A method, device, equipment, and medium for automatically detecting the parking status of vehicles at intersections.

Abstract

This invention discloses an automatic detection method, device, equipment, and medium for vehicle parking status at intersections. The method includes: when a vehicle is detected entering the intersection, acquiring trajectory point data consisting of multiple continuous trajectory points, including the current trajectory point; collaboratively determining whether the vehicle is parked based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data; and determining the parking status based on the parking duration when the vehicle is determined to be parked and its travel direction is consistent with the main traffic direction corresponding to the intersection. This invention accurately distinguishes between effective parking and low-speed creep scenarios through multi-point collaborative analysis, and eliminates interference by combining directional consistency verification. Without relying on additional hardware and high-precision maps, it achieves low-cost, high-precision, low-interference, and wide-coverage automatic detection and hierarchical early warning of parking behavior at intersections.

Description

Technical Field

[0001] This invention relates to the field of road traffic safety technology, and more specifically, to a method, device, equipment, and medium for automatically detecting the parking status of vehicles at intersections. Background Technology

[0002] In the area of ​​road traffic safety for trucks, especially in supervising the enforcement of mandatory parking regulations such as "stop when turning right" and "yield to oncoming traffic," the current approach mainly relies on the following two methods: The first method, manual patrols or fixed camera video recognition, is costly, has limited coverage, is severely affected by weather, lighting, and angle, and has a high misjudgment rate, making it impossible to achieve all-weather, large-scale monitoring across the entire road network.

[0003] The second method involves in-vehicle navigation software reminders. However, this method requires drivers to actively install and open a specific navigation app, resulting in extremely poor universality. The navigation system will continuously output route guidance unrelated to safety, causing driver fatigue and desensitization to safety alerts, ultimately leading to the neglect of critical safety reminders. Furthermore, the positioning accuracy and reporting frequency of civilian GPS are insufficient, making it difficult to accurately distinguish between complex scenarios such as "intentional brief stops" and "low-speed crawling / frequent stops and starts in traffic jams."

[0004] As a result, existing technologies cannot achieve low-cost, high-precision, low-interference, and wide-coverage automatic detection and accurate early warning of parking behavior at intersections, leading to a large number of violations going undetected and long-term safety hazards. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method, apparatus, equipment and medium for automatic detection of vehicle parking status at intersections, aiming to solve at least one of the above-mentioned technical problems.

[0006] In a first aspect, the technical solution of the present invention to solve the above-mentioned technical problems is as follows: an automatic detection method for vehicle parking status at intersections, the method comprising: When a vehicle is detected entering the intersection, multiple consecutive trajectory points, including the vehicle's current trajectory point, are acquired to form the event window trajectory point data. Based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data, determine whether the vehicle has stopped; When a vehicle is determined to be parked and its direction of travel is consistent with the main traffic direction at the intersection, the parking status of the vehicle is determined based on the duration of its parking.

[0007] This invention provides an automatic vehicle parking status detection method at intersections. First, by constructing an event window containing multiple continuous trajectory points for data sampling, the detection process ensures complete coverage of the deceleration to stop and the stop to start process, avoiding the randomness and partiality of single-point data sampling. Second, by employing multi-dimensional kinematic features of speed, acceleration, and jerk to collaboratively determine parking behavior, it can accurately distinguish between intentional parking and complex scenarios such as low-speed creep and stop-and-go traffic, significantly improving the accuracy and reliability of parking detection. Third, after determining parking, a consistency check between the driving direction and the main traffic direction at the intersection is introduced, effectively eliminating interference from irrelevant scenarios such as vehicles making U-turns or driving parallel to other roads, improving the effectiveness and specificity of the detection results. Finally, the parking status is determined based on the parking duration, providing a precise basis for subsequent differentiated processing. Therefore, this invention achieves low-cost, high-precision, low-interference, and wide-coverage automatic detection of parking behavior at intersections without relying on additional hardware or high-precision maps, effectively solving the technical problems of high false positive rates, poor universality, and difficulty in large-scale deployment in existing technologies.

[0008] Based on the above technical solution, the present invention can be further improved as follows.

[0009] Furthermore, the above-mentioned determination of whether the vehicle has stopped based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data includes: If the trajectory point data in the event window simultaneously meet the following preset conditions, the vehicle is determined to be stopped. The preset conditions include: there are continuous near-zero speed trajectory points with speeds less than a preset speed threshold, and the number of near-zero speed trajectory points is not less than a preset number; among all trajectory points, the trajectory point with the smallest acceleration value has an acceleration less than a preset acceleration threshold; and the standard deviation of the acceleration of all trajectory points is less than a preset stability threshold.

