Traffic event perception methods, systems, electronic devices, and media

Abstract

The application relates to the technical field of edge cloud perception, in particular to a traffic event perception method and system, an electronic device and a medium, wherein the method comprises the following steps: receiving a traffic event perception instruction, determining a reference road section corresponding to a target road section, acquiring traffic state information of the reference road section, judging whether the traffic state information is consistent with preset safe traffic state information, if not, determining that the traffic state information is abnormal, and perceiving whether a traffic event occurs on the target road section, otherwise, determining that the traffic state information is not abnormal, and no traffic event occurs. Therefore, the problem that the traffic event perception capability is reduced due to low coverage of a video acquisition device, so that a traffic event on a road cannot be processed in time and road traffic smoothness is affected is solved, traffic events of each road section in a road scene are comprehensively perceived, the road scene is no longer limited by the coverage degree of the video acquisition device, and the traffic event perception efficiency is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of edge cloud perception, and in particular to a traffic event perception method and system, an electronic device and a medium. BACKGROUND

[0002] With the development of high-tech in China, the Internet of Things has ushered in a new high tide. In terms of automobiles, in the field of road traffic, timely detection and handling of traffic events occurring on the road can ensure smooth operation and driving safety of road traffic.

[0003] In related technologies, a traffic event perception system mainly relies on video acquisition devices deployed on the road to perceive traffic events.

[0004] However, since the coverage of the video acquisition device on the road is relatively low, this perception method reduces the perception ability of traffic events, thereby causing some traffic events to be unable to be handled in a timely manner, and further affecting the smoothness of road traffic. SUMMARY

[0005] The present application provides a traffic event perception method, system, electronic device and medium to solve the problem of low coverage of video acquisition devices, which reduces the perception ability of traffic events, and thus cannot handle traffic events on the road in a timely manner, affecting the smoothness of road traffic.

[0006] The first aspect of the present application provides a traffic event perception method, comprising the following steps:

[0007] receiving a traffic event perception instruction, and determining a reference road section corresponding to a target road section according to the traffic event perception instruction, and obtaining traffic state information of the reference road section;

[0008] determining whether the traffic state information is consistent with preset safe traffic state information; and

[0009] if the traffic state information is not consistent with the preset safe traffic state information, it is determined that the traffic state information is abnormal, and it is determined whether a traffic event occurs on the target road section based on the traffic state information, otherwise, it is determined that the traffic state information is not abnormal, and the traffic event does not occur.

[0010] According to one embodiment of the present application, the determination of whether a traffic event occurs on the target road section based on the traffic state information comprises:

[0011] calculating a state feature value of the reference road section in at least one detection dimension according to the traffic state information of the reference road section;

[0012] If the state feature value in the at least one detection dimension satisfies a traffic event identification condition, it is determined that a traffic event occurs on the target road section.

[0013] According to an embodiment of the present application, if the state feature value in the at least one detection dimension satisfies a traffic event identification condition, it is determined that a traffic event occurs on the target road section, including:

[0014] inputting the state feature value in the at least one detection dimension into a preset anomaly detection model to generate a target identification result, wherein the target neural network is obtained by training a mapping relationship between the state feature value and the identification result in the preset anomaly detection model, and the mapping relationship is used to represent the traffic event identification condition;

[0015] If the target identification result corresponds to a traffic event, it is determined that a traffic event occurs on the target road section.

[0016] According to an embodiment of the present application, the detection dimension includes at least one of a state change dimension of the reference road section in a current period, a state difference dimension between the current period and a corresponding historical period of the reference road section, and a state difference dimension between the reference road section and other reference road sections.

[0017] According to an embodiment of the present application, the traffic state information of the reference road section is obtained, including:

[0018] obtaining traffic state reference information of the reference road section by using a traffic state acquisition device associated with the reference road section;

[0019] obtaining map data of the reference road section;

[0020] obtaining bus IC (Integrated Circuit) card information of the reference road section;

[0021] obtaining traffic state information of the reference road section according to the traffic state reference information, the map data and the bus IC card information.

[0022] According to an embodiment of the present application, after it is determined that a traffic event occurs on the target road section, it further includes:

[0023] generating traffic event reminding information according to the traffic event;

[0024] sending the traffic event reminding information to a requester of the traffic event perception instruction.

