Data processing method and device, electronic equipment and storage medium

Abstract

The invention provides a data processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of intelligent traffic, and the specific implementation scheme is as follows: obtaining the driving track data of a first vehicle, a second vehicle, a third vehicle and a fourth vehicle on a to-be-detected road section; calculating a first speed difference and a second speed difference between the first vehicle and the second vehicle in the first time period and the second time period and a third speed difference and a fourth speed difference between the third vehicle and the fourth vehicle in the first time period and the second time period according to the trajectory data, the speed interval of the first vehicle is matched with the speed interval of the second vehicle, and the speed interval of the third vehicle is matched with the speed interval of the fourth vehicle; and when the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference, determining that the potential bus lane exists in the to-be-detected road section. According to the invention, the coverage degree of bus lane detection is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically the field of intelligent transportation technology. Background Art

[0002] Bus lanes are very important in map data. Timely and accurate lane-level information reminders can provide decision-making basis for users or autonomous driving to choose drivable lanes, avoid unusable bus lanes, and reduce the occurrence of violations. Summary of the invention

[0003] The present disclosure provides a data processing method, device, electronic device and storage medium.

[0004] According to one aspect of the present disclosure, there is provided a data processing method, comprising:

[0005] Acquire trajectory data of a first vehicle, a second vehicle, a third vehicle, and a fourth vehicle traveling on a road section to be detected, wherein the first vehicle and the third vehicle are buses, the second vehicle and the fourth vehicle are other types of vehicles other than buses, and the trajectory data include data of a first time period and a second time period, and the vehicle flow rate per unit time in the first time period is greater than the vehicle flow rate per unit time in the second time period;

[0006] Calculate, according to the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, wherein the speed interval of the first vehicle matches the speed interval of the second vehicle, and the speed interval of the third vehicle matches the speed interval of the fourth vehicle;

[0007] When the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference, it is determined that there is a potential bus lane in the road section to be detected.

[0008] According to another aspect of the present disclosure, a bus lane detection device is provided, comprising:

[0009] A data acquisition module is used to acquire trajectory data of a first vehicle, a second vehicle, a third vehicle, and a fourth vehicle traveling on a road section to be detected, wherein the first vehicle and the third vehicle are buses, the second vehicle and the fourth vehicle are other types of vehicles other than buses, and the trajectory data includes data of a first time period and a second time period, and the vehicle flow rate per unit time in the first time period is greater than the vehicle flow rate per unit time in the second time period;

[0010] a speed difference calculation module, configured to calculate, based on the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, wherein the speed interval of the first vehicle matches the speed interval of the second vehicle, and the speed interval of the third vehicle matches the speed interval of the fourth vehicle;

[0011] A lane determination module is used to determine that there is a potential bus lane in the road section to be detected when the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1-1 is a flowchart of a first data processing method provided by the present disclosure;

[0014] Figure 1-2 is an example diagram of the driving speed of a bus in two time periods on a road section L provided by the present disclosure;

[0015] Figure 1-3 is an example diagram of the driving speed of a car on a road section L in two time periods according to the present disclosure;

[0016] Figure 1-4 is an example diagram of the speed difference comparison between a car and a bus in two time periods on a road section L provided by the present disclosure;

[0017] Figure 2-1 This is a possible implementation of step S102 provided in the present disclosure;

[0018] Figure 2-2 is an example diagram of a trajectory line provided according to the present disclosure;

[0019] Figure 3 is a flow chart of a second data processing method provided by the present disclosure;

[0020] Figure 4-1 is a flowchart of a third data processing method provided by the present disclosure;

[0021] Figure 4-2 is an example diagram of processing image data of a road section to be detected according to the present disclosure;

[0022] Figure 5 is a structural schematic diagram of a data processing device provided according to the present disclosure;

[0023] Figure 6 It is a block diagram of an electronic device used to implement the data processing method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0025] In the related art, bus lane data in map data mainly comes from road image data collected by collection vehicles. The road image data is initially identified and then the identified information is manually verified and confirmed. However, this method is limited by the coverage and scale of the collection vehicles. Bus lanes cannot be determined in areas with low coverage of the collection vehicles, and covered areas cannot be detected multiple times in a short period of time. It is difficult to detect bus lanes that have changed. In addition, the transmission cost of the large amount of image data collected is relatively high.

