traffic dynamics of traffic participants can be displayed in a multi-dimensional and multi-faceted manner, thereby providing a more targeted and directional display of various indicator data required for traffic planning.

[0025] In step 110, the first traffic dataset of traffic participants is obtained.

[0026] According to some embodiments, the traffic participants can be motor vehicles, non-motor vehicles, pedestrians, airplanes, trains, and ships, etc. By uniformly and dynamically sensing traffic data from all traffic participants across the entire network, information barriers between different traffic types can be broken down, information gaps can be eliminated, and big data integration can be achieved.

[0027] According to some embodiments, the traffic participants may include at least one of motor vehicles, non-motor vehicles, and pedestrians. When multiple traffic participants include at least one of motor vehicles, non-motor vehicles, and pedestrians, obtaining a first traffic dataset of traffic participants may include: obtaining multiple images containing the traffic participants; and obtaining the first traffic dataset of traffic participants based on the multiple images.

[0028] In some examples, multiple images containing at least one of motor vehicles, non-motor vehicles, and pedestrians can be obtained through vehicle-mounted cameras (e.g., dashcams), fixed surveillance cameras on roads, cameras on drones, etc. For example, video data captured by a camera can be acquired, and multiple images including at least one traffic participant, such as motor vehicles, non-motor vehicles, and pedestrians, can be obtained by extracting frames from the video data.

[0029] In some examples, the acquired surveillance images or video data can be preprocessed. For instance, the acquired images or videos can be assessed for sharpness to filter out blurry images or videos. Alternatively, the image or video data acquired by the camera can be corrected, such as image tilt correction, to automatically detect the tilt direction and angle based on image features. Commonly used tilt angle correction methods include, but are not limited to, projection-based methods, Hough transform methods, linear fitting-based methods, and methods that perform Fourier transform to the frequency domain for detection. Thus, multiple images containing at least one of motor vehicles, non-motor vehicles, and pedestrians can be obtained based on the corrected image or video data.

[0030] After obtaining multiple images containing at least one of motor vehicles, non-motor vehicles, and pedestrians, a first traffic dataset containing at least one of motor vehicles, non-motor vehicles, and pedestrians can be obtained based on these multiple images.

[0031] According to some embodiments, this attribute field may include a timestamp and speed. Therefore, obtaining a first traffic dataset of traffic participants from multiple images may include: for each of the multiple images, determining the relative position of the traffic participant to a fixed reference point in the image and the timestamp of the image; and determining the speed of the traffic participant based on the relative position and timestamp.

[0032] In some examples, the fixed reference point can include lane lines, buildings, bus stops, subway stations, train stations, and any other possible reference point. Therefore, traffic participants such as motor vehicles, non-motorized vehicles, and / or pedestrians can be identified, and corresponding fixed reference points can be determined, thereby determining the relative positional relationship between each traffic participant and the corresponding fixed reference point. Based on the relative positional changes of the same traffic participant (e.g., a car) in multiple images and the timestamps of the corresponding images, the speed of that traffic participant can be determined. In some examples, this speed can include acceleration, average speed, etc.

[0033] According to some embodiments, a first traffic dataset of traffic participants can be obtained based on the multiple images using a pre-trained deep learning-based recognition model.

[0034] In some examples, different recognition models or algorithms can be assigned to different traffic entities, such as vehicle recognition models, face recognition models, etc., to identify the location of each traffic entity. Alternatively, the location of each traffic entity can be identified using an image classification model. For example, this image classification model could be a trained convolutional neural network model used to determine the category of objects in an image, such as people, traffic lights, cars, buildings, lane lines, etc. For instance, corresponding labels can be added to the images as training data, with each label being the name of a concept or category. Given enough training data (typically hundreds of images per label), the image classification model can learn to predict whether a new image belongs to certain label categories in the training data. The identified traffic entities are then labeled in the images using the appropriate recognition model, thereby further determining the corresponding traffic data.

[0035] According to some embodiments, the attribute field described above may also include a geographic location. In some examples, this geographic location may include satellite positioning data, such as latitude and longitude coordinates.

[0036] In some embodiments, obtaining a first traffic dataset of traffic participants from multiple images may include: for each of the multiple images, determining the relative position of the traffic participant to a fixed reference point in the image; and determining the geographical location of the traffic participant based on the relative position and the geographical location of the fixed reference point.

