Intelligent highway time synchronization information fusion method and device using cache mechanism

Abstract

The application provides a smart road time synchronization information fusion method and device using a cache mechanism, which comprises the following steps: 1) clock calibration is performed on all sensing devices; 2) a vehicle target is detected, sensing data and sensing time are recorded, and transmission is performed; 3) the time delay of each sensing device is calculated by receiving data and recording the receiving time, and the comprehensive cache time T is obtained; 4) a data cache space is constructed; 5) a request is sent at time t, and the data pipeline can transmit the data belonging to the range of [t-T, t] back and store it in the data cache space; 6) the information at time t-T is read, and the fusion processing of the multi-source heterogeneous sensing data at time t is completed; 7) if the time delay of a certain device exceeds the set T, an alarm is sent. The application can effectively solve the data loss caused by data integration and network congestion in the smart road environment, avoid the error information fusion caused by data receiving delay, and improve the accuracy and reliability of traffic information in the smart road environment.

Description

Technical Field

[0001] This invention relates to the field of smart highways under intelligent transportation, and in particular to a method and apparatus for fusion of time synchronization information of smart highways utilizing a caching mechanism. Background Technology

[0002] As traditional road construction systems mature, smart highways have become a crucial opportunity for their transformation and upgrading. In a smart highway environment, the fusion and processing of sensory information from different devices with varying spatiotemporal dimensions is a critical prerequisite for realizing the various functions of a smart highway. Therefore, information fusion technology for smart highways is a pressing challenge that needs to be overcome.

[0003] The core element of smart highways lies in the use of data. The perception, transmission, and processing of vehicle target information on the road are essential steps to obtain accurate data. In particular, when different devices take different times to process and generate structured data, and when data transmission networks take different times, the system may not be able to receive the current perception data in real time, affecting the fusion of multi-source heterogeneous data and thus causing data errors. Summary of the Invention

[0004] The problem to be solved by the present invention is to provide a smart highway time synchronization information fusion method and device that utilizes a caching mechanism to address the difficulties of existing information fusion technology. This method can effectively solve the problem of asynchrony in the reception of different types of data and improve the fusion accuracy of multi-source heterogeneous information.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] The first aspect provides a method for fusing time synchronization information of smart highways using a caching mechanism, including:

[0007] Time synchronization of all sensing devices and information computing systems;

[0008] The system acquires and processes information about vehicle targets within the detection range, records the detection time of the vehicle targets, and transmits the timestamp, location, and speed information over the network in the form of data packets.

[0009] Based on the data packets received, the receiving time, and the sensing time within a certain period, the latency of each sensing device is statistically analyzed, and the overall buffer duration T is calculated.

[0010] A data cache space is constructed based on the comprehensive cache duration T and the current time. At time t, a data request is sent to the data pipeline to store the data whose perception time belongs to the corresponding data cache space. At time t, data with perception time tT is extracted from the data cache space, and a fusion algorithm for multi-source heterogeneous data is executed to obtain the fused traffic information.

[0011] In one implementation, time synchronization is performed on all sensing devices and information computing systems, including:

[0012] Within a local area network, clock calibration is performed on all sensing devices and information computing systems using NTP servers, GPS, or BeiDou time synchronization to ensure that the time of all sensing devices and information computing systems remains synchronized.

[0013] In one implementation, the latency of each sensing device is statistically analyzed based on the type, reception time, and time range of the received data packets, including:

[0014] Based on the received data packets, retrieve any sensing device and list the data acquisition latency of that device:

[0015]

[0016] Among them, t kj Let t represent the time delay sequence of each target information sensed by the j-th device of the k-th type of sensing device; different values ​​of k represent different types of sensing devices, including microwave radar, lidar, fiber optics, and license plate recognition devices; ri -t ci This represents the latency of sensing the i-th target information by a certain device. Let mj be the sensing time of the mj-th target information on the j-th device. Indicates the time of receiving the target information; m j This represents the mj-th target perceived by the j-th device;

[0017] The latency values ​​of all devices belonging to the same sensing type were compiled, and the data latency statistics of microwave radar, lidar, fiber optic, and license plate recognition systems were obtained separately. The latency values ​​were then arranged in ascending order.

