Traffic signal light cycle length determination method, apparatus, device, and storage medium

Abstract

The present disclosure provides a cycle length determination method, device and equipment of traffic signal light and storage medium, relates to the fields of intelligent transportation, cloud computing, big data and the like. The specific implementation scheme is: according to the coordinate position and time stamp of each trajectory point in the target moving trajectory of a plurality of target objects in a set period, determine the switching point in the plurality of target moving trajectories;Wherein, the switching point is the trajectory point of the target object switching from the stop state to the moving state;According to the difference between the time stamp of each switching point, the cycle length of the traffic signal light is determined. Therefore, according to a large number of moving trajectories, the cycle length of the traffic signal light can be determined, which can improve the accuracy and reliability of the determination result.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of artificial intelligence, in particular to the technical field of intelligent transportation, cloud computing, big data, and the like, and more particularly to a cycle length determination method and device for traffic signal lights, equipment and a storage medium. BACKGROUND

[0002] Traffic signal lights are the most complex and user-perceived traffic scenarios for travel navigation. Mining the cycle length of traffic signal lights helps the construction of intelligent transportation, and can also alleviate the anxiety of users when waiting for a red light due to unknown red light duration.

[0003] Therefore, how to accurately mine the cycle length of traffic signal lights is very important. SUMMARY

[0004] The present disclosure provides a cycle length determination method and device for traffic signal lights, equipment and a storage medium.

[0005] According to an aspect of the present disclosure, a cycle length determination method for traffic signal lights is provided, comprising:

[0006] obtaining target movement trajectories of a plurality of target objects within a set period;

[0007] determining switching points in the plurality of target movement trajectories according to the coordinate positions and time stamps of each trajectory point in the plurality of target movement trajectories; wherein the switching point is a trajectory point at which the target object switches from a stopped state to a moving state;

[0008] determining the cycle length of the traffic signal lights according to the difference between the time stamps of each switching point.

[0009] According to another aspect of the present disclosure, a cycle length determination device for traffic signal lights is provided, comprising:

[0010] an acquisition module configured to obtain target movement trajectories of a plurality of target objects within a set period;

[0011] a first determination module configured to determine switching points in the plurality of target movement trajectories according to the coordinate positions and time stamps of each trajectory point in the plurality of target movement trajectories; wherein the switching point is a trajectory point at which the target object switches from a stopped state to a moving state;

[0012] a second determination module configured to determine the cycle length of the traffic signal lights according to the difference between the time stamps of each switching point.

[0013] According to still another aspect of the present disclosure, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory in communication with the at least one processor; wherein

[0016] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for determining cycle length of traffic signal according to any one of the aspects of the present disclosure.

[0017] According to still another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium of computer instructions for causing a computer to perform the method for determining cycle length of traffic signal according to any one of the aspects of the present disclosure.

[0018] According to still another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method for determining cycle length of traffic signal according to any one of the aspects of the present disclosure.

[0019] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0021] Figure 1 Flowchart of the method for determining cycle length of traffic signal provided by the first embodiment of the present disclosure;

[0022] Figure 2 Flowchart of the method for determining cycle length of traffic signal provided by the second embodiment of the present disclosure;

[0023] Figure 3 Flowchart of the method for determining cycle length of traffic signal provided by the third embodiment of the present disclosure;

[0024] Figure 4 Flowchart of the method for determining cycle length of traffic signal provided by the fourth embodiment of the present disclosure;

[0025] Figure 5 Flowchart of the method for determining cycle length of traffic signal provided by the fifth embodiment of the present disclosure;

[0026] Figure 6 Flowchart of the method for determining cycle length of traffic signal provided by the sixth embodiment of the present disclosure;

[0027] Figure 7A flowchart of a method for determining a cycle length of a traffic signal according to an embodiment of the present disclosure is shown.

[0028] Figure 8 A schematic diagram of a mining principle of a cycle length of a traffic signal according to an embodiment of the present disclosure is shown.

[0029] Figure 9 A structural schematic diagram of a device for determining a cycle length of a traffic signal according to an embodiment of the present disclosure is shown.

[0030] Figure 10 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0031] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding them. These should be considered in their context only. Thus, those of ordinary skill in the art will recognize various changes and modifications of the embodiments described herein, without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0032] Currently, the cycle length of a traffic signal can be mined in the following ways:

[0033] First, the cycle length of a traffic signal is determined according to the complete stop-and-wait time of a vehicle and other information corresponding to the vehicle trajectory map in a posteriori manner.

[0034] For example, the trajectory information at a certain time, the trajectory information in a period of time before the certain time, and the trajectory information in a period of time after the certain time can be extracted, the stop-and-wait time of each trajectory at the corresponding time is determined according to the above trajectory information, and the cycle length of the traffic signal is determined by comprehensively reproducing all trajectories at the certain time.

[0035] Second, the cycle length of a traffic signal is manually checked by driving. For example, some traffic signals can be selected, and then a person drives to the intersection where the traffic signals are located and waits for a complete cycle of the traffic signals.

