TWI758903B

TWI758903B - Method and server for estimating degree of chaos in traffic flow

Info

Publication number: TWI758903B
Application number: TW109135456A
Authority: TW
Inventors: 莊育祥; 姜芝怡; 高果; 謝兆糧
Original assignee: 中華電信股份有限公司
Priority date: 2020-10-14
Filing date: 2020-10-14
Publication date: 2022-03-21
Also published as: TW202215385A

Abstract

The present invention provides a method and server for estimating the degree of chaos in the traffic flow, wherein the degree of chaos in the traffic flow can be understood as an indicator used to quantify the situation of the traffic flow in a road section. In this way, it can be evaluated whether the traffic of the road section will be affected due to the chaotic traffic flow, and further evaluate whether the road section is prone to accidents or casualties.

Description

估計車流混亂程度的方法及伺服器Method and server for estimating the degree of traffic chaos

本發明是有關於一種交通偵測技術，且特別是有關於一種估計車流混亂程度的方法及伺服器。 The present invention relates to a traffic detection technology, and more particularly, to a method and a server for estimating the degree of chaotic traffic flow.

因路況複雜或駕駛貪急搶快等行為導致的車流穿插的情形，不僅會降低路段行車速度也會增加車禍事故發生的機率。由高公局發布之”國道交通事故統計及特性分析”中亦有點出車流交織變化情形易發生交通事故。 The interspersed traffic flow caused by complex road conditions or greedy driving behaviors will not only reduce the driving speed of the road section, but also increase the probability of car accidents. In the "Statistics and Characteristic Analysis of National Road Traffic Accidents" issued by the Gao Gong Bureau, there are also some changes in traffic flow that are prone to traffic accidents.

然而針對車輛間變換穿插的情形，目前尚未有任何一種指標可以量化表示。 However, for the situation of inter-vehicle transformation and interspersed, there is no index that can be quantitatively expressed.

有鑑於此，本發明提供一種估計車流混亂程度的方法及伺服器，其可用於解決上述技術問題。 In view of this, the present invention provides a method and a server for estimating the degree of traffic chaos, which can be used to solve the above technical problems.

本發明提供一種估計車流混亂程度的方法，包括：透過設置於一特定道路的一第一門架偵測通過第一門架的多個第一車輛及各第一車輛通過第一門架的一第一時間點；透過設置於特定道路的一第二門架偵測在一第一時段內通過第二門架的多個第二車輛，其中第二門架位於第一門架的下游，且第二門架及第一門架之間具有一特定道路段；在所述多個第二車輛中找出匹配於所述多個第一車輛的一部分的多個第一特定車輛，並基於各第一特定車輛的第一時間點定義一第一參考時間區間；基於第一參考時間區間與一第二參考時間區間的一重疊時間區間在第一參考時間區間內定義一子時間區間，其中第二參考時間區間對應於先於第一時段的一第二時段；估計各第一特定車輛自第一門架至第二門架的一順序變換度及一變換車道量；估計特定道路段在第一時段內的一新進車流量；估計特定道路段在子時間區間內的一離開車流量；基於重疊時間區段及第一時段估計第一時段與第二時段之間的一時間重疊度；基於順序變換度、變換車道量、新進車流量、離開車流量及時間重疊度估計特定道路段在第一時段內的一車流混亂程度。 The present invention provides a method for estimating the degree of chaotic traffic flow, comprising: detecting a plurality of first vehicles passing through the first gantry through a first gantry disposed on a specific road A first time point when the vehicle and each first vehicle pass through the first gantry; a second gantry set on a specific road is used to detect a plurality of second vehicles passing through the second gantry within a first period of time, wherein The second gantry is located downstream of the first gantry, and there is a specific road section between the second gantry and the first gantry; the plurality of second vehicles are found to match the plurality of first vehicles A part of a plurality of first specific vehicles, and define a first reference time interval based on the first time point of each first specific vehicle; based on an overlapping time interval of the first reference time interval and a second reference time interval A sub-time interval is defined within a reference time interval, wherein the second reference time interval corresponds to a second time period prior to the first time period; a sequence change of each first specific vehicle from the first gantry to the second gantry is estimated estimating a new incoming traffic flow for a specific road segment in a first time period; estimating an outgoing traffic flow for a specific road segment in a sub-time interval; estimating a first time period based on the overlapping time segment and the first time period a temporal overlap degree with the second time period; based on the sequence change degree, the amount of changing lanes, the new incoming traffic flow, the leaving traffic flow and the time overlap degree, a traffic flow disorder degree of a specific road segment in the first time period is estimated.