[0018] t k =sort(t k1 ,t k2 ,…,t kj ,…,t kn )

[0019] Among them, t k Let t represent the increasing time delay sequence of all target information sensed by the k-th type of sensing device, sort(·) represent the sorting function, n represent the total number of devices belonging to the k-th type of sensing device, and t represent the time delay sequence of all target information sensed by the k-th type of sensing device. k1 t kn Let be the time delay values ​​of the 1st and nth devices in the kth type of sensing devices;

[0020] Based on the data latency values ​​of various sensing devices, the latency value at the 95th percentile is taken as the overall latency value for that type of sensing device.

[0021]

[0022] Among them, t k-95 Indicates from t k The delay value at the 95th percentile is extracted from the data, and floor(·) is the floor function; t 1-95 t 2-95 t 3-95 and t 4-95 These represent the overall latency values ​​of microwave radar, lidar, fiber optic, and license plate recognition devices, respectively.

[0023] In one implementation, the overall cache duration T is calculated as follows:

[0024] T = max(t) 1-95 ,t 2-95 ,t 3-95 ,t 4-95 )

[0025] Here, max(·) represents taking the maximum value.

[0026] In one implementation, a data cache space is constructed based on the overall cache duration T and the current time, including:

[0027] Using the overall cache duration T as the width of the time window, the current time t as the end point of the time window, and time tT as the start point of the time window, a data cache space that can accommodate perceived information within the range of tT to t is constructed.

[0028] In one implementation, at the current time t, the data pipeline receives various types of sensor information sensed at time t, and also receives various types of sensor information sensed in the time period [tT,t) but with a delay in reception.

[0029] In one embodiment, the method further includes:

[0030] If the latency of a certain sensing device is detected to exceed the overall cache duration T, it is assumed that the device has lost data and an alarm is issued. If the overall latency of the device is detected to be less than the overall cache duration T, the time scale of the data cache space is updated.

[0031] Based on the same inventive concept, a second aspect of the present invention provides a smart highway time synchronization information fusion device utilizing a caching mechanism, comprising:

[0032] The time synchronization module is used to synchronize the time of all sensing devices and information computing systems.

[0033] The information perception module is used to acquire and process information about vehicle targets within the detection range, record the perception time of the detected vehicle targets, and transmit the timestamp, location, and speed information over the network in the form of data packets.

[0034] The network transmission module is used to calculate the latency of each sensing device based on the data packets received, the receiving time, and the sensing time within a certain period of time, and to obtain the overall buffer duration T.

[0035] The information fusion module is used to construct a data cache space based on the comprehensive cache duration T and the current time. At time t, it sends a data request to the data pipeline to store the data whose perception time belongs to the corresponding data cache space. At time t, it extracts data with perception time tT from the data cache space and executes a fusion algorithm for multi-source heterogeneous data to obtain the fused traffic information.

[0036] Based on the same inventive concept, a third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method described in the first aspect.

[0037] Based on the same inventive concept, a fourth aspect of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect.

[0038] Compared with the prior art, the advantages and beneficial technical effects of the present invention are as follows:

[0039] (1) Highly practical: This invention makes up for the defects of data loss and abnormal jumps in real-time processing of multi-source heterogeneous data, and provides more accurate information support for smart applications in the smart highway environment.

[0040] (2) Strong stability: The cached information fusion method proposed in this invention, together with the real-time information fusion method, constitutes two parallel schemes of the information fusion system.

[0041] (3) Strong adaptability: When the overall latency of the sensing device or the latency of a certain device changes, the information fusion module can adjust and optimize itself. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of the intelligent highway time synchronization information fusion method utilizing a caching mechanism provided in an embodiment of the present invention.

[0044] Figure 2 This is a schematic diagram of the cache structure design of a smart highway time synchronization information fusion method utilizing a caching mechanism in an embodiment of the present invention;

[0045] Figure 3 This is a flowchart of a delay detection method for a smart highway time synchronization information fusion method utilizing a caching mechanism, as described in an embodiment of the present invention.

[0046] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0048] The purpose of this invention is to provide a smart highway time synchronization information fusion method that utilizes a caching mechanism to overcome data loss caused by time asynchrony and reduce information fusion errors.