[0036] Third, distribution statistics. For example, based on all vehicle trajectories in a target time period, the first starting point (referred to as switching point in the present disclosure) is found, the deviation time of all trajectories and the starting point is calculated, the distribution information of the deviation time is counted, and the cycle length of the traffic signal is determined based on the periodicity characteristics of the distribution information.

[0037] However, the first method is difficult to accurately identify a complete stop of a vehicle. For example, it is difficult to determine the state of the stop light according to the driving track of the vehicle, which indicates that the vehicle is driving and stopping frequently. In addition, there may be some abnormal driving tracks, such as abnormal driving, illegal driving, and long-time parking of the vehicle due to the driver picking up passengers on the roadside. The accuracy and reliability of the cycle length of the traffic signal determined according to the driving track of a vehicle cannot be guaranteed.

[0038] The second method can accurately identify a complete stop, but the manual verification method has high labor and financial costs, and the roads that can be covered are relatively limited, which cannot achieve large-scale collection of the cycle length of the intersection traffic signal.

[0039] The third method can preliminarily count the cycle length of the traffic signal, but the distribution of the basic data strictly depends on the accuracy of the first starting point, and the deviation of all tracks from the starting point leads to many random error factors, which cannot accurately count the best cycle division point based on the distribution.

[0040] To solve at least one of the above problems, the present disclosure provides a traffic signal cycle length determination method, device, equipment and storage medium.

[0041] The traffic signal cycle length determination method, device, equipment and storage medium of the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0042] Figure 1 The flowchart of the traffic signal cycle length determination method provided by the first embodiment of the present disclosure is shown.

[0043] The embodiments of the present disclosure take the traffic signal cycle length determination method configured in the traffic signal cycle length determination device as an example. The traffic signal cycle length determination device can be applied to any electronic device, so that the electronic device can perform the cycle length function of the traffic signal.

[0044] The electronic device can be any device with computing power, such as a PC (Personal Computer), a mobile terminal, a server, etc. The mobile terminal can be a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc. with various operating systems, touch screens and / or display screens.

[0045] As shown in the traffic signal cycle length determination method, the method can include the following steps: Figure 1

[0046] Step 101, obtaining the target moving track of a plurality of target objects in a set period.​

[0047] In the embodiments of the present disclosure, the set time period is a time period set in advance, for example, the set time period is [t1, t2], t2 may be the current time for example, and the time difference t2-t1 may be set in advance, for example, t2-t1=10 min (minutes).

[0048] In the embodiments of the present disclosure, the target object can be a vehicle, a pedestrian, or the like, and when the target object is a vehicle, the type of the vehicle is not limited, for example, the target object can be a taxi, a socialized management vehicle, a bus, a truck, a small car, or the like.

[0049] In the embodiments of the present disclosure, the target moving track of each target object in the set time period can be obtained. For example, the target moving track of each target object in the set time period can be obtained from a plurality of data sources.

[0050] It should be noted that in the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information are all carried out on the premise of obtaining the consent of the user, and all comply with the relevant legal regulations and do not violate public order and good customs.

[0051] In step 102, the switching points in the plurality of target moving tracks are determined according to the coordinate positions and time stamps of the track points in the plurality of target moving tracks; wherein the switching point is a track point at which the target object switches from a stop state to a moving state.

[0052] In the embodiments of the present disclosure, the target moving track can include the coordinate positions of the track points, the time stamps at which the target object moves to the track points, and the instantaneous speed or moving speed of the target object moving to the track points.

[0053] In the embodiments of the present disclosure, for any one of the plurality of target moving tracks, the switching point corresponding to the target moving track can be determined from the track points according to the coordinate positions and time stamps of the track points in the target moving track, wherein the switching point is a track point at which the target object switches from a stop state to a moving state.

[0054] In step 103, the cycle length of the traffic signal lamp is determined according to the difference between the time stamps of the switching points.

[0055] In the embodiments of the present disclosure, the cycle length of the traffic signal lamp can be determined according to the difference between the time stamps of the switching points.

[0056] In a possible implementation of the embodiments of the present disclosure, in the case that each target moving track indicates that the target object only passes the same traffic signal light, at this time, the period length of the traffic signal light matching the same lane direction can be determined according to the difference between the time stamps of the switching points of each target moving track in the same lane and according to the coordinates of each track point in each target moving track.

[0057] As an example, when the difference between the time stamps of the switching points of each target moving track in the same lane is relatively large, at this time, it indicates that each switching point is the position point at which each target object switches from the stop state to the moving state after the red light in different rounds, and in the present disclosure, the period length of the traffic signal light can be determined according to the following two methods:

[0058] Firstly, the difference between the time stamps of any two switching points of the switching points of each target moving track in the same lane is determined to obtain at least one first difference value (for example, the larger time stamp is subtracted from the smaller time stamp to obtain a first difference value with a positive value), and a first error (for example, mean square error, mean square error, etc.) between any candidate period length in the set of candidate period lengths and each first difference value is determined, so that the first target period length can be determined from each candidate period length according to the first error of each candidate period length, for example, the candidate period length with the minimum first error can be taken as the first target period length, so that the first target period length can be taken as the period length of the traffic signal light.