[0010] Furthermore, the above-mentioned determination of a vehicle's parking status based on its parking duration includes: If the parking time falls within the time range corresponding to the first preset time and the second preset time, the parking status is determined to be complete parking. If the parking time exceeds the second preset time, the parking status is determined to be compliant parking; If the parking duration is less than the first preset duration, the parking status is determined to be illegal parking.

[0011] Furthermore, the aforementioned parking duration is determined based on the following method: Get the timestamp corresponding to the first near-zero speed trajectory point in the continuous near-zero speed trajectory points data in the event window, and determine it as the parking start time; The vehicle's current speed is continuously monitored, and the timestamp corresponding to the trajectory point where the speed first exceeds the preset exit speed threshold is obtained and determined as the parking end time. The difference between the parking end time and the parking start time is the parking duration.

[0012] Furthermore, whether the aforementioned vehicles entered the intersection is determined based on the following methods: Obtain the target polygon corresponding to the monitoring area of ​​the intersection. The target polygon is formed by extending the four parking lines corresponding to the monitoring area outward by a preset distance. Based on the vehicle's current trajectory points, the ray-mapping method is used to detect whether the vehicle is within the target polygon. If so, it is determined that the vehicle has entered the intersection.

[0013] Furthermore, whether the aforementioned vehicles are traveling in the same direction as the main traffic flow at the intersection is determined based on the following method: Obtain the vehicle's current heading angle; Calculate the angle difference between the current heading angle and the main traffic direction at the intersection; If the absolute value of the angle difference is less than the preset angle threshold, the vehicle's driving direction is consistent with the corresponding traffic direction at the intersection; otherwise, they are not.

[0014] Furthermore, after determining the vehicle's parking status, the above method also includes: When the parking status is complete, the vehicle's compliance with parking rules for this instance is recorded; When the parking status is compliant parking, a level one warning is triggered, generating positive feedback information and pushing it to the vehicle's on-board terminal; When the parking status is illegal parking, a level two warning is triggered, and a warning message is generated and pushed to the vehicle's on-board terminal.

[0015] Secondly, in order to solve the above-mentioned technical problems, the present invention also provides an automatic vehicle intersection parking status detection device, the device comprising: The acquisition module is used to acquire multiple continuous trajectory points, including the vehicle's current trajectory point, when a vehicle is detected entering an intersection, to form the trajectory point data of the event window. The parking judgment module is used to determine whether the vehicle is stopped based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data; The parking status determination module is used to determine the parking status of a vehicle based on its parking duration when the vehicle is determined to be parked and its driving direction is consistent with the main traffic direction corresponding to the intersection.

[0016] Thirdly, in order to solve the above-mentioned technical problems, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the automatic detection method for vehicle parking status at intersections of the present application.

[0017] Fourthly, in order to solve the above-mentioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the automatic vehicle intersection parking state detection method of the present application.

[0018] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below.

[0020] Figure 1 This is a flowchart illustrating an automatic vehicle parking status detection method according to an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating a scenario where the driving direction is consistent with the main traffic direction at an intersection, according to one embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an automatic vehicle parking status detection device at an intersection, provided in one embodiment of the present invention. Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0021] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0022] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0023] The data acquisition process involved in this invention follows the principles of legality, legitimacy, and necessity. Based on obtaining the explicit authorization and consent of the user, only the minimum necessary information required to achieve the purpose is collected, and data security protection obligations are fulfilled in accordance with the law.

[0024] The solution provided by the embodiments of the present invention can be applied to any application scenario that requires automatic detection of vehicle parking status at intersections, especially for intersections with mandatory parking regulations such as "stop when turning right" and "yield to oncoming traffic".

[0025] The solution provided in this invention can be applied to any application scenario that requires target detection.

[0026] like Figure 1 The flowchart shown below illustrates that the automatic vehicle parking status detection method provided by the present invention may include the following steps: S10, when a vehicle is detected entering the intersection, multiple continuous trajectory points, including the vehicle's current trajectory point, are acquired to form the event window trajectory point data; S20: Determine whether the vehicle has stopped based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data. S30: When a vehicle is determined to be parked and its direction of travel is consistent with the main traffic direction at the intersection, the parking status of the vehicle is determined based on the duration of its parking.