[0026] In order to solve at least one of the above problems, the present disclosure provides a data processing method, including:

[0027] Acquire trajectory data of a first vehicle, a second vehicle, a third vehicle, and a fourth vehicle traveling on a road section to be detected, wherein the first vehicle and the third vehicle are buses, the second vehicle and the fourth vehicle are other types of vehicles other than buses, and the trajectory data include data of a first time period and a second time period, and the vehicle flow rate per unit time in the first time period is greater than the vehicle flow rate per unit time in the second time period;

[0028] Calculate, according to the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, wherein the speed interval of the first vehicle matches the speed interval of the second vehicle, and the speed interval of the third vehicle matches the speed interval of the fourth vehicle;

[0029] When the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference, it is determined that there is a potential bus lane in the road section to be detected.

[0030] The data processing method provided by the present disclosure obtains the trajectory data of buses and other types of vehicles traveling on the road section to be detected in the first time period and the trajectory data of buses and other types of vehicles traveling on the road section to be detected in the second time period, respectively, regards the first vehicle and the second vehicle as a pair of control groups, and the third vehicle and the fourth vehicle as another pair of control groups, and calculates the speed difference of each control group in the first time period and the second time period respectively. As the traffic volume increases, the speed difference of each control group decreases, indicating that in different time periods, the driving states of buses and other types of vehicles on the road section to be detected are quite different, thereby determining that there may be potential bus lanes on the road section to be detected. The detection of bus lanes is realized according to the characteristics of the trajectory data of different types of vehicles. Compared with the method of collecting images by a collection vehicle and then judging manually, the coverage is higher; the state of the current lane in the road section to be detected may be obtained more timely, which improves the timeliness of bus lane detection and reduces the difficulty and cost of bus lane detection; and the speed difference is calculated by using multiple pairs of control groups, which reduces the error that may exist in a single sample and improves the accuracy of bus lane detection.

[0031] See also Figure 1-1 , the present disclosure provides a flow chart of a first data processing method, including:

[0032] Step S101: Acquire trajectory data of a first vehicle, a second vehicle, a third vehicle, and a fourth vehicle traveling on a road section to be detected;

[0033] Among them, the first vehicle and the third vehicle are bus-type vehicles, the second vehicle and the fourth vehicle are other types of vehicles other than buses, the trajectory data includes data of a first time period and a second time period, and the vehicle flow per unit time in the first time period is greater than the vehicle flow per unit time in the second time period.

[0034] The first vehicle and the third vehicle can be any type of buses, and the second vehicle and the fourth vehicle can be any type of cars, including Class A0 (small car), Class A (compact car), Class B (mid-size car), Class C (luxury car) and Class D (large car), etc.

[0035] In the present application, the first vehicle and the third vehicle, and the second vehicle and the fourth vehicle, are only distinguished by different trajectory data, reflecting the speed difference between two different types of vehicles in different time periods.

[0036] The speed of the first vehicle is usually lower than that of the second vehicle, and the speed of the third vehicle is usually lower than that of the fourth vehicle. Since bus lanes only allow buses to pass through, and other types of vehicles other than buses pass through non-bus lanes, if there is a bus lane, the speeds of the first and third bus-type vehicles are less affected by the traffic flow, while the speeds of the second and fourth non-bus vehicles are more affected by the traffic flow; if there is no bus lane, the first, second, third and fourth vehicles pass through the same lane, and the two different types of vehicles are more similarly affected by the traffic flow.

[0037] If the traffic volume per unit time of the first time period is greater than the traffic volume per unit time of the second time period, the first time period is considered as the peak period of the road, and the second time period is considered as the non-peak period of the road. For example, the first time period is the morning peak period of 7:30-9:30, and the second time period is the non-peak period of 13:00-15:00.

[0038] In one embodiment of the present disclosure, the traffic volume per unit time of the first time period is greater than the traffic volume per unit time of the second time period, and the difference exceeds a preset traffic volume difference threshold. Specifically, the preset traffic volume difference threshold is calculated based on the historical traffic volume of the road section to be detected within a preset recording time period.

[0039] For example, the preset recording time period may be the past week, month, three months, etc., and the full-day traffic volume of the road section to be detected during this time period is recorded every day, and the difference in traffic volume per unit time between the first time period with less traffic volume and the second time period with greater traffic volume of the road section to be detected is determined. The difference in traffic volume of each day of the road section to be detected during the preset recording time period is calculated, which may be by calculating the average value, mode, etc., to obtain the preset traffic volume difference threshold.