[0059] Secondly, the difference between the time stamps of any two switching points of the switching points of each target moving track in the same lane is determined to obtain at least one first difference value (for example, the larger time stamp is subtracted from the smaller time stamp to obtain a first difference value with a positive value), and the set of candidate period lengths is divided to obtain a plurality of candidate period length sub-sets, and the second target period length is determined from each candidate period length sub-set according to each first difference value, for example, the error (for example, mean square error, mean square error, etc.) between the second target period length and each first difference value is minimum, so that the period length of the traffic signal light can be determined according to each second target period length. For example, the second target period length with the highest confidence can be determined from each second target period length and taken as the period length of the traffic signal light.

[0060] As another example, when the difference between the timestamps of the switching points of each target moving trajectory located in the same lane is relatively small, at this time, it indicates that multiple target objects in each switching point contain the position points of the target objects switching from a stop state to a moving state after the same round of red light, in the present disclosure, the target switching points can be determined from each switching point according to the timestamps of each switching point (for example, the target switching point can be the switching point of the first moving target object after a round of red light, and for example, it can be the switching point of the second moving target object after a round of red light), and the cycle length of the traffic signal lamp can be determined according to the difference between the timestamps of each target switching point. For example, the cycle length of the traffic signal lamp can be determined in the following two ways:

[0061] First, the difference between the timestamps of any two target switching points in each target switching point located in the same lane is determined to obtain at least one first difference value (for example, the larger timestamp is subtracted from the smaller timestamp to obtain a first difference value with a positive value), and the first error (for example, mean square error, mean square error, etc.) between any candidate cycle length in the set of candidate cycle lengths and each first difference value is determined, so that the first target cycle length can be determined from each candidate cycle length according to the first error of each candidate cycle length, for example, the candidate cycle length with the smallest first error can be taken as the first target cycle length, so that the first target cycle length can be taken as the cycle length of the traffic signal lamp.

[0062] Second, the difference between the timestamps of any two target switching points in each target switching point located in the same lane is determined to obtain at least one first difference value (for example, the larger timestamp is subtracted from the smaller timestamp to obtain a first difference value with a positive value), and the set of candidate cycle lengths is divided to obtain multiple candidate cycle length sub-sets, and the second target cycle length is determined from each candidate cycle length sub-set according to each first difference value, for example, the error (for example, mean square error) between the second target cycle length and each first difference value is the smallest, so that the cycle length of the traffic signal lamp can be determined according to each second target cycle length. For example, the second target cycle length with the highest confidence can be determined from each second target cycle length and taken as the cycle length of the traffic signal lamp.

[0063] It should be noted that in actual application, it is also possible that each target moving trajectory indicates that the target object passes through at least two traffic signal lamps, which will be described in detail in subsequent embodiments, and the present disclosure will not be repeated here.

[0064] The method for determining the cycle length of a traffic signal according to the embodiments of the present disclosure determines switching points in the plurality of target movement trajectories according to the coordinate positions and time stamps of the trajectory points in the target movement trajectories of the plurality of target objects in a set period; wherein the switching points are the trajectory points at which the target objects switch from a stopped state to a moving state; and determines the cycle length of the traffic signal according to the differences between the time stamps of the switching points. Thus, the cycle length of the traffic signal is determined according to a large number of movement trajectories, which can improve the accuracy and reliability of the determination result.

[0065] To clearly illustrate how the cycle length of the traffic signal is determined according to the differences between the time stamps of the switching points in the above embodiments of the present disclosure, the present disclosure further provides a method for determining the cycle length of a traffic signal.

[0066] Figure 2 A flowchart of the method for determining the cycle length of a traffic signal provided in Embodiment Two of the present disclosure is shown in FIG. 2.

[0067] As shown in FIG. 2, the method for determining the cycle length of a traffic signal can include the following steps: Figure 2

[0068] Step 201: Obtain target movement trajectories of a plurality of target objects in a set period.

[0069] Step 202: Determine switching points in the plurality of target movement trajectories according to the coordinate positions and time stamps of the trajectory points in the plurality of target movement trajectories; wherein the switching points are the trajectory points at which the target objects switch from a stopped state to a moving state.

[0070] The explanations of steps 201 to 202 can be referred to the related descriptions in any of the embodiments of the present disclosure, which will not be repeated here.

[0071] Step 203: Cluster the switching points according to the coordinate positions and time stamps of the switching points to obtain a plurality of first clusters.

[0072] In the embodiments of the present disclosure, the switching points can be clustered according to the coordinate positions and time stamps of the switching points to obtain a plurality of first clusters, wherein the distances between the coordinate positions of the switching points in the same cluster are relatively small, and the differences between the time stamps of the switching points in the same cluster are relatively small. That is, each cluster contains switching points of each target object moving after the same round of red light of the same traffic signal.

[0073] Step 204: Determine target switching points from each first cluster according to the time stamps of the switching points in each first cluster.

[0074] ​In the embodiments of the present disclosure, for any one of the first clusters, a target switching point can be determined from the first cluster according to the timestamps of the switching points in the first cluster. For example, the switching point with the smallest timestamp in the first cluster can be taken as the target switching point, i.e., the target switching point is the switching point of the first moving target object after a round of red light; for another example, the switching point with the second smallest timestamp in the first cluster can be taken as the target switching point, i.e., the target switching point is the switching point of the second moving target object after a round of red light, and so on.