[0025] According to an embodiment of the present application, the traffic event perception method further includes:

[0026] a plurality of road segments closest to the target road segment are determined as reference road segments for display according to the traffic state information;

[0027] the reference road segments are displayed in a preset display interface to display the traffic event occurring on the target road segment.

[0028] According to the traffic event perception method provided in the embodiments of the present application, the traffic event perception instruction is received, the reference road segments corresponding to the target road segment are determined, the traffic state information of the reference road segments is obtained, and it is determined whether the traffic state information is consistent with the preset safe traffic state information. If the traffic state information is not consistent with the preset safe traffic state information, it is determined that the traffic state information is abnormal, and it is perceived whether the traffic event occurs on the target road segment. If the traffic state information is consistent with the preset safe traffic state information, it is determined that the traffic state information is not abnormal, and the traffic event does not occur. Thus, the problem that the traffic event perception capability is reduced due to the low coverage of the video acquisition device, and the traffic event on the road cannot be processed in time, thereby affecting the smoothness of the road traffic, is solved. The traffic events of all road segments in the road scene are perceived comprehensively, and the traffic event perception efficiency is effectively improved.

[0029] The second aspect of the embodiments of the present application provides a traffic event perception system, comprising:

[0030] The acquisition module is configured to receive a traffic event perception instruction, determine reference road segments corresponding to a target road segment according to the traffic event perception instruction, and obtain traffic state information of the reference road segments.

[0031] The determination module is configured to determine whether the traffic state information is consistent with preset safe traffic state information.

[0032] The perception module is configured to determine that the traffic state information is abnormal if the traffic state information is not consistent with the preset safe traffic state information, perceive whether the traffic event occurs on the target road segment based on the traffic state information, and determine that the traffic state information is not abnormal and the traffic event does not occur if the traffic state information is consistent with the preset safe traffic state information.

[0033] According to one embodiment of the present application, the perception module comprises:

[0034] The detection unit is configured to calculate state feature values of the reference road segments in at least one detection dimension according to the traffic state information of the reference road segments.

[0035] The determination unit is configured to determine that the traffic event occurs on the target road segment if the state feature values in the at least one detection dimension satisfy traffic event determination conditions.

[0036] According to one embodiment of the present application, the determination unit is specifically configured to:

[0037] input the state feature value in the at least one detection dimension into a preset anomaly detection model to generate a target identification result, wherein the target neural network is obtained by training a target neural network based on a mapping relationship between a state feature value and an identification result in the preset anomaly detection model, and the mapping relationship is used to represent the traffic event identification condition;

[0038] If the target identification result corresponds to a traffic event, it is determined that a traffic event occurs on the target road segment.

[0039] According to an embodiment of the present application, the detection dimension includes at least one of a state change dimension of the reference road segment in a current period, a state difference dimension of the reference road segment between the current period and a corresponding historical period, and a state difference dimension between the reference road segment and other reference road segments.

[0040] According to an embodiment of the present application, the acquisition module is specifically configured to:

[0041] acquire traffic state reference information of the reference road segment by using a traffic state acquisition device associated with the reference road segment;

[0042] acquire map data of the reference road segment;

[0043] acquire bus IC card information of the reference road segment;

[0044] obtain traffic state information of the reference road segment according to the traffic state reference information, the map data, and the bus IC card information.

[0045] According to an embodiment of the present application, after determining that a traffic event occurs on the target road segment, the determination unit is further configured to:

[0046] generate traffic event reminder information according to the traffic event;

[0047] send the traffic event reminder information to a requestor of the traffic event perception instruction.

[0048] According to an embodiment of the present application, the traffic event perception system described above is further configured to:

[0049] a plurality of road segments containing the traffic state information and closest to the target road segment are used as reference display road segments;

[0050] display the reference display road segments in a preset display interface to display the traffic event occurring on the target road segment.

[0051] According to the traffic event perception system provided in the embodiments of the present application, the traffic event perception instruction is received, the reference road section corresponding to the target road section is determined, the traffic state information of the reference road section is acquired, and it is determined whether the traffic state information is consistent with the preset safe traffic state information. If not, it is determined that the traffic state information is abnormal, and it is perceived whether the traffic event occurs on the target road section. Otherwise, it is determined that the traffic state information is not abnormal, and the traffic event does not occur. Thus, the problem that the traffic event perception capability is reduced due to the low coverage of the video acquisition device, and thus the traffic event on the road cannot be processed in time and the road traffic smoothness is affected is solved, so that the traffic events of all road sections in the road scene are perceived comprehensively, and the traffic event perception efficiency is effectively improved.