[0040] The trajectory data of the first vehicle includes the driving data of the first vehicle during peak hours on the road and non-peak hours on the road, the trajectory data of the second vehicle includes the driving data of the second vehicle during peak hours on the road and non-peak hours on the road, the trajectory data of the third vehicle includes the driving data of the third vehicle during peak hours on the road and non-peak hours on the road, and the trajectory data of the fourth vehicle includes the driving data of the fourth vehicle during peak hours on the road and non-peak hours on the road, such as the vehicle's driving route, driving time, and driving speed changes.

[0041] It should be noted that the trajectory data can be obtained through electronic map navigation with the user's permission.

[0042] Step S102: Calculate, based on the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period;

[0043] The speed interval of the first vehicle matches the speed interval of the second vehicle, and the speed interval of the third vehicle matches the speed interval of the fourth vehicle.

[0044] It should be understood that the speed range refers to the high-speed range and low-speed range for vehicles of the same type. For example, the average speed can be calculated based on the speeds of multiple vehicles of the same type passing through the section to be detected within the historical time period. The speed exceeding the average speed is in the high-speed range, and the speed not exceeding the average speed is in the low-speed range. The speeds of multiple vehicles of the same type passing through the section to be detected within the historical time period can also be sorted, and the high-speed range and the low-speed range can be specifically limited in values, for example, a bus speed of 5-10m / s is in the low-speed range.

[0045] The speed ranges of different types of vehicles have different corresponding speed values. For example, if the average speed of a bus is 12 m / s, then when the bus is 15 m / s, it is in the high-speed range; if the average speed of a car is 30 m / s, then when the car is 15 m / s, it is in the low-speed range.

[0046] The speed interval of the first vehicle matches the speed interval of the second vehicle, which means that the first vehicle and the second vehicle are both in the low-speed interval of their respective types of vehicles, or are both in the high-speed interval. The speed interval of the third vehicle matches the speed interval of the fourth vehicle, which means that the third vehicle and the fourth vehicle are both in the low-speed interval of their respective types of vehicles, or are both in the high-speed interval.

[0047] According to the trajectory data of the first vehicle and the second vehicle, and according to the trajectory data of the third vehicle and the fourth vehicle, two speed differences between the two types of vehicles in the first time period and the second time period are calculated respectively. Specifically, the speed difference calculation method of the two time periods is the same, for example, the speed of the first vehicle minus the speed of the second vehicle, or the speed of the second vehicle minus the speed of the first vehicle.

[0048] Step S103: When the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference, it is determined that there is a potential bus lane in the road section to be detected.

[0049] The first vehicle and the second vehicle are regarded as a pair of control groups, and the third vehicle and the fourth vehicle are regarded as another pair of control groups. In actual calculations, more pairs of control groups can be selected for comparison. When the speed differences of multiple pairs of control groups are increasing, that is, when the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference, it means that the difference between the driving speed of non-bus type vehicles and the driving speed of bus type vehicles is generally increasing, the driving speed of non-bus type vehicles is much faster than that of bus type vehicles, and the impact of different traffic flows on non-bus type vehicles and bus type vehicles is quite different, so it is determined that there may be bus lanes on the road section to be detected, that is, there are potential bus lanes.

[0050] For example, if there is a potential bus lane in the road section to be detected, the bus lane only allows the first bus type vehicle to pass, and the second non-bus type vehicle can only pass in the non-bus lane. The traffic volume in the first time period is 200 vehicles / hour, and the second time period is 50 vehicles / hour. The preset traffic volume difference threshold is 100 vehicles / hour. It is considered that the first time period is the peak period and the second time period is the non-peak period. In the first time period, the driving speed of the first vehicle in the road section to be detected is 20 kilometers / hour, and the driving speed of the second vehicle in the road section to be detected is 30 kilometers / hour. The first speed difference between the two is 10 kilometers / hour; in the second time period, the driving speed of the first vehicle in the road section to be detected is 30 kilometers / hour, and the driving speed of the second vehicle in the road section to be detected is 60 kilometers / hour, and the second speed difference between the two is 30 kilometers / hour. The second speed difference is larger than the first speed difference. When the first vehicle and the second vehicle are multiple vehicles, the second speed difference and the first speed difference have multiple values, and the second speed difference has a tendency to increase compared with the first speed difference. Thus, it is determined that there is a potential bus lane in the road section to be detected.

[0051] For example, Figure 1-2 The driving speed of the bus on section L in two time periods (A hour and B hour) is given. Figure 1-3 The driving speed of the car in two time periods on the road section L is given. Figure 1-4 The speed difference between the car and the bus in two time periods on section L is given.