[0037] In some examples, the geographical location of fixed reference points within the camera's field of view can be determined. For instance, a fixed camera at a traffic intersection films traffic participants passing through the area in a preset orientation. Lane lines, trees, buildings, etc., filmed by the camera in its current orientation can serve as fixed reference points, and their geographical location data can be determined. Therefore, based on the geographical location of these fixed reference points and the relative positions of the traffic participants to them, the geographical location of the traffic participants can be determined.

[0038] In some embodiments, the geographic location may be location information uploaded by the navigation device of a traffic participant. For example, vehicle trajectory data and positioning information collected by an in-vehicle navigation device in a vehicle acting as a traffic participant can be obtained. The satellite navigation system used to enable the navigation device to receive signals from it may be a global navigation satellite system, such as the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), the BeiDou-2 Navigation Satellite System (BDS), or the European Union's Galileo system. The satellite navigation system may also be a regional navigation satellite system, such as the BeiDou-1 system, the Indian Navigation Satellite System (NAVIC), or the Quasi-Zenith Satellite System (QZSS). The navigation device may be a high-sensitivity GPS receiver, a traditional GPS receiver, a handheld receiver, an outdoor receiver, or a motion receiver.

[0039] In some examples, navigation devices can connect to satellites via GPS assistance or enhancement, directly via an intermediary device (e.g., a cellular tower or station), or via any other communication method that can send satellite signals to the navigation device (e.g., satellite broadcast microwave signals) or provide orbital data or almanacs to the satellite (e.g., rover-based assistance). Additionally, navigation devices can transmit collected location information via networks such as wireless local area networks (WLANs), wide area networks (WANs), wireless networks such as radio waves, cellular networks, satellite communication networks, and / or local or short-range wireless networks used to transmit location information (e.g., Bluetooth).

[0040] According to some embodiments, Figure 2 A flowchart of a method 200 for determining the relative position of traffic participants to a fixed reference object in a picture is shown. Figure 2 As shown, method 200 may include: step 210, determining the orientation of the traffic participant relative to a fixed reference object; step 220, determining the distance between the traffic participant and the fixed reference object based on the scaling ratio of the image relative to the actual object; and step 230, determining the relative position based on orientation and distance.

[0041] In some examples, the orientation can be determined based on a base point, azimuth, or direction. For instance, the azimuth or direction of the traffic participant relative to the fixed reference point can be determined using the fixed reference point as the base point. Alternatively, the traffic participant can also be used as the base point; there is no limitation on this. Furthermore, the actual distance between the fixed reference point and the traffic participant can be determined based on the scaling ratio of the image relative to the actual object. Thus, the relative position between the fixed reference point and the traffic participant is determined by the orientation and distance.

[0042] like Figure 3a and 3b As shown, the corresponding recognition model can identify the vehicle 301, pedestrian 302, and gas station 303 in each image. Furthermore, the positions of vehicle 301 and pedestrian 302 relative to gas station 303 can be determined. Figure 3a and 3b Taking vehicle 301 as an example, and gas station 303 as a base point, the azimuth or direction (e.g., 40° west of due north) of vehicle 301 relative to gas station 303 is determined. Then, based on the image scaling, the distances of vehicle 301 and pedestrian 302 to gas station 303 are determined. Therefore, based on these distances and azimuths, the relative positions of vehicle 301 and pedestrian 302 relative to gas station 303 are determined. Figure 3a and 3b The obtained relative position changes of motor vehicle 301 and pedestrian 302 and Figure 3aand 3b The corresponding timestamps can be used to further determine the speeds of motor vehicle 301 and pedestrian 302. It should be understood that, although... Figure 3a and 3b The two images in the example illustrate the process of identifying traffic data, but any number of images are possible and are not limited here.

[0043] According to some embodiments, when the traffic participant is an aircraft, the attribute field may include at least one of the following attribute fields: flight number, flight route, takeoff and landing time, flight altitude, flight speed, orientation, geographical location, etc. For example, the flight route field may include the planned route and the actual route, and the takeoff and landing time may include the planned takeoff and landing time, the actual takeoff and landing time, etc.

