Road network flow observation method based on exclusion theorem and bayonet camera

Abstract

The invention relates to the technical field of road network flow observation, and discloses a road network flow observation method based on the exclusion theorem and a bayonet camera, which comprises the following steps: acquiring bayonet data collected by the bayonet camera; according to the obtained checkpoint data, extracting road network traffic observed by each checkpoint camera; constructing a road network flow calculation model based on the repulsion principle, and fitting the road network flow calculation model based on the repulsion principle by adopting a least square method according to the road network flow observed by each bayonet camera; and performing consistency observation on the road network flow of the bayonet camera according to the fitted road network flow calculation model. According to the method, the checkpoint cameras are used as observation equipment, deeper laws and relations between checkpoint equipment are mined based on the repulsion principle, and then flow fluctuation caused by random failure of the checkpoints is corrected, so that consistent observation of road network flow is achieved, and the accuracy and robustness of road network monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of road network flow observation, and in particular to a road network flow observation method based on the inclusion-exclusion theorem and a bayonet camera. Background Art

[0002] With the improvement of people's living standards and the acceleration of urbanization, the number of cars in cities has grown rapidly, far exceeding the carrying capacity of urban road network infrastructure, and urban congestion has become a prominent problem. As an extremely complex system, the urban road network is limited by the current computing power. The traffic flow law at the traditional road section level is powerless to alleviate large-scale surface congestion. As an important characteristic variable describing the state of the road network, road network flow is crucial for extracting the traffic flow law at the road network level and thus alleviating urban congestion. At present, the estimation methods for road network flow mainly focus on two observation methods: ring detector data and floating vehicle trajectory data. However, a large number of studies have shown that the installation position of the ring detector and the unknown permeability and uneven distribution of floating vehicles will cause inconsistent errors in the estimation of road network flow. In addition, random failures of observation equipment due to various reasons (such as unstable network and power supply) cause inconsistent observations. It is impossible to directly compare the road network flow under different observations, which is not conducive to decision-making by traffic managers. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the present invention provides a road network flow observation method based on the inclusion-exclusion theorem and a checkpoint camera.

[0004] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is:

[0005] A road network flow observation method based on the inclusion-exclusion theorem and a checkpoint camera comprises the following steps:

[0006] Get the bayonet data collected by the bayonet camera;

[0007] According to the acquired checkpoint data, the road network traffic observed by each checkpoint camera is extracted;

[0008] Construct a road network flow calculation model based on the principle of inclusion and exclusion, and use the least squares method to fit the road network flow calculation model based on the principle of inclusion and exclusion according to the road network flow observed by each camera.

[0009] The road network flow of the checkpoint camera is observed for consistency based on the fitted road network flow calculation model.

[0010] As a preferred embodiment, the road network flow calculation model based on the inclusion-exclusion principle is specifically as follows:

[0011]

[0012] Among them, V m represents the road network traffic observed by m checkpoint cameras, α m It represents the maximum number of times that m camera cameras can capture the same vehicle in a set time period, x k represents the total number of vehicles that can be captured by selecting k camera heads from n camera heads, m αm Indicates the maximum number of times the same vehicle is photographed α m The threshold of the number of cameras at the time of the checkpoint.

[0013] Preferably, according to the road network flow observed by each camera, the least square method is used to fit the road network flow calculation model based on the inclusion-exclusion principle, including the following steps:

[0014] According to the maximum number of times all the camera cameras capture a certain vehicle in a set time period, the road network traffic observed by any number of camera cameras with the same number of times as the maximum number is randomly selected;

[0015] According to the road network flow observed by the selected number of checkpoint cameras, the least square method is used to construct a linear equation group of the road network flow calculation model based on the inclusion-exclusion principle;

[0016] The linear equations of the road network flow calculation model based on the inclusion-exclusion principle are solved to obtain the fitted model parameters.