[0049] The main idea of ​​this invention is as follows: Under the premise of system clock calibration for all sensing devices on the smart highway, the latency statistics submodule calculates the latency of each device based on the received data packets within a certain time period, compiles the latency of each type of sensor, and then calculates the comprehensive buffer duration T as the time scale of the data buffer space. The data buffer space uses the current time t as the upper limit of the time window and time tT as the lower limit of the time window, storing sensing data within the range of [tT, t] for sensing times, enabling the waiting reception of delayed data. At time t, the information fusion module reads the data from time tT from the buffer space, executes the information fusion algorithm for multi-source heterogeneous data, and outputs the expected traffic information. Similarly, when proceeding to the next time t+δ, the data buffer space stores sensing data within the range of [t+δt-T, t+δt] for sensing times, and the information fusion module executes the information fusion algorithm on the multi-source heterogeneous data at time t+δt-T.

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Example 1

[0052] This invention provides a method for fusing time synchronization information of smart highways using a caching mechanism, including:

[0053] Time synchronization of all sensing devices and information computing systems;

[0054] The system acquires and processes information about vehicle targets within the detection range, records the detection time of the vehicle targets, and transmits the timestamp, location, and speed information over the network in the form of data packets.

[0055] Based on the type, reception time, and time range of the received data packets, the latency of each sensing device is statistically analyzed, and the overall buffer duration T is calculated.

[0056] A data cache space is constructed based on the comprehensive cache duration T and the current time. At time t, a data request is sent to the data pipeline to store the data whose perception time belongs to the corresponding data cache space. At time t, data with perception time tT is extracted from the data cache space, and a fusion algorithm for multi-source heterogeneous data is executed to obtain the fused traffic information.

[0057] In practice, the sensing equipment includes all types of sensors such as microwave radar, lidar, fiber optics, and license plate recognition. Acquiring and processing information about vehicle targets mainly refers to acquiring and processing the vehicle's position and speed information.

[0058] Data from each device is transmitted over the network in the form of data packets. The unique characteristics of each data packet include a fixed IP address or the device's own ID. Both IP and ID information are included in the transmitted data packets, and the type of sensor device can be determined by parsing a fixed location field.

[0059] After calculating the latency of each sensing device, the overall buffer duration T is further obtained.

[0060] After a data request is sent to the data pipeline at time t, the data pipeline sends back the accumulated data whose sensing time falls within the interval [tT, t] and stores it in the data cache space. Then, the data with sensing time tT can be extracted and then fused.

[0061] In one implementation, time synchronization is performed on all sensing devices and information computing systems, including:

[0062] Within a local area network, clock calibration is performed on all sensing devices and information computing systems using NTP servers, GPS, or BeiDou time synchronization to ensure that the time of all sensing devices and information computing systems remains synchronized.

[0063] In practice, clock calibration involves using an NTP server to calibrate the clock systems of roadside microwave radar, roadside lidar, road surface fiber optic cables, and license plate recognition systems all located within the same local area network. Alternatively, GPS or BeiDou time synchronization can be used to calibrate all sensing devices, while simultaneously calibrating the clock system of the information computing system. The aim is to ensure that the clocks of all sensing devices and the information computing system are consistent, guaranteeing that the intervals at which various devices perceive information are identical. The information computing system is a server system that includes an information fusion module.

[0064] In one implementation, the latency of each sensing device is statistically analyzed based on the type, reception time, and time range of the received data packets, including:

[0065] Based on the received data packets, retrieve any sensing device and list the data acquisition latency of that device:

[0066]

[0067] Among them, t kj Let t represent the time delay sequence of each target information sensed by the j-th device of the k-th type of sensing device; different values ​​of k represent different types of sensing devices, including microwave radar, lidar, fiber optics, and license plate recognition devices; ri -t ci This represents the latency of sensing the i-th target information by a certain device. Let mj be the sensing time of the mj-th target information on the j-th device. Indicates the time of receiving the target information; m j This represents the mj-th target perceived by the j-th device;

[0068] The latency values ​​of all devices belonging to the same sensing type were compiled, and the data latency statistics of microwave radar, lidar, fiber optic, and license plate recognition systems were obtained separately. The latency values ​​were then arranged in ascending order.

[0069] t k =sort(t k1 ,t k2 ,…,t kj ,…,t kn )

[0070] Among them, t k Let t represent the increasing time delay sequence of all target information sensed by the k-th type of sensing device, sort(·) represent the sorting function, n represent the total number of devices belonging to the k-th type of sensing device, and t represent the time delay sequence of all target information sensed by the k-th type of sensing device. k1 t kn Let be the time delay values ​​of the 1st and nth devices in the kth type of sensing devices;

[0071] Based on the data latency values ​​of various sensing devices, the latency value at the 95th percentile is taken as the overall latency value for that type of sensing device.