[0052] The third aspect of the embodiments of the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the traffic event perception method according to the above embodiments.

[0053] The fourth aspect of the embodiments of the present application provides a computer readable storage medium having a computer program stored thereon. The program is executed by a processor to implement the traffic event perception method according to the above embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0054] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, wherein:

[0055] Figure 1 The traffic event perception method according to the embodiments of the present application is shown in the flowchart.

[0056] Figure 2 The traffic event perception system according to one embodiment of the present application is shown in the schematic diagram.

[0057] Figure 3 The traffic event perception system according to the embodiments of the present application is shown in the block schematic diagram.

[0058] Figure 4 The structural schematic diagram of the electronic device provided in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0059] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0060] With reference to the accompanying drawings, the traffic event perception method, system, electronic device and medium according to embodiments of the present application are described below, and in view of the above background, the present application provides a traffic event perception method, in which a traffic event perception instruction is received, a reference road section corresponding to a target road section is determined, traffic state information of the reference road section is obtained, it is determined whether the traffic state information is consistent with preset safe traffic state information, if not, it is determined that the traffic state information is abnormal, and it is determined whether a traffic event occurs in the target road section, otherwise, it is determined that the traffic state information is not abnormal, and no traffic event occurs. Thus, the problem that the traffic event perception ability is reduced due to low coverage of the video acquisition device, so that the traffic event on the road cannot be processed in time and the road traffic smoothness is affected is solved, so that the traffic events of each road section in the road scene are comprehensively perceived, and the limitation of the coverage of the video acquisition device is no longer existed, so that the traffic event perception efficiency is effectively improved.

[0061] Specifically, Figure 1 is a flowchart of a traffic event perception method according to an embodiment of the present application.

[0062] As Figure 1 shown, the traffic event perception method comprises the following steps:

[0063] In step S101, a traffic event perception instruction is received, and a reference road section corresponding to a target road section is determined according to the traffic event perception instruction, and traffic state information of the reference road section is obtained.

[0064] The traffic event perception instruction can come from the perception device of the traffic event itself, so as to generate periodic or continuous traffic event perception instructions to periodically or continuously perform the perception operation of the traffic event; the traffic event perception instruction can also come from various request modes other than the perception device of the traffic event, for example, the manager of the road, etc., and in actual application, the perception permission of the traffic event can also be issued in advance, so as to provide perception service only to the request party with the perception permission.

[0065] Specifically, the traffic event perception method according to the embodiments of the present application can perceive the traffic events occurring in the road scene from the road section dimension, and can be applied to various road scenes, for example, expressway, urban road, national road, provincial road, wharf ship access channel, logistics path, bicycle lane, electric vehicle lane or pedestrian lane, etc., which are not limited here.

[0066] Furthermore, embodiments of this application can divide roads in various road scenarios into several road segments as reference road segments, and use road segments as processing units for traffic event perception. The specifications and number of road segments are not limited; in practical applications, the division can be made as needed. It should be understood that the target road segment can be any road segment in the road scenario.

[0067] It should be noted that the reference road segment in this application embodiment includes one or more of the following: the target road segment itself, the upstream road segment of the target road segment, or the downstream road segment of the target road segment. The upstream road segment can be a road segment upstream of and adjacent to the target road segment, or it can be a road segment upstream of the target road segment but separated from it by one or more intervening road segments. Accordingly, in this embodiment, the number of upstream road segments of the target road segment in the reference road segment can be one or more; similarly, the number of downstream road segments of the target road segment can also be one or more.

[0068] Furthermore, in the embodiments of this application, reference road segments can be pre-specified. For example, the target road segment itself, as well as the upstream and downstream road segments adjacent to the target road segment, can be used as reference road segments. In this case, the reference road segments of the target road segment c, as well as the reference road segments of the upstream road segment b and the downstream road segment d adjacent to the target road segment c, can be determined and represented as (b, c, d).

