Method, device and program for adaptively controlling traffic signals

Abstract

The present disclosure provides a method and apparatus for adaptively controlling a traffic signal. The method for adaptively controlling a traffic signal based on a traffic control plan includes identifying, by a processor (806, 907), an external intervention occurring at an intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan, and modifying, by the processor (806, 907), the traffic control plan based on the traffic control behavior caused by the external intervention.

Description

[Technical field]

[0001] The present invention relates broadly, but not exclusively, to methods, apparatus and systems for adaptively controlling traffic signals. [Background technology]

[0002] Adaptive control systems such as Split Cycle Offset Optimization Technique (SCOOT) and Sydney Coordinated Adaptive Traffic System (SCATS) were initially developed for adaptive phase control where traffic lights are switched through multiple phases in a cyclical sequence. Traffic engineers can manually select the phases and predefine their ordering in the cyclical sequence. These systems can make real-time adjustments in the time between each phase, which are based on measurements of traffic flow saturation levels.

[0003] Newer generations of Adaptive Traffic Signal Control (ATSC) systems are self-adaptive or self-learning. They can detect road incidents, predict traffic flow, and respond to traffic conditions. They are also integrated traffic management and control systems that perform coordinated optimization of larger areas of the road network. Summary of the Invention [Problem to be solved by the invention]

[0004] However, these adaptive signal control systems rely on expected or predictable traffic flow patterns. If there is a traffic jam or obstruction on the road, an accident or detour, or if the traffic light signal is out of order, traffic police officers may manually direct traffic to avoid confusion for drivers. These traffic police officers typically do not receive instructions from the associated traffic signal control system and do not preempt their own next action system regarding traffic direction. Thus, such traffic direction is not integrated into the relevant traffic management and control system, which may result in the system being less effective.

[0005] Disclosed herein are embodiments of devices and methods for adaptively controlling traffic signals that address one or more of the above problems.

[0006] Furthermore, other desirable features and characteristics will become apparent from the following detailed description and the appended claims, taken in conjunction with the accompanying drawings and this background of the disclosure. [Means for solving the problem]

[0007] In a first aspect, the present disclosure provides a method for adaptively controlling traffic signals based on a traffic control plan, the method including: identifying, by a processor, an external intervention occurring at an intersection, the external intervention causing traffic control behavior at the intersection that deviates from the traffic control plan; and modifying, by the processor, the traffic control plan based on the traffic control behavior caused by the external intervention.

[0008] In a second aspect, the present disclosure provides an apparatus for adaptively controlling traffic signals based on a traffic control plan, the apparatus comprising a memory in communication with a processor, the memory storing a computer program recorded therein, the computer program executable by the processor to cause the apparatus to at least identify an external intervention occurring at an intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan, and modifying the traffic control plan based on the traffic control behavior caused by the external intervention.

[0009] In a third aspect, the present disclosure provides a system for adaptively controlling a traffic signal, the system comprising an apparatus of the second aspect and at least one image capture device.

[0010] The accompanying drawings, in which like reference numbers may refer to identical or functionally similar elements throughout the different views, are incorporated in and form a part of the specification, together with the following detailed description, and illustrate various embodiments by way of non-limiting examples only and serve to explain various principles and advantages according to the present embodiments. [Brief description of the drawings]

[0011] Embodiments of the present invention will be better understood and readily apparent to those skilled in the art from the following description, given by way of example only, in conjunction with the drawings in which: [Figure 1] 1 shows an illustrative example of manual guidance of traffic at an intersection, according to various embodiments of the present disclosure. [Diagram 2] 1 shows a schematic diagram of an adaptive traffic signal control system according to various embodiments of the present disclosure. [Diagram 3] 1 illustrates examples of traffic hand signals according to various embodiments of the present disclosure. [Figure 4] 1 is a graph illustrating traffic flow according to various embodiments of the present disclosure. [Diagram 5] 1 illustrates an example of an exemplary control strategy implemented by manual guidance of traffic, according to various embodiments of the present disclosure. [Figure 6A]4 illustrates an example of flow rate and turn ratio at an intersection according to various embodiments of the present disclosure. [Figure 6B] 4 illustrates an example of flow rate and turn ratio at an intersection according to various embodiments of the present disclosure. [Figure 7A] 1 illustrates an exemplary flow chart for adaptive traffic control, according to various embodiments of the present disclosure. [Figure 7B] 1 illustrates an exemplary flow chart for adaptive traffic control, according to various embodiments of the present disclosure. [Figure 7C] 1 illustrates an exemplary flow chart for adaptive traffic control, according to various embodiments of the present disclosure. [Figure 7D] 1 illustrates an exemplary flow chart for adaptive traffic control, according to various embodiments of the present disclosure. [Figure 7E] 1 illustrates an exemplary flow chart for adaptive traffic control, according to various embodiments of the present disclosure. [Figure 8] FIG. 1 shows a block diagram illustrating a system for adaptive traffic control according to various embodiments of the present disclosure. [Figure 9] 1 illustrates an exemplary computing device that can be used to execute the methods of the previous figures. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Explanation of terms Intersection refers to a traffic intersection (e.g., a T-junction, a crossroads, a roundabout, or any similar intersection) where a traffic control system is implemented to control traffic signals so that vehicles and pedestrians can navigate the intersection safely and efficiently.