[0072]

[0073] Among them, t k-95 Indicates from t k The delay value at the 95th percentile is extracted from the data, and floor(·) is the floor function; t 1-95 t 2-95 t 3-95 and t 4-95 These represent the overall latency values ​​of microwave radar, lidar, fiber optic, and license plate recognition devices, respectively.

[0074] Specifically, the latency consists of two parts: the time consumed by the sensing device to process and generate structured information such as position and velocity, and the time consumed by the network to transmit data packets. The latency of each target information is calculated as the difference between the sensing time and the receiving time.

[0075] In one implementation, the overall cache duration T is calculated as follows:

[0076] T = max(t) 1-95 ,t 2-95 ,t 3-95 ,t 4-95 )

[0077] Here, max(·) represents taking the maximum value.

[0078] To ensure that the information fusion module can receive the sensing data from different sensors and devices and to minimize data loss due to delays, the overall latency level representing all sensing data, i.e., the comprehensive buffer duration T, is calculated using the above formula.

[0079] In one implementation, a data cache space is constructed based on the overall cache duration T and the current time, including:

[0080] Using the overall cache duration T as the width of the time window, the current time t as the end point of the time window, and time tT as the start point of the time window, a data cache space that can accommodate perceived information within the range of tT to t is constructed.

[0081] Specifically, at the current time t, the starting point of the time window is tT, and the ending point of the time window is t. The data cache space stores various types of sensing data whose sensing time is within the range of [tT, t]. When updated to a new time t+δt, the time window of the data cache space will be updated to [t+δt-T, t+δt]. According to this rule, the caching time range of the data cache space is constantly changing as time goes by.

[0082] In one implementation, at the current time t, the data pipeline receives various sensor information sensed at time t, and also receives various sensor information sensed during the time interval [tT, t) but with a delay in reception. This avoids the loss of sensed data due to short delays. After receiving the data, the data pipeline extracts all data content and stores it in the data cache space of the information fusion module.

[0083] At the current time t, there might be sensor data from time t that was sensed but not fully stored in the data cache due to delay. The information fusion module doesn't immediately process the data from time t; instead, it extracts the sensed data from time tT from the data cache, performs a multi-source heterogeneous information fusion algorithm on it, and outputs accurate traffic information. Based on the time caching mechanism, information fusion relies on data from past times. Specifically, the information fusion module processes sensed data from a past time, not the sensed data from the current time.

[0084] Among them, the fusion algorithm of multi-source heterogeneous information refers to the multi-sensor data fusion method, such as estimation algorithms (weighted average, Kalman filter, maximum likelihood estimation), stochastic algorithms (Bayesian theory, DS evidence theory, production rules), artificial intelligence algorithms (neural network, fuzzy logic theory), etc.

[0085] In one embodiment, the method further includes:

[0086] If the latency of a sensor exceeds the overall cache duration T, it is assumed that data loss has occurred, and an alarm is issued indicating a significant latency fault requiring maintenance. If the overall latency of the devices is less than the overall cache duration T, it indicates that data transmission is stabilizing. In this case, the information fusion module will select the newly calculated overall latency as the new overall cache duration and adjust the time scale of the data cache space. In other words, the time scale of the data cache space is updated.

[0087] In the specific implementation process, during the regular testing and maintenance of the information fusion module, if the average latency value of a certain device calculated by the latency statistics submodule exceeds the original set comprehensive buffer duration T, it is considered that there is some data loss in the information fusion system, and the time scale of the existing data buffer space is no longer suitable for the data transmission requirements of the device. The information fusion module will then issue an alarm to remind the user to check the clock system of the device with abnormal latency. If the overall average latency of the device calculated by the latency statistics submodule is lower than the original set comprehensive buffer duration T, it indicates that the performance of the existing sensing data transmission has improved, and the time scale of the data buffer space can be updated to the newly calculated overall average latency of the device.

[0088] The following detailed description, using specific embodiments and accompanying drawings, illustrates a smart highway time synchronization information fusion method utilizing a caching mechanism provided by the present invention. Figures 1 to 3 As shown, Figure 1 This is a schematic diagram of the information fusion method. Figure 2 This is a schematic diagram of the cache structure design; Figure 3 This is a flowchart of the delay detection process for information fusion methods.