[0069] Optionally, the embodiments of this application may not specify reference road segments. For example, when the traffic status information in the road scenario is incomplete, the N road segments that have traffic status information and are closest to the target road segment can be used as reference road segments, where the N road segments may include the target road segment itself, and N is an integer greater than or equal to 2.

[0070] Furthermore, in some embodiments, obtaining traffic status information of a reference road segment includes: using traffic status acquisition equipment associated with the reference road segment to obtain traffic status reference information of the reference road segment; obtaining map data of the reference road segment; obtaining public transport IC card information of the reference road segment; and obtaining traffic status information of the reference road segment based on the traffic status reference information, map data, and public transport IC card information.

[0071] Specifically, in the embodiments of this application, the traffic event sensing device is typically integrated into a computing device by software or a combination of software and hardware.

[0072] Specifically, such as Figure 2As shown, the embodiment of the present application responds to the perception instruction of the traffic event according to the driving data of the vehicle, the perception data of the roadside basic perception device, the perception data of the map, positioning, traffic control, weather and other resource platforms, and the optical fiber and edge cloud analysis server, and determines the reference road section corresponding to the target road section according to the traffic event perception instruction, to obtain the traffic state information of the reference road section. Among them, the driving data of the vehicle, the perception data of the roadside basic perception device and the resource platform data are connected to the edge cloud analysis server through the optical fiber.

[0073] Further, the traffic state information of the embodiment of the present application can be obtained by using the traffic state acquisition device associated with the reference road section, obtaining the traffic state reference information corresponding to the traffic reference road section, using the open source data obtained by using the Gaode map, and using the bus IC card information obtained by using the bus background, to obtain the traffic state information of the reference road section.

[0074] Among them, the traffic state acquisition device includes one or more of image acquisition devices, video acquisition devices, ETC (Electronic Toll Collection, full-automatic electronic toll collection system) sensing devices, toll collection devices, navigation devices, geomagnetic sensing devices, and map devices on the roadside and vehicle-mounted side; the traffic state information includes but is not limited to speed information, flow information or density information. Among them, the density information refers to the spacing information of the traffic object, for example, the spacing between vehicles, the spacing between people, the spacing between ships, etc. Correspondingly, the state dimension of the traffic state includes but is not limited to speed, flow or density.

[0075] It should be noted that in actual application, a plurality of traffic state acquisition devices are usually arranged in the road environment and distributed on each road section in the road environment. For a single road section, the types of traffic state acquisition devices thereon can be one or more, and the number of devices under a single traffic state acquisition device can also be one or more.

[0076] Therefore, in the embodiment of the present application, for any reference road section, the traffic state information of the reference road section can be determined by using the traffic state reference information collected by the traffic state acquisition device on the reference road section.

[0077] Further, for a reference road section, if the traffic state collection device associated with the reference road section is one, the traffic state reference information collected by the traffic state collection device can be taken as the traffic state information of the reference road section; if the traffic state collection device associated with the reference road section is multiple, the multiple traffic state reference information can be data fused to obtain the traffic state information corresponding to the reference road section. Therefore, in this case, for the same state dimension, the state reference values provided by the multiple traffic state collection devices can not be completely the same. For example, for the speed dimension, the speed value provided by the traffic state collection device A is 50 km / h, and the speed value provided by the traffic state collection device B is 60 km / h.

[0078] Therefore, in this implementation manner, for the target state dimension, the state reference values under the target state dimension can be respectively obtained from the multiple traffic state reference information, and the multiple obtained state reference values can be fused to generate the state value under the target state dimension, and then the traffic state information corresponding to the reference road section can be constructed according to the state value under the target state dimension.

[0079] Further, as discussed above, after obtaining the traffic state information of the reference road section, the embodiment of the present application first obtains the state reference values under the target state dimension from the multiple traffic state reference information, and performs fusion processing, such as one or more of the mean value operation, the maximum value operation, the intermediate value operation or the weighted summation operation, on the multiple obtained state reference values, so as to generate the state value under the target state dimension; secondly, the traffic state information corresponding to the reference road section is constructed according to the state value under the target state dimension, wherein the target state dimension includes the latitude and longitude, the speed, the flow or the density, and is any one of the state dimensions included in the traffic state information.