本發明提供一種估計車流混亂程度的伺服器，包括儲存電路及處理器。儲存電路儲存多個模組。處理器耦接儲存電路，存取所述多個模組以執行下列步驟：透過設置於一特定道路的一第一門架偵測通過第一門架的多個第一車輛及各第一車輛通過第一門架的一第一時間點；透過設置於特定道路的一第二門架偵測在一第一時段內通過第二門架的多個第二車輛，其中第二門架位於第一門架的下游，且第二門架及第一門架之間具有一特定道路段；在所述多個第二車輛中找出匹配於所述多個第一車輛的一部分的多個第一特定車輛，並基於各第一特定車輛的第一時間點定義一第一參考時間區間；基於第一參考時間區間與一第二參考時間區間的一重疊時間區間在第一參考時間區間內定義一子時間區間，其中第二參考時間區間對應於先於第一時段的一第二時段；估計各第一特定車輛自第一門架至第二門架的一順序變換度及一變換車道量；估計第一時段內的一新進車流量；估計子時間區間內的一離開車流量；基於重疊時間區段及第一時段估計第一時段與第二時段之間的一時間重疊度；基於順序變換度、變換車道量、新進車流量、離開車流量及時間重疊度估計特定道路段在第一時段內的一車流混亂程度。 The present invention provides a server for estimating the chaotic degree of traffic flow, which includes a storage circuit and a processor. The storage circuit stores a plurality of modules. The processor is coupled to the storage circuit, and accesses the modules to perform the following steps: detecting a plurality of first vehicles and each first vehicle passing through the first gantry through a first gantry disposed on a specific road A first time point passing through the first gantry; a plurality of second vehicles passing through the second gantry within a first period of time are detected through a second gantry disposed on a specific road, wherein the second gantry is located on the first gantry. Downstream of a gantry, and there is a specific road between the second gantry and the first gantry segment; find a plurality of first specific vehicles matching a part of the plurality of first vehicles among the plurality of second vehicles, and define a first reference time based on the first time point of each first specific vehicle interval; a sub-time interval is defined within the first reference time interval based on an overlapping time interval of the first reference time interval and a second reference time interval, wherein the second reference time interval corresponds to a second time interval preceding the first time period time period; estimate a sequence change degree and a change lane amount of each first specific vehicle from the first gantry to the second gantry; estimate a new incoming traffic flow in the first time period; estimate a departing traffic flow in the sub-time interval ; estimate a temporal overlap between the first and second time periods based on the overlapping time segment and the first time segment; estimate a specific road segment based on the sequence change degree, the amount of lane changes, the flow of new incoming traffic, the flow of departing traffic, and the degree of temporal overlap The degree of chaos in a traffic flow in the first period.

100:伺服器 100: Server

102:儲存電路 102: Storage circuit

104:處理器 104: Processor

300:特定道路 300: specific road

310:第一門架 310: The first gantry

320:第二門架 320: Second gantry

330,340:特定道路段 330,340: specific road segments

T1:第一參考時間區間 T1: The first reference time interval

T2:第二參考時間區間 T2: Second reference time interval

OT:重疊時間區間 OT: Overlapping time interval

ST1:子時間區間 ST1: sub time interval

1~15:車輛 1~15: Vehicle

S210~S290:步驟 S210~S290: Steps

圖1是依據本發明之一實施例繪示的估計車流混亂程度的伺服器示意圖。 FIG. 1 is a schematic diagram of a server for estimating the degree of traffic chaos according to an embodiment of the present invention.

圖2是依據本發明之一實施例繪示的估計車流混亂程度的方法流程圖。 FIG. 2 is a flowchart of a method for estimating the degree of confusion of traffic flow according to an embodiment of the present invention.

圖3是依據本發明之一實施例繪示的特定道路示意圖。 FIG. 3 is a schematic diagram of a specific road according to an embodiment of the present invention.

圖4是依據本發明之一實施例繪示的車流示意圖。 FIG. 4 is a schematic diagram of traffic flow according to an embodiment of the present invention.

概略而言，本發明提出一種估計車流混亂程度的伺服器及方法，其中所述車流混亂程度可理解為用於量化一路段車流穿插情形的指標。藉此，可以評估此路段會否因混亂的車流影響交通運輸量，並更進一步評估該路段是否容易因此發生事故或傷亡。 Roughly speaking, the present invention provides a server and method for estimating the degree of traffic chaos, wherein the degree of traffic chaos can be understood as an index used to quantify the situation of traffic interspersed in a segment. In this way, it is possible to assess whether this road section will affect the traffic volume due to chaotic traffic flow, and further assess whether this road section is prone to accidents or casualties.

此外，所述車流混亂程度亦可讓公部門在進行交通決策上也有量化的數據可供參考，有數據佐證也更能強化該政策執行的重要性及合理性。若能有效地在相對混亂的路段上執行適合的交控策略如增設告示或雙白線減少車輛變化車道，相信能大幅降低事故發生率增加路段交通運輸量。以下將作進一步說明。 In addition, the level of traffic chaos can also allow the public sector to have quantitative data for reference in making traffic decisions, and data support can further strengthen the importance and rationality of the implementation of the policy. If appropriate traffic control strategies can be effectively implemented on relatively chaotic road sections, such as adding notices or double white lines to reduce vehicles changing lanes, it is believed that the accident rate can be greatly reduced and the traffic volume of the road section can be greatly reduced. It will be further explained below.

請參照圖1，其是依據本發明之一實施例繪示的估計車流混亂程度的伺服器示意圖。如圖1所示，伺服器100可包括儲存電路102及處理器104。 Please refer to FIG. 1 , which is a schematic diagram of a server for estimating the degree of traffic chaos according to an embodiment of the present invention. As shown in FIG. 1 , the server 100 may include a storage circuit 102 and a processor 104 .

儲存電路102例如是任意型式的固定式或可移動式隨機存取記憶體(Random Access Memory，RAM)、唯讀記憶體(Read-Only Memory，ROM)、快閃記憶體(Flash memory)、硬碟或其他類似裝置或這些裝置的組合，而可用以記錄多個程式碼或模組。 The storage circuit 102 is, for example, any type of fixed or removable random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), flash memory (Flash memory), hard drive A disc or other similar device or a combination of these devices may be used to record multiple code or modules.

處理器104耦接於儲存電路102，並可為一般用途處理器、特殊用途處理器、傳統的處理器、數位訊號處理器、多個微處理器(microprocessor)、一個或多個結合數位訊號處理器核心的微處理器、控制器、微控制器、特殊應用積體電路(Application Specific Integrated Circuit，ASIC)、現場可程式閘陣列電路(Field Programmable Gate Array，FPGA)、任何其他種類的積體電路、狀態機、基於進階精簡指令集機器(Advanced RISC Machine，ARM)的處理器以及類似品。 The processor 104 is coupled to the storage circuit 102 and can be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more combined digital signal processing Microprocessor, controller, microcontroller, application specific integrated circuit (Application Specific Integrated Circuit) Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA), any other kind of integrated circuit, state machine, Advanced RISC Machine (ARM) based processor, and similar products.