[0075] In step 205, the cycle length of the traffic signal lamp is determined according to the difference between the timestamps of the target switching points.

[0076] In the embodiments of the present disclosure, the cycle length of the traffic signal lamp can be determined according to the difference between the timestamps of the target switching points.

[0077] As a possible implementation manner, in the case that each target moving trajectory indicates that the target object only passes through the same traffic signal lamp, the cycle length of the traffic signal lamp can be determined according to the following two manners:

[0078] Firstly, the difference between the timestamps of any two target switching points located in the same lane is determined to obtain at least one first difference value (for example, the larger timestamp is subtracted from the smaller timestamp to obtain a first difference value with a positive value), and a first error (for example, mean square error, mean square deviation, etc.) between any candidate cycle length in the set of candidate cycle lengths and each first difference value is determined, so that the first target cycle length can be determined from the candidate cycle lengths according to the first error of each candidate cycle length, for example, the candidate cycle length with the smallest first error can be taken as the first target cycle length, so that the first target cycle length can be taken as the cycle length of the traffic signal lamp.

[0079] Secondly, the difference between the timestamps of any two target switching points located in the same lane is determined to obtain at least one first difference value (for example, the larger timestamp is subtracted from the smaller timestamp to obtain a first difference value with a positive value), and the set of candidate cycle lengths is divided to obtain a plurality of candidate cycle length sub-sets, and the second target cycle length is determined from each candidate cycle length sub-set according to each first difference value, for example, the error (for example, mean square error) between the second target cycle length and each first difference value is the smallest, so that the cycle length of the traffic signal lamp can be determined according to each second target cycle length. For example, the second target cycle length with the highest confidence can be determined from each second target cycle length and taken as the cycle length of the traffic signal lamp.

[0080] It should be noted that in actual application, each target moving track may also indicate that the target object passes at least two traffic lights, which will be described in detail in subsequent embodiments, and the present disclosure will not be repeated here.

[0081] The method for determining the cycle length of the traffic light according to the embodiments of the present disclosure can determine the switching point of the target object that moves earliest after each round of red light from each switching point, so as to effectively determine the cycle length of the traffic light according to the switching point of the target object that moves earliest, and improve the effectiveness and accuracy of the determination result.

[0082] In order to clearly illustrate how the cycle length of the traffic light is determined according to the difference between the time stamps of the target switching points in the above-mentioned embodiments of the present disclosure, the present disclosure further provides a method for determining the cycle length of the traffic light.

[0083] Figure 3 The flowchart of the method for determining the cycle length of the traffic light provided in Embodiment Three of the present disclosure is shown.

[0084] As shown in Figure 3 , the method for determining the cycle length of the traffic light can include the following steps:

[0085] Step 301: obtaining the target moving tracks of a plurality of target objects within a set period.

[0086] Step 302: determining the switching points in the plurality of target moving tracks according to the coordinate positions and time stamps of the track points in the plurality of target moving tracks; wherein the switching point is the track point at which the target object switches from a stopped state to a moving state.

[0087] Step 303: clustering the switching points according to the coordinate positions and time stamps of the switching points to obtain a plurality of first clusters.

[0088] Step 304: determining the target switching point from each first cluster according to the time stamps of the switching points in each first cluster.

[0089] The explanation and description of steps 301 to 304 can be referred to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0090] Step 305: clustering the target switching points according to the coordinate positions of the target switching points to obtain at least one second cluster.

[0091] In the embodiments of the present disclosure, the target switching points can be clustered according to the coordinate positions of the target switching points, to obtain at least one second cluster, that is, the corresponding target switching points of the same traffic light are included in the same second cluster. That is to say, when the number of second clusters is multiple, the number of traffic lights is also multiple, and the number of second clusters is the same as the number of traffic lights.

[0092] In step 306, for any second cluster, the difference between the timestamps of any two target switching points in the second cluster is determined to obtain at least one first difference value.

[0093] In the embodiments of the present disclosure, for any second cluster in the at least one second cluster, the difference between the timestamps of any two target switching points in the second cluster can be determined to obtain at least one first difference value (for example, the larger timestamp is subtracted from the smaller timestamp to obtain the first difference value with a positive value).

[0094] In step 307, for any candidate cycle length in the set of candidate cycle lengths, a first error between the candidate cycle length and each first difference value is determined.

[0095] In the embodiments of the present disclosure, the set of candidate cycle lengths includes a plurality of candidate cycle lengths set according to experience, for example, the set of candidate cycle lengths can include each integer value in [50 seconds, 400 seconds].

[0096] In the embodiments of the present disclosure, for any candidate cycle length in the set of candidate cycle lengths, a first error (such as mean square error, mean square error, etc.) between the candidate cycle length and each first difference value can be determined.

[0097] In step 308, a first target cycle length is determined from the candidate cycle lengths according to the first errors of the candidate cycle lengths.

[0098] In the embodiments of the present disclosure, the first target cycle length can be determined from the candidate cycle lengths according to the first errors of the candidate cycle lengths, for example, the candidate cycle length with the minimum first error can be taken as the first target cycle length.