[0052] Figure 1-2 and Figure 1-3 In the table, the horizontal axis is the speed of the vehicle (m / s), and the vertical axis is the number of vehicles of the same type at each speed (probability density). The values ​​near the dashed line and dashed line in the table on the far left and in the middle of the figure ( Figure 1-2 29.97 and 31.11, Figure 1-3The 38.98 and 43.53 in the table refer to the average speed of the type of vehicles in that hour, and the table on the far right refers to the speed difference between the type of vehicles in hour A and hour B.

[0053] Figure 1-4 In the table, the horizontal axis is the speed difference between buses and cars (m / s), and the vertical axis is the number of vehicles at each speed difference (probability density). The leftmost and middle tables in the figure show the speed difference of different types of vehicles in different time periods, and the values ​​near the dotted line (11.02 and 14.44 are the average speed differences within the hour). A bus and a car are regarded as a pair of control groups. The strip table on the far right is the superimposed speed distribution result after tracking multiple pairs of control groups, where each bar corresponds to a pair of control groups, indicating the difference in speed difference between two different types of vehicles in the control group in different time periods.

[0054] from Figure 1-2 It can be seen that the speed of the bus on section L at hour A (a peak time period) and hour B (a non-peak time period) is not much different. Figure 1-3 It can be seen that there is a significant difference in the speed of cars on section L between hour A and hour B, and the speed during non-peak hours has increased significantly. Figure 1-4 It means that at hour A and hour B, the speed difference between many pairs of cars and buses increases, and the overall trend is increasing, so there is a potential bus lane on section L.

[0055] As can be seen from the above, the data processing method provided by the present disclosure obtains the trajectory data of buses and other types of vehicles traveling on the road section to be detected in the first time period and the trajectory data of buses and other types of vehicles traveling on the road section to be detected in the second time period, respectively, and regards the first vehicle and the second vehicle as a pair of control groups, and the third vehicle and the fourth vehicle as another pair of control groups, and respectively calculates the speed difference of each control group in the first time period and the second time period. As the traffic volume increases, the speed difference of each control group becomes smaller, indicating that in different time periods, the driving states of buses and other types of vehicles on the road section to be detected are quite different, thereby determining that there may be bus lanes on the road section to be detected. The detection of bus lanes is realized according to the characteristics of the trajectory data of different types of vehicles, and the coverage is higher than the method of collecting images by the collection vehicle and then judging manually; the state of the current lane in the road section to be detected can be obtained more timely, which improves the timeliness of bus lane detection and reduces the difficulty and cost of bus lane detection; and the speed difference is calculated by using multiple pairs of control groups, which reduces the error that may exist in a single sample and improves the accuracy of bus lane detection.

[0056] In one possible implementation, Figure 2-1As shown, the trajectory data includes coordinate information and timestamp information of a plurality of trajectory points. The above step S102 calculates, according to the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, including:

[0057] Step S201: calculating first speed information of the first vehicle in the first time period and second speed information of the first vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the first vehicle in the first time period and the second time period respectively;

[0058] Step S202: calculating the third speed information of the second vehicle in the first time period and the fourth speed information of the second vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the second vehicle in the first time period and the second time period respectively;

[0059] Step S203: calculating the fifth speed information of the third vehicle in the first time period and the sixth speed information of the third vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the third vehicle in the first time period and the second time period respectively;

[0060] Step S204: calculating the seventh speed information of the fourth vehicle in the first time period and the eighth speed information of the fourth vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the fourth vehicle in the first time period and the second time period respectively;

[0061] Step S205: Based on the first speed information and the third speed information, obtain the first speed difference; based on the second speed information and the fourth speed information, obtain the second speed difference; based on the fifth speed information and the seventh speed information, obtain the third speed difference; based on the sixth speed information and the eighth speed information, obtain the fourth speed difference.

[0062] Track data includes coordinate information and timestamp information of multiple track points (for example, when a vehicle is driving on a road section, a track point is generated every 1 second), which can also be called a track vector. The coordinate information refers to the GPS (Global Positioning System) coordinates (x, y) of the track point, and the timestamp information refers to the time when the corresponding track point is generated. Track lines are formed between track points, such as Figure 2-2As shown. The distance between two adjacent track points divided by the time difference between the two track points can be used to obtain the linear speed of the vehicle in this section of the track line. The average linear speed of all track lines of the vehicle on the road section to be detected is the speed information of the vehicle on the road section to be detected.

[0063] The speed difference between the two types of vehicles in the same time period is determined according to the speed information of the two types of vehicles in the same time period.