[0017] As a preferred embodiment, the linear equation group of the road network flow calculation model based on the inclusion-exclusion principle is specifically:

[0018]

[0019] Among them, V m represents the road network traffic observed by m checkpoint cameras, V n represents the road network traffic observed by n checkpoint cameras, x n,αm Indicates that when the total number of camera mounts is n, select α from n camera mounts. m The total number of vehicles that can be captured by the camera, x n,αn Indicates that when the total number of camera mounts is n, select α from n camera mounts. n The total number of vehicles that can be captured by the bayonet camera, α m It represents the maximum number of times m camera cameras capture the same vehicle in a set time period, α n Indicates the maximum number of times that n camera cameras capture the same vehicle in a set time period.

[0020] Preferably, the road network traffic observed by the checkpoint camera is the number of different vehicles photographed by the checkpoint camera in a set time period.

[0021] Preferably, the consistency observation of the road network flow of the checkpoint camera is performed according to the fitted road network flow calculation model, including the following steps:

[0022] Select two groups of checkpoint cameras at different time periods, and determine the corresponding fitted road network flow calculation model according to the road network flow observed by the two groups of checkpoint cameras;

[0023] The number of checkpoint cameras to be observed for consistency is set, and the road network flow consistency observation results of the corresponding number of checkpoint cameras are calculated using the fitted road network flow calculation model.

[0024] As a preferred embodiment, the calculation formula of the road network flow consistency observation result of the checkpoint camera is:

[0025]

[0026] in, express The road network traffic observed by the checkpoint cameras, express The road network flow observed by the group of checkpoint cameras, m represents the number of selected checkpoint cameras, Indicated in When grouping camera, select from n1 camera The total number of vehicles that can be captured by a bayonet camera, Indicated in When grouping camera mounts, select from n2 camera mounts The total number of vehicles that can be captured by a bayonet camera, express The maximum number of times a group of checkpoint cameras can capture the same vehicle in a set time period. express The maximum number of times the camera in the group camera captures the same vehicle in the set time period, n1 represents The total number of cameras in the group, n2 indicates The total number of group mount cameras.

[0027] The present invention has the following beneficial effects:

[0028] The present invention uses the bayonet camera as the observation device, and based on the principle of inclusion and exclusion, it excavates the deeper laws and connections between bayonet devices, and then corrects the flow fluctuation caused by the random failure of the bayonet, thereby realizing the consistent observation of the road network flow. This method can not only circumvent the limitations of the ring detector and floating vehicle trajectory data itself, but also cope with the situation of random failure of equipment in actual scenarios, and improve the accuracy and robustness of road network monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flowchart of a road network flow observation method based on the inclusion-exclusion theorem and the checkpoint camera;

[0030] Figure 2 The frequency distribution of the number of vehicles captured by the bayonet camera;

[0031] Figure 3 Schematic diagram of the step function of the maximum number of times a camera captures the same vehicle and the number of cameras. DETAILED DESCRIPTION

[0032] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0033] like Figure 1 As shown, the embodiment of the present invention provides a road network flow observation method based on the inclusion-exclusion theorem and a checkpoint camera, comprising the following steps S1 to S4:

[0034] S1, obtaining the bayonet data collected by the bayonet camera;

[0035] In an optional embodiment of the present invention, this embodiment collects checkpoint data by using checkpoint cameras arranged in the traffic road network, thereby obtaining the checkpoint data in the road network.

[0036] S2. Extract the road network traffic observed by each camera at each checkpoint based on the acquired checkpoint data;

[0037] In an optional embodiment of the present invention, the present embodiment processes the acquired checkpoint data to extract the road network traffic observed by each checkpoint camera.

[0038] Specifically, this embodiment determines the vehicle license plate numbers photographed by each checkpoint camera in a set time period based on the checkpoint data collected by each checkpoint camera, and then obtains the number of different vehicles photographed by each checkpoint camera in the set time period, which is the road network traffic observed by each checkpoint camera.

[0039] S3, constructing a road network flow calculation model based on the principle of inclusion and exclusion, and fitting the road network flow calculation model based on the principle of inclusion and exclusion using the least squares method according to the road network flow observed by each camera at each checkpoint;

[0040] In an optional embodiment of the present invention, a group of bayonet cameras Cn ={c1,c2,...,c n The number of different vehicles captured within the set time period [t1, t2], that is, the road network flow, is expressed as V n (t1, t2), n represents the number of camera mounts. For a given camera mount c i , use p i (t1, t2) represents the time interval [t1, t2] during which the camera c i The set of different vehicles captured. In this example, [t1, t2] will be omitted, but all quantities are associated with the same time interval.