[0099] In step 309, the cycle length of the traffic light matched with the coordinate positions of the target switching points in the second cluster is determined according to the first target cycle length.

[0100] In the embodiments of the present disclosure, the first target cycle length can be taken as the cycle length of the traffic light matched with the coordinate positions of the target switching points in the second cluster.

[0101] The cycle length determination method of the traffic signal lamp can effectively determine the cycle length of each traffic signal lamp when the number of traffic signal lamps is at least one, so as to meet the actual application requirements.

[0102] It should be noted that for a road section with less traffic flow or a non-peak period, not every cycle of the traffic signal lamp has a target object passing through. At this time, the difference between the time stamps of adjacent target switching points may be much larger than the cycle length of the traffic signal lamp. In this way, the first target cycle length determined according to the candidate cycle length set is a multiple of the cycle length of the traffic signal lamp. Therefore, in order to improve the accuracy and reliability of the cycle length determination result of the traffic signal lamp, the candidate cycle length set can be divided, and the cycle length of the traffic signal lamp is determined according to each candidate cycle length sub-set obtained by the division. The following will be described in combination with Figure 4 The above process will be described in detail.

[0103] Figure 4 The flowchart of the cycle length determination method of the traffic signal lamp provided in Embodiment Four of the present disclosure.

[0104] As Figure 4 shown, the cycle length determination method of the traffic signal lamp can include the following steps:

[0105] Step 401: Obtain the target moving trajectories of a plurality of target objects in a set period.

[0106] Step 402: Determine the switching points in the plurality of target moving trajectories according to the coordinate positions and time stamps of the trajectory points in the plurality of target moving trajectories; wherein the switching point is a trajectory point at which the target object switches from a stopped state to a moving state.

[0107] Step 403: Cluster the switching points according to the coordinate positions and time stamps of the switching points, to obtain a plurality of first clusters.

[0108] Step 404: Determine the target switching points from each first cluster according to the time stamps of the switching points in each first cluster.

[0109] Step 405: Cluster the target switching points according to the coordinate positions of the target switching points, to obtain at least one second cluster.

[0110] Step 406: For any second cluster, determine the difference between the time stamps of any two target switching points in the second cluster, to obtain at least one first difference value.

[0111] The explanation of steps 401 to 406 can be referred to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0112] Step 407, the set of candidate cycle time lengths is divided to obtain a plurality of candidate cycle time length sub-sets.

[0113] In the embodiments of the present disclosure, the set of candidate cycle time lengths can be divided to obtain a plurality of candidate cycle time length sub-sets.

[0114] For example, taking an example that the set of candidate cycle time lengths contains each integer value in [50 seconds, 400 seconds], the set of candidate cycle time lengths can be divided into 3 candidate cycle time length sub-sets: candidate cycle time length sub-set 1, candidate cycle time length sub-set 2, and candidate cycle time length sub-set 3, wherein the candidate cycle time length sub-set 1 can contain each integer value in [50 seconds, 100 seconds], the candidate cycle time length sub-set 2 can contain each integer value in [100 seconds, 200 seconds], and the candidate cycle time length sub-set 3 can contain each integer value in [200 seconds, 400 seconds], or the set of candidate cycle time lengths can be divided into 4 candidate cycle time length sub-sets: candidate cycle time length sub-set A, candidate cycle time length sub-set B, candidate cycle time length sub-set C, and candidate cycle time length sub-set D, wherein the candidate cycle time length sub-set A can contain each integer value in [50 seconds, 100 seconds], the candidate cycle time length sub-set B can contain each integer value in [100 seconds, 200 seconds], the candidate cycle time length sub-set C can contain each integer value in [200 seconds, 300 seconds], and the candidate cycle time length sub-set D can contain each integer value in [300 seconds, 400 seconds], and the like, which are not listed one by one here.

[0115] Step 408, according to each first difference, a second target cycle time length is determined from each candidate cycle time length sub-set.

[0116] In the embodiments of the present disclosure, according to each first difference, a second target cycle time length can be determined from each candidate cycle time length sub-set.

[0117] As a possible implementation manner, for any one of the plurality of candidate cycle time length sub-sets, a second error (such as mean square error, mean square error, etc.) between each candidate cycle time length in the candidate cycle time length sub-set and each first difference can be determined, so that according to the second error of each candidate cycle time length in the candidate cycle time length sub-set, a second target cycle time length can be determined from each candidate cycle time length in the candidate cycle time length sub-set. For example, the candidate cycle time length with the smallest second error can be taken as the second target cycle time length.

[0118] Thus, the second target cycle length with the minimum error between each first difference value is determined from each candidate cycle length sub-set, which can represent the cycle rule of the traffic signal light, so as to determine the cycle length of the traffic signal light according to each second target cycle length, which can improve the accuracy and reliability of the determination result.

[0119] At step 409, the cycle length of the traffic signal light matching the coordinate position of each target switching point in the second cluster is determined according to each second target cycle length.

[0120] In the embodiments of the present disclosure, the cycle length of the traffic signal light matching the coordinate position of each target switching point in the second cluster can be determined according to each second target cycle length. For example, the second target cycle length with the maximum confidence can be taken as the cycle length of the traffic signal light matching the coordinate position of each target switching point in the second cluster.