[0089] This embodiment discloses a method for fusing time synchronization information of smart highways using a caching mechanism, as detailed below:

[0090] 1) Time synchronization. Before officially activating the information sensing module, network transmission module, and information fusion module, an NTP time server is used to provide unified time synchronization services for data flow hardware such as sensing devices and information computing devices in the local area network environment, ensuring that all hardware systems maintain time synchronization;

[0091] 2) Perception Data Perception. Microwave radar, lidar, and license plate recognition devices are distributed at different nodes on the road to detect vehicle targets within a local area; fiber optics enable the detection of vehicle targets across the entire area. When a vehicle target enters the monitoring range of a sensor, the sensor calculates the vehicle's position, speed, and other information, and simultaneously timestamps the information based on its own clock system.

[0092] 3) Data packet transmission. Each sensing device transmits the real-time vehicle target information it senses in the form of data packets with a fixed structure to the information computing system (including information fusion module, latency statistics submodule, data pipeline and other functional applications) through the local area network;

[0093] 4) Sensor Latency Statistics. The latency statistics submodule accumulates data packets of a certain duration (e.g., 4 hours or 6 hours), calculates the difference between the sensing time and the reception time of the vehicle target information, and compiles the latency information for each sensor and each type of sensor, thereby determining the overall buffer duration. For example, taking fiber optic sensor data as an example, the latency values ​​for fiber optic data are listed below:

[0094] t fiber1 =[500,610,550,720,670,540,450,640,830,680]

[0095] t fiber2 =[630,650,680,620,580,710,750,940,950,870,900,670,630,700]

[0096] Among them, t fiberThese are statistical values ​​for fiber optic latency; the data in rows 1 and 2 represent the time difference between the fiber optic sensing of vehicle information and the receiving of vehicle information on the left and right sides of the road, respectively. The number of latency values ​​represents the number of vehicle target information sensed by the fiber optic cable, and the unit is milliseconds.

[0097]

[0098] Among them, t fiber An increasing time delay sequence of all perceived target information.

[0099]

[0100] Among them, t fiber-95 This represents the 95th percentile delay value of the optical fiber. Combining the statistical delay values ​​of the left and right lanes of the road, the 95th percentile delay of the optical fiber is calculated to be 900 ms.

[0101] Similarly, if we obtain t micwave-95 =1000ms, t lidar-95 =550ms,t license-95 =850ms, then the overall cache duration can be calculated.

[0102] T = max(t) micwave-95 ,t lidar-95 ,t license-95 ,t fiber-95 ) = 1000ms

[0103] 5) Data Cache Space Construction. The comprehensive cache duration T calculated by the latency statistics submodule is used as the time window range. For example, if the current Unix time 1663711201000 (Beijing time: 2022-09-21 06:00:01:000) is used as the upper limit of the time window, then the lower limit of the time window is 1663711200000 (Beijing time: 2022-09-21 06:00:00:000). The data cache space can store sensing data within the sensing time range of [1663711200000, 1663711201000].

[0104] 6) Sensing Data Caching. Taking δt = 200ms, at the current time (Unix time: 1663711201000; Beijing time: 2022-09-21 06:00:01:000), the data cache space will actively access the data pipeline, retrieve the sensing data accumulated in the pipeline with sensing times of 1663711200000, 1663711200200, 1663711200400, 1663711200600, 1663711200800, and 1663711201000, and store them.

[0105] 7) Fusion data extraction. At the current moment (Unix time: 1663711201000; Beijing time: 2022-09-21 06:00:01:000), the information fusion module will read the perception data at the moment of 1663711200000 (Beijing time: 2022-09-21 06:00:00:000) from the data cache space, execute the multi-source heterogeneous data fusion algorithm, and output the accurate information of vehicle targets on the road at the moment of 1663711200000.

[0106] 8) Regular delay detection. When performing regular synchronous time calibration checks on sensing devices and information computing systems, it is also necessary to calculate the overall delay of sensing data. If the overall delay of a certain statistics is lower than the existing comprehensive cache duration, the newly calculated overall delay will be used as the new comprehensive cache duration to construct the data cache space. For example, if the calculated overall delay T average = 800ms < T = 1000ms, a data cache space with a time scale of 800ms will be constructed. If the delay of a certain device detected exceeds the existing comprehensive cache duration, an alarm message will be sent to prompt the repair and debugging of the abnormal device. For example, if t 1j = 1500ms > T = 1000ms, it means that the delay of the j-th device in the microwave radar is abnormal, and a warning message about this device will be sent.