[0044] According to some embodiments, when the traffic participant is a train, the attribute field may include at least one of the following attribute fields: train number, route, timetable information, ticket information, etc. For example, the route may include information on each stop, the timetable information may include planned execution time information and actual execution time information, the ticket information may include seat class, available tickets, etc.

[0045] For example, flight data provided by airlines and / or train data provided by railway departments can be obtained. Furthermore, in some examples, the obtained traffic data can be categorized into flight data, train data, and other types of traffic data. Thus, based on one or more attribute values ​​corresponding to each type of traffic data, one or more additional attribute values ​​can be derived more specifically.

[0046] According to some embodiments, the method 100 of this disclosure may further include: data cleaning of the first traffic dataset.

[0047] In some embodiments, the first traffic dataset is cleaned, including but not limited to checking the completeness, uniqueness, and legality of the traffic data, performing data dimensionality upgrades or downscaling, data compression, data transformation, supplementing incomplete data, discarding incomplete data, etc.

[0048] According to some embodiments, data cleaning of the first traffic dataset may include: for each piece of traffic data in the first traffic dataset: determining whether there is an attribute field with missing attribute values ​​in the traffic data; and in response to the existence of an attribute field with missing attribute values ​​being a specified attribute field, filling the attribute field with missing attribute values ​​in the traffic data with attribute values.

[0049] According to some embodiments, filling attribute values ​​into the attribute fields of traffic data includes: filling them with attribute values ​​from the attribute fields of other traffic data of the traffic participant corresponding to the traffic data; or, filling the attribute fields with interpolation from the traffic data adjacent to the traffic data of the traffic participant corresponding to the traffic data; or, estimating and filling attribute values ​​with the attribute fields of the attribute fields of the traffic participants corresponding to the traffic data from the previous predetermined number of traffic data.

[0050] For example, attribute values ​​can be estimated using extrapolation. Extrapolation is a general term for methods that infer future trends based on past and present development trends. Extrapolation is a good approximation method; for a low-precision approximation value already obtained, a few simple arithmetic operations can quickly yield a high-precision approximation value. Therefore, extrapolation can be performed based on the attribute values ​​of the corresponding attribute fields from a predetermined number of traffic data points for the same traffic participant to accurately fill in missing attribute values, thus improving data accuracy.

[0051] It should be understood that other suitable methods for determining whether traffic data has missing attribute fields, and other suitable methods for filling attribute values ​​(such as filling based on the mean, median, mode, etc.), are also possible and are not limited here.

[0052] According to some embodiments, data cleaning of the first traffic dataset may include: determining whether the first traffic dataset contains duplicate traffic data; and deduplicating the duplicate traffic data.

[0053] For example, you can check if the value of a key attribute in a traffic data entry is duplicated with the value of a corresponding attribute in other traffic data entries. For instance, the key attribute could be a data ID. Additionally, you can also check if an entire traffic data entry is duplicated with other traffic data entries.

[0054] It should be understood that other suitable methods for determining whether duplicate traffic data is included are also possible, and no limitation is made here.

[0055] According to some embodiments, data cleaning of the first traffic dataset may include: determining whether the first traffic dataset contains abnormal traffic data; and deleting the abnormal traffic data.

[0056] For example, you can check whether the specific values ​​of each field in a data record are within a reasonable range. For instance, speed cannot be negative or excessively large values ​​such as 100,000 m / s. Alternatively, you can check whether a data record contains null values.

[0057] It should be understood that other suitable methods are possible to determine whether traffic data containing anomalies are included, and no limitation is made here.

[0058] According to some embodiments, data cleaning of the first traffic dataset may also include: performing numerical conversion on multiple traffic data, including but not limited to: converting strings to numbers, unifying the unit format of data, removing unnecessary whitespace information, converting the format of time information, converting the encoding format of data (e.g., UTF or half-width / full-width), retaining two decimal places of data, and converting between uppercase and lowercase letters.

[0059] In step 120, based on the attribute values ​​of the attribute fields, the additional attribute fields of the traffic data in the first traffic dataset and the additional attribute values ​​of the additional attribute fields are obtained, thereby obtaining the second traffic dataset.