[0027] The method of this invention, firstly, constructs an event window containing multiple continuous trajectory points for data sampling, ensuring that the detection process covers the entire process from deceleration to stopping and from stopping to starting, avoiding the randomness and partiality of single-point data sampling; secondly, it uses multi-dimensional kinematic features of speed, acceleration, and jerk to collaboratively determine parking behavior, accurately distinguishing between intentional parking and complex scenarios such as low-speed creep and stop-and-go traffic, significantly improving the accuracy and reliability of parking detection; thirdly, after determining parking, it introduces a consistency check between the driving direction and the main traffic direction at the intersection, effectively eliminating interference from irrelevant scenarios such as vehicles making U-turns at intersections or driving parallel to other roads, improving the effectiveness and specificity of the detection results; finally, it determines the parking state based on the parking duration, providing a precise basis for subsequent differentiated processing. Therefore, this invention achieves low-cost, high-precision, low-interference, and wide-coverage automatic detection of parking behavior at intersections without relying on additional hardware or high-precision maps, effectively solving the technical problems of high false positive rates, poor universality, and difficulty in large-scale deployment in existing technologies.

[0028] The following specific embodiments further illustrate the solution of the present invention. In this embodiment, the provided method for automatically detecting the parking status of vehicles at intersections may include the following steps: S10, when a vehicle is detected entering the intersection, multiple continuous trajectory points, including the vehicle's current trajectory point, are acquired to form the event window trajectory point data; Among them, the event window trajectory point data refers to a continuous data set containing multiple trajectory points that is specifically extracted after a vehicle is detected entering the intersection monitoring area in order to analyze whether it has stopped.

[0029] Specifically, in this embodiment of the invention, in order to accurately identify the vehicle status, the cloud platform can continuously receive vehicle trajectory point data periodically reported by the vehicle-mounted GPS terminal. The data for each trajectory point includes at least location (longitude and latitude), instantaneous speed, heading angle, and timestamp information. When a vehicle is detected to have entered the monitoring area corresponding to a preset intersection, the event detection process is triggered.

[0030] The event window trajectory point data includes multiple consecutive historical trajectory points, including the current trajectory point, which together form an "event window." This window is used for subsequent comprehensive analysis of the parking status. The length of the event window can be configured according to the reporting frequency of GPS data. For example, in a scenario where the terminal reporting interval is 2-5 seconds, the window can be set to include 3-5 consecutive trajectory points (covering a time range of approximately 6-25 seconds) to ensure that the complete deceleration, stopping, and starting process can be captured, achieving a balance between real-time performance and accuracy.

[0031] In one specific embodiment, whether the vehicle has entered the intersection is determined based on the following method: Obtain the target polygon corresponding to the monitoring area of ​​the intersection. The target polygon is formed by extending the four parking lines corresponding to the monitoring area outward by a preset distance. Based on the vehicle's current trajectory points, the ray-mapping method is used to detect whether the vehicle is within the target polygon. If so, it is determined that the vehicle has entered the intersection.

[0032] As an example, the cloud platform pre-builds a lightweight model (which can be called an intersection area vector model or intersection model, and can be built offline) for each key monitored intersection, namely a target polygon P. This polygon is not a simple high-precision map, but is formed by extending the stop lines in the four directions of the intersection outwards by a certain distance (e.g., 50 meters, this distance is configurable). When the current trajectory point Q of a vehicle is received, the ray casting method is used to determine whether the current trajectory point is located inside the target polygon P. If so, it is determined that the vehicle has entered the monitoring area of ​​the intersection, thus triggering the subsequent S20 step. This method does not require a high-precision map; it can achieve highly reliable entry detection using only civilian GPS accuracy.

[0033] S20: Determine whether the vehicle has stopped based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data. After determining the monitoring area corresponding to the vehicle's entry into the intersection, a refined analysis is performed using the event window trajectory point data constructed in S10. To avoid misjudgments caused by GPS signal noise or low-speed creep, this step employs a multi-dimensional kinematic feature collaborative analysis method to calculate the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data.

[0034] First, obtain the raw speed sequence reported by the vehicle terminal. The raw speed sequence refers to the data set of instantaneous speed values, which are periodically reported by the vehicle terminal (such as a GPS device) at certain time intervals and have not undergone any processing, arranged in chronological order.

[0035] The original velocity sequence can be represented as: The corresponding timestamp sequence is .