在本發明的實施例中，處理器104可存取儲存電路102中記錄的模組、程式碼來實現本發明提出的估計車流混亂程度的方法，其細節詳述如下。 In the embodiment of the present invention, the processor 104 can access the modules and program codes recorded in the storage circuit 102 to implement the method for estimating the degree of traffic chaos proposed by the present invention, the details of which are described below.

請參照圖2，其是依據本發明之一實施例繪示的估計車流混亂程度的方法流程圖。本實施例的方法可由圖1的伺服器100執行，以下即搭配圖1所示的元件說明圖2各步驟的細節。另外，為使本案概念更易於理解，以下將另輔以圖3及圖4作說明，其中圖3是依據本發明之一實施例繪示的特定道路示意圖，而圖4是依據本發明之一實施例繪示的車流示意圖。 Please refer to FIG. 2 , which is a flowchart of a method for estimating the degree of confusion of traffic flow according to an embodiment of the present invention. The method of this embodiment can be executed by the server 100 in FIG. 1 , and the details of each step in FIG. 2 will be described below in conjunction with the components shown in FIG. 1 . In addition, in order to make the concept of the present case easier to understand, the following description will be supplemented with FIG. 3 and FIG. 4 , wherein FIG. 3 is a schematic diagram of a specific road according to an embodiment of the present invention, and FIG. 4 is an embodiment of the present invention. A schematic diagram of the traffic flow shown in the embodiment.

首先，在步驟S210中，處理器104可透過設置於特定道路300的第一門架310偵測通過第一門架310的多個第一車輛及各第一車輛通過第一門架310的第一時間點。在步驟S220中，處理器104可透過設置於特定道路300的第二門架320偵測在第一時段內通過第二門架320的多個第二車輛，其中第二門架320位於第一門架310的下游，且第二門架320及第一門架310之間具有一特定道路段330。換言之，行駛於特定道路段330上的車輛將先經過第一門架310再經過第二門架320。此外，處理器104亦可取得各第二車輛通過第二門架320的第二時間點，以作為估計其他特定道路段的依據，但可不限於此。 First, in step S210 , the processor 104 may detect a plurality of first vehicles passing through the first gantry 310 and the number of first vehicles passing through the first gantry 310 through the first gantry 310 disposed on the specific road 300 . one point in time. In step S220, the processor 104 may detect a plurality of second vehicles passing through the second gantry 320 within the first period of time through the second gantry 320 disposed on the specific road 300, wherein the second gantry 320 is located at the first Downstream of the gantry 310 and between the second gantry 320 and the first gantry 310 is a specific road section 330 . In other words, a vehicle traveling on a specific road segment 330 will first pass through the first gantry 310 and then through the second gantry 320 . In addition, the processor 104 can also obtain the second time point at which each second vehicle passes the second gantry 320 as an estimate of the second time point. The basis for his specific road segment, but not limited to this.

應了解的是，雖以上內容將第二門架320描述為位於第一門架的下游，但對於對向車道而言，第一門架310亦可理解為位於第二門架320的下游，且第二門架320及第一門架310之間具有另一特定道路段340，但可不限於此。 It should be understood that, although the above description describes the second gantry 320 as being located downstream of the first gantry, for the opposite lane, the first gantry 310 can also be understood as being located downstream of the second gantry 320, And there is another specific road section 340 between the second gantry 320 and the first gantry 310 , but not limited to this.

為便於說明，以下將僅以特定道路段330(即，第二門架320位於第一門架310下游)為例進行說明，但本發明可不限於此。 For the convenience of description, the following description will only take a specific road section 330 (ie, the second gantry 320 is located downstream of the first gantry 310 ) as an example, but the present invention may not be limited thereto.

在本發明的實施例中，特定道路300例如是高速公路，而第一門架310及第二門架320例如是eTag門架或其他可在車輛通過時辨識車輛身分及通過時間的門架，但可不限於此。 In the embodiment of the present invention, the specific road 300 is, for example, a highway, and the first gantry 310 and the second gantry 320 are, for example, eTag gantry or other gantry that can identify the identity of the vehicle and the passing time when the vehicle passes, But not limited to this.

在圖4中，假設處理器104透過第一門架310偵測到的第一車輛包括車輛1~15及其他以點狀格代表的車輛，而各第一車輛通過第一門架310的第一時間點可如圖4所例示。舉例而言，車輛1通過第一門架310的第一時間點例如是07：43，車輛5通過第一門架310的第一時間點例如是07：46，其餘第一車輛通過第一門架310的第一時間點可依此類推，於此不另贅述。 In FIG. 4 , it is assumed that the first vehicles detected by the processor 104 through the first gantry 310 include vehicles 1 to 15 and other vehicles represented by dotted grids, and each of the first vehicles passes through the first gantry 310 . A point in time may be exemplified in FIG. 4 . For example, the first time point when the vehicle 1 passes the first door frame 310 is, for example, 07:43, the first time point when the vehicle 5 passes the first door frame 310 is, for example, 07:46, and the rest of the first vehicles pass the first door. The first time point of the rack 310 can be deduced by analogy, which will not be repeated here.