[0060] In some examples, the traffic data in the first traffic dataset is supplemented with additional attribute fields to form the second traffic dataset. That is, the second traffic dataset includes the traffic data in the first traffic dataset that has attribute fields and attribute values, as well as the newly added additional attribute fields and additional attribute values.

[0061] In some examples, additional attribute fields can be added to a portion of the traffic data in the first traffic dataset. For instance, a certain attribute field of a traffic data entry can be used as an additional attribute field for other traffic data entries that do not have that attribute field. In this case, the second traffic dataset includes the portion of the first traffic dataset without the added attribute field and the portion with the added attribute field and its value. In other examples, one or more additional attribute fields can be added to all traffic data in the first traffic dataset to provide more comprehensive statistical analysis. In this case, the second traffic dataset includes all traffic data in the first traffic dataset after the addition of the additional attribute field and its value; that is, every traffic data entry in the second traffic dataset has an additional attribute field and its value.

[0062] For example, when traffic data for a traffic participant includes latitude and longitude coordinates, the administrative region information traversed by the participant can be determined based on these coordinates, including but not limited to: province, city, and district. For instance, additional city and province attributes can be added to store the city and province where the participant was located at various times, obtained through latitude and longitude coordinates, as additional geographic location attributes. Additional or replacement locations can also be further determined based on attributes such as time and geographic location to determine weather attributes, etc. Additionally or replacement locations can also be further determined based on attributes such as time and speed to determine attributes such as average speed and acceleration.

[0063] According to some embodiments, the method 100 according to this disclosure may further include: merging traffic data in the second traffic dataset according to the attribute values ​​of the same attribute fields or the additional attribute values ​​of the same additional attribute fields.

[0064] In some examples, traffic data from one or more types of traffic participants in a second traffic dataset can be merged based on the same attribute values ​​or additional attribute values. For instance, information on motor vehicles, non-motor vehicles, and pedestrians can be retrieved within a given time range and / or a given area, and then merged according to the same attribute names to obtain a second traffic dataset containing the merged data. The merged traffic data can be used to subsequently determine traffic statistics for a specific area within the corresponding time range, such as traffic flow or activity levels. Alternatively, train data, motor vehicle data, and aircraft data can also be merged for subsequent analysis and processing.

[0065] In step 130, in response to the lookup request, a subset of traffic data is determined from the second traffic dataset, each piece of traffic data in the subset having an attribute value or additional attribute value that satisfies the lookup request; and in step 140, target information is generated based on the subset of traffic data.

[0066] Each piece of traffic data in a subset of traffic data can have attribute values, additional attribute values, or both that satisfy the search request. For example, based on the timestamp attribute, one can search for aircraft data, train data, motor vehicle data, non-motor vehicle data, pedestrian data, etc., within a specified time period to obtain the corresponding traffic data subset; alternatively, one can search for aircraft data, train data, motor vehicle data, non-motor vehicle data, pedestrian data, etc., within a specified time period based on time and geographical location (latitude and longitude, city, road) to obtain the corresponding traffic data subset. It should be understood that a traffic data subset can also be determined from the second traffic dataset based on other attribute values ​​or additional attribute values, which is not limited here.

[0067] Therefore, according to some embodiments, generating target information based on a subset of traffic data includes obtaining statistical indicators or geographic trajectory map data from the attribute values ​​or additional attribute values ​​of the traffic data in the subset of traffic data.

[0068] In some embodiments, the statistical indicators may be, for example, average speed, travel time, mileage, cities passed through, and road traffic flow. For instance, the travel time, mileage, and cities passed through for a given traffic participant can be determined based on information such as time and geographic location. Alternatively, road information can be determined based on geographic location information, and statistical indicators such as road traffic flow, vehicle density, and the proportion of large vehicles within a certain time period on a certain road segment can be further calculated. In some examples, traffic data from subsets of traffic data can be merged according to corresponding attribute values ​​or additional attribute values ​​to obtain statistical indicators or geographic trajectory map data based on the merged data. For example, traffic data of one or more types of traffic participants within a specified time period can be merged based on time attributes to calculate traffic indicators for that specified time period.

[0069] In some embodiments, based on a search request for the movement trajectory of one or more traffic participants within a predetermined time period, the geographical location and time of the one or more traffic participants within that predetermined time period can be determined from multiple traffic data sets. This geographical location information can be, for example, latitude and longitude information. For instance, the determined geographical location and time information can be used to generate JSON data as geographic trajectory map data.