[0121] As a possible implementation, the confidence of each second target cycle length can be determined in the following manner:

[0122] The target switching points in the second cluster can be sorted in chronological order to obtain a sorted sequence, and the difference between the time stamps of adjacent target switching points in the sorted sequence is determined to obtain at least one second difference value (for example, subtracting the smaller time stamp from the larger time stamp to obtain a second difference value with a positive value). Then, the third error (such as mean square error, mean square error, etc.) between each second target cycle length and each second difference value can be determined, so that the confidence of each second target cycle length can be determined according to the third error of each second target cycle length, wherein the confidence and the third error are negatively correlated, that is, the smaller the third error, the greater the confidence, and vice versa, the greater the third error, the smaller the confidence.

[0123] Thus, in the present disclosure, the third target cycle length can be determined from each second target cycle length according to the confidence of each second target cycle length, for example, the second target cycle length with the highest confidence can be taken as the third target cycle length (that is, the second target cycle length with the smallest third error is taken as the third target cycle length), so that the third target cycle length can be taken as the cycle length of the traffic signal light matching the coordinate position of each target switching point in the second cluster.

[0124] Thus, the cycle length of the traffic signal light can be effectively determined according to each second target cycle length, which can improve the effectiveness of the cycle length determination.

[0125] The method for determining the cycle length of the traffic signal light according to the embodiments of the present disclosure considers that for a road section with less traffic or off-peak hours, not every cycle of the traffic signal light has a target object passing through, and in the case that the first target cycle length determined according to the candidate cycle length set is a multiple of the cycle length of the traffic signal light, the candidate cycle length set is divided in the present disclosure, and the cycle length of the traffic signal light is determined according to each candidate cycle length sub-set obtained by the division, which can improve the accuracy and reliability of the determination result of the cycle length of the traffic signal light.

[0126] It should be noted that the cycle of collecting and reporting the trajectory points by the target object or the terminal device bound to the target object is different during the movement of different target objects, and different reporting cycles will affect the accuracy of the determination result of the cycle length of the traffic signal light. For example, vehicle 1 and vehicle 2 report a trajectory point every 1 second, vehicle 3 reports a trajectory point every 3 seconds, and vehicle 4 reports a trajectory point every 10 seconds. Obviously, the accuracy of the calculated cycle length according to the trajectory points of vehicle 1 and vehicle 2 is higher than that of vehicle 3 and vehicle 4. For example, vehicle 4 reports a trajectory point at the last second of the red light, starts 1 second later, and reports another trajectory point 9 seconds after starting. According to the moving trajectory of vehicle 4, the determined switching point has a 9-second delay. Obviously, if the cycle length of the traffic signal light is calculated according to the switching point of vehicle 4, the calculation result is not accurate. Therefore, in a possible implementation manner of the embodiments of the present disclosure, in order to improve the accuracy of the calculation result of the cycle length, each moving trajectory can be filtered according to the reporting cycle of the trajectory points in each moving trajectory to retain high-quality target moving trajectories. The following will be described in combination with Figure 5 The above process will be described in detail.

[0127] Figure 5 The flowchart of the method for determining the cycle length of the traffic signal light provided in the fifth embodiment of the present disclosure is shown in the figure.

[0128] As Figure 5 shown, the method for determining the cycle length of the traffic signal light can include the following steps:

[0129] Step 501: Obtain the candidate moving trajectories of a plurality of target objects in a set period.

[0130] It should be noted that the explanations and descriptions of the set period and the target object in the foregoing embodiments also apply to this embodiment, which will not be described herein.

[0131] In the embodiments of the present disclosure, the candidate moving trajectories of a plurality of target objects in a set period can be obtained. For example, the candidate moving trajectories of a plurality of target objects in a set period can be obtained from a plurality of data sources.

[0132] At step 502, for any candidate moving trajectory in the plurality of candidate moving trajectories, a difference between time stamps of adjacent trajectory points in the candidate moving trajectory is determined according to the coordinate positions and the time stamps of the trajectory points in the candidate moving trajectory.

[0133] In the embodiments of the present disclosure, for any candidate moving trajectory in the plurality of candidate moving trajectories, a difference between time stamps of adjacent trajectory points in the candidate moving trajectory can be determined according to the coordinate positions and the time stamps of the trajectory points in the candidate moving trajectory, such as a difference value, an absolute value of the difference value.

[0134] The difference between the time stamps of the adjacent trajectory points is used to indicate a reporting period of the trajectory points.

[0135] At step 503, the candidate moving trajectory is filtered in response to the difference between the time stamps of the adjacent trajectory points being greater than a set difference threshold.

[0136] In the embodiments of the present disclosure, the set difference threshold is a pre-set difference threshold, such as 2 seconds, 3 seconds, etc. in the case of taking the absolute value of the difference between the time stamps as an example.

[0137] In the embodiments of the present disclosure, the candidate moving trajectory can be filtered in the case that the difference between the time stamps of the adjacent trajectory points in the candidate moving trajectory is greater than the set difference threshold, and the candidate moving trajectory can be retained in the case that the difference between the time stamps of the adjacent trajectory points in the candidate moving trajectory is less than or equal to the set difference threshold.