[0080] Therefore, after the state reference values provided by the various traffic state collection devices in the road environment are fused, the data coverage of the entire road section in the road environment can be achieved, so as to obtain the traffic state information of the entire road section, thereby providing a more comprehensive and accurate data basis for the traffic event perception scheme.

[0081] It should be understood that in the embodiment of the present application, other implementation manners can also be used to obtain the traffic state information of the reference road section, such as analyzing the traffic state information of the reference road section according to the road sections upstream or downstream of the reference road section whose traffic state information is known, and the like, which are not limited here.

[0082] In step S102, it is judged whether the traffic state information is consistent with the preset safe traffic state information.

[0083] The preset safe traffic state information can be safe traffic state information set by a user or safe traffic state information obtained through computer simulation multiple times, and is not specifically limited here.

[0084] Specifically, the traffic state information of the reference road section is obtained, and it is determined whether the traffic state information is consistent with the preset safe traffic state information, so as to more accurately analyze whether a traffic event occurs on the target road section.

[0085] In step S103, if the traffic state information is inconsistent with the preset safe traffic state information, it is determined that the traffic state information is abnormal, and it is determined whether a traffic event occurs on the target road section based on the traffic state information, otherwise, it is determined that the traffic state information is not abnormal, and no traffic event occurs.

[0086] Specifically, the embodiment of the present application can detect whether there is abnormal fluctuation between the traffic states of the reference road section according to the traffic state information corresponding to the reference road section, if there is abnormal fluctuation, it is determined that the traffic state information of the reference road section is abnormal, and it is determined whether a traffic event occurs on the target road section based on the traffic state information, otherwise, it is determined that the traffic state information is not abnormal, and no traffic event occurs.

[0087] Further, in some embodiments, determining whether a traffic event occurs on the target road section based on the traffic state information comprises: calculating a state feature value of the reference road section in at least one detection dimension according to the traffic state information of the reference road section; if the state feature value in at least one detection dimension satisfies a traffic event determination condition, it is determined that a traffic event occurs on the target road section.

[0088] Further, in some embodiments, if the state feature value in at least one detection dimension satisfies the traffic event determination condition, it is determined that a traffic event occurs on the target road section, comprising: inputting the state feature value in at least one detection dimension into a preset abnormality detection model to generate a target determination result; if the target determination result corresponds to occurrence of a traffic event, it is determined that a traffic event occurs on the target road section.

[0089] The preset abnormality detection model includes one or more of a deep learning model or a logistic regression model, and is obtained by training a target neural network based on a mapping relationship between the state feature value and the determination result, and the mapping relationship is used to represent the traffic event determination condition.

[0090] Specifically, in the embodiment of the present application, first, according to the traffic state information corresponding to the reference road section, the state feature value of the reference road section in at least one detection dimension is calculated, wherein the detection dimension includes at least one of the state change dimension of the reference road section in the current period, the state difference dimension of the reference road section between the current period and the corresponding historical period, and the state difference dimension between the reference road section and other reference road sections, that is, at least one state feature value of the reference road section in at least one of the state change dimension of the reference road section in the current period, the state difference dimension of the reference road section between the current period and the corresponding historical period, and the state difference dimension between the reference road section and other reference road sections is calculated according to the traffic state information corresponding to the reference road section; second, if the state feature value satisfies the traffic event identification condition, at least one state feature value is input into a preset anomaly detection model to generate a target identification result.

[0091] Wherein, the length of the current period can be a preset length, and the end point can be the current time; the detection dimension can also include other dimensions that can reflect the traffic state fluctuation of the reference road section; the state feature value includes but is not limited to the state difference value between the reference road section at the current time and other times in the current period, the state change rate of the reference road section in the current period, the state difference value between the reference road section and other reference road sections, the state difference value and the state ratio value of the reference road section at each time between the current period and the corresponding historical period, and the state difference value or the state ratio value. Similarly, the state feature value can also include other state feature values that can reflect the traffic state fluctuation of the reference road section, which are not limited here.

[0092] Further, the authentication result output by the anomaly detection model can include a first result corresponding to the occurrence of a traffic event and a second result corresponding to the non-occurrence of a traffic event, and if the target identification result is the first result, it can be determined that a traffic event occurs on the target road section. Wherein, the anomaly detection module can use a random forest module or a logistic regression model, or other anomaly detection models that can realize classification, which are not limited here.