[0107] The present invention discloses a method and device for intelligent highway time synchronization information fusion using a cache mechanism. The device consists of three parts: an information perception module, a network transmission module, and an information fusion module. The specific implementation method includes: 1) Using a local area network to calibrate the clocks of all sensing devices; 2) The sensing device detects a vehicle target, records the perception data and the perception moment, and transmits it through the network; 3) The delay statistics sub-module receives the data and records the reception moment, calculates the delays of each sensing device, and obtains the comprehensive cache duration T; 4) Taking the cache duration T as the time window, with the current moment t as the lower limit and t - T as the upper limit, construct the data cache space; 5) At the moment of t, send a request, and the data pipeline can return the data belonging to the range [t - T, t] and store it in the data cache space; 6) The information fusion module reads the information at the moment of t - T from the data cache space and completes the fusion processing of multi-source heterogeneous sensing data at the moment of t; 7) If the information fusion module detects that the delay of a certain device exceeds the set T, an alarm will be sent to the management platform. The present invention can effectively solve the data loss situation caused by data integration and network congestion in the intelligent highway environment, avoid the wrong information fusion caused by data reception delay, and improve the accuracy and credibility of traffic information in the intelligent highway environment.

[0108] Embodiment 2

[0109] Based on the same inventive concept, this embodiment provides a smart highway time synchronization information fusion device utilizing a caching mechanism, the device comprising:

[0110] The time synchronization module is used to synchronize the time of all sensing devices and information computing systems.

[0111] The information perception module is used to acquire and process information about vehicle targets within the detection range, record the perception time of the detected vehicle targets, and transmit the timestamp, location, and speed information over the network in the form of data packets.

[0112] The network transmission module is used to calculate the latency of each sensor device based on the type, reception time, and time range of the received data packets, and to obtain the overall buffer duration T.

[0113] The information fusion module is used to construct a data cache space based on the comprehensive cache duration T and the current time. At time t, it sends a data request to the data pipeline to store the data whose perception time belongs to the corresponding data cache space. At time t, it extracts data with perception time tT from the data cache space and executes a fusion algorithm for multi-source heterogeneous data to obtain the fused traffic information.

[0114] The network transmission module is mainly used to receive data packets sent by various sensing devices from the information sensing module, and to perform latency statistics of each device and calculate the overall buffer duration through the latency statistics submodule.

[0115] Since the device described in Embodiment 2 of this invention is the same device used in implementing the smart highway time synchronization information fusion method utilizing a caching mechanism in Embodiment 1 of this invention, those skilled in the art can understand the specific structure and variations of this device based on the method described in Embodiment 1 of this invention, and therefore will not be repeated here. All devices used in the method of Embodiment 1 of this invention fall within the scope of protection of this invention.

[0116] Example 3

[0117] Based on the same inventive concept, please refer to Figure 4 The present invention also provides a computer-readable storage medium 300 having a computer program 311 stored thereon, which, when executed, implements the method described in Embodiment 1.

[0118] Since the computer-readable storage medium described in Embodiment 3 of this invention is the same computer-readable storage medium used in implementing the smart highway time synchronization information fusion method utilizing a caching mechanism in Embodiment 1 of this invention, those skilled in the art can understand the specific structure and variations of this computer-readable storage medium based on the method described in Embodiment 1 of this invention, and therefore will not be repeated here. All computer-readable storage media used in the method of Embodiment 1 of this invention fall within the scope of protection of this invention.

[0119] Example 4

[0120] Based on the same inventive concept, this application also provides a computer device, such as... Figure 5 As shown, it includes a memory 401, a processor 402, and a computer program 403 stored in the memory and executable on the processor. When the processor executes the program, it implements the method in Embodiment 1.

[0121] Since the computer device described in Embodiment 4 of this invention is the same computer device used in implementing the intelligent highway time synchronization information fusion method utilizing a caching mechanism in Embodiment 1 of this invention, those skilled in the art can understand the specific structure and variations of this computer device based on the method described in Embodiment 1 of this invention, and therefore will not be repeated here. All computer devices used in the method of Embodiment 1 of this invention fall within the scope of protection of this invention.

[0122] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0124] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0125] Obviously, those skilled in the art can make various modifications and variations to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations to the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention also intends to include these modifications and variations.