在圖4中，繪示為點狀格的車輛例如是有被第一門架310偵測到但未被第二門架320偵測到的車輛，亦即可能已透過特定道路段330上的其他出口(例如交流道)離開特定道路段330，但可不限於此。 In FIG. 4 , the vehicle shown as a dotted grid is, for example, a vehicle detected by the first gantry 310 but not detected by the second gantry 320 , that is, it may have passed through a vehicle on a specific road section 330 . Other exits, such as interchanges, leave the particular road segment 330, but may not be so limited.

另外，假設所考慮的第一時段為08：10~08：15，則處理器 104在步驟S220所取得的第二車輛例如可包括車輛5~10以及介於車輛5及10之間的其他以斜線格代表的車輛，但可不限於此。 In addition, assuming that the considered first period is 08:10~08:15, the processor 104 The second vehicle obtained in step S220 may include, for example, vehicles 5 to 10 and other vehicles represented by diagonal lines between vehicles 5 and 10, but it is not limited thereto.

在圖4中，繪示為斜線格的車輛例如是未被第一門架310偵測到但有被第二門架320偵測到的車輛，亦即這些車輛可能透過特定道路段330上的其他出口(例如交流道)進入特定道路段330，但可不限於此。 In FIG. 4 , the vehicles shown as diagonal grids are, for example, vehicles that are not detected by the first gantry 310 but are detected by the second gantry 320 , that is, these vehicles may pass through the vehicles on the specific road section 330 . Other exits (eg, interchanges) enter specific road segments 330, but may not be limited thereto.

之後，在步驟S230中，處理器104可在所述多個第二車輛中找出匹配於所述多個第一車輛的一部分的多個第一特定車輛，並基於各第一特定車輛的第一時間點定義第一參考時間區間。由圖4可看出，處理器104可將第二車輛中的車輛5~10作為上述第一特定車輛，並可依據車輛5~10個別的第一時間點定義第一參考時間區間。 Afterwards, in step S230, the processor 104 may find a plurality of first specific vehicles matching a part of the plurality of first vehicles among the plurality of second vehicles, and based on the first specific vehicle of each first specific vehicle A time point defines the first reference time interval. As can be seen from FIG. 4 , the processor 104 can regard the vehicles 5 to 10 in the second vehicle as the above-mentioned first specific vehicle, and can define the first reference time interval according to the respective first time points of the vehicles 5 to 10 .

在一實施例中，處理器104可在上述第一特定車輛的第一時間點中找出最大時間點及最小時間點，並將最大時間點與最小時間點之間的時間區間定義為第一參考時間區間。以圖4為例，在車輛5~10中，處理器104可以車輛9的第一時間點(即，07：55)作為最大時間點，並以車輛5的第一時間點(即，07：46)作為最小時間點。在此情況下，處理器104可將07：46~07：55定義為第一參考時間區間T1。 In one embodiment, the processor 104 may find the maximum time point and the minimum time point in the first time point of the first specific vehicle, and define the time interval between the maximum time point and the minimum time point as the first time point. Reference time interval. Taking FIG. 4 as an example, in vehicles 5 to 10, the processor 104 may take the first time point of vehicle 9 (ie, 07:55) as the maximum time point, and use the first time point of vehicle 5 (ie, 07:55) as the maximum time point. 46) as the minimum time point. In this case, the processor 104 may define 07:46~07:55 as the first reference time interval T1.

接著，在步驟S240中，處理器104可基於第一參考時間區間T1與第二參考時間區間T2的重疊時間區間在第一參考時間區間T1內定義子時間區間ST1，其中第二參考時間區間T2可對應於先於第一時段(即，08：10~08：15)的第二時段(即，08：05~08：10)。 Next, in step S240, the processor 104 may define a sub-time interval ST1 within the first reference time interval T1 based on the overlapping time interval of the first reference time interval T1 and the second reference time interval T2, wherein the second reference time interval T2 yes It should be in the second period (ie, 08:05~08:10) that precedes the first period (ie, 08:10~08:15).

在一實施例中，處理器104可基於定義第一參考時間T1的原則來定義對應於第二時段的第二參考時間T2。例如，處理器104可透過第二門架320偵測在第二時段內通過第二門架320的多個第三車輛(例如是圖4中在車輛5之前通過第二門架320的繪示為斜線格的車輛及車輛1~4)及各第三車輛通過該第二門架的第三時間點。之後，處理器104可在這些第三車輛中找出匹配於上述第一車輛的另一部分的多個第二特定車輛(例如是車輛1~4)，並基於各第二特定車輛的第一時間點定義第二參考時間區間T2。 In one embodiment, the processor 104 may define the second reference time T2 corresponding to the second period based on the principle of defining the first reference time T1. For example, the processor 104 may detect, through the second gantry 320 , a plurality of third vehicles passing through the second gantry 320 during the second period of time (eg, as shown in FIG. 4 , which passes through the second gantry 320 before the vehicle 5 ) is the third time point at which the vehicles in the diagonal grid and vehicles 1 to 4) and each third vehicle pass through the second gantry. Afterwards, the processor 104 may find a plurality of second specific vehicles (eg, vehicles 1 to 4 ) matching another part of the first vehicle in the third vehicles, and based on the first time of each second specific vehicle The point defines a second reference time interval T2.

在圖4中，處理器104例如可以車輛3的第一時間點(例如07：48)作為最大時間點，並以車輛1的第一時間點(例如07：43)作為最小時間點，進而據以定義第二參考時間區間T2為07：43~07：48，但可不限於此。 In FIG. 4 , the processor 104 may, for example, take the first time point of the vehicle 3 (for example, 07:48) as the maximum time point, and the first time point of the vehicle 1 (for example, 07:43) as the minimum time point, and then use the first time point of the vehicle 1 (for example, 07:43) as the minimum time point. The second reference time interval T2 is defined as 07:43-07:48, but it is not limited to this.

