A big data-based vehicle turning and staying event detection method and device

Abstract

This invention relates to the field of big data analytics, and discloses a method and device for detecting vehicle turning and stopping events based on big data. A positioning device is installed on the vehicle, and this device uploads the vehicle's trajectory point data every set time interval t. An algorithm calculates the trajectory point data to determine whether a stopping event has occurred before the vehicle turns. The invention also discloses a storage medium storing a big data-based vehicle turning and stopping event detection program. When executed by a processor, this program implements the big data-based vehicle turning and stopping event detection method described above. This invention, by installing a positioning device on the vehicle, which records and uploads vehicle trajectory point data in real time, and using this data to calculate and determine whether a stopping event has occurred before the vehicle turns, has advantages such as high calculation speed and high accuracy, greatly improving the safe driving performance of trucks.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, and in particular to a method for detecting vehicle turning and stopping events based on big data. Background Technology

[0002] Visibility is limited within factory areas, especially for trucks. A brief stop before turning allows them to observe their surroundings and ensure they don't collide with oncoming vehicles or pedestrians. Therefore, for safety, many freight companies encourage truck drivers to make brief stops before turning. Current technology uses video recognition to detect these pre-turn stops. However, video is composed of consecutive frames, meaning video recognition is essentially image recognition. The differences between frames are minimal, as are the differences between frames showing brief stops and those without. Therefore, identifying pre-turn stops using images is extremely difficult, computationally intensive, and lacks accuracy.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a vehicle turning and stopping event detection method based on big data. By installing a positioning device on the vehicle, the positioning device records the vehicle's trajectory point data and uses this data to calculate and determine whether a stopping event has occurred before the vehicle turns. This method has the advantages of fast calculation speed and high accuracy, which greatly improves the safe driving performance of trucks.

[0005] To achieve the above objectives, the present invention provides a method for detecting vehicle turning and stopping events based on big data. A positioning device is installed on the vehicle, and the positioning device uploads the vehicle's trajectory point data every set time t. An algorithm is used to calculate the trajectory point data to determine whether a stopping event has occurred before the vehicle turns.

[0006] Optionally, the trajectory point data includes device ID, timestamp, speed, and course. The step of calculating and determining whether a stop event occurred before the vehicle turned using the trajectory point data includes:

[0007] S1. Collect trajectory point data P for each device in the last two hours: P = (ID, T, S, C), where ID represents the device number, T represents the timestamp at a certain moment, S represents the vehicle's speed at that moment, C represents the vehicle's heading at that moment, and P represents the trajectory point data at that moment.

[0008] S2. When the set time t is 2 seconds, each device has 3600 trajectory point data. The 3600 trajectory point data are sorted in ascending order using the timestamp T in the trajectory point P to obtain array B = [P1, P2, P3, P4, ..., P3599, P3600].

[0009] S3. Set the time from the brief pause before the turn to the completion of the turn as t. 停 When t 停 = 50 seconds, divide array B into 144 smaller arrays in an orderly manner, with 25 trajectory points in each smaller array. Let b1 = [P1, P2, P3, ..., P25] represent the first smaller array, b2 = [P26, P27, P28, ..., P50] represent the second smaller array, and so on, with b144 = [P3576, P3577, P3578, ..., P3600] representing the last smaller array.

[0010] S4. Loop through the first subarray b1 and compare the first point P1 with each of the subsequent trajectory points P2, P3, P4, ... P25. Determine whether a stop event has occurred based on the set judgment conditions.

[0011] S5. After looping through the small array b1, if a record of turning without stopping is found, store the four fields of device ID, start time T1, end time Ti, and not stopping into the database.

[0012] S6. For the other subarrays b2, b3, b4...b144, perform the calculations according to the logic of S4 and S5.

[0013] S7. Once all the subarrays have been traversed, the traversal of the device is complete, and all records of turning without stopping have been found. The same method can be used to explore other devices.

[0014] Optionally, it also includes S8, an optimization of step S4: In the trajectory points of the subarray bn, if the heading change is greater than 90°, the time change is greater than 20 seconds, and the speed of each point is greater than 5km / h, then check the last 7 trajectory points in the previous subarray bn-1. If there is a trajectory point with a speed less than 5km / h among these 7 trajectory points, it means that the vehicle stopped while turning; otherwise, the vehicle did not stop while turning, where 2≤n≤144.