[0013] Adaptive traffic control systems such as SCOOT and SCATS use adaptive phase control in which traffic lights are switched through multiple phases in a cyclical sequence. For example, the traffic control system determines and implements the optimal duration that the green light is on for vehicles to drive through or turn at an intersection, the optimal duration that the green light is on for pedestrians to cross an intersection, and other similar durations such that vehicular congestion and traffic congestion are minimized while maintaining a high level of safety for both vehicles and pedestrians alike so that accidents are avoided.

[0014] Furthermore, unlike traditional traffic control systems, these adaptive traffic control systems are able to make real-time adjustments in the time between phases, which are based on measurements of traffic flow saturation levels. Newer ASTC systems can detect road incidents, predict traffic flow, and respond to traffic conditions in real-time. Generally, these systems are implemented to perform coordinated optimization of traffic control over large areas of a road network, which may include one or more intersections.

[0015] External intervention refers to a factor outside the traffic control plan that causes traffic control behavior to deviate from the traffic control plan. For example, external intervention at an intersection may cause a vehicle to cross the intersection or turn at an intersection when the vehicle is not supposed to do so based on the traffic control plan. In another example, external intervention at an intersection may cause a pedestrian to cross the road at the intersection when the pedestrian is not supposed to do so based on the traffic control plan. External intervention may include manual intervention, such as police or road safety personnel directing traffic, or accidents and other anomalies that may affect traffic flow. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Where reference is made in any one or more of the accompanying drawings to steps and / or features that may have the same reference numbers, those steps and / or features have the same function(s) or operation(s) for the purposes of this description, unless a contrary intention appears.

[0017] It should be noted that the descriptions contained in the "Background" section and the above descriptions of prior art configurations relate to descriptions of devices that form public knowledge through their use, and should not be construed as a representation by the inventor(s) or patent applicant that such devices in any way form part of the common general knowledge in the art.

[0018] Typically, the control of traffic signals at an intersection may be performed by a traffic control system. The traffic control system may implement a traffic control plan at the intersection to control the traffic signals at the intersection, as well as for adjacent intersections covered by the traffic control system. When an external intervention occurs at an intersection, where the control plan exercised by the external intervention overrides the existing traffic control plan at the intersection, the adjacent intersections of the intersection may not be optimized. For example, the external intervention may be a manual intervention by traffic police or road safety personnel directing traffic at the intersection. To address this override problem, this "manual intervention" may be used as a new variable in the existing traffic control plan and also as a constraint in the traffic control plan for the adjacent intersections.

[0019] Various prior arts have proposed techniques to predict and maximize traffic flow. However, such techniques require a large amount of data, and therefore it is unrealistic to assume that there is sufficient traffic flow data regarding external intervention situations (especially when manual intervention is involved) to support the techniques. Another proposed solution utilizes fuzzy logic to improve traffic signal control systems. However, this solution expects all traffic controllers at all intersections to be in good working order to enjoy the benefits of such fuzzy logic-based adaptive signal control. Yet another proposed solution involves falling back to a local traffic signal control system in case of failure of a centralized or regional traffic control system, but does not take into account manual intervention by traffic police officers to manually direct traffic, which is still a widely used method in many cities around the world.

[0020] 1 shows an example diagram 100 for manual guidance of traffic at an intersection. A traffic control system, such as an ATSC system, can implement a traffic control plan at one or more intersections to control traffic signals at the intersection. However, a situation may arise where manual guidance of traffic may occur at an intersection 102, for example, where a traffic police officer or any other traffic safety personnel manually guides traffic, for example, using a manual signal to override a traffic signal condition at the intersection 102. Thus, manual guidance of traffic occurring at the intersection 102 can be detected and analyzed, such that the traffic control plan for the local area within the vicinity of the intersection can be adjusted accordingly.