[0041] Let the network flow v i =|p i |It is a bayonet camera c i The number of different vehicles captured. According to the inclusion-exclusion principle, the road network flow is expressed as:

[0042]

[0043] in, Indicates number i k The number of vehicles that can be captured by the bayonet camera.

[0044] definition

[0045]

[0046] Among them, x n, k It indicates the total number of vehicles that can be captured by selecting k camera from n camera bayonet cameras when the total number of camera bayonet cameras is n.

[0047] Therefore, the road network flow is expressed as:

[0048]

[0049] Definition C n,k For a subset of cameras with the number k:

[0050]

[0051] Obviously, In the positive integer Z + Fixed v∈Z + , and define the frequency distribution λ of the number of vehicles captured by the camera k (v) is:

[0052]

[0053] That is, the frequency distribution λ n,k(v) is the number of k bayonet combinations that have exactly v elements at the intersection. Then, x n,k It can be restated as follows:

[0054]

[0055] Therefore x n,k equal Figure 2 The area enclosed by the dashed line.

[0056] According to the probability density distribution function of the number of vehicles captured by the bayonet camera:

[0057]

[0058] satisfy:

[0059]

[0060] A series of frequency distributions Ω n ={f n,k (·): k = 1, ..., n} is determined by the road network flow state s∈S during [t1, t2]. During [t1, t2], the maximum number of times the camera can capture the same car is denoted by α n This means that when k>α n hour,

[0061]

[0062] So the distribution Ω n It can be expressed as

[0063]

[0064] For a given road network flow state s∈S, it determines a unique set Ω n , so the network accumulates V n It can be expressed as

[0065]

[0066] Next, m camera mounts are randomly selected from the n camera mounts. This means that the probability of each camera mount being selected is m / n. The total number of k camera mount combinations is Reduce to Therefore C n,k Each camera combination C∈C n,k The following have the same probability of being selected for deletion:

[0067]

[0068] Moreover, this probability is independent of v. Therefore, it can be concluded that in a probabilistic sense, the PDF function f n,k (·)≡f m,k (·) is applicable to any 1≤k≤m.

[0069] The following analysis shows different m values ​​and corresponding V in different situations. m .

[0070] When α m =α n When the network based on m camera heads is accumulated,

[0071]

[0072] Therefore, f n,k (·)=f m,k (·) is the result of randomly selecting m cameras. Can be replaced with:

[0073]

[0074] Therefore, the network accumulation based on m camera ports is further expressed as:

[0075]

[0076] Since k≤α n , and α n is much smaller than n and m, so we can get:

[0077]

[0078] Therefore, the network accumulation based on m camera bayonet can be further expressed as:

[0079]

[0080] When α m <α n When , the maximum number of shots of the same vehicle by m camera ports is less than the maximum number of shots of the same vehicle by n camera ports. Therefore, the road network traffic observed by m camera ports is

[0081]

[0082] In summary, assuming that α m is a step function about m, such as Figure 3 As shown. In each interval [m i ,m i+1 ], α m Take the same value. In this way, V mIt can be written as a piecewise function related to the number of camera ports m, and a road network flow calculation model based on the inclusion-exclusion principle is constructed, which can be expressed as:

[0083]

[0084] Among them, V m represents the road network traffic observed by m checkpoint cameras, α m It represents the maximum number of times that m camera cameras can capture the same vehicle in a set time period, x k represents the total number of vehicles that can be captured by selecting k camera heads from n camera heads, m αm Indicates the maximum number of times the same vehicle is photographed α m The threshold of the number of cameras at the time of the checkpoint.

[0085] In an optional embodiment of the present invention, this embodiment uses the least square method to fit the road network flow calculation model based on the inclusion-exclusion principle according to the road network flow observed by each camera at the checkpoint, including the following steps:

[0086] According to the maximum number of times all the camera cameras capture a certain vehicle in a set time period, the road network traffic observed by any number of camera cameras with the same number of times as the maximum number is randomly selected;

[0087] According to the road network flow observed by the selected number of checkpoint cameras, the least square method is used to construct a linear equation group of the road network flow calculation model based on the inclusion-exclusion principle;

[0088] The linear equations of the road network flow calculation model based on the inclusion-exclusion principle are solved to obtain the fitted model parameters.