[0015] Optionally, the determination conditions in S4 include: ① When the heading change Ci-C1>=90°, where Ci represents the heading of a later point and C1 represents the heading of the first point; and Ti-T1>20, where Ti represents the timestamp of a later point and C1 represents the timestamp of the first point; and the speed of each point from P1 to Pi is greater than 5km / h, it indicates that the vehicle did not stop during the turn from P1 to Pi; ② When the heading change Ci-C1>=90°; and Ti-T1>20; and the speed of some points from P1 to Pi is less than 5km / h, it indicates that the vehicle stopped during the turn from P1 to Pi; ③ When the heading change Ci-C1<90°, the vehicle did not turn, and determinations ① and ② are not required.

[0016] Optionally, if either condition ① or ② occurs during the loop, the loop traversal of subarray b1 is terminated, and the loop traversal of the next subarray b2 begins.

[0017] Optionally, if condition ③ is met during the loop, the second point P2 is compared with each of its subsequent trajectory points P3, P4, P5, ..., P25 one by one. The calculation logic is the same as that for the first point P1, and so on, until either of the conditions ① or ② occurs or the last point P25 has been traversed, at which point the loop traversal of the subarray b1 is terminated.

[0018] Optionally, the vehicle is a truck.

[0019] Furthermore, to achieve the above objectives, the present invention also proposes a vehicle turning and stopping event detection device based on big data, comprising: a memory, a processor, and a vehicle turning and stopping event detection program based on big data stored in the memory and executable on the processor, wherein the vehicle turning and stopping event detection program based on big data is configured to implement the vehicle turning and stopping event detection method based on big data as described above.

[0020] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a vehicle turning and stopping event detection program based on big data. When the vehicle turning and stopping event detection program based on big data is executed by a processor, it implements the vehicle turning and stopping event detection method based on big data as described above.

[0021] Beneficial effects: This invention, by installing a positioning device on the vehicle, records and uploads the vehicle's trajectory point data in real time. The trajectory point data is used to calculate and determine whether a stop event occurs before the vehicle turns. It has the advantages of fast calculation speed and high accuracy, which greatly improves the safe driving performance of trucks. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the structure of a fine-grained permission access synchronization device based on an isolated network in the hardware operating environment involved in the embodiments of the present invention;

[0023] Figure 2 This is a flowchart illustrating an embodiment of the vehicle turning and stopping event detection method based on big data according to the present invention.

[0024] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0025] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0026] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a vehicle turning and stopping event detection device based on big data, which is part of the hardware operating environment involved in the embodiments of the present invention.

[0027] like Figure 1 As shown, the vehicle turning and stopping event detection device based on big data may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0028] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the vehicle turning and stopping event detection device based on big data, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0029] like Figure 1As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a vehicle turning and stopping event detection program based on big data.

[0030] exist Figure 1 In the big data-based vehicle turning and stopping event detection device shown, the network interface 1004 is mainly used for data communication with the network node packaging device; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the big data-based vehicle turning and stopping event detection device of the present invention can be set in the big data-based vehicle turning and stopping event detection device. The big data-based vehicle turning and stopping event detection device calls the big data-based vehicle turning and stopping event detection program stored in the memory 1005 through the processor 1001 and executes the big data-based vehicle turning and stopping event detection method provided in the embodiment of the present invention.

[0031] Based on the above hardware structure, an embodiment of the vehicle turning and stopping event detection method based on big data of the present invention is proposed.

[0032] Reference Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the vehicle turning and stopping event detection method based on big data according to the present invention.

[0033] In this embodiment, the vehicle turning and stopping event detection method based on big data includes the following steps:

[0034] Step S10: Install a positioning device on the vehicle. In this embodiment, the positioning device records and uploads the vehicle's trajectory point data. The trajectory point data is used to calculate and determine whether a stopping event occurs before the vehicle turns, thereby effectively monitoring whether the truck driver stops before turning, which greatly improves the driving safety of the truck.

[0035] The trajectory point data includes device ID, timestamp, speed, and course.

[0036] This embodiment uses vehicle parameter data from four dimensions—device ID, timestamp, speed, and course—to determine whether a stop event occurred before the vehicle turns.

[0037] Step S20: The positioning device uploads the vehicle's trajectory point data every set time t.

[0038] Step S30: The algorithm calculates trajectory point data to determine whether a stopping event occurred before the vehicle turned.

[0039] In the specific implementation, the determination of whether a stop event occurred before the vehicle turns is made using the device ID, timestamp, speed, and course, including the following steps:

[0040] S1. Collect trajectory point data P for each device in the last two hours: P = (ID, T, S, C), where ID represents the device number, T represents the timestamp at a certain moment, S represents the vehicle's speed at that moment, C represents the vehicle's heading at that moment, and P represents the trajectory point data at that moment.