[0036] To eliminate noise such as instantaneous jumps in the raw GPS velocity signal, the raw velocity sequence within the event window can be smoothed to obtain a smoothed velocity sequence. In a preferred embodiment, a three-point weighted moving average method can be used. This method calculates the smoothing value using the current data point and its preceding and following adjacent points, effectively filtering out high-frequency noise while maintaining good real-time performance. Specifically, for the raw velocity sequence... The smoothed velocity sequence is represented as: ; Among them, the points The calculation formula is as follows: ; in, This represents the first velocity in the smoothed velocity sequence. The velocity values ​​at each time point; , , These represent the first and second digits of the original velocity sequence, respectively. The velocity values ​​of each trajectory point and its preceding and following adjacent trajectory points; These correspond to the weight coefficients of the previous trajectory point, the current trajectory point, and the next trajectory point, respectively. For example, we can take... (That is, to give higher weight to the current trajectory point); This represents the total number of points in the original velocity sequence.

[0037] When determining the weight coefficients of each data point in the smoothing algorithm, a comprehensive balance can be made between vehicle motion patterns and business requirements. In some specific embodiments, the weight of the current trajectory point can be set to be larger, such as 1, 2, 1, forming a three-point triangular window smoothing; alternatively, filtering theories such as minimum mean square error, low-pass / Gaussian windows, or parameter optimization based on labeled data can be used to set the weights.

[0038] In the process of generating the smoothed velocity sequence described above, by using the above-mentioned... trajectory points In the calculation formula Traverse from 2 to The original velocity sequence can then be calculated. The corresponding Values ​​(i.e.) arrive For the first and last trajectory points (i=1 and i=n) in the original velocity sequence, the above-mentioned method cannot be applied due to the lack of preceding or succeeding trajectory points. trajectory points The calculation formula can be directly retained, let as well as The output sequence after smoothing is a new velocity sequence of the same length as the original velocity sequence.

[0039] Then, based on the smoothed velocity sequence Calculate the acceleration and jerk at each trajectory point.

[0040] Acceleration represents the rate of change of velocity, and the formula for calculation is as follows: ; in, Indicates the first The acceleration of each trajectory point; Indicates the first The timestamp of each trajectory point Indicates the first -1 timestamp of a trajectory point; The speed may not be constant, but is adapted to reporting jitter over 2-5 seconds. In this embodiment of the invention, the unit of speed is uniformly set to... .

[0041] Jerk represents the rate of change of acceleration and effectively reflects the smoothness and urgency of driving behavior. The formula for calculating jerk is: ; in, Indicates the first The jerk at each trajectory point reflects how quickly the acceleration changes. Indicates the first Acceleration at each trajectory point.

[0042] After combining the calculated velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data, it is determined whether the vehicle has truly stopped.

[0043] In a specific embodiment, determining whether the vehicle has stopped based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data includes: If the event window trajectory point data simultaneously meet the following preset conditions, the vehicle is determined to be parked. The preset conditions include: There are continuous near-zero velocity trajectory points with speeds less than a preset velocity threshold, and the number of near-zero velocity trajectory points is not less than a preset number; among all trajectory points, the trajectory point with the smallest acceleration value has an acceleration less than a preset acceleration threshold; the standard deviation of the acceleration of all trajectory points is less than a preset stability threshold.

[0044] As an example, let's further explain the above-mentioned preset conditions: Condition A (Velocity Continuously Near Zero): Detects whether a continuous segment of "near-zero velocity trajectory points" exists in the trajectory point data within the event window. The velocities of these near-zero velocity trajectory points are all less than a preset velocity threshold. For example, a speed of 2 km / h, and the number of points in this continuous trajectory must be no less than a preset number. This condition is used to distinguish whether the vehicle has slowed down briefly or has actually come to a complete stop.

[0045] Condition B (Significant Active Deceleration): Find the acceleration values ​​of all trajectory points in the event window trajectory point data and obtain their minimum value min(a). This minimum value must be less than a preset negative acceleration threshold. For example, -0.5 m / s². This condition is used to prove that the vehicle has come to a stop from a normal driving state through a single instance of active braking, ruling out the possibility that the vehicle has been crawling at a low speed in place.

[0046] Condition C (Smooth Parking Process): Calculate the standard deviation σ(j) of the acceleration j of all trajectory points in the event window trajectory point data. This standard deviation must be less than a preset stability threshold. Frequent starts and stops in congested traffic can cause drastic fluctuations in acceleration, with a large standard deviation. In contrast, a single, intentional, and smooth stop results in a relatively gradual change in acceleration with a smaller standard deviation. This condition can effectively eliminate the possibility of starting and stopping in congested traffic.

[0047] Only when conditions A, B, and C are all met simultaneously will the vehicle be deemed to have committed a valid parking event; otherwise, it will be considered an invalid action (such as traffic congestion).