[0021] For example, a traffic police officer or road safety personnel directing traffic at the intersection 102 may be detected by one or more video cameras. These cameras may capture images of the person directing traffic at the intersection 102 and analyze the captured images via video analytics or other similar techniques to determine a control plan to be implemented by the person. This control plan may then be integrated into the traffic control plan implemented by the traffic control system for the intersection 102, such that the traffic control plan is modified or adjusted based on the control plan of the manual traffic guidance. The adjusted traffic control plan delivers predictable traffic flow patterns to the traffic control system and becomes an adaptive constraint for optimization of traffic control. Thus, advantageously, the manual guidance of traffic at the intersection 102 is incorporated as a variable into the traffic control plan of the traffic control system, allowing the system to better adapt to real-world conditions to implement an efficient traffic control plan.

[0022] Additionally, the traffic control plans of neighboring intersections, such as, for example, 104, 106, 108, and 110, within the local area of ​​intersection 102, are also adjusted or modified based on the control plan for manual traffic guidance. This advantageously reduces the impact of manual traffic guidance around the local area of ​​intersection 102. It will be appreciated that the traffic control plans of other intersections further away from intersection 102 may also be adjusted or modified accordingly.

[0023] FIG. 2 shows a schematic diagram of an exemplary ATSC system 200 according to various embodiments of the present disclosure. The ATSC system may have a subsystem 202 supporting manual guidance having a manual guidance detection module 204 and a local area signal control module 206. Traffic sensor(s) 208, such as video / surveillance / CCTV cameras, may capture video and / or images of an intersection covered by the ATSC system in real time and provide the captured video as input to an analysis module 210, where video and other analysis techniques may be used to process the captured video or images. The processed video or images may then be provided as input to the subsystem 202, and a control plan and / or traffic flow information for the intersection may then be determined based on the processed video or images. The determined information is then provided as input to a subsystem 212 for global adaptive signal control, and the provided information is used as an update constraint or variable to modify or adjust the traffic control plan implemented at the intersection by the ATSC system 200. The modified or adjusted traffic control plan is then implemented by the traffic controller(s) module 214, which controls the traffic signals at the intersection based on the modified or adjusted traffic control plan.

[0024] It will be appreciated that traffic control planning for more than one intersection may be performed in real time. Additionally, the traffic control system may include a single processor capable of performing the functions of at least subsystems 202, 204, 206, 210, and 212, such as identifying an external intervention occurring at an intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan for the intersection, and modifying the traffic control plan based on the traffic control behavior caused by the external intervention.

[0025] A method for detecting manual traffic guidance at an intersection may include detecting the presence of a traffic police officer or other traffic safety personnel directing traffic via video analysis. To improve the accuracy of the detection, supporting methods such as anomaly detection by comparison of the current traffic flow (from sensors such as induction loops, lidar, video, etc.) with the current traffic signal control (issued by a traffic control system such as an ATSC system) may be implemented. Another method to improve the detection accuracy may be the implementation of an automatic fault detection or monitoring system for traffic lights to ensure that the traffic lights at the intersection are functioning properly.

[0026] Videos acquired from video / surveillance / CCTV cameras are usually stored in mpg or any video codec format. Each video may be read out and split into multiple frames per video. Through video analysis techniques known in the art, captured videos of possible external interventions at an intersection acquired from video / surveillance / CCTV cameras may be processed for detection of manual interventions, for example, for detection of police officers or other road safety personnel directing traffic at the intersection. Labeling may be done for traffic police (especially those wearing police uniforms, police badges or ID tags), other road safety personnel (e.g., those wearing safety vests, safety helmets, holding batons, or having other similar characteristics), and also for hand signals. FIG. 3 shows a diagram 300 of common hand signals that may be used to direct traffic and which video analysis techniques may be utilized to detect them. For example, object detection methods such as Region Based Convolutional Neural Network (RCNN), Detectron, You Only Look Once (YOLO), or other similar methods can be applied to detect hand signs used during manual intervention. The sequence in which these hand signs are used, as well as the duration for which each hand sign is used, can also be determined. This information may be used to determine the control plan in which manual intervention is applied at the intersection.