[0064] As can be seen from the above, the data processing method provided by the present invention utilizes the vehicle's trajectory point coordinate information and timestamp information to determine the speeds of different types of vehicles at different times, and based on this, calculates the speed difference of different types of vehicles in different time periods, thereby achieving accurate calculation of the speed difference of each type of vehicle. Based on this, whether there is a bus lane in the road section to be detected is detected, thereby improving the accuracy of bus lane detection.

[0065] In one embodiment of the present disclosure, Figure 3 As shown, after determining that there is a potential bus lane in the road section to be detected, the method further includes:

[0066] Step S301: obtaining a first difference between a second speed difference and the first speed difference, and a second difference between the fourth speed difference and the third speed difference;

[0067] Step S302: when both the first difference and the second difference exceed a preset difference threshold, determining that there is a bus lane on the road section to be detected;

[0068] Step S303: if there is no bus lane marking for the road section to be detected in the map data, add the bus lane marking for the road section to be detected.

[0069] The preset difference threshold is determined based on the historical average speed or the historical maximum speed of each type of vehicle during off-peak and peak periods of the road section to be detected within the preset recording time period. For example, within the preset recording time period, the historical average speed of buses during off-peak periods is 20, the historical average speed of buses during peak periods is 30, the historical average speed of cars during off-peak periods is 40, and the historical average speed of cars during peak periods is 60, then the preset difference threshold is (60-30)-(40-20)=10.

[0070] When both the first difference and the second difference exceed the preset difference threshold, it means that the speed differences of multiple pairs of vehicle control groups of different types vary significantly with different time periods, so that the detection confidence of whether there is a bus lane on the road section to be detected is high, and it is determined that there is a bus lane on the road section to be detected. If there is no bus lane mark on the road section to be detected in the map data, a bus lane mark is added to the road section to be detected in the map data.

[0071] As can be seen from the above, the data processing method provided by the present disclosure, after determining that there is a potential bus lane on the road section to be detected, if the speed differences of multiple pairs of vehicle control groups of different types change significantly with different time periods, it can be determined that there is a bus lane, and the map data is updated without the need to collect images for review. Compared with the collection vehicle collecting images of each road section and detecting bus lanes based on the collected images, the detection method is simpler and more accurate, and can effectively improve the efficiency and accuracy of bus lane detection.

[0072] In one embodiment of the present disclosure, Figure 4-1 As shown, after determining that there is a potential bus lane in the road section to be detected, the method further includes:

[0073] Step S401: Acquire image data of each lane in the road section to be detected;

[0074] Step S402: using an image recognition algorithm and / or a text recognition algorithm to recognize the image data, and obtaining lane feature information in the road section to be detected;

[0075] Wherein, the lane feature information includes at least one of image feature information and text feature information;

[0076] Step S403: When the lane characteristic information indicates that a target lane among the lanes of the road section to be detected is a bus lane, and there is no bus lane marking for the road section to be detected in the map data, add the bus lane marking to the road section to be detected.

[0077] After determining that there is a bus lane in the road section to be detected, obtain the image data of each lane of the road section to be detected, and use the image recognition algorithm and / or text recognition algorithm to identify the lane feature information of each lane of the road section to be detected, whether there are single yellow dashed lines, double yellow dashed lines, bus lane signs, etc. that can indicate that the target lane is a bus lane. If one or more feature information in the detected image feature information and text feature information indicates the existence of a bus lane, it means that there is a target lane that is a bus lane in each lane of the road section to be detected. Check whether there is a bus lane mark on the road section to be detected in the electronic map. If not, add a bus lane mark.

[0078] In an example, the above data processing method can be used to train a prediction model, such as xgboost (distributed gradient boosting library), and the trajectory data can be input into the prediction model to obtain the prediction result of whether there is a bus lane in the road section to be detected. When the prediction result indicates that there is a bus lane in the road section to be detected, neural networks such as Deeplabv3+ (a convolutional neural network for semantic segmentation) and ResNes50 (a convolutional neural network based on a residual network architecture) are used to recognize image features, and OCR (Optical Character Recognition) is used to recognize text features in the image (mainly road surface text extraction). When the lane feature information indicates that the target lane is a bus lane, a strategic decision on map data processing is given, and the road network information in the base map data is checked, that is, whether there is a bus lane marking in the road section to be detected in the map data, and the map data is updated in a timely manner. Figure 4-2 shown.

[0079] In one example, the image data may come from feedback data from users of electronic maps on the road sections to be detected.