[0048] Specifically, in this embodiment of the invention, condition A can be expressed by the following formula: in, Indicates the current time point, from Start to Total includes ( - ( ) + 1) = One point; This indicates an indicator function that takes the value 1 if the condition is true and 0 otherwise. This indicates a preset speed threshold; This indicates that the event window trajectory point data satisfies... The preset number of trajectory points; This indicates the number of trajectory points corresponding to the event window, that is, the number of trajectory points contained in the trajectory point data of the event window. Specifically, this indicates the duration corresponding to the event window trajectory point data. Sampling average interval Then it contains Each point is rounded up to ensure coverage of the entire time window.

[0049] In this embodiment of the invention, condition B can be expressed by the following formula: ; in, Indicates the first The acceleration of each trajectory point. Indicates the active deceleration threshold (triggered when acceleration is negative, optionally...). Possible values Condition B indicates that the minimum acceleration in the event window trajectory point data is less than a negative deceleration threshold. This indicates that the vehicle is actively decelerating from a moving state.

[0050] In this embodiment of the invention, condition C can be expressed by the following formula: ; in, This represents the threshold for the smoothness of the parking process. It represents the standard deviation of the accelerometer sequence in the event window trajectory point data, and is used to measure the magnitude of start-stop fluctuations.

[0051] in, This represents the average value of the jerk in the trajectory point data of the event window.

[0052] A vehicle is considered to have entered into a valid parking event only if conditions A, B, and C are all met simultaneously; otherwise, the event is considered invalid.

[0053] The embodiments of the present invention determine parking by using a three-dimensional time sequence of "speed-acceleration-jerk" collaborative determination. Compared with the traditional single-point speed determination, it can accurately distinguish between "intentional parking" and complex scenarios such as "low-speed creep / frequent start-stop in traffic jams", which significantly improves the accuracy of parking determination under complex urban traffic flow.

[0054] S30: When a vehicle is determined to be parked and its direction of travel is consistent with the main traffic direction at the intersection, the parking status of the vehicle is determined based on the duration of its parking.

[0055] After determining that the vehicle has stopped, it is also necessary to perform direction verification and parking duration calculation to ultimately determine whether the vehicle's parking status is complete, compliant, or illegal. Directional consistency verification is performed to exclude scenarios where the vehicle is making a U-turn at an intersection or is parked on a side road / parallel road that is unrelated to the main traffic direction at the intersection.

[0056] In one specific embodiment, whether the vehicle's direction of travel is consistent with the main traffic direction corresponding to the intersection is determined based on the following method: Obtain the vehicle's current heading angle; Calculate the angle difference between the current heading angle and the main traffic direction at the intersection; If the absolute value of the angle difference is less than the preset angle threshold, the vehicle's driving direction is consistent with the corresponding traffic direction at the intersection; otherwise, they are not.

[0057] As an example, see Figure 2 Obtain the current heading angle reported by the vehicle. and the predefined main traffic direction at the intersection. Perform a comparison. Calculate the angle difference. .if Less than the preset angle threshold For example, at 45°, the vehicle's direction of travel is considered to be consistent with the main traffic direction at the intersection, such as when the vehicle is making a right turn or going straight through the intersection. It should be noted that when the intersection model is initially set, a fixed reference direction is assigned to each key monitored intersection according to its main traffic direction, which can be north, east, or other directions.

[0058] After the direction verification is passed, the specific duration of this parking session, i.e., the parking time, is calculated.

[0059] In one specific embodiment, the parking duration is determined based on the following method: Get the timestamp corresponding to the first near-zero speed trajectory point in the continuous near-zero speed trajectory points data in the event window, and determine it as the parking start time; The system continuously monitors the vehicle's current speed and obtains the timestamp corresponding to the trajectory point where the speed first exceeds the preset exit speed threshold. This timestamp is then determined as the parking end time. The difference between the parking end time and the parking start time is the parking duration.

[0060] Specifically, the starting point for timing (parking start time). Precisely defined as the first velocity in the event window trajectory point data that is lower than zero within a segment of "continuous near-zero velocity trajectory points" satisfying condition A. The timestamp of the trajectory point (i.e., the first near-zero velocity trajectory point); the timing endpoint (the time the parking ended). Defined as the speed in the trajectory point data of the event window after the vehicle restarts. First time exceeding the preset export speed threshold The parking duration is calculated using the timestamp of a trajectory point at a speed of 5 km / h. .

[0061] The parking status of the vehicle is determined by combining the calculated parking duration.

[0062] In one specific embodiment, determining the parking status of a vehicle based on its parking duration includes: If the parking time falls within the time range corresponding to the first preset time and the second preset time, the parking status is determined to be complete parking. If the parking time exceeds the second preset time, the parking status is determined to be compliant parking; If the parking duration is less than the first preset duration, the parking status is determined to be illegal parking.