[0027] Situations may arise where hand signals cannot be detected using video analytics, or where external / manual intervention does not appear to be present in the intersection, or where a person directing traffic at the intersection cannot be clearly seen. In such cases, anomaly detection techniques can be used to check for manual intervention. For example, anomaly detection methods known in the art can be used to detect any abnormal changes in traffic flow patterns, which can help identify any faulty intersections and the resulting traffic flows. With reference to graph 400 in FIG. 4, the normal traffic flow at the intersection during a day can be represented by line 402, and the current traffic flow at the intersection can be represented by line 404. Anomalies that deviate from the normal traffic flow as shown in line 402 can be detected for line 404, as seen in abnormally high traffic flow during a red traffic light (i.e., when vehicles should be stopped and therefore traffic flow should be low), and / or abnormally low traffic flow during a green traffic light (i.e., when vehicles should be moving and therefore traffic flow should be high). The anomaly can be determined to be an abnormal change in the traffic flow pattern. Further investigation of the situation at the intersection may then be required. Advantageously, anomaly detection methods can be used to infer a control plan triggered by external / manual intervention based on traffic flow patterns and other traffic variables. This can be done using machine learning approaches.

[0028] The sensor information may be used to understand the control plan executed by manual guidance from the most recent cycle or cycles of the traffic light sequence. For example, information such as cycle start time, cycle duration, green duration, yellow duration, turn sequence, and other similar information may be obtained to determine the control plan executed manually or by external intervention. These information may be presented as shown in diagram 500 of FIG. 5. For example, in cycle duration 502, turn sequence 504 may occur at green duration 506 and yellow duration 508. These information may be combined with traffic flow information of turn sequence 504 and all other sequences in cycle duration 502 to infer the control plan executed by external intervention. For example, the sensor information may be utilized to understand the sequence of turn events (as shown in turn sequence 504) and their durations (as shown in green duration 506 and yellow duration 508) so that a control plan may be inferred.

[0029] The sensor information may also be used to understand the current traffic situation from the most recent cycle or cycles of the traffic light sequence. For example, information such as flow rate f, turning ratio r, and other similar information may be obtained to determine a control plan to be executed manually or by external intervention. These information may be presented as shown in diagram 600 of FIG. 6A and diagram 610 of FIG. 6B. For example, diagram 600 shows a traffic flow from side a 602 with flow rate 604, which turns left to side b 606 with turning ratio 608, goes straight to side c 610 with turning ratio 612, and turns right to side d 614 with turning ratio 616. Diagram 620 shows a traffic flow from side d 622 with flow rate 624, which turns left to side a 626 with turning ratio 628, goes straight to side b 630 with turning ratio 632, and turns right to side c 634 with turning ratio 636.

[0030] 7A illustrates an example flow chart 700 for simulation-based adaptive traffic control, according to various embodiments of the present disclosure. For example, intersection z may be under external intervention. Through a process 702 that utilizes video and other analysis techniques, it is determined that the external intervention z With intersection z having a traffic volume (i.e., having traffic flow rate(s) and turning ratio(s)) represented by z In addition, the traffic control plan (e.g., T n The control plan CP may also be determined in process 702 using video and other analysis techniques. z , traffic volume T z and traffic volume T n This information is input to process 704, where the control plan CP z , traffic volume T z and traffic volume T n These variations are then combined into a control plan CP z , traffic volume T z , and traffic volume T n Based on each transformation of z, the possible traffic conditions and corresponding control plans CP n Alternatively, the user-defined control plan CP z , traffic volume T z , and traffic volume T n may be provided instead of a simulation. The user-defined control plan and traffic information are then input to process 708, where the (user-defined) control plan CP z , traffic volume T z and traffic volume T n Further variations of , are then generated, and these generated variations are then subjected to a simulation process 710 to generate possible traffic conditions and corresponding control plans CP for adjacent or nearby intersections of intersection z based on each variation. nIt will be appreciated that processes 704, 706, 708, and 710 may be implemented as online (e.g., real-time connection with a traffic control system) and / or offline processes.