[0093] Specifically, the embodiment of the present application takes the random forest model as an example, in which implementation, at least one state feature value can be input into the random forest model, and each decision tree in the random forest model can independently give a classification result, that is, two classification results are independently voted, thereby the random forest model can respectively count the number of votes under the first result and the second result, and then the classification result with more votes is taken as the target identification result.

[0094] It should be noted that the above implementation details of the random forest model are only exemplary, and the embodiment of the present application is not limited here.

[0095] Further, in the above implementation manner, the embodiment of the present application can also pre-train the anomaly monitoring model. In the training process, the training data can be input into the anomaly detection model for the anomaly detection model to learn the mapping relationship between the state feature value and the determination result, that is, the aforementioned traffic event determination condition. The training data can include the reference road segment state feature value corresponding to the sample road segment and the determination result corresponding to the sample road segment, and the training process can be stopped when the accuracy of the anomaly detection model reaches the preset requirement.

[0096] For the case where the combination manner of the reference road segment of the target road segment is uncertain, the anomaly detection model can be trained to learn the mapping relationship between the state feature value and the determination result under different combination manners of the reference road segment.

[0097] Further, in this case, based on the trained anomaly detection model, in the process of perceiving the traffic event on the target road segment, the actual combination manner of the reference road segment corresponding to the target road segment and at least one state value of the reference road segment can be input into the anomaly detection model. For the target road segment, different traffic event determination conditions can be set for different combinations of the reference road segment. This is mainly because the influence degree and the state dimension of the influence of the traffic event occurring on the target road segment on different reference road segments can not be completely the same, and therefore the fluctuation of the traffic state caused by the same traffic event on the target road segment for different combinations of the reference road segment can not be completely the same. Therefore, in the anomaly detection model, the target determination result can be generated based on the mapping relationship between the state feature value and the determination result under the actual combination manner of the reference road segment. The combination manner can be represented as the positional relationship between the reference road segment and the target road segment and the like.

[0098] Further, the embodiment of the present application can also determine whether the at least one state feature value of the reference road segment meets the traffic event determination condition by using other implementation manners, for example, the traffic event determination condition can be represented as a plurality of judgment conditions, and whether the at least one state feature value of the reference road segment meets these judgment conditions is judged, so as to determine whether the at least one state feature value meets the traffic event determination condition, and further more quickly determine whether the traffic event occurs on the target road segment.

[0099] Further, in some embodiments, after determining that the traffic event occurs on the target road segment, the method further includes: generating traffic event reminding information according to the traffic event; and sending the traffic event reminding information to the requestor of the traffic event perception instruction.

[0100] Specifically, the embodiment of the present application can also send a reminding notification to the requestor of the traffic event perception in the case of perceiving that the traffic event occurs on the target road segment, so as to remind the requestor to handle the traffic event and avoid the situation of causing traffic road congestion.

[0101] Further, in some embodiments, the traffic event perception method described above further comprises: taking a plurality of road segments containing traffic state information and closest to the target road segment as display reference road segments; and displaying the reference display road segments in a preset display interface to display the traffic event occurring on the target road segment.

[0102] The preset display interface can be a vehicle-mounted display screen or other electronic devices with display functions, which are not limited here.

[0103] Specifically, in the embodiments of the present application, based on a plurality of road segments pre-divided in a road scene and the perception results of traffic events on each road segment, a plurality of road segments containing traffic state information and closest to the target road segment can be taken as display reference road segments on the display interface of the perception device or the display interface of the traffic event perception requester mentioned in the above embodiments, and at least one reference display road segment in the road scene can be displayed in a preset display interface. If it is determined that a traffic event occurs on the target road segment in the at least one reference display road segment, the traffic event occurring in the road scene and the location of the traffic event are displayed, and a prompt effect is rendered for the target road segment in the display interface to display the traffic event occurring on the target road segment, so that the traffic event occurring in the road scene can be displayed more intuitively and accurately.

[0104] In summary, the embodiments of the present application have the following advantages:

[0105] (1) The present application is suitable for connecting edge cloud devices, and can also be used to connect regional clouds and connect central clouds, and has the advantages of distributed deployment and strong scalability.