由圖4可知，第一參考時間區間T1與第二參考時間區間T2可具有重疊時間區間OT，即07：46~07：48。在此情況下，處理器104可據以在第一參考時間區間T1內定義子時間區間ST1。在一實施例中，處理器104可在重疊時間區間OT內定義特定時間點，並將第一參考時間區間T1的最大時間點(即，07：55)及特定時間點之間的時間區間定義為子時間區間ST1。舉例而言，處理器104例如可選定重疊時間區間OT的中間時間點(即，07：47)作為上述特定時間點。在此情況下，處理器104即可將07：47~07：55 作為上述子時間區間ST1，但可不限於此。 It can be seen from FIG. 4 that the first reference time interval T1 and the second reference time interval T2 may have an overlapping time interval OT, that is, 07:46 to 07:48. In this case, the processor 104 may define the sub-time interval ST1 within the first reference time interval T1 accordingly. In one embodiment, the processor 104 may define a specific time point within the overlapping time interval OT, and define the maximum time point (ie, 07:55) of the first reference time interval T1 and the time interval between the specific time points is the sub-time interval ST1. For example, the processor 104 may, for example, select the middle time point (ie, 07:47) of the overlapping time interval OT as the above-mentioned specific time point. In this case, the processor 104 can convert 07:47~07:55 As the above-mentioned sub-time interval ST1, it is not limited to this.

之後，在步驟S250中，處理器104可估計各第一特定車輛(即，車輛5~10)自第一門架310至第二門架320的順序變換度及變換車道量。 Afterwards, in step S250, the processor 104 may estimate the sequence change degree and lane change amount of each first specific vehicle (ie, vehicles 5-10) from the first gantry 310 to the second gantry 320.

在一實施例中，對於第一特定車輛中的一參考車輛而言，處理器104可經配置以：取得參考車輛在上述第一特定車輛中通過第一門架310的第一順序及通過第二門架320的第二順序；估計第一順序與第二順序之間的一順序差值；將各第一特定車輛的順序差值加總為順序變換度。 In one embodiment, for a reference vehicle in the first specific vehicle, the processor 104 may be configured to: obtain a first order in which the reference vehicle passes through the first mast 310 in the first specific vehicle and a first pass through the first specific vehicle. Second order of the two-gantry 320; estimating an order difference between the first order and the second order; summing the order difference of each first specific vehicle as a degree of order transformation.

在圖4情境中，各第一特定車輛(即，車輛5~10)在上述第一特定車輛中通過第一門架310的第一順序及通過第二門架320的第二順序可如下表一所例示。 In the scenario of FIG. 4 , the first sequence of passing through the first mast 310 and the second sequence of passing through the second mast 320 for each of the first specific vehicles (ie, vehicles 5 to 10 ) in the above-mentioned first specific vehicle may be as follows An example.

基於表一，處理器104可將所示的順序差值加總為各第一特定車輛(即，車輛5~10)自第一門架310至第二門架320的順序變換度(即，0+0+0+1+1+2=4)，但可不限於此。 Based on Table 1, the processor 104 may sum the sequence differences shown as each The degree of sequence change (ie, 0+0+0+1+1+2=4) from the first mast 310 to the second mast 320 for a specific vehicle (ie, vehicles 5 to 10 ), but not limited thereto.

另外，對於參考車輛而言，處理器104可經配置以：取得參考車輛通過第一門架310時所在的一第一車道及通過第二門架320時所在的一第二車道；估計第一車道與第二車道之間的車道差值；將各第一特定車輛的車道差值加總為變換車道量。 Additionally, for the reference vehicle, the processor 104 may be configured to: obtain a first lane in which the reference vehicle passes the first gantry 310 and a second lane in which it passes the second gantry 320; estimate the first The lane difference between the lane and the second lane; the lane difference for each first specific vehicle is summed as the lane change amount.

在一實施例中，假設特定道路段330共具有3個車道(下稱1、2、3號車道)，而各第一特定車輛(即，車輛5~10)在通過第一門架310時所在的第一車道序及通過第二門架320時所在的第二車道可如下表二所例示。 In one embodiment, it is assumed that the specific road segment 330 has a total of 3 lanes (hereinafter referred to as lanes 1, 2, and 3), and each of the first specific vehicles (ie, vehicles 5 to 10 ) passes through the first gantry 310 . The sequence of the first lane and the second lane when passing through the second gantry 320 can be exemplified in Table 2 below.

基於表二，處理器104可將所示的車道差值加總為各第一特定車輛(即，車輛5~10)自第一門架310至第二門架320的變換車道量(即，0+0+0+1+1+2=4)，但可不限於此。 Based on Table 2, the processor 104 may sum the lane difference values shown as the lane change amount (ie, 0+0+0+1+1+2=4), but not limited to this.

在步驟S260中，處理器104可估計特定道路段330在第一時段內的新進車流量。在圖4中，處理器104可將介於車輛5~10之間的斜線格數(即，6)作為特定道路段330在第一時段內的新進車流量。 In step S260, the processor 104 may estimate the new traffic flow of the specific road segment 330 during the first period of time. In FIG. 4 , the processor 104 may take the number of diagonal grids (ie, 6) between vehicles 5 to 10 as the new traffic flow of the specific road segment 330 in the first time period.

在步驟S270中，處理器104可估計特定道路段330在子時間區間ST1內的離開車流量。在圖4中，處理器104可將子時間區間ST1內的點狀格數(即，8)作為特定道路段330在子時間區間ST1內的離開車流量。 In step S270, the processor 104 may estimate the outgoing traffic flow of the specific road segment 330 within the sub-time interval ST1. In FIG. 4 , the processor 104 may take the number of dots (ie, 8) in the sub-time interval ST1 as the outgoing traffic flow of the particular road segment 330 in the sub-time interval ST1.