[0089] Specifically, according to the road network flow calculation model based on the inclusion-exclusion principle, by determining the maximum number of times all the camera ports capture a certain vehicle in a set time period, randomly selecting the road network flow observed by any number of camera ports with the same number of times, and using the least squares method to construct the linear equation group of the road network flow calculation model based on the inclusion-exclusion principle, it is expressed as:

[0090]

[0091] Among them, n represents the total number of camera mounts, m represents the number of selected camera mounts, V1, V2, V3, V m 、V n They represent the road network traffic observed by the corresponding number of selected camera ports, x n,1 、x n,2 、x n,3 、x n,αm 、x n,αn Respectively, αm It represents the maximum number of times that m camera cameras can capture a vehicle in a set time period, α n Indicates the maximum number of times a vehicle is photographed by n camera heads in a set time period.

[0092] By solving the linear equations of the road network flow calculation model based on the inclusion-exclusion principle, the fitting model parameters x can be obtained. n,1 、x n,2 、x n,3 、x n,αm 、x n,αn .

[0093] S4. Conduct consistency observation of the road network flow of the checkpoint camera based on the fitted road network flow calculation model.

[0094] In an optional embodiment of the present invention, the embodiment performs consistency observation of the road network flow of the checkpoint camera according to the fitted road network flow calculation model, including the following steps:

[0095] Select two groups of checkpoint cameras at different time periods, and determine the corresponding fitted road network flow calculation model according to the road network flow observed by the two groups of checkpoint cameras;

[0096] The number of checkpoint cameras to be observed for consistency is set, and the road network flow consistency observation results of the corresponding number of checkpoint cameras are calculated using the fitted road network flow calculation model.

[0097] Specifically, two groups of camera heads at different time periods are selected. n1≠n2, the model parameters of the road network flow calculation model based on the inclusion-exclusion principle obtained by fitting in step S3 can be used to determine the corresponding fitted road network flow calculation model.

[0098] Then set the number of cameras to be observed for consistency m (m<n1,m<n2), and calculate the maximum number of times the vehicle is photographed The determined fitted road network flow calculation model is used to calculate the road network flow consistency observation results of the corresponding number of camera ports, which can be expressed as:

[0099]

[0100] in, express The road network traffic observed by the checkpoint cameras, express The road network flow observed by the group of checkpoint cameras, m represents the number of selected checkpoint cameras, Indicated in When grouping camera, select from n1 camera The total number of vehicles that can be captured by a bayonet camera, Indicated in When grouping camera mounts, select from n2 camera mounts The total number of vehicles that can be captured by a bayonet camera, express The maximum number of times a group of checkpoint cameras can capture the same vehicle in a set time period. express The maximum number of times the camera in the group camera captures the same vehicle in the set time period, n1 represents The total number of cameras in the group, n2 indicates The total number of group mount cameras.

[0101] In order to solve the problem that due to the existence of random failure of the bayonet, the observation bayonet equipment sets in different time periods will be inconsistent, which will cause errors in the estimation and use of road network traffic, the present invention provides a road network traffic consistency observation method based on the inclusion-exclusion theorem and the bayonet camera. The method uses the bayonet camera as the observation device, and mines the deeper laws and connections between the bayonet devices based on the inclusion-exclusion principle, and then corrects the traffic fluctuation caused by the random failure of the bayonet, thereby realizing the consistency observation of the road network traffic. This method can not only circumvent the limitations of the ring detector and the floating vehicle trajectory data itself, but also cope with the situation of random failure of equipment in actual scenarios. It is more practical and can provide a basis for long-term monitoring of the road network.

[0102] Based on the inclusion-exclusion theorem, the present invention provides a theoretical calculation formula for the road network flow, and further fits the original data through the linear least squares method to obtain The method can convert the road network flow observed by different numbers of checkpoints into the average value of the observed flow under the same number of checkpoints (only the number of checkpoints needs to be the same, not the checkpoint numbers need to be exactly the same), which greatly improves the practicality.