[0063] As an example, the first preset duration can be set to 1 second, and the second preset duration to 3 seconds. Then: If 1 second ≤ ≤3 seconds indicates that the vehicle has completed the full parking maneuver and is considered a complete parking; if If the time is greater than 3 seconds, it means the vehicle not only stopped but remained stationary for a considerable period, possibly due to yielding or other reasons, and is therefore considered legally parked; if If the vehicle slows down only for less than 1 second, it is considered to have only symbolically slowed down and not come to a complete stop, and is therefore deemed to be illegally parked.

[0064] After determining the parking status, feedback can be provided on the parking operation based on the different parking statuses.

[0065] In one specific embodiment, after determining the parking status of the vehicle, the method further includes: When the parking status is complete parking, the system records that the vehicle complied with the parking rules; when the parking status is compliant parking, a level one warning is triggered, generating positive feedback information and pushing it to the vehicle's onboard terminal; when the parking status is illegal parking, a level two warning is triggered, generating warning information and pushing it to the vehicle's onboard terminal.

[0066] As an example, for complete parking, only the vehicle's compliance with parking rules for this instance can be recorded; for compliant parking, a level one warning is triggered, generating positive feedback information and pushing it to the vehicle's in-vehicle terminal, such as a voice prompt like "Safe passage, thank you for your cooperation"; for illegal parking, a level two warning is triggered, generating warning information and pushing it to the vehicle's in-vehicle terminal, such as immediately pushing a strong reminder to the driver's terminal, and reporting the violation record with algorithmic confidence to the fleet and traffic police management platform.

[0067] This invention employs a tiered early warning mechanism, which, through the tiered, target-specific design and differentiated push notifications, achieves highly accurate reminders with minimal interference, causing almost no disruption to compliant drivers and precisely targeting violations.

[0068] The embodiments of the present invention enable high-precision, low-interference automatic detection and graded early warning of vehicle parking status at intersections using only existing GPS trajectory data without relying on additional hardware and high-precision maps.

[0069] To better illustrate and understand the principle of the method provided by this invention, the following description uses an optional specific embodiment to illustrate the solution of this invention. It should be noted that the specific implementation of each step in this specific embodiment should not be construed as a limitation of the solution of this invention. Other implementations that can be conceived by those skilled in the art based on the principle of the solution provided by this invention should also be considered within the scope of protection of this invention.

[0070] In this embodiment of the invention, the method can be implemented based on a complete automatic vehicle intersection parking status detection system, which includes the following three components: Vehicle-mounted terminal: Utilizes the vehicle's existing GPS equipment to collect real-time location, speed, heading angle, and timestamp, and periodically reports them to the cloud via cellular network; Cloud processing platform: As the core of this invention, it is responsible for receiving data reported by the vehicle terminal and sequentially executing core algorithm logic such as state perception, intersection matching, parking event determination, and dynamic early warning decision-making. Early warning distribution module: Pushes the judgment results and early warning instructions generated by the cloud processing platform to the driver terminal, fleet management platform and traffic police supervision platform to realize hierarchical early warning and information closed loop.

[0071] This invention first samples data by constructing an event window containing multiple continuous trajectory points, ensuring that the detection process covers the entire process from deceleration to stopping and from stopping to starting, avoiding the randomness and partiality of single-point data sampling. Second, it uses multi-dimensional kinematic features of speed, acceleration, and jerk to collaboratively determine parking behavior, accurately distinguishing between intentional parking and complex scenarios such as low-speed creep and stop-and-go traffic, significantly improving the accuracy and reliability of parking detection. Third, after determining parking, it introduces a consistency check between the driving direction and the main traffic direction at the intersection, effectively eliminating interference from irrelevant scenarios such as vehicles making U-turns at intersections or driving parallel to other roads, improving the effectiveness and specificity of the detection results. Finally, it determines the parking status based on the parking duration, providing a precise basis for subsequent differentiated processing. Thus, this invention achieves low-cost, high-precision, low-interference, and wide-coverage automatic detection of parking behavior at intersections without relying on additional hardware or high-precision maps, effectively solving the technical problems of high false positive rates, poor universality, and difficulty in large-scale deployment in existing technologies.