[0070] In step 160, the extracted target information is displayed visually.

[0071] According to some embodiments, when the target information includes geographic trajectory map data, visualizing the target information may include: generating a trajectory map based on the geographic trajectory map data; and displaying the generated trajectory map statically or dynamically.

[0072] For example, online open-source map data and / or offline map data can be preset, such as raster formats like PDF and PNG, vector map data, and geoJSON format map data, which can display the geographical overview of a certain area. The determined geographical trajectory map data is then projected onto the preset map data to form the corresponding trajectory map, such as... Figure 4 As shown, 401 is a map, and 402 is a trajectory projected onto map 401.

[0073] In some examples, the generated trajectory map can be displayed using either static or dynamic methods. For instance, the generated trajectory map can be dynamically displayed based on the time sequence corresponding to each geographic location in the geographic trajectory data.

[0074] In some examples, the extracted target information can be displayed on the front-end page in any suitable manner, including but not limited to various styles of graphical displays such as charts, lists, bar charts, line charts, pie charts, heatmaps, and trend charts. For example, the extracted target information can be visualized using the visualization library Echarts, and ultimately displayed intuitively and aesthetically on the front-end page.

[0075] In some examples, based on the aforementioned heat map table, the geographic areas favored by relevant traffic participants can be displayed in a specially highlighted format within a preset map data, such as... Figure 5 As shown.

[0076] It should be understood that other applications or methods are possible for displaying the extracted target information on the front end, and no restrictions are imposed here.

[0077] By monitoring and displaying the spatiotemporal distribution characteristics of various types of traffic data, we can present the various indicator data required for traffic planning in a more targeted and specific manner, providing important basis for various aspects such as road capacity, traffic management, traffic flow prediction, and traffic accident detection.

[0078] According to embodiments of this disclosure, a traffic data visualization device 600 is also provided, such as... Figure 6 As shown, the system includes: an acquisition unit 610 configured to acquire a first traffic dataset of traffic participants, wherein each traffic data item in the first traffic dataset includes multiple attribute fields; a derivation unit 620 configured to obtain additional attribute fields and additional attribute values ​​of the traffic data in the first traffic dataset based on the attribute values ​​of the attribute fields, thereby obtaining a second traffic dataset; a search unit 630 configured to determine a subset of traffic data from the second traffic dataset in response to a search request, wherein each traffic data item in the subset of traffic data has an attribute value or additional attribute value that satisfies the search request; an extraction unit 640 configured to generate target information based on the subset of traffic data; and a visualization unit 650 configured to perform visualization processing on the target information.

[0079] Here, the operation of each of the above-mentioned units 610 to 650 of the traffic data visualization device 600 is similar to the operation of steps 110 to 150 described above, and will not be repeated here.

[0080] According to embodiments of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions that, when executed by the at least one processor, cause the at least one processor to perform the methods of the present disclosure.

[0081] According to embodiments of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause the computer to perform the methods described in the present disclosure.

[0082] According to embodiments of this disclosure, a computer program product is also provided, including a computer program, wherein the computer program implements the methods described in this disclosure when executed by a processor.

[0083] Reference Figure 7 The computing device 700 will now be described as an example of a hardware device that can be applied to various aspects of this disclosure. The computing device 700 can be any machine configured to perform processing and / or computation, and can be, but is not limited to, a workstation, server, desktop computer, laptop computer, tablet computer, personal digital assistant, smartphone, in-vehicle computer, or any combination thereof. The aforementioned traffic data visualization apparatus can be implemented wholly or at least partially by the computing device 700 or similar devices or systems.