[0031] CP from processes 706 and 710 n and their corresponding inputs (control plan CP z , traffic volume T z and traffic volume T n The simulation results of junction z) are then stored in database 712 as a cumulative pre-learned situation that can be referenced by the adaptive traffic control system to determine a suitable control plan for the neighboring intersections of intersection Z. In other words, the cumulative pre-learned situation can be saved data from past simulations of traffic conditions for intersection Z and neighboring or nearby intersections of intersection z (or other intersections whose situation or location may be similar to intersection z) based on previously encountered or previous user-defined control plans and traffic parameters. For example, the control plan CP z , traffic volume T z , and traffic volume T n Values ​​of may be obtained from process 702 using video and other analysis techniques and provided as inputs to process 714, which may include cumulative pre-training conditions (e.g., CP n Previous simulation results and control plan CP z , traffic volume T z , and traffic volume T n In process 714, it is determined whether there is a cumulative pre-learned situation similar to the current situation (e.g., the control plan CP z , traffic volume T z , and traffic volume T n The previously stored value of the control plan CP z , traffic volume T z , and traffic volume T n, the pre-trained situation that is most similar to the current situation is determined and input to process 718, and then the appropriate pre-trained control plan (e.g., the control plan CP n ) is applied to intersections adjacent or nearby intersection z. If in process 714 it is determined that there is no suitable cumulative pre-learned situation, then fuzzy logic in process 716 can be implemented to determine an appropriate control strategy for the adjacent intersection. Fuzzy logic refers to a non-linear mapping of inputs to obtain a scalar output. This is called the control strategy CP z , traffic volume T z , and traffic volume T n , fuzzy logic may be utilized when no suitable pre-trained control plan is available for retrieval in database 712. In this case, the control plan CP z The external intervention with a set of,T,is used as a parameter to determine the optimal control plan for the adjacent intersections,with traffic volume T z and traffic volume T n may be included as input parameters for determining an optimal control plan via fuzzy logic, and the determined optimal control plan may be applied to the associated adjacent intersections, or a pre-trained control plan CP having the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections as corresponding simulation inputs may be included. n The determined control strategy may then be input to process 718 for application to intersections adjacent or nearby intersection z. Advantageously, process 714 provides a fallback position when a pre-learned situation that most closely resembles the current traffic situation is not available.

[0032] 7B illustrates another example flow chart 720 for simulation-based adaptive traffic control according to various embodiments of the present disclosure. For example, intersection z may be under external intervention. In process 722, sensor information of cycle start time, cycle duration, green duration, yellow duration, turn sequence, and other similar information at intersection z may be obtained via traffic sensors. The sensor information may further include information of cycle start time, cycle duration, green duration, yellow duration, turn sequence, and other similar information from other intersections, for example, adjacent to intersection z.

[0033] External intervention may be provided through process 724, which utilizes video and other analytical techniques to analyze sensor information. z Intersection z having a traffic volume (i.e., having a traffic flow rate(s) and a turning ratio(s)) represented by z In addition, the control plan represented by the following formula can be determined:

number

number

number

number

number

number

number

number

number

[0034] 7C illustrates another example flowchart 740 for simulation-based adaptive traffic control, according to various embodiments of the present disclosure. The process illustrated in flowchart 740 is the same as that illustrated in flowchart 720, except that the parameter CP z , T z and

number

[0035] 7D illustrates another example flowchart 750 for simulation-based adaptive traffic control, according to various embodiments of the present disclosure. The parameter CP z , T z ,

number

number

[0036] 7E shows an example flowchart 760 of how the model M may be utilized for simulation-based adaptive traffic control, according to various embodiments of the present disclosure. In a process 762, similar to process 724 of flowchart 720, video and other analysis techniques are applied to determine the parameters CP z , T z , and

number

number

number

number

number

number

[0037] FIG. 8 illustrates a block diagram illustrating a system 800 for adaptive traffic control according to various embodiments. In one example, management of video or image input is performed by at least an image capture device 802 and an apparatus 804. The system 800 comprises an image capture device 802 in communication with the apparatus 804. In one implementation, the apparatus 804 can be generally described as a physical device comprising at least one processor 806 and at least one memory 808 including computer program code. The at least one memory 808 and the computer program code, together with the at least one processor 806, are configured to cause the physical device to perform the operations described in FIG. 2 and FIG. 7. The processor 806 is configured to receive images from the image capture device 802 or retrieve images from a database 810.

[0038] Video or image capture device 802 may be a device capable of inputting video or images. For example, digital video may be input, or physical media containing digital video (i.e., storage drives, DVDs, VCDs, and other similar media) or analog video (i.e., video cassettes or other similar media) may be input so that the video or multiple images taken from the video are scanned and used as input. The image capture device may also be a video / CCTV / surveillance camera from which video may be captured and used as input for device 804.

[0039] The apparatus 804 may be configured to communicate with the image capture device 802 and the database 810. The database may comprise software and / or operating systems for the apparatus 804 and the system 800, and may also comprise stored data of pre-learned situations as described in FIG. 7. In one example, the apparatus 804 may receive an input video or a plurality of images from a video of an intersection from the image capture device 802 or retrieve from the database 810, and after processing the input video or the plurality of images from the video by the processor 806 in the apparatus 804, identify an external intervention occurring at the intersection, where the external intervention causes a traffic control behavior at the intersection that deviates from an existing traffic control plan for the intersection. The apparatus 804 may also be configured to modify the existing traffic control plan based on the traffic control behavior caused by the external intervention.