[0041] S2. When the set time t is 2 seconds, each device has 3600 trajectory point data. The 3600 trajectory point data are sorted in ascending order using the timestamp T in the trajectory point P to obtain array B = [P1, P2, P3, P4, ..., P3599, P3600].

[0042] S3. Set the time from the brief pause before the turn to the completion of the turn as t. 停 When t 停 = 50 seconds, divide array B into 144 smaller arrays in an orderly manner, with 25 trajectory points in each smaller array. Let b1 = [P1, P2, P3, ..., P25] represent the first smaller array, b2 = [P26, P27, P28, ..., P50] represent the second smaller array, and so on, with b144 = [P3576, P3577, P3578, ..., P3600] representing the last smaller array.

[0043] S4. Iterate through the first subarray b1, comparing the first point P1 with each subsequent trajectory point P2, P3, P4, ..., P25, and determine whether a stop event has occurred based on the set judgment conditions. The judgment conditions in S4 include: ① When the heading change Ci-C1>=90°, where Ci represents the heading of a later point and C1 represents the heading of the first point; and Ti-T1>20, where Ti represents the timestamp of a later point and C1 represents the timestamp of the first point; and the speed of each point from P1 to Pi is greater than 5km / h, it means that the vehicle did not stop during the turn from P1 to Pi; ② When the heading change Ci-C1>=90°; and Ti-T1>20; and the speed of some points from P1 to Pi is less than 5km / h, it means that the vehicle stopped during the turn from P1 to Pi; ③ When the heading change Ci-C1<90°, the vehicle did not turn, and judgments ① and ② are not required.

[0044] It should be noted that if either condition ① or ② occurs during the loop, the loop will terminate the iteration of subarray b1 and begin the iteration of the next subarray b2.

[0045] If condition ③ is met during the loop, then the second point P2 is compared with each of its subsequent trajectory points P3, P4, P5, ..., P25 one by one. The calculation logic is the same as that for the first point P1, and so on, until either of the conditions ① or ② occurs or the last point P25 has been traversed, at which point the loop traversal of the small array b1 is terminated.

[0046] Specifically, the vehicle in question is a truck.

[0047] S5. After looping through the small array b1, if a record of turning without stopping is found, store the four fields of device ID, start time T1, end time Ti, and not stopping into the database.

[0048] S6. For the other subarrays b2, b3, b4...b144, perform the calculations according to the logic of S4 and S5.

[0049] S7. Once all the subarrays have been traversed, the traversal of the device is complete, and all records of turning without stopping have been found. The same method can be used to explore other devices.

[0050] S8. In the trajectory points of the subarray bn, if the heading change is greater than 90°, the time change is greater than 20 seconds, and the speed of each point is greater than 5 km / h, then check the last 7 trajectory points in the previous subarray bn-1. If there is a trajectory point with a speed less than 5 km / h among these 7 trajectory points, it means that the vehicle stopped while turning; otherwise, the vehicle did not stop while turning, where 2≤n≤144.

[0051] It should be noted that when the vehicle stops far from the turning intersection, the algorithm may detect that the vehicle has not stopped while turning, which may result in a false judgment. Therefore, for each subarray after b1, if the vehicle has turned and the speed of all trajectory points is greater than 5km / h, the algorithm needs to go back to the previous subarray and observe its last 7 points to optimize the calculation logic in step S4 and ensure that the vehicle has not actually stopped.

[0052] Understandably, this embodiment divides the trajectory data into 144 small arrays through the above steps. These 144 small arrays are sorted according to timestamps, and are not only globally ordered but also ordered within the small arrays. Each small array contains 50 seconds of driving trajectory points. Suppose we take the 100th small array, which contains 25 positioning points. These positioning points are sorted by timestamp from smallest to largest. The algorithm detects that the heading of these 25 points has changed and is greater than or equal to 90°. At this point, we consider that the truck has turned in this small array. However, we do not detect any points with a speed less than 5 km / h in these 25 points. But it is possible that there are points with a speed less than 5 km / h before this small array. In this case, we need to check if there are any points with a speed less than 5 km / h in the last 7 points of the 99th small array. If there are, it means that the truck has stopped; otherwise, it has not stopped.

[0053] This embodiment, based on the above steps, can detect whether each vehicle has stopped before turning. Verified with real data, the algorithm performs exceptionally well, achieving an accuracy rate of 99.96%, and its calculation speed is extremely fast. It fully meets the design requirements for safety monitoring in vehicle operation systems, significantly improving the safe driving performance of trucks.

[0054] Furthermore, this embodiment of the invention also proposes a storage medium storing a vehicle turning and stopping event detection program based on big data. When the vehicle turning and stopping event detection program based on big data is executed by a processor, it implements the steps of the vehicle turning and stopping event detection method based on big data as described above.