[0072] Based on and Figure 1 Based on the same principle as the method shown, this embodiment of the invention also provides an automatic vehicle intersection parking status detection device 20, such as... Figure 3 As shown, the automatic vehicle parking status detection device 20 at the intersection may include an acquisition module 210, a parking judgment module 220, and a parking status judgment module 230, wherein: The acquisition module 210 is used to acquire multiple continuous trajectory points, including the current trajectory point of the vehicle, when a vehicle is detected entering the intersection, to form event window trajectory point data. The parking judgment module 220 is used to determine whether the vehicle is parked based on the velocity, acceleration and jerk of each trajectory point in the trajectory point data of the event window; The parking status determination module 230 is used to determine the parking status of a vehicle based on its parking duration when the vehicle is determined to be parked and the vehicle's driving direction is consistent with the main traffic direction corresponding to the intersection.

[0073] Furthermore, when the parking determination module 220 determines whether a vehicle is parked based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data, it is specifically used for: If the trajectory point data in the event window simultaneously meet the following preset conditions, the vehicle is determined to be stopped. The preset conditions include: there are continuous near-zero speed trajectory points with speeds less than a preset speed threshold, and the number of near-zero speed trajectory points is not less than a preset number; among all trajectory points, the trajectory point with the smallest acceleration value has an acceleration less than a preset acceleration threshold; and the standard deviation of the acceleration of all trajectory points is less than a preset stability threshold.

[0074] Furthermore, when determining the parking status of a vehicle based on its parking duration, the aforementioned parking status determination module 230 is specifically used for: If the parking time falls within the time range corresponding to the first preset time and the second preset time, the parking status is determined to be complete parking. If the parking time exceeds the second preset time, the parking status is determined to be compliant parking; If the parking duration is less than the first preset duration, the parking status is determined to be illegal parking.

[0075] Furthermore, the aforementioned parking duration is determined based on the following method: Get the timestamp corresponding to the first near-zero speed trajectory point in the continuous near-zero speed trajectory points data in the event window, and determine it as the parking start time; The vehicle's current speed is continuously monitored, and the timestamp corresponding to the trajectory point where the speed first exceeds the preset exit speed threshold is obtained and determined as the parking end time. The difference between the parking end time and the parking start time is the parking duration.

[0076] Furthermore, whether the aforementioned vehicles entered the intersection is determined based on the following methods: Obtain the target polygon corresponding to the monitoring area of ​​the intersection. The target polygon is formed by extending the four parking lines corresponding to the monitoring area outward by a preset distance. Based on the vehicle's current trajectory points, the ray-mapping method is used to detect whether the vehicle is within the target polygon. If so, it is determined that the vehicle has entered the intersection.

[0077] Furthermore, whether the aforementioned vehicles are traveling in the same direction as the main traffic flow at the intersection is determined based on the following method: Obtain the vehicle's current heading angle; Calculate the angle difference between the current heading angle and the main traffic direction at the intersection; If the absolute value of the angle difference is less than the preset angle threshold, the vehicle's driving direction is consistent with the corresponding traffic direction at the intersection; otherwise, they are not.

[0078] Furthermore, after determining the vehicle's parking status, the aforementioned device also includes: The early warning module is used to record the vehicle's compliance with parking rules when the parking status is complete; when the parking status is compliant, it triggers a level one early warning, generates positive feedback information and pushes it to the vehicle's on-board terminal; when the parking status is illegal parking, it triggers a level two early warning, generates early warning information and pushes it to the vehicle's on-board terminal.

[0079] The automatic vehicle intersection parking status detection device of the present invention can execute the automatic vehicle intersection parking status detection method provided in the present invention. The implementation principle is similar. The actions performed by each module and unit in the automatic vehicle intersection parking status detection device in each embodiment of the present invention correspond to the steps in the automatic vehicle intersection parking status detection method in each embodiment of the present invention. For detailed functional descriptions of each module of the automatic vehicle intersection parking status detection device, please refer to the descriptions in the corresponding automatic vehicle intersection parking status detection methods shown above, which will not be repeated here.

[0080] The aforementioned automatic vehicle intersection parking status detection device can be a computer program (including program code) running on a computer device, such as an application software; the device can be used to execute the corresponding steps in the method provided in the embodiments of the present invention.

[0081] In some embodiments, the automatic vehicle intersection parking status detection device provided in this invention can be implemented using a combination of hardware and software. As an example, the automatic vehicle intersection parking status detection device provided in this invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the automatic vehicle intersection parking status detection method provided in this invention. For example, the processor in the form of a hardware decoding processor can be one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0082] In other embodiments, the automatic vehicle parking status detection device at intersections provided in this invention can be implemented in software. Figure 3 An automatic vehicle intersection parking status detection device stored in a memory is shown. It can be software in the form of programs and plug-ins, and includes a series of modules, including an acquisition module 210, a parking judgment module 220 and a parking status judgment module 230, for implementing the automatic vehicle intersection parking status detection method provided in the embodiments of the present invention.