Claims

1. A method for fusing time synchronization information in smart highways using a caching mechanism, characterized in that: include: Time synchronization of all sensing devices and information computing systems; The system acquires and processes information about vehicle targets within the detection range, records the detection time of the vehicle targets, and transmits the timestamp, location, and speed information over the network in the form of data packets. Based on the data packets received, the receiving time, and the sensing time within a certain period, the latency of each sensing device is statistically analyzed, and the overall buffer duration T is calculated. A data cache space is constructed based on the comprehensive cache duration T and the current time. At time t, a data request is sent to the data pipeline to store the data whose perception time belongs to the corresponding data cache space. At time t, data with perception time tT is extracted from the data cache space, and a multi-source heterogeneous data fusion algorithm is executed to obtain the fused traffic information. The latency of each sensor device is calculated based on the type, timing, and time range of the received data packets, including: Based on the received data packets, retrieve any sensing device and list the data acquisition latency of that device: in, This represents the time delay sequence of each target information sensed by the j-th device of the k-th type of sensing device; different values ​​of k represent different types of sensing devices, including microwave radar, lidar, fiber optics and license plate recognition devices; This represents the latency of sensing the i-th target information by a certain device. For the j-th device The perception time of target information. Indicates the time when the target information was received; This represents the sensed information of the j-th device. One goal; The latency values ​​of all devices belonging to the same sensing type were compiled, and the data latency statistics of microwave radar, lidar, fiber optic, and license plate recognition systems were obtained separately. The latency values ​​were then arranged in ascending order. in, This represents the increasing time delay sequence of all target information sensed by the k-th type of sensing device. This represents the sorting function, where n represents the total number of devices belonging to the k-th class of sensors. , Let be the time delay values ​​of the 1st and nth devices in the kth type of sensing devices; Based on the data latency values ​​of various sensing devices, the latency value at the 95th percentile is taken as the overall latency value for that type of sensing device. in, Indicates from The delay value extracted from the 95th percentile. It is a rounding function; , , and These represent the overall latency values ​​of microwave radar, lidar, fiber optic, and license plate recognition devices, respectively. The calculation method for the overall cache duration T is as follows: in, This indicates taking the maximum value; The data cache space is constructed based on the overall cache duration T and the current time, including: Using the overall cache duration T as the width of the time window, the current time t as the end point of the time window, and time tT as the start point of the time window, a data cache space that can accommodate perceived information within the range of tT~t is constructed.

2. The intelligent highway time synchronization information fusion method utilizing a caching mechanism as described in claim 1, characterized in that, Time synchronization of all sensing devices and information computing systems, including: Within a local area network, clock calibration is performed on all sensing devices and information computing systems using NTP servers, GPS, or BeiDou time synchronization to ensure that the time of all sensing devices and information computing systems remains synchronized.

3. The intelligent highway time synchronization information fusion method utilizing a caching mechanism as described in claim 1, characterized in that, At the current time t, the data pipeline will receive various sensor information sensed at time t, and will also receive various sensor information sensed in the time period [tT, t) but with a delay in reception.

4. The intelligent highway time synchronization information fusion method utilizing a caching mechanism as described in claim 1, characterized in that, The method further includes: If the latency of a certain sensing device is detected to exceed the overall cache duration T, it is assumed that the device has lost data and an alarm is issued. If the overall latency of the device is detected to be less than the overall cache duration T, the time scale of the data cache space is updated.

5. A smart highway time synchronization information fusion device utilizing a caching mechanism, characterized in that, Based on the method described in claim 1, the apparatus includes: The time synchronization module is used to synchronize the time of all sensing devices and information computing systems. The information perception module is used to acquire and process information about vehicle targets within the detection range, record the perception time of the detected vehicle targets, and transmit the timestamp, location, and speed information over the network in the form of data packets. The network transmission module is used to calculate the latency of each sensing device based on the data packets received, the receiving time, and the sensing time within a certain period of time, and to obtain the overall buffer duration T. The information fusion module is used to construct a data cache space based on the comprehensive cache duration T and the current time. At time t, it sends a data request to the data pipeline to store the data whose perception time belongs to the corresponding data cache space. At time t, it extracts data with perception time tT from the data cache space and executes a fusion algorithm for multi-source heterogeneous data to obtain the fused traffic information.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed, it implements the method as described in any one of claims 1 to 4.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 4.

Images