[0040] Figure 9 illustrates an exemplary computing device 900, hereinafter referred to interchangeably as computer system 900 or device 900, one or more such computing devices 900 may be used to implement the system 800 shown in Figure 8 or the methods of the previous figures. The following description of computing device 900 is provided by way of example only and is not intended to be limiting.

[0041] 9, the exemplary computing device 900 includes a processor 907 for executing software routines. Although a single processor is shown for clarity, the computing device 900 may also include a multi-processor system. The processor 907 is connected to a communications infrastructure 906 for communicating with other components of the computing device 900. The communications infrastructure 906 may include, for example, a communications bus, crossbar, or network.

[0042] The computing device 900 further includes a primary memory 908, such as random access memory (RAM), and a secondary memory 910. The secondary memory 910 may include a storage drive 912, which may be, for example, a hard disk drive, a solid state drive, or a hybrid drive, and / or a removable storage drive 914, which may include a magnetic drive, an optical disk drive, a solid state storage drive (e.g., a USB flash drive, a flash memory device, a solid state drive, or a memory card), or the like. The removable storage drive 914 reads from and / or writes to a removable storage medium 918 in a well-known manner. The removable storage medium 918 may include magnetic, optical disk, non-removable storage media, etc., that are read from and written to by the volatile memory drive 914. As will be appreciated by one of ordinary skill in the art(s), the removable storage medium 918 includes a computer-readable storage medium having computer-executable program code instructions and / or data stored thereon.

[0043] In alternative implementations, the secondary memory 910 may additionally or alternatively include other similar means for allowing computer programs or other instructions to be loaded into the computing device 900. Such means may include, for example, a removable storage unit 922 and interface 920. Examples of removable storage units 922 and interfaces 920 include program cartridges and cartridge interfaces (such as those found in video game console devices), removable memory chips (such as EPROMs or PROMs) and associated sockets, removable solid-state storage drives (such as USB flash drives, flash memory devices, solid-state drives or memory cards), and other removable storage units 922 and interfaces 920 that allow software and data to be transferred from the removable storage unit 922 to the computer system 900.

[0044] The computing device 900 also includes at least one communication interface 924. The communication interface 924 allows software and data to be transferred between the computing device 900 and external devices via a communication path 926. In various embodiments of the invention, the communication interface 924 allows data to be transferred between the computing device 900 and a data communication network, such as a public or private data communication network. The communication interface 924 may be used to exchange data between different computing devices 900, which form part of an interconnected computer network. Examples of the communication interface 924 may include a modem, a network interface (such as an Ethernet card), a communication port (such as serial, parallel, printer, GPIB, IEEE 1394, RJ45, etc.), an antenna with associated circuitry, etc. The communication interface 924 may be wired or wireless. The software and data transferred via the communication interface 924 is in the form of signals, which may be electronic, electromagnetic, optical, or other signals capable of being received by the communication interface 924. These signals are provided to the communication interface via the communication path 924.

[0045] As shown in FIG. 9, the computing device 900 may further include a display interface 902 that performs operations for rendering images or videos on an associated display 930, and an audio interface 932 that performs operations for playing audio content via associated speaker(s) 934.

[0046] As used herein, the term "computer program product" (or computer readable medium, which may be a non-transitory computer readable medium) may refer, in part, to removable storage medium 918, removable storage unit 922, a hard disk installed in storage drive 912, or a carrier wave that carries software to communication interface 924 via communication path 926 (wireless link or cable). A computer readable storage medium (or a plurality of computer readable media) refers to any non-transitory, non-volatile tangible storage medium that provides recorded instructions and / or data to computing device 900 for execution and / or processing. Examples of such storage media include magnetic, CD-ROM, Blu-ray disk, hard disk drive, ROM or IC, solid state storage drive (such as USB flash drive, flash memory device, solid state drive or memory card), hybrid drive, magneto-optical disk, or computer readable card such as PC card, etc., whether such device is internal or external to computing device 900. Examples of transitory or non-tangible computer-readable transmission media that may be involved in providing software, application programs, instructions, and / or data to computing device 900 include wireless or infrared transmission channels, as well as network connections to other computers or networked devices, and the Internet or intranets, including email transmissions and information stored on websites and the like.

[0047] Computer programs (also referred to as computer program code) are stored in primary memory 908 and / or secondary memory 910. Computer programs may also be received via communications interface 924. Such computer programs, when executed, enable computing device 900 to perform one or more features of the embodiments discussed herein. In various embodiments, the computer programs, when executed, enable processor 907 to perform the features of the above-mentioned embodiments. Such computer programs thus represent controllers of computer system 900.