[0083] The modules described in the embodiments of the present invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0084] Based on the same principles as the methods shown in the embodiments of the present invention, the embodiments of the present invention also provide an electronic device, which may include, but is not limited to: a processor and a memory; the memory for storing computer programs; and the processor for executing the methods shown in any embodiment of the present invention by invoking the computer programs.

[0085] In one alternative embodiment, an electronic device is provided, such as Figure 4 As shown, Figure 4 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0086] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0087] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0088] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0089] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0090] Among these, electronic devices can also be terminal devices. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0091] This invention provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0092] According to another aspect of the present invention, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various embodiments described above.

[0093] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0094] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0095] The computer-readable storage medium provided in this invention can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0096] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0097] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. A method for automatically detecting the parking status of vehicles at intersections, characterized in that, include: When a vehicle is detected entering the intersection, multiple consecutive trajectory points, including the current trajectory point of the vehicle, are acquired to form event window trajectory point data. Based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data, determine whether the vehicle has stopped; When a vehicle is determined to be parked and its direction of travel is consistent with the main traffic direction at the intersection, the parking status of the vehicle is determined based on the duration of its parking.

2. The method according to claim 1, characterized in that, The step of determining whether the vehicle has stopped based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data includes: If the event window trajectory point data simultaneously meet the following preset conditions, the vehicle is determined to be stopped. The preset conditions include: there are continuous near-zero speed trajectory points with speeds less than a preset speed threshold, and the number of near-zero speed trajectory points is not less than a preset number; among all trajectory points, the trajectory point with the smallest acceleration value has an acceleration less than a preset acceleration threshold; and the standard deviation of the acceleration of all trajectory points is less than a preset stability threshold.

3. The method according to claim 1, characterized in that, Determining the parking status of a vehicle based on its parking duration includes: If the parking duration falls within the time range corresponding to the first preset duration and the second preset duration, the parking status is determined to be complete parking. If the parking duration exceeds the second preset duration, the parking status is determined to be compliant parking; If the parking duration is less than the first preset duration, the parking status is determined to be illegal parking.

4. The method according to claim 2, characterized in that, The parking duration is determined based on the following method: Obtain the timestamp corresponding to the first near-zero speed trajectory point in the continuous near-zero speed trajectory points in the event window trajectory point data, and determine it as the parking start time; The vehicle's current speed is continuously monitored, and the timestamp corresponding to the trajectory point where the speed first exceeds the preset exit speed threshold is obtained and determined as the parking end time. The difference between the parking end time and the parking start time is the parking duration.

5. The method according to claim 1, characterized in that, Whether a vehicle has entered the intersection is determined based on the following methods: Obtain the target polygon corresponding to the monitoring area of ​​the intersection. The target polygon is formed by extending the four parking lines corresponding to the monitoring area outward by a preset distance. Based on the vehicle's current trajectory point, the ray-mapping method is used to detect whether the vehicle is within the target polygon. If so, it is determined that the vehicle has entered the intersection.

6. The method according to claim 1, characterized in that, Whether the vehicle's direction of travel is consistent with the main traffic direction corresponding to the intersection is determined based on the following method: Obtain the current heading angle of the vehicle; Calculate the angle difference between the current heading angle and the main traffic direction at the intersection; If the absolute value of the included angle difference is less than a preset angle threshold, then the vehicle's driving direction is consistent with the traffic direction corresponding to the intersection; otherwise, they are not.

7. The method according to claim 3, characterized in that, After determining the parking status of the vehicle, the process also includes: When the parking status is complete parking, the vehicle's compliance with parking rules for this instance is recorded; When the parking status is compliant parking, a level one warning is triggered, and positive feedback information is generated and pushed to the vehicle's on-board terminal; When the parking status is illegal parking, a level two warning is triggered, and a warning message is generated and pushed to the vehicle's on-board terminal.

8. An automatic vehicle parking status detection device at an intersection, characterized in that, include: The acquisition module is used to acquire multiple continuous trajectory points, including the current trajectory point of the vehicle, when a vehicle is detected entering the intersection, to form event window trajectory point data. The parking determination module is used to determine whether the vehicle is parked based on the velocity, acceleration, and jerk of each trajectory point in the event window trajectory point data. The parking status determination module is used to determine the parking status of a vehicle based on its parking duration when the vehicle is determined to be parked and the vehicle's travel direction is consistent with the main traffic direction corresponding to the intersection.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-7.

Images