[0080] As can be seen from the above, the data processing method provided by the present invention, after determining that there is a potential bus lane in the road section to be detected, verifies the existence of the bus lane based on the image data of the road section to be detected, thereby providing double insurance for the bus lane detection. The map data is updated only after the doubly determined target lane. Compared with the single detection method in which the collection vehicle detects the bus lane only based on the collected images, this method can more accurately realize the detection of the bus lane.

[0081] In one embodiment of the present disclosure, before acquiring the image data of the road section to be detected, the method further includes:

[0082] Step 1: In response to the user uploading a road segment image in the interface of the electronic map, a lane selection mark and a position mark are displayed in the interface, so that the user can add lane information to the currently uploaded road segment image and confirm the position information corresponding to the road segment image;

[0083] Step 2: Upload the road section image and the corresponding lane information and location information to the image database of the electronic map;

[0084] The above step S401 acquires the image data of each lane in the road section to be detected, including:

[0085] Image data whose position information is located at the road section to be detected is acquired in the image database, and image data of each lane is obtained based on the lane information corresponding to the position information.

[0086] When the user uploads the feedback image of the road section, the user is reminded to add lane information to the image and confirm the position information. The lane information indicates which lane of the road section the current image corresponds to, and the position information indicates the world coordinate information of the road section. The road section image and its corresponding lane information and position information are uploaded to the image database of the electronic map. When acquiring the image data of the road section to be detected, the corresponding image data can be quickly locked in the image database according to the position information, and the lane corresponding to each image data can be clearly determined according to the lane information, so as to realize the acquisition of image data of each lane in the road section to be detected.

[0087] As can be seen from the above, the data processing method provided by the present disclosure, in response to the user's operation of uploading a road section image in the interface of the electronic map, displays a lane selection mark and a coordinate confirmation mark in the interface, so that the user can add lane information to the currently uploaded road section image and confirm the position information corresponding to the road section image, so that when acquiring the image data of the road section to be detected, the image data corresponding to each lane in the road section to be detected can be quickly locked in the image database according to the position information and lane information, thereby reducing the possibility of confusion between the lanes existing in the same road section for the subsequent marking of the bus lanes, and further improving the efficiency and accuracy of bus lane detection.

[0088] See also Figure 5 The present disclosure also provides a schematic structural diagram of a bus lane detection device, including:

[0089] The data acquisition module 501 is used to acquire the trajectory data of the first vehicle, the second vehicle, the third vehicle and the fourth vehicle traveling on the road section to be detected, wherein the first vehicle and the third vehicle are buses, the second vehicle and the fourth vehicle are other types of vehicles other than buses, and the trajectory data includes data of a first time period and a second time period, and the vehicle flow rate per unit time in the first time period is greater than the vehicle flow rate per unit time in the second time period;

[0090] a speed difference calculation module 502, configured to calculate, based on the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, wherein the speed interval of the first vehicle matches the speed interval of the second vehicle, and the speed interval of the third vehicle matches the speed interval of the fourth vehicle;

[0091] The lane determination module 503 is configured to determine that there is a potential bus lane in the road section to be detected when the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference.

[0092] As can be seen from the above, the bus lane detection device provided by the present disclosure obtains the trajectory data of buses and other types of vehicles traveling on the road section to be detected in the first time period and the trajectory data of buses and other types of vehicles traveling on the road section to be detected in the second time period, respectively, and regards the first vehicle and the second vehicle as a pair of control groups, and the third vehicle and the fourth vehicle as another pair of control groups, and respectively calculates the speed difference of each control group in the first time period and the second time period. As the traffic volume increases, the speed difference of each control group becomes smaller, indicating that in different time periods, the driving states of buses and other types of vehicles on the road section to be detected are quite different, thereby determining that there may be bus lanes on the road section to be detected. The detection of bus lanes is realized according to the characteristics of the trajectory data of different types of vehicles, and the coverage is higher than the method of collecting images by the collection vehicle and then judging manually; the state of the current lane in the road section to be detected can be obtained more timely, which improves the timeliness of bus lane detection and reduces the difficulty and cost of bus lane detection; and the use of multiple pairs of control groups to calculate the speed difference reduces the error that may exist in a single sample and improves the accuracy of bus lane detection.