[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0106] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0107] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A road network flow observation method based on the inclusion-exclusion theorem and a bayonet camera, characterized in that: The following steps are involved: Get the bayonet data collected by the bayonet camera; According to the acquired checkpoint data, the road network traffic observed by each checkpoint camera is extracted; Construct a road network flow calculation model based on the principle of inclusion and exclusion, and use the least squares method to fit the road network flow calculation model based on the principle of inclusion and exclusion according to the road network flow observed by each camera. The road network flow of the checkpoint camera is observed for consistency based on the fitted road network flow calculation model.

2. A road network flow observation method based on the inclusion-exclusion theorem and a bayonet camera according to claim 1, characterized in that: The road network flow calculation model based on the inclusion-exclusion principle is as follows: Among them, V m represents the road network traffic observed by m checkpoint cameras, α m It represents the maximum number of times that m camera cameras can capture the same vehicle in a set time period, x k represents the total number of vehicles that can be captured by selecting k camera heads from n camera heads, m αm Indicates the maximum number of times the same vehicle is photographed α m The threshold of the number of cameras at the time of the checkpoint.

3. A road network flow observation method based on the inclusion-exclusion theorem and a bayonet camera according to claim 1, characterized in that: According to the road network flow observed by each camera, the least square method is used to fit the road network flow calculation model based on the inclusion-exclusion principle, including the following steps: According to the maximum number of times all the camera cameras capture a certain vehicle in a set time period, the road network traffic observed by any number of camera cameras with the same number of times as the maximum number is randomly selected; According to the road network flow observed by the selected number of camera ports, a linear equation group of the road network flow calculation model based on the inclusion-exclusion principle is constructed by using the least square method; The linear equations of the road network flow calculation model based on the inclusion-exclusion principle are solved to obtain the fitted model parameters.

4. A road network flow observation method based on the inclusion-exclusion theorem and a bayonet camera according to claim 3, characterized in that: The linear equations of the road network flow calculation model based on the inclusion-exclusion principle are as follows: Among them, V m represents the road network traffic observed by m checkpoint cameras, V n represents the road network traffic observed by n checkpoint cameras, x n,αm Indicates that when the total number of camera mounts is n, select α from n camera mounts. m The total number of vehicles that can be captured by the camera, x n,αn Indicates that when the total number of camera mounts is n, select α from n camera mounts. n The total number of vehicles that can be captured by the bayonet camera, α m It represents the maximum number of times m camera cameras capture the same vehicle in a set time period, α n Indicates the maximum number of times that n camera cameras capture the same vehicle in a set time period.

5. The road network flow observation method based on the inclusion-exclusion theorem and the bayonet camera according to claim 1 is characterized in that: The road network traffic observed by the checkpoint camera is the number of different vehicles captured by the checkpoint camera in a set time period.

6. The road network flow observation method based on the inclusion-exclusion theorem and the bayonet camera according to claim 1 is characterized in that: The road network flow of the checkpoint camera is observed for consistency according to the fitted road network flow calculation model, including the following steps: Select two groups of checkpoint cameras at different time periods, and determine the corresponding fitted road network flow calculation model according to the road network flow observed by the two groups of checkpoint cameras; The number of checkpoint cameras to be observed for consistency is set, and the road network flow consistency observation results of the corresponding number of checkpoint cameras are calculated using the fitted road network flow calculation model.

7. A road network flow observation method based on the inclusion-exclusion theorem and a bayonet camera according to claim 6, characterized in that: The calculation formula for the road network flow consistency observation result of the checkpoint camera is: in, express The road network traffic observed by the checkpoint cameras, express The road network flow observed by the group of checkpoint cameras, m represents the number of selected checkpoint cameras, Indicated in When grouping camera, select from n1 camera The total number of vehicles that can be captured by a camera. Indicated in When grouping camera mounts, select from n2 camera mounts The total number of vehicles that can be captured by a camera. express The maximum number of times a group of checkpoint cameras can capture the same vehicle in a set time period. express The maximum number of times the camera in the group camera captures the same vehicle in the set time period, n1 represents The total number of cameras in the group, n2 indicates The total number of group mount cameras.

Images