[0106] (2) The present application can provide low latency, improve user experience, be suitable for various complex demand scenarios in real life, maximize the application value of edge computing, especially intelligent networked vehicles and intelligent traffic situation perception in complex environments, and improve driving safety and traffic efficiency.

[0107] According to the traffic event perception method of the embodiments of the present application, by receiving a traffic event perception instruction, determining the reference road segment corresponding to the target road segment, obtaining the traffic state information of the reference road segment, and determining whether the traffic state information is consistent with the preset safe traffic state information, if not, it is determined that the traffic state information is abnormal, and whether a traffic event occurs on the target road segment is perceived, otherwise, it is determined that the traffic state information is not abnormal, and no traffic event occurs. Thus, the problem that the perception ability of traffic events is reduced due to the low coverage of video collection devices, so that traffic events on the road cannot be processed in time, and the smoothness of road traffic is affected is solved, so that the traffic events in the road scene are perceived comprehensively, and are no longer limited by the coverage of the video collection device, thereby effectively improving the perception efficiency of traffic events.

[0108] Figure 3 is a block schematic diagram of a traffic event perception system according to an embodiment of the present application.

[0109] As shown in Figure 3 , the traffic event perception system 10 comprises an acquisition module 100, a judgment module 200 and a perception module 300.

[0110] The acquisition module 100 is configured to receive a traffic event perception instruction, and determine a reference road section corresponding to a target road section according to the traffic event perception instruction, and acquire traffic state information of the reference road section.

[0111] The judgment module 200 is configured to judge whether the traffic state information is consistent with preset safe traffic state information.

[0112] The perception module 300 is configured to determine that the traffic state information is abnormal if the traffic state information is not consistent with the preset safe traffic state information, and perceive whether a traffic event occurs on the target road section based on the traffic state information, or determine that the traffic state information is not abnormal and no traffic event occurs.

[0113] Further, in some embodiments, the perception module 300 comprises:

[0114] a detection unit configured to calculate a state feature value of the reference road section in at least one detection dimension according to the traffic state information of the reference road section.

[0115] a determination unit configured to determine that a traffic event occurs on the target road section if the state feature value in the at least one detection dimension satisfies a traffic event determination condition.

[0116] Further, in some embodiments, the determination unit is specifically configured to:

[0117] input the state feature value in the at least one detection dimension into a preset abnormality detection model to generate a target determination result, wherein the target neural network is obtained by training a mapping relationship between the state feature value and the determination result in the preset abnormality detection model, and the mapping relationship is used to represent the traffic event determination condition.

[0118] If the target determination result corresponds to occurrence of a traffic event, it is determined that a traffic event occurs on the target road section.

[0119] Further, in some embodiments, the detection dimension comprises at least one of a state change dimension of the reference road section in a current period, a state difference dimension of the reference road section between the current period and a corresponding historical period, and a state difference dimension between the reference road section and other reference road sections.

[0120] Further, in some embodiments, the acquisition module 100 is specifically used for:

[0121] acquiring traffic state reference information of the reference road section by using the traffic state acquisition device associated with the reference road section;

[0122] acquiring map data of the reference road section;

[0123] acquiring bus IC card information of the reference road section;

[0124] obtaining traffic state information of the reference road section according to the traffic state reference information, the map data and the bus IC card information.

[0125] Further, in some embodiments, after determining that the traffic event occurs on the target road section, the determination unit is further used for:

[0126] generating traffic event reminding information according to the traffic event;

[0127] sending the traffic event reminding information to a requester of the traffic event sensing instruction.

[0128] Further, in some embodiments, the traffic event sensing system 10 is further used for:

[0129] taking a plurality of road sections closest to the target road section and containing the traffic state information as the reference road sections;

[0130] displaying the reference road sections in a preset display interface to display the traffic event occurring on the target road section.

[0131] According to the traffic event sensing system provided in the embodiments of the present application, by receiving the traffic event sensing instruction, determining the reference road sections corresponding to the target road section, acquiring the traffic state information of the reference road sections, determining whether the traffic state information is consistent with the preset safe traffic state information, if not, determining that the traffic state information is abnormal, and sensing whether the traffic event occurs on the target road section, or otherwise, determining that the traffic state information is not abnormal, and the traffic event does not occur. Thus, the problem that the sensing capability of the traffic event is reduced due to the low coverage rate of the video acquisition device, and thus the traffic event on the road cannot be processed in time, and the road traffic smoothness is affected is solved, so that the traffic event of each road section in the road scene is sensed comprehensively, and is no longer limited by the coverage degree of the video acquisition device, and thus the sensing efficiency of the traffic event is effectively improved.