[0093] In one embodiment of the present disclosure, the trajectory data includes coordinate information and timestamp information of multiple trajectory points, and the speed difference calculation module 502 is specifically used to:

[0094] Calculate first speed information of the first vehicle in the first time period and second speed information of the first vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the first vehicle in the first time period and the second time period respectively;

[0095] Calculate the third speed information of the second vehicle in the first time period and the fourth speed information of the second vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the second vehicle in the first time period and the second time period respectively;

[0096] Calculate the fifth speed information of the third vehicle in the first time period and the sixth speed information of the third vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the third vehicle in the first time period and the second time period respectively;

[0097] Calculate the seventh speed information of the fourth vehicle in the first time period and the eighth speed information of the fourth vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the fourth vehicle in the first time period and the second time period respectively;

[0098] The first speed difference is obtained based on the first speed information and the third speed information; the second speed difference is obtained based on the second speed information and the fourth speed information; the third speed difference is obtained based on the fifth speed information and the seventh speed information; and the fourth speed difference is obtained based on the sixth speed information and the eighth speed information.

[0099] As can be seen from the above, the bus lane detection device provided by the present invention utilizes the vehicle's trajectory point coordinate information and timestamp information to determine the speeds of different types of vehicles at different times, and based on this calculates the speed difference of different types of vehicles in different time periods, thereby achieving accurate calculation of the speed difference of each type of vehicle. Based on this, it is detected whether there is a bus lane in the road section to be detected, thereby improving the accuracy of bus lane detection.

[0100] In one embodiment of the present disclosure, the device further includes:

[0101] a difference acquisition module, configured to acquire a first difference between the second speed difference and the first speed difference, and a second difference between the fourth speed difference and the third speed difference;

[0102] A difference comparison module, configured to determine that a bus lane exists in the road section to be detected when both the first difference and the second difference exceed a preset difference threshold;

[0103] The map data updating module is used to add the bus lane marking to the road section to be detected when there is no bus lane marking on the road section to be detected in the map data.

[0104] As can be seen from the above, the bus lane detection provided by the present disclosure, after determining that there is a potential bus lane in the road section to be detected, if the speed difference of multiple pairs of vehicle control groups of different types changes significantly with different time periods, it can be determined that there is a bus lane, and the map data is updated without the need to collect images for review. Compared with the collection vehicle collecting images of each road section and detecting bus lanes based on the collected images, the detection method is simpler and more accurate, and can effectively improve the efficiency and accuracy of bus lane detection.

[0105] In one embodiment of the present disclosure, the device further includes:

[0106] An image data acquisition module, used to acquire image data of each lane in the road section to be detected;

[0107] An information recognition module, used to recognize the image data using an image recognition algorithm and / or a text recognition algorithm to obtain lane feature information in the road section to be detected, wherein the lane feature information includes at least one of image feature information and text feature information;

[0108] A map checking module is used to add a bus lane label to the road section to be detected when the lane characteristic information indicates that a target lane among the lanes of the road section to be detected is a bus lane, and there is no bus lane label for the road section to be detected in the map data.

[0109] As can be seen from the above, the bus lane detection device provided by the present invention, after determining that there is a potential lane in the road section to be detected, verifies the existence of the bus lane based on the image data of the road section to be detected, thereby providing double insurance for the bus lane detection. The map data is updated only after the doubly determined target lane. Compared with the single detection method in which the collection vehicle detects the bus lane only based on the collected images, this method can more accurately realize the detection of the bus lane.

[0110] In one embodiment of the present disclosure, the device further includes:

[0111] An information prompt module, for responding to a user's operation of uploading a road segment image in an interface of an electronic map, displaying a lane selection mark and a position mark in the interface, so that the user can add lane information to the road segment image currently uploaded and confirm the position information corresponding to the road segment image;

[0112] An image uploading module, used to upload the road section image and the corresponding lane information and location information to the image database of the electronic map;

[0113] The image data acquisition module is specifically used for:

[0114] Image data whose position information is located at the road section to be detected is acquired in the image database, and image data of each lane is obtained based on the lane information corresponding to the position information.

[0115] As can be seen from the above, the data processing device provided by the present disclosure, in response to the user's operation of uploading a road section image in the interface of the electronic map, displays a lane selection mark and a position mark in the interface, so that the user can add lane information to the currently uploaded road section image and confirm the position information corresponding to the road section image, so that when acquiring the image data of the road section to be detected, the image data corresponding to each lane in the road section to be detected can be quickly locked in the image database according to the position information and lane information, thereby reducing the possibility of confusion between the lanes existing in the same road section for the subsequent marking of the bus lanes, and further improving the efficiency and accuracy of bus lane detection.