[0138] At step 504, a target moving trajectory is determined according to the retained candidate moving trajectories.

[0139] In the embodiments of the present disclosure, the retained candidate moving trajectories can be used as the target moving trajectory.

[0140] At step 505, a switching point in the plurality of target moving trajectories is determined according to the coordinate positions and the time stamps of the trajectory points in the plurality of target moving trajectories, and the switching point is a trajectory point at which the target object switches from a stop state to a moving state.

[0141] At step 506, a cycle length of the traffic signal lamp is determined according to a difference between time stamps of the switching points.

[0142] The explanation of steps 505 to 506 can be referred to the related description in any embodiment of the present disclosure, and will not be repeated here.

[0143] The cycle time determination method of the traffic signal lamp can realize filtering of the mobile trajectories according to the reporting cycle of the trajectory points in each mobile trajectory, so as to retain a target mobile trajectory with a relatively small reporting cycle, and can improve the accuracy and reliability of the calculation result.

[0144] It should be noted that some abnormal mobile trajectories may appear in the mobile trajectory of the target object. For example, when the target object is a vehicle, the vehicle may stop and start, or the vehicle may stop for a long time due to a fault during driving, or the vehicle may stop for a long time due to a driver picking up passengers on the roadside. It is difficult to accurately identify a complete stop of the vehicle according to the above mobile trajectory, and the accuracy and reliability of the cycle time of the traffic signal lamp determined according to the above mobile trajectory cannot be guaranteed. Therefore, in a possible implementation manner of the embodiment of the present disclosure, in order to improve the accuracy of the cycle time calculation result, the mobile trajectory of the target object can be filtered to retain a high-quality target mobile trajectory. The following will be described in combination with Figure 6 The above process will be described in detail.

[0145] Figure 6 The flowchart of the cycle time determination method of the traffic signal lamp provided in the sixth embodiment of the present disclosure is shown.

[0146] As Figure 6 shown, the cycle time determination method of the traffic signal lamp can include the following steps:

[0147] Step 601: Obtain candidate mobile trajectories of a plurality of target objects in a set period.

[0148] The explanation of step 601 can refer to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0149] Step 602: For any candidate mobile trajectory in the plurality of candidate mobile trajectories, according to the coordinate position and timestamp of each trajectory point in the candidate mobile trajectory, determine the total moving time of the corresponding target object, and the first position where the corresponding target object stops moving and the first stop time of the first position.

[0150] In the embodiment of the present disclosure, for any candidate mobile trajectory in the plurality of candidate mobile trajectories, the total moving time of the corresponding target object can be determined according to the timestamp of each trajectory point in the candidate mobile trajectory. For example, the difference between the latest timestamp and the earliest timestamp can be obtained to obtain the total moving time of the corresponding target object.

[0151] Also, according to the coordinate position and the timestamp of each trajectory point in the candidate moving trajectory, the first position where the corresponding target object stops moving and the first stop duration of the first position can be determined. For example, the coordinate position of a trajectory point in a certain time period in the candidate moving trajectory of the target object remains unchanged, and the unchanged coordinate position is the first position, and the duration of the above-mentioned time period is the first stop duration.

[0152] In step 603, according to the first stop duration of each first position, the total stop duration of the corresponding target object is determined.

[0153] In the embodiments of the present disclosure, the number of first positions can be at least one, and the total stop duration of the corresponding target object can be determined according to the first stop duration of each first position. For example, the sum of the first stop durations can be used as the total stop duration.

[0154] In step 604, in response to the ratio between the total stop duration and the total moving duration being greater than a set proportion threshold, and / or there being at least one first stop duration greater than a set duration threshold, the candidate moving trajectory is filtered.

[0155] In the embodiments of the present disclosure, the set proportion threshold is a pre-set proportion threshold, for example, the set proportion threshold can be 20%, 30%, etc.

[0156] In the embodiments of the present disclosure, the set duration threshold is a pre-set duration threshold, for example, the set duration threshold can be 90 seconds, 120 seconds, etc.

[0157] In the embodiments of the present disclosure, when the ratio between the total stop duration and the total moving duration is greater than the set proportion threshold, and / or there is at least one first stop duration greater than the set duration threshold, the candidate moving trajectory can be filtered. When the ratio between the total stop duration and the total moving duration is less than or equal to the set proportion threshold, and each first stop duration is less than or equal to the set duration threshold, the candidate moving trajectory can be retained.

[0158] In step 605, according to each retained candidate moving trajectory, a target moving trajectory is determined.

[0159] In the embodiments of the present disclosure, each retained candidate moving trajectory can be used as the target moving trajectory.

[0160] In step 606, according to the coordinate position and the timestamp of each trajectory point in a plurality of target moving trajectories, a switching point in the plurality of target moving trajectories is determined; wherein the switching point is a trajectory point where the target object switches from a stop state to a moving state.

[0161] In step 607, according to the difference between the timestamps of each switching point, the cycle duration of the traffic signal lamp is determined.