在步驟S280中，處理器104可基於重疊時間區段OT及第一時段估計第一時段與第二時段之間的時間重疊度。在一實施例中，處理器104可以重疊時間區段OT(即，07：46~07：48)的長度(2分鐘)除以第一時段的時間長度(即，5分鐘)，以獲得時間重疊度(即，0.4)，但可不限於此。 In step S280, the processor 104 may estimate the degree of temporal overlap between the first period and the second period based on the overlapping time period OT and the first period. In one embodiment, the processor 104 may divide the length (2 minutes) of the overlapping time period OT (ie, 07:46~07:48) by the time length of the first period (ie, 5 minutes) to obtain the time The degree of overlap (ie, 0.4), but may not be limited thereto.

之後，在步驟S290中，處理器104可基於順序變換度、變換車道量、新進車流量、離開車流量及時間重疊度估計特定道路段330在第一時段內的車流混亂程度。在一實施例中，處理器104可基於多元迴歸分析法取得順序變換度、變換車道量、新進車流量、離開車流量及時間重疊度個別對應的係數。 Afterwards, in step S290, the processor 104 may estimate the degree of traffic chaos of the specific road segment 330 in the first period based on the degree of sequence change, the amount of changed lanes, the flow of new incoming vehicles, the flow of departing vehicles, and the degree of temporal overlap. In one embodiment, the processor 104 may obtain the coefficients corresponding to the order change degree, the lane change amount, the new incoming traffic flow, the departing traffic flow and the time overlap degree based on the multiple regression analysis method.

以順序變換度為例，處理器104可基於順序變換度的歷史數值及歷史事故資料進行多元迴歸分析，以取得順序變換度對應的係數。例如，處理器104可收集多個路段個別的歷史順序變換度及對應的歷史事故資料(例如有發生事故為1，沒發生事故為 0)，並據以進從多元迴歸分析，以取得順序變換度對應的係數。此外，處理器104可基於相似的原則取得變換車道量、新進車流量、離開車流量及時間重疊度個別對應的係數，其細節於此不另贅述。 Taking the order transformation degree as an example, the processor 104 may perform multiple regression analysis based on the historical value of the order transformation degree and historical accident data to obtain the coefficient corresponding to the order transformation degree. For example, the processor 104 can collect individual historical sequence transformation degrees of multiple road segments and corresponding historical accident data (for example, if an accident occurs, 1 is used, and if no accident occurs, it is 1). 0), and based on the multiple regression analysis to obtain the coefficients corresponding to the degree of order transformation. In addition, the processor 104 can obtain the coefficients corresponding to the lane change amount, the new incoming traffic flow, the departing traffic flow and the time overlap degree based on a similar principle, the details of which are not described here.

之後，處理器104可將順序變換度(例如4)、變換車道量(例如4)、新進車流量(例如6)、離開車流量(例如8)及時間重疊度(例如0.4)個別乘以對應的係數並加總為車流混亂程度。在一實施例中，假設順序變換度、變換車道量、新進車流量、離開車流量及時間重疊度對應的係數分別為0.5、0.2、0.2、0.2、6，則車流混亂程度可經計算為8(即，4x0.5+0.2x6+0.2x4+0.2x8+6x0.4)。 Afterwards, the processor 104 may individually multiply the order change degree (eg 4), the lane change amount (eg 4), the new incoming traffic volume (eg 6), the departing traffic volume (eg 8) and the time overlap (eg 0.4) by the corresponding The coefficients of , and summed up as the degree of traffic chaos. In one embodiment, assuming that the coefficients corresponding to the degree of sequence change, the amount of changed lanes, the flow of new incoming vehicles, the flow of departing vehicles, and the degree of time overlap are 0.5, 0.2, 0.2, 0.2, and 6, respectively, the degree of traffic confusion can be calculated as 8 (ie, 4x0.5+0.2x6+0.2x4+0.2x8+6x0.4).

在一實施例中，若所取得的車流混亂程度高於一車流亂度門檻值，則處理器104可發布告警訊息予交通控管人員，以提醒交通控管人員採取相關的措施，例如觀察特定道路段330的CCTV以找出特定道路段330出現車流混亂的原因等，但可不限於此。 In one embodiment, if the obtained traffic flow disorder degree is higher than a traffic flow disorder degree threshold, the processor 104 may issue a warning message to the traffic control personnel to remind the traffic control personnel to take relevant measures, such as observing certain traffic conditions. The CCTV of the road segment 330 is used to find out the reason for the traffic chaos in the specific road segment 330, but it is not limited to this.

綜上所述，本發明至少具備以下特點：(1)可透過既有的車道門架偵測記錄以評估某路段的車流混亂程度，其中此車流混亂程度可量化一路段中車流穿插的情形，藉此可以評估該路段會否因混亂的車流影響交通運輸量，並更進一步評估該路段是否容易因此發生事故或傷亡；(2)上述車流混亂程度亦可讓公部門在進行交通決策上也有量化的數據可供參考，有數據佐證也更能強化該政策執行的重要性及合理性。若能有效地在相對混亂的路段上執行適合的交控策略如增設告示或雙白線減少車輛變化車道，相信能大幅降低事故發生率增加路段交通運輸量。 To sum up, the present invention has at least the following features: (1) The degree of traffic chaos in a certain road section can be evaluated through the existing lane gantry detection records, wherein the degree of traffic chaos can quantify the situation of traffic interspersed in a road section, In this way, it is possible to assess whether the road section will affect the traffic volume due to chaotic traffic flow, and further assess whether the road section is prone to accidents or casualties; (2) The above-mentioned degree of traffic chaos can also be quantified by the public sector in making traffic decisions The data can be used for reference, and it can be more Strengthen the importance and rationality of the implementation of this policy. If appropriate traffic control strategies can be effectively implemented on relatively chaotic road sections, such as adding notices or double white lines to reduce vehicles changing lanes, it is believed that the accident rate can be greatly reduced and the traffic volume of the road section can be greatly reduced.