[0055] Since this storage medium adopts all the technical solutions of the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0056] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0057] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0058] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0059] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, node packaging device, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0060] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for detecting vehicle turning and stopping events based on big data, characterized in that, The method includes the following steps: A positioning device is installed on the vehicle. The positioning device uploads the vehicle's trajectory data every set time interval t. The algorithm calculates trajectory point data to determine whether a vehicle stopped before turning; The trajectory point data includes device ID, timestamp, speed, and course. The steps for calculating and determining whether a stop event occurred before the vehicle turned using the trajectory point data include: S1. Collect trajectory point data P for each device in the last two hours: P = (ID, T, S, C), where ID represents the device number, T represents the timestamp at a certain moment, S represents the vehicle's speed at that moment, C represents the vehicle's heading at that moment, and P represents the trajectory point data at that moment. S2. When the set time t is 2 seconds, each device has 3600 trajectory point data. The 3600 trajectory point data are sorted in ascending order using the timestamp T in the trajectory point P to obtain array B = [P1, P2, P3, P4, ..., P3599, P3600]. S3. Set the time from the brief pause before the turn to the completion of the turn as t. 停 When t 停 = 50 seconds, divide array B into 144 smaller arrays in an orderly manner, with 25 trajectory points in each smaller array. Let b1 = [P1, P2, P3, ..., P25] represent the first smaller array, b2 = [P26, P27, P28, ..., P50] represent the second smaller array, and so on, with b144 = [P3576, P3577, P3578, ..., P3600] representing the last smaller array. S4. Loop through the first subarray b1 and compare the first point P1 with each of the subsequent trajectory points P2, P3, P4, ... P25. Determine whether a stop event has occurred based on the set judgment conditions. S5. After looping through the small array b1, if a record of turning without stopping is found, store the four fields of device ID, start time T1, end time Ti, and not stopping into the database. S6. For the other subarrays b2, b3, b4...b144, perform the calculations according to the logic of S4 and S5. S7. Once all the subarrays have been traversed, the traversal of the device is complete, and all records of turning without stopping have been found. The same method is used to explore other devices. S8. Optimization of step S4: In the trajectory points of the subarray bn, if the heading change is greater than 90°, the time change is greater than 20 seconds, and the speed of each point is greater than 5km / h, then check the last 7 trajectory points in the previous subarray bn-1. If there is a trajectory point with a speed less than 5km / h among these 7 trajectory points, it means that the vehicle stopped while turning; otherwise, the vehicle did not stop while turning, where 2≤n≤144; The judgment conditions in S4 include: ① When the heading change Ci-C1>=90°, where Ci represents the heading of a later point, and C1 represents the heading of the first point; Furthermore, if Ti-T1>20, where Ti represents the timestamp of a later point and C1 represents the timestamp of the first point; and if the speed of each point from P1 to Pi is greater than 5km / h, then the vehicle did not stop during the turn from P1 to Pi; ② If the heading change Ci-C1>=90; and Ti-T1>20; and if the speed of some points from P1 to Pi is less than 5km / h, then the vehicle stopped during the turn from P1 to Pi; ③ If the heading change Ci-C1<90°, then the vehicle did not turn, and the judgments in ① and ② are not required.

2. The vehicle turning and stopping event detection method based on big data as described in claim 1, characterized in that, If either condition ① or ② occurs during the loop, the loop will terminate and the iteration of the subarray b1 will begin, starting the iteration of the next subarray b2.

3. The vehicle turning and stopping event detection method based on big data as described in claim 1, characterized in that, If condition ③ is met during the loop, then the second point P2 is compared with each of its subsequent trajectory points P3, P4, P5, ..., P25 one by one. The calculation logic is the same as that for the first point P1, and so on, until either of the conditions ① or ② occurs or the last point P25 has been traversed, at which point the loop traversal of the small array b1 is terminated.

4. The vehicle turning and stopping event detection method based on big data as described in claim 1, characterized in that, The vehicle in question is a truck.

5. A vehicle turning and stopping event detection device based on big data, characterized in that, include: The system includes a memory, a processor, and a big data-based vehicle turning and stopping event detection program stored in the memory and executable on the processor, the big data-based vehicle turning and stopping event detection program being configured to implement the big data-based vehicle turning and stopping event detection method as described in any one of claims 1 to 4.

6. A storage medium, characterized in that, The storage medium stores a vehicle turning and stopping event detection program based on big data. When the big data-based vehicle turning and stopping event detection program is executed by the processor, it implements the vehicle turning and stopping event detection method based on big data as described in any one of claims 1 to 4.

Images