[0132] Figure 4 A structural schematic diagram of an electronic device provided in the embodiments of the present application is shown. The electronic device can include:

[0133] a memory 401, a processor 402, and a computer program stored in the memory 401 and executable on the processor 402.

[0134] The processor 402 implements the traffic event perception method provided in the above embodiments when executing a program.

[0135] Further, the electronic device further comprises:

[0136] The communication interface 403 is configured to communicate between the memory 401 and the processor 402.

[0137] The memory 401 is configured to store a computer program executable on the processor 402.

[0138] The memory 401 can include a high-speed RAM memory, and can further include a non-volatile memory, for example, at least one disk memory.

[0139] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 4 In the figure, only one thick line is used to represent, but it does not mean that there is only one bus or one type of bus.

[0140] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can complete communication between each other through an internal interface.

[0141] The processor 402 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0142] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the traffic event perception method as above.

[0143] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the description of the specification, the illustrative description of the above terms is not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the features of different embodiments or examples described in the specification and the features of different embodiments or examples, without contradiction.

[0144] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0145] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the description of the specification, the illustrative description of the above terms is not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the features of different embodiments or examples described in the specification and the features of different embodiments or examples, without contradiction.

[0146] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. A traffic incident perception method, characterized by, The method comprises the following steps: receiving a traffic event perception instruction, and determining a reference road section corresponding to a target road section according to the traffic event perception instruction, and acquiring traffic state information of the reference road section, comprising: acquiring traffic state reference information of the reference road section by using a traffic state acquisition device associated with the reference road section; acquiring map data of the reference road section; acquiring bus IC card information of the reference road section; and performing fusion processing on the traffic state reference information, the map data and the bus IC card information to obtain the traffic state information of the reference road section; determining whether the traffic state information is consistent with preset safe traffic state information; and if the traffic state information is not consistent with the preset safe traffic state information, determining that the traffic state information is abnormal, and perceiving whether a traffic event occurs on the target road section based on the traffic state information, comprising: calculating state feature values of the reference road section in at least one detection dimension according to the traffic state information of the reference road section, the detection dimension comprising at least one of a state change dimension of the reference road section in a current period, a state difference dimension between the current period and a corresponding historical period of the reference road section, and a state difference dimension between the reference road section and other reference road sections; inputting the state feature values in the at least one detection dimension into a preset abnormality detection model to generate a target determination result, wherein the target neural network is obtained by training a mapping relationship between state feature values and determination results in the preset abnormality detection model, and the mapping relationship is used to represent the traffic event determination condition; if the target determination result corresponds to a traffic event, determining that a traffic event occurs on the target road section; and generating traffic event reminding information according to the traffic event; sending the traffic event reminding information to a requester of the traffic event perception instruction; a plurality of road sections containing the traffic state information and closest to the target road section are used as display reference road sections; a plurality of road sections containing the traffic state information and closest to the target road section are used as reference display road sections based on a plurality of road sections pre-divided in a road scene; the reference display road sections are displayed in a preset display interface, and a prompt effect is rendered for the target road section in the display interface to display a traffic event occurring on the target road section. otherwise, it is determined that the traffic state information is not abnormal, and the traffic event does not occur.

2. A traffic incident detection system for performing the method of claim 1, characterized by comprise: an acquisition module configured to receive a traffic event perception instruction, and determine a reference road section corresponding to a target road section according to the traffic event perception instruction, and acquire traffic state information of the reference road section; a determination module configured to determine whether the traffic state information is consistent with preset safe traffic state information; and a perception module configured to, if the traffic state information is not consistent with the preset safe traffic state information, determine that the traffic state information is abnormal, and perceive whether a traffic event occurs on the target road section based on the traffic state information, otherwise, determine that the traffic state information is not abnormal, and the traffic event does not occur.

3. An electronic device, comprising: comprise: A memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the traffic incident detection method of claim 1.

4. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by a processor for implementing the traffic incident detection method of claim 1.

Images