雖然本發明已以實施例揭露如上，然其並非用以限定本發明，任何所屬技術領域中具有通常知識者，在不脫離本發明的精神和範圍內，當可作些許的更動與潤飾，故本發明的保護範圍當視後附的申請專利範圍所界定者為準。 Although the present invention has been disclosed above by the embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, The protection scope of the present invention shall be determined by the scope of the appended patent application.

S210~S290:步驟 S210~S290: Steps

Claims

一種估計車流混亂程度的方法，包括：透過設置於一特定道路的一第一門架偵測通過該第一門架的多個第一車輛及各該第一車輛通過該第一門架的一第一時間點；透過設置於該特定道路的一第二門架偵測在一第一時段內通過該第二門架的多個第二車輛，其中該第二門架位於該第一門架的下游，且該第二門架及該第一門架之間具有一特定道路段；在該些第二車輛中找出匹配於該些第一車輛的一部分的多個第一特定車輛，並基於各該第一特定車輛的該第一時間點定義一第一參考時間區間；基於該第一參考時間區間與一第二參考時間區間的一重疊時間區間在該第一參考時間區間內定義一子時間區間，其中該第二參考時間區間對應於先於該第一時段的一第二時段；估計各該第一特定車輛自該第一門架至該第二門架的一順序變換度及一變換車道量；估計該特定道路段在該第一時段內的一新進車流量；估計該特定道路段在該子時間區間內的一離開車流量；基於該重疊時間區段及該第一時段估計該第一時段與該第二時段之間的一時間重疊度；基於該順序變換度、該變換車道量、該新進車流量、該離開車流量及該時間重疊度估計該特定道路段在該第一時段內的一車流混亂程度。 A method of estimating the degree of chaotic traffic flow, including: Detecting a plurality of first vehicles passing through the first gantry and a first time point when each of the first vehicles passes through the first gantry through a first gantry disposed on a specific road; Detecting a plurality of second vehicles passing through the second gantry within a first period of time through a second gantry disposed on the specific road, wherein the second gantry is located downstream of the first gantry, and the There is a specific road section between the second gantry and the first gantry; finding a plurality of first specific vehicles matching a part of the first vehicles among the second vehicles, and defining a first reference time interval based on the first time point of each of the first specific vehicles; A sub-time interval is defined within the first reference time interval based on an overlapping time interval of the first reference time interval and a second reference time interval, wherein the second reference time interval corresponds to a time period preceding the first time period second period; estimating a sequence change degree and a lane change amount of each first specific vehicle from the first gantry to the second gantry; estimating a new traffic flow for the particular road segment during the first period; estimating an outgoing traffic flow for the particular road segment within the sub-time interval; estimating a degree of temporal overlap between the first period and the second period based on the overlapping time period and the first period; Based on the order change degree, the change lane amount, the new incoming traffic flow, the departing traffic flow and the time overlap degree, a traffic flow disorder degree of the specific road segment in the first time period is estimated.

如請求項1所述的方法，其中基於該些第一特定車輛的該第一時間點定義該第一參考時間區間的步驟包括：在該些第一特定車輛的該第一時間點中找出一最大時間點及一最小時間點；將該最大時間點與該最小時間點之間的時間區間定義為該第一參考時間區間。 The method of claim 1, wherein the step of defining the first reference time interval based on the first time points of the first specific vehicles comprises: finding a maximum time point and a minimum time point among the first time points of the first specific vehicles; A time interval between the maximum time point and the minimum time point is defined as the first reference time interval.

如請求項2所述的方法，其中基於該第一參考時間區間與該第二參考時間區間的該重疊時間區間在該第一參考時間區間內定義該子時間區間的步驟包括：在該重疊時間區間內定義一特定時間點，並將該最大時間點及該特定時間點之間的時間區間定義為該子時間區間。 The method of claim 2, wherein the step of defining the sub-time interval within the first reference time interval based on the overlapping time interval of the first reference time interval and the second reference time interval comprises: A specific time point is defined within the overlapping time interval, and a time interval between the maximum time point and the specific time point is defined as the sub-time interval.

如請求項1所述的方法，更包括：透過該第二門架偵測在該第二時段內通過該第二門架的多個第三車輛及各該第三車輛通過該第二門架的一第三時間點；在該些第三車輛中找出匹配於該些第一車輛的另一部分的多個第二特定車輛，並基於各該第二特定車輛的該第一時間點定義該第二參考時間區間。 The method according to claim 1, further comprising: detecting, through the second gantry, a plurality of third vehicles passing through the second gantry and a third time point at which each of the third vehicles passes through the second gantry during the second period; A plurality of second specific vehicles matching another part of the first vehicles are found among the third vehicles, and the second reference time interval is defined based on the first time point of each of the second specific vehicles.