[0116] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0117] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0118] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0119] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0120] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0121] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0122] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0124] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0126] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0127] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0128] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0129] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A data processing method, comprising: Acquire trajectory data of a first vehicle, a second vehicle, a third vehicle, and a fourth vehicle traveling on a road section to be detected, wherein the first vehicle and the third vehicle are buses, the second vehicle and the fourth vehicle are other types of vehicles other than buses, and the trajectory data include data of a first time period and a second time period, and the vehicle flow rate per unit time in the first time period is greater than the vehicle flow rate per unit time in the second time period; Calculate, according to the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, wherein the speed interval of the first vehicle matches the speed interval of the second vehicle, and the speed interval of the third vehicle matches the speed interval of the fourth vehicle; When the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference, it is determined that there is a potential bus lane in the road section to be detected.

2. The method according to claim 1, wherein: The trajectory data includes coordinate information and timestamp information of a plurality of trajectory points, and calculating, based on the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, including: Calculate first speed information of the first vehicle in the first time period and second speed information of the first vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the first vehicle in the first time period and the second time period respectively; Calculate the third speed information of the second vehicle in the first time period and the fourth speed information of the second vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the second vehicle in the first time period and the second time period respectively; Calculate the fifth speed information of the third vehicle in the first time period and the sixth speed information of the third vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the third vehicle in the first time period and the second time period respectively; Calculate the seventh speed information of the fourth vehicle in the first time period and the eighth speed information of the fourth vehicle in the second time period according to the track point coordinate information corresponding to the timestamp information of the fourth vehicle in the first time period and the second time period respectively; The first speed difference is obtained based on the first speed information and the third speed information; the second speed difference is obtained based on the second speed information and the fourth speed information; the third speed difference is obtained based on the fifth speed information and the seventh speed information; and the fourth speed difference is obtained based on the sixth speed information and the eighth speed information.

3. The method according to claim 1, after determining that there is a potential bus lane on the road section to be detected, the method further comprises: acquiring a first difference between the second speed difference and the first speed difference, and a second difference between the fourth speed difference and the third speed difference; When both the first difference and the second difference exceed a preset difference threshold, determining that a bus lane exists in the road section to be detected; When there is no bus lane marking for the road section to be detected in the map data, the bus lane marking is added to the road section to be detected.

4. The method according to claim 1, after determining that there is a potential bus lane in the road section to be detected, the method further comprises: Acquire image data of each lane in the road section to be detected; Using an image recognition algorithm and / or a text recognition algorithm to recognize the image data, and obtaining lane feature information in the road section to be detected, wherein the lane feature information includes at least one of image feature information and text feature information; When the lane characteristic information indicates that a target lane among the lanes of the road section to be detected is a bus lane, and there is no bus lane marking for the road section to be detected in the map data, the bus lane marking is added to the road section to be detected.

5. According to the method described in claim 1, the difference between the traffic volume per unit time in the first time period and the traffic volume per unit time in the second time period exceeds a preset traffic volume difference threshold, and the preset traffic volume difference threshold is calculated based on the historical traffic volume of the road section to be detected within a preset recording time period.

6. The method according to claim 4, before acquiring the image data of the road section to be detected, the method further comprises: In response to a user uploading a road segment image in an interface of an electronic map, a lane selection mark and a position mark are displayed in the interface, so that the user can add lane information to the road segment image currently uploaded and confirm the position information corresponding to the road segment image; Uploading the road section image and the corresponding lane information and location information to an image database of an electronic map; The step of acquiring image data of each lane in the road section to be detected includes: Image data whose position information is located at the road section to be detected is acquired in the image database, and image data of each lane is obtained based on the lane information corresponding to the position information.

7. A data processing device, comprising: A data acquisition module is used to acquire trajectory data of a first vehicle, a second vehicle, a third vehicle, and a fourth vehicle traveling on a road section to be detected, wherein the first vehicle and the third vehicle are buses, the second vehicle and the fourth vehicle are other types of vehicles other than buses, and the trajectory data includes data of a first time period and a second time period, and the vehicle flow rate per unit time in the first time period is greater than the vehicle flow rate per unit time in the second time period; a speed difference calculation module, configured to calculate, based on the trajectory data, a first speed difference between the first vehicle and the second vehicle in the first time period, a second speed difference between the first vehicle and the second vehicle in the second time period, a third speed difference between the third vehicle and the fourth vehicle in the first time period, and a fourth speed difference between the third vehicle and the fourth vehicle in the second time period, wherein the speed interval of the first vehicle matches the speed interval of the second vehicle, and the speed interval of the third vehicle matches the speed interval of the fourth vehicle; A lane determination module is used to determine that there is a potential bus lane in the road section to be detected when the second speed difference exceeds the first speed difference and the fourth speed difference exceeds the third speed difference.

8. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images