[0048] The software may be stored in a computer program product and loaded into the computing device 900 using the removable storage drive 914, the storage drive 912, or the interface 920. The computer program product may be a non-transitory computer readable medium. Alternatively, the computer program product may be downloaded to the computer system 900 via the communications path 926. The software, when executed by the processor 907, causes the computing device 900 to perform the functions of the embodiments described herein.

[0049] It should be understood that the embodiment of Figure 9 is presented by way of example only. Thus, in some embodiments, one or more features of computing device 900 may be omitted. Also, in some embodiments, one or more features of computing device 900 may be combined together. Additionally, in some embodiments, one or more features of computing device 900 may be divided into one or more component parts.

[0050] Those skilled in the art will appreciate that numerous variations and / or modifications may be made to the invention as shown in the specific embodiments without departing from the spirit or scope of the invention as broadly described. For example, while the above description primarily presents alerts on a visual interface, it should be appreciated that alternative embodiments may use other types of alert presentations, such as audio alerts, to implement the method. Some modifications are contemplated and may be incorporated, such as adding access points, modifying login routines, etc. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive.

[0051] For example, some or all of the above embodiments may be described as, but are not limited to, the following supplementary notes. (Appendix 1) 1. A method for adaptively controlling traffic signals based on a traffic control plan, comprising: identifying, by a processor, an external intervention occurring at an intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan; modifying, by the processor, the traffic control plan based on the traffic control behavior caused by the external intervention; A method comprising: (Appendix 2) 2. The method of claim 1, wherein identifying the external intervention includes detecting manual guidance of traffic at the intersection using video analysis. (Appendix 3) 2. The method of claim 1, wherein identifying the external intervention includes using machine learning to detect anomalies in traffic flow patterns and other traffic variables at the intersection. (Appendix 4) 2. The method of claim 1, further comprising determining a control plan for the external intervention and a resulting traffic flow at the intersection based on the traffic control behavior caused by the external intervention. (Appendix 5) determining traffic flows at adjacent intersections of the intersection; generating one or more control plans for the adjacent intersection from one or more simulations, the one or more simulations having simulation inputs based on the control plan of the external intervention, the resulting traffic flow at the intersection, and a deformation of the traffic flow at the adjacent intersection; storing the generated control plan or plans along with their corresponding simulation inputs as pre-trained control plans; 5. The method of claim 4, further comprising: (Appendix 6) determining traffic flows at adjacent intersections of the intersection; deriving a pre-trained control plan having inputs corresponding to the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections, the pre-trained control plan being an output of a simulation based on the inputs, the inputs including a control plan at the intersection, the resulting traffic flow at the intersection, and a deformation of the traffic flow at the adjacent intersections; applying the retrieved pre-trained control plan to the neighboring intersections of the intersection; 5. The method of claim 4, further comprising: (Appendix 7) determining traffic flows at adjacent intersections of the intersection; determining an optimal control plan via fuzzy logic, the fuzzy logic being a non-linear mapping process that determines the optimal control plan based on the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections; applying the optimal control plan to the adjacent intersections of the intersection or storing the optimal control plan as a pre-trained control plan using the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections as corresponding simulation inputs; 5. The method of claim 4, further comprising: (Appendix 8) 1. An apparatus for adaptively controlling a traffic signal based on a traffic control plan, comprising: a memory in communication with a processor, the memory storing a computer program recorded therein, the computer program causing the device to at least: identifying an external intervention occurring at an intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan; Modifying the traffic control plan based on the traffic control behavior caused by the external intervention. Executable by the processor such that Device. (Appendix 9) 9. The apparatus of claim 8, wherein identifying the external intervention includes detecting manual direction of traffic at the intersection using video analysis. (Appendix 10) 9. The apparatus of claim 8, wherein identifying the external intervention includes using machine learning to detect anomalies in traffic flow patterns and other traffic variables at the intersection. (Appendix 11) The memory and the computer program, when executed by the processor, further cause the apparatus to: determining a control plan for the external intervention and a resulting traffic flow at the intersection based on the traffic control behavior caused by the external intervention; 9. The apparatus of claim 8. (Appendix 12) The memory and the computer program are executed by the processor to cause the device to: determining traffic flows at adjacent intersections of the intersection; generating one or more control plans for the adjacent intersection from one or more simulations, the one or more simulations having simulation inputs based on the control plan of the external intervention, the resulting traffic flow at the intersection, and a deformation of the traffic flow at the adjacent intersection; storing the generated control plan or plans along with their corresponding simulation inputs as pre-trained control plans; 12. The apparatus of claim 11, further comprising: (Appendix 13) The memory and the computer program are executed by the processor to cause the device to: determining traffic flows at adjacent intersections of the intersection; deriving a pre-trained control plan having inputs corresponding to the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections, the pre-trained control plan being an output of a simulation based on the inputs, the inputs including a control plan at the intersection, the resulting traffic flow at the intersection, and a deformation of the traffic flow at the adjacent intersections; applying the retrieved pre-trained control plan to the neighboring intersections of the intersection; 12. The apparatus of claim 11, further comprising: (Appendix 14) The memory and the computer program are executed by the processor to cause the device to: determining traffic flows at adjacent intersections of the intersection; determining an optimal control plan via fuzzy logic, the fuzzy logic being a non-linear mapping process that determines the optimal control plan based on the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections; applying the optimal control plan to the adjacent intersections of the intersection or storing the optimal control plan as a pre-trained control plan using the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections as corresponding simulation inputs; 12. The apparatus of claim 11, further comprising: (Appendix 15) 1. A system for adaptively controlling a traffic signal, comprising: An apparatus according to any one of claims 8 to 14 and at least one image capture device; A system comprising:

[0052] This application claims priority to Singapore Patent Application No. 10202109141Q filed on August 20, 2021, the disclosure of which is incorporated herein by reference in its entirety. [Explanation of symbols]

[0053] 102 Intersection 200 Adaptive Traffic Signal Control (ATSC) System 202 Subsystem 204 Manual Guidance Detection Module 206 Local Area Signal Control Module 208 Traffic Sensor(s) 210 Analysis Module 212 Subsystem 214 Traffic Controller(s) Module 502 cycle duration 504 Turn Sequence 506 Green Light Duration 508 Yellow Light Duration

Claims

1. 1. A method for adaptively controlling traffic signals based on a traffic control plan, comprising: identifying, by a processor, an external intervention occurring at an intersection using video analysis to detect manual guidance of traffic at the intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan; modifying, by the processor, the traffic control plan based on the traffic control behavior caused by the external intervention; A method comprising:

2. The method of claim 1 , wherein identifying the external intervention comprises using machine learning to detect anomalies in traffic flow patterns and other traffic variables at the intersection.

3. The method of claim 1 , further comprising determining a control plan for the external intervention and a resulting traffic flow at the intersection based on the traffic control behavior caused by the external intervention.

4. determining traffic flows at adjacent intersections of the intersection; generating one or more control plans for the adjacent intersection from one or more simulations, the one or more simulations having simulation inputs based on the control plan of the external intervention, the resulting traffic flow at the intersection, and a deformation of the traffic flow at the adjacent intersection; storing the generated control plan or plans along with their corresponding simulation inputs as pre-trained control plans; The method of claim 3 further comprising:

5. determining traffic flows at adjacent intersections of the intersection; deriving a pre-trained control plan having inputs corresponding to the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections, the pre-trained control plan being an output of a simulation based on the inputs, the inputs including a control plan at the intersection, the resulting traffic flow at the intersection, and a deformation of the traffic flow at the adjacent intersections; applying the retrieved pre-trained control plan to the neighboring intersections of the intersection; The method of claim 3 further comprising:

6. determining traffic flows at adjacent intersections of the intersection; determining an optimal control plan via fuzzy logic, the fuzzy logic being a non-linear mapping process that determines the optimal control plan based on the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections; applying the optimal control plan to the adjacent intersections of the intersection or storing the optimal control plan as a pre-trained control plan using the control plan of the external intervention, the resulting traffic flow at the intersection, and the traffic flow at the adjacent intersections as corresponding simulation inputs; The method of claim 3 further comprising:

7. 1. An apparatus for adaptively controlling a traffic signal based on a traffic control plan, comprising: a memory in communication with a processor, the memory storing a computer program recorded therein, the computer program causing the device to at least: identifying an external intervention occurring at an intersection using video analysis to detect manual guidance of traffic at the intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan; Modifying the traffic control plan based on the traffic control behavior caused by the external intervention. Executable by the processor such that Device.

8. The apparatus of claim 7 , wherein identifying the external intervention comprises using machine learning to detect anomalies in traffic flow patterns and other traffic variables at the intersection.

9. A program for adaptively controlling a traffic signal based on a traffic control plan, comprising: identifying an external intervention occurring at an intersection using video analysis to detect manual guidance of traffic at the intersection, the external intervention causing a traffic control behavior at the intersection that deviates from the traffic control plan; modifying the traffic control plan based on the traffic control behavior caused by the external intervention; A program that causes a computer to execute the following.

Images