[0084] The computing device 700 may include elements that are connected to or communicate with the bus 702 (possibly via one or more interfaces). For example, the computing device 700 may include the bus 702, one or more processors 704, one or more input devices 706, and one or more output devices 708. The one or more processors 704 may be any type of processor and may include, but are not limited to, one or more general-purpose processors and / or one or more dedicated processors (e.g., special-purpose processing chips). The input devices 706 may be any type of device capable of inputting information to the computing device 700 and may include, but are not limited to, a mouse, keyboard, touchscreen, microphone, and / or remote control. The output devices 708 may be any type of device capable of presenting information and may include, but are not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. The computing device 700 may also include or be connected to a non-transitory storage device 710. The non-transitory storage device can be any storage device that is non-transitory and capable of storing data, and may include, but is not limited to, disk drives, optical storage devices, solid-state storage, floppy disks, flexible disks, hard disks, magnetic tapes or any other magnetic media, optical discs or any other optical media, ROM (read-only memory), RAM (random access memory), cache memory and / or any other memory chip or cartridge, and / or any other medium from which a computer can read data, instructions, and / or code. The non-transitory storage device 710 can be detached from an interface. The non-transitory storage device 710 may have data / programs (including instructions) / code for implementing the methods and steps described above. The computing device 700 may also include a communication device 712. The communication device 712 can be any type of device or system that enables communication with external devices and / or with a network, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication devices and / or chipsets, such as Bluetooth™ devices, 1302.11 devices, WiFi devices, WiMax devices, cellular communication devices and / or the like.

[0085] The computing device 700 may also include working memory 714, which may be any type of working memory that can store programs (including instructions) and / or data useful to the operation of the processor 704, and may include, but is not limited to, random access memory and / or read-only memory devices.

[0086] The software elements (programs) may reside in the working memory 714, including but not limited to the operating system 716, one or more application programs 718, drivers, and / or other data and code. Instructions for performing the methods and steps described above may be included in one or more application programs 718, and the aforementioned traffic data visualization device can be implemented by the processor 704 reading and executing the instructions of one or more application programs 718. The executable code or source code of the instructions of the software elements (programs) may be stored in a non-transitory computer-readable storage medium (e.g., the aforementioned storage device 710) and may be stored in the working memory 714 during execution (possibly compiled and / or installed). The executable code or source code of the instructions of the software elements (programs) may also be downloaded from a remote location.

[0087] It should also be understood that various modifications can be made depending on specific requirements. For example, custom hardware can also be used, and / or specific elements can be implemented using hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. For example, some or all of the disclosed methods and apparatus can be implemented by programming hardware (e.g., programmable logic circuits including field-programmable gate arrays (FPGAs) and / or programmable logic arrays (PLAs)) using logic and algorithms according to this disclosure in assembly language or hardware programming languages ​​(such as Verilog, VHDL, C++).

[0088] It should also be understood that the aforementioned methods can be implemented using a server-client model. For example, the client can receive user input data and send it to the server. Alternatively, the client can receive user input data, perform a portion of the processing described in the aforementioned methods, and send the resulting data to the server. The server can receive data from the client, execute the aforementioned methods or a portion thereof, and return the execution result to the client. The client can receive the execution result from the server and, for example, present it to the user via an output device.

[0089] It should also be understood that the components of computing device 700 can be distributed across a network. For example, some processing can be performed using one processor, while other processing can be performed simultaneously by another processor located far away from that processor. Other components of computing system 700 can also be distributed similarly. Thus, computing device 700 can be interpreted as a distributed computing system that performs processing in multiple locations.

[0090] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A method for traffic data visualization, comprising: obtaining a first traffic data set of a traffic participant, each traffic data in the first traffic data set comprising a plurality of attribute fields; deriving an additional attribute field of traffic data in the first traffic data set and an additional attribute value of the additional attribute field according to attribute values of the attribute fields, thereby obtaining a second traffic data set; determining a subset of traffic data from the second traffic data set in response to a search request, each traffic data in the subset of traffic data having an attribute value or an additional attribute value satisfying the search request; generating target information according to the subset of traffic data; and visualizing the target information; wherein the traffic participant comprises at least one of a motor vehicle, a non-motor vehicle and a pedestrian, and the obtaining of the first traffic data set of the traffic participant comprises: obtaining a plurality of pictures containing the traffic participant; and obtaining the first traffic data set of the traffic participant according to the plurality of pictures; wherein the attribute fields comprise a timestamp and a speed, and the obtaining of the first traffic data set of the traffic participant according to the plurality of pictures comprises: determining, for each picture in the plurality of pictures, a relative position of the traffic participant to a fixed reference in the picture and a timestamp of the picture; and determining a speed of the traffic participant based on the relative position and the timestamp; wherein the attribute fields further comprise a geographical position, and the obtaining of the first traffic data set of the traffic participant according to the plurality of pictures comprises: determining, for each picture in the plurality of pictures, a relative position of the traffic participant to a fixed reference in the picture; and determining a geographical position of the traffic participant based on the relative position and a geographical position of the fixed reference; wherein the determining of the relative position of the traffic participant to the fixed reference in the picture comprises: determining an orientation of the traffic participant relative to the fixed reference; determining a distance of the traffic participant to the fixed reference according to a scaling ratio of the picture relative to an actual object; and determining the relative position based on the orientation and the distance. the obtaining of the first traffic data set of the traffic participant according to the plurality of pictures comprises:

2. The method of claim 1, wherein, obtaining the first traffic data set of the traffic participant based on the plurality of pictures by using a pre-trained deep learning-based recognition model. the traffic participant comprises an airplane, and the attribute fields comprise at least one of a flight number, a flight route, a take-off and landing time, a flight height, a flight speed, an orientation, a geographical position.

3. The method of claim 1, wherein, the traffic participant comprises a train, and the attribute fields comprise at least one of a train number, a route, time information, ticket information.

4. The method of claim 1, wherein, performing data cleaning on the first traffic data set.

5. The method of claim 1, further comprising: 6.The method of claim 5, wherein the performing of data cleaning on the first traffic data set comprises: for each traffic data in the first traffic data set, determining whether the traffic data has an attribute field with a missing attribute value; and ​ ​ In response to the attribute field with the missing attribute value being a specified attribute field, the attribute field of the traffic data is filled with an attribute value.

7. The method of claim 6, wherein, The filling of the attribute field of the traffic data with an attribute value includes: filling with an attribute value of the attribute field of other traffic data of a traffic participant corresponding to the traffic data; interpolating and filling the attribute field with corresponding traffic data adjacent to the traffic data of the traffic participant corresponding to the traffic data; or estimating and filling an attribute value with attribute values of the attribute field of a predetermined number of pieces of traffic data of the traffic participant corresponding to the traffic data.

8. The method of claim 5, wherein, The data cleaning of the first set of traffic data includes: determining whether the first set of traffic data includes duplicate traffic data; and de-duplicating the duplicate traffic data.

9. The method of claim 5, wherein, The data cleaning of the first set of traffic data includes: determining whether the first set of traffic data includes traffic data with an anomaly; and deleting the traffic data with the anomaly.

10. The method of claim 1, wherein, The generation of the target information according to the subset of traffic data includes: obtaining a statistical index or geographic trajectory graph data according to an attribute value or additional attribute value of traffic data in the subset of traffic data.

11. The method of claim 10, wherein, The target information includes the geographic trajectory graph data, and the visualization of the target information includes: generating a trajectory graph based on the geographic trajectory graph data; and statically or dynamically displaying the generated trajectory graph.

12. The method of any one of claims 1 to 11, further comprising: The traffic data in the second set of traffic data is merged according to attribute values of the same attribute field or additional attribute values of the same additional attribute field.

13. A traffic data visualization device for performing the method according to any one of claims 1-12, the device comprising: an acquisition unit configured to acquire a first set of traffic data of traffic participants, each piece of traffic data in the first set of traffic data including a plurality of attribute fields; a derivation unit configured to derive an additional attribute field and an additional attribute value of the additional attribute field of traffic data in the first set of traffic data according to attribute values of the attribute fields, thereby obtaining a second set of traffic data; a search unit configured to determine a subset of traffic data from the second set of traffic data in response to a search request, each piece of traffic data in the subset of traffic data having an attribute value or an additional attribute value satisfying the search request; an extraction unit configured to generate target information according to the subset of traffic data; and a visualization unit configured to visualize the target information.

14. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions that, when executed by the at least one processor, cause the at least one processor to perform the method of any one of claims 1-12. The computer instructions, when executed by one or more processors of a computing device, cause the computing device to perform the method of any one of claims 1-12.

15. A computer readable storage medium having stored thereon computer instructions, wherein, ​ 16. A computer program product comprising a computer program, wherein, The computer program, which when executed by a processor implements the method of any one of claims 1-12.

Images