如請求項1所述的方法，其中該些第一特定車輛包括一參考車輛，且估計各該第一特定車輛自該第一門架至該第二門架的該順序變換度的步驟包括：對於該參考車輛而言，取得該參考車輛在該些第一特定車輛中通過該第一門架的一第一順序及通過該第二門架的一第二順序；估計該第一順序與該第二順序之間的一順序差值；將各該第一特定車輛的該順序差值加總為該順序變換度。 The method of claim 1 , wherein the first specific vehicles comprise a reference vehicle, and the step of estimating the degree of sequence transformation of each of the first specific vehicles from the first mast to the second mast comprises: For the reference vehicle, obtaining a first sequence of passing the reference vehicle through the first gantry and a second sequence of passing through the second gantry in the first specific vehicles; estimating an order difference between the first order and the second order; The sequence difference value of each of the first specific vehicles is summed up as the sequence change degree.

如請求項1所述的方法，其中該些第一特定車輛包括一參考車輛，且估計各該第一特定車輛自該第一門架至該第二門架的該變換車道量的步驟包括：對於該參考車輛而言，取得該參考車輛通過該第一門架時所在的一第一車道及通過該第二門架時所在的一第二車道；估計該第一車道與該第二車道之間的一車道差值；將各該第一特定車輛的該車道差值加總為該變換車道量。 The method of claim 1, wherein the first specific vehicles comprise a reference vehicle, and the step of estimating the lane change amount of each of the first specific vehicles from the first gantry to the second gantry comprises: For the reference vehicle, obtain a first lane where the reference vehicle passes through the first gantry and a second lane where it passes through the second gantry; estimating a lane difference between the first lane and the second lane; The lane difference value of each of the first specific vehicles is summed as the lane change amount.

如請求項1所述的方法，其中基於該重疊時間區段及該第一時段估計該第一時段與該第二時段之間的該時間重疊度的步驟包括：以該重疊時間區段的長度除以該第一時段的一時間長度，以獲得該時間重疊度。 The method of claim 1, wherein the step of estimating the degree of time overlap between the first time period and the second time period based on the overlapping time period and the first time period comprises: The time overlap degree is obtained by dividing the length of the overlapping time segment by a time length of the first time period.

如請求項1所述的方法，其中基於該順序變換度、該變換車道量、該新進車流量、該離開車流量及該時間重疊度估計該特定道路段在該第一時段內的該車流混亂程度的步驟包括：基於一多元迴歸分析法取得該順序變換度、該變換車道量、該新進車流量、該離開車流量及該時間重疊度個別對應的一係數；將該順序變換度、該變換車道量、該新進車流量、該離開車流量及該時間重疊度個別乘以對應的該係數並加總為該車流混亂程度。 The method of claim 1, wherein the traffic chaos of the specific road segment within the first period is estimated based on the order change degree, the change lane amount, the new incoming traffic flow, the departing traffic flow and the temporal overlap degree Degree steps include: Based on a multiple regression analysis method, obtain a coefficient corresponding to the sequence change degree, the lane change amount, the new incoming traffic flow, the departing traffic flow and the time overlap degree respectively; Multiply the sequence change degree, the change lane amount, the new incoming traffic flow, the departing traffic flow and the time overlap degree by the corresponding coefficients and add up to the traffic flow disorder degree.

一種估計車流混亂程度的伺服器，包括：一儲存電路，儲存多個模組；以及一處理器，耦接該儲存電路，存取該些模組以執行下列步驟：透過設置於一特定道路的一第一門架偵測通過該第一門架的多個第一車輛及各該第一車輛通過該第一門架的一第一時間點；透過設置於該特定道路的一第二門架偵測在一第一時段內通過該第二門架的多個第二車輛，其中該第二門架位於該第一門架的下游，且該第二門架及該第一門架之間具有一特定道路段；在該些第二車輛中找出匹配於該些第一車輛的一部分的多個第一特定車輛，並基於各該第一特定車輛的該第一時間點定義一第一參考時間區間；基於該第一參考時間區間與一第二參考時間區間的一重疊時間區間在該第一參考時間區間內定義一子時間區間，其中該第二參考時間區間對應於先於該第一時段的一第二時段；估計各該第一特定車輛自該第一門架至該第二門架的一順序變換度及一變換車道量；估計該特定道路段在該第一時段內的一新進車流量；估計該特定道路段在該子時間區間內的一離開車流量；基於該重疊時間區段及該第一時段估計該第一時段與該第二時段之間的一時間重疊度；基於該順序變換度、該變換車道量、該新進車流量、該離開車流量及該時間重疊度估計該特定道路段在該第一時段內的一車流混亂程度。 A server that estimates the level of confusion in traffic, including: a storage circuit storing a plurality of modules; and A processor, coupled to the storage circuit, accesses the modules to perform the following steps: Detecting a plurality of first vehicles passing through the first gantry and a first time point when each of the first vehicles passes through the first gantry through a first gantry disposed on a specific road; Detecting a plurality of second vehicles passing through the second gantry within a first period of time through a second gantry disposed on the specific road, wherein the second gantry is located downstream of the first gantry, and the There is a specific road section between the second gantry and the first gantry; finding a plurality of first specific vehicles matching a part of the first vehicles among the second vehicles, and defining a first reference time interval based on the first time point of each of the first specific vehicles; A sub-time interval is defined within the first reference time interval based on an overlapping time interval of the first reference time interval and a second reference time interval, wherein the second reference time interval corresponds to a time period preceding the first time period second period; estimating a sequence change degree and a lane change amount of each first specific vehicle from the first gantry to the second gantry; estimating a new traffic flow for the particular road segment during the first period; estimating an outgoing traffic flow for the particular road segment within the sub-time interval; estimating a degree of temporal overlap between the first period and the second period based on the overlapping time period and the first period; Based on the sequence change degree, the change lane amount, the new incoming traffic flow, the departing traffic flow and the time overlap degree, a traffic flow disorder degree of the specific road segment in the first time period is estimated.