[0162] The explanation of steps 606 to 607 can be referred to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0163] The method for determining the cycle length of the traffic signal according to the embodiments of the present disclosure can filter abnormal moving trajectories, for example, when the target object is a vehicle, the moving trajectories of walking, stopping and long-time parking can be filtered to retain high-quality target moving trajectories, so that the cycle length of the traffic signal is calculated according to the high-quality target moving trajectories, which can improve the accuracy and reliability of the calculation result.

[0164] It should be noted that there may be some abnormal moving trajectories in the moving trajectories of each target object, for example, when the target object is a vehicle, the vehicle may have abnormal driving, illegal driving, etc., and the accuracy and reliability of the cycle length of the traffic signal determined according to the above moving trajectories cannot be guaranteed. Therefore, in a possible implementation manner of the embodiments of the present disclosure, in order to improve the accuracy of the cycle length calculation result, the moving trajectories of the target objects can be filtered to retain high-quality target moving trajectories. The following will be described in combination with Figure 7 The above process will be described in detail.

[0165] Figure 7 The flowchart of the method for determining the cycle length of the traffic signal provided in the seventh embodiment of the present disclosure is shown.

[0166] As shown in the method for determining the cycle length of the traffic signal can include the following steps: Figure 7

[0167] Step 701, obtaining candidate moving trajectories of a plurality of target objects in a set period.

[0168] The explanation of step 701 can be referred to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0169] Step 702, determining a second position and a target period according to the coordinate position and time stamp of each trajectory point in the plurality of candidate moving trajectories, wherein at least two target objects are in a stop state when the distance between the target objects and the second position is less than a set distance threshold in the target period.

[0170] In the embodiments of the present disclosure, the set distance threshold is a smaller distance threshold set in advance.

[0171] ​In the embodiments of the present disclosure, the candidate moving trajectories of the plurality of target objects can be counted to determine the first position and a target period, wherein the distance between the coordinate positions of each trajectory point of the candidate moving trajectories of at least two target objects in the target period and the second position is less than a set distance threshold, and the instantaneous speed or moving speed of each trajectory point of the candidate moving trajectories of the at least two target objects in the target period is zero, that is, the at least two target objects are in a stop state in the target period.

[0172] Step 703, filtering, from the plurality of candidate moving trajectories, the candidate moving trajectories that pass through the second position and have a moving speed greater than a set speed threshold in the target period.

[0173] In the embodiments of the present disclosure, the set speed threshold is a pre-set speed threshold, and it should be understood that the set speed threshold is a smaller speed threshold, for example, the set speed threshold can be 0, 1 km / h, 2 km / h, 3 km / h, etc.

[0174] In the embodiments of the present disclosure, the candidate moving trajectories that pass through the second position and have a moving speed greater than a set speed threshold in the target period can be filtered from the plurality of candidate moving trajectories.

[0175] For example, assuming that the speeds of eight of the ten moving trajectories are zero at a certain intersection, and they are all waiting for a red light, at this time, one moving trajectory passes through the intersection, which can be considered as the trajectory of a violating vehicle, and therefore, the moving trajectory can be filtered.

[0176] Step 704, determining a target moving trajectory according to the retained candidate moving trajectories.

[0177] In the embodiments of the present disclosure, the retained candidate moving trajectories can be used as the target moving trajectory.

[0178] Step 705, determining a switching point in the plurality of target moving trajectories according to the coordinate positions and time stamps of the trajectory points in the plurality of target moving trajectories, wherein the switching point is a trajectory point at which the target object switches from a stop state to a moving state.

[0179] Step 706, determining the cycle length of the traffic signal according to the difference between the time stamps of the switching points.

[0180] The explanation and description of steps 705 to 706 can be referred to the related description in any of the embodiments of the present disclosure, and will not be repeated here.

[0181] It should be noted that the present disclosure only takes steps 501 to 504, steps 601 to 605, and steps 701 to 704 as three parallel implementations for example, and in actual application, any two of the above three implementations can be combined to filter the candidate moving track, or the above three implementations can be combined to filter the candidate moving track, and the present disclosure does not limit this.

[0182] The method for determining the cycle length of the traffic signal lamp can filter the abnormal moving track, for example, can filter the moving track of illegal driving to retain the high-quality target moving track, so as to calculate the cycle length of the traffic signal lamp according to the high-quality target moving track, and can improve the accuracy and reliability of the calculation result.

[0183] In any one embodiment of the present disclosure, the mining principle of the cycle length of the traffic signal lamp can be as shown in Figure 8 Specifically, the cycle length of the traffic signal lamp can be mined by the following steps:

[0184] First, according to the traffic signal lamp information in the real world, a cycle true value system of the traffic signal lamp is constructed.

[0185] With the gradual popularization of intelligent transportation, a part of the intersection can be installed with signal control equipment, and the cycle length of the traffic signal lamp can be adjusted in real time through the signal control equipment to relieve traffic congestion, so that more car owners enjoy the green wave experience and improve the travel efficiency. By receiving the cycle data of the traffic signal lamp in real time, and deriving the true value data (such as the real cycle length, light state, countdown, time period, etc.) under different cycle lengths according to the above data.

[0186] For example, the cycle true value system can be constructed by the second-level information of the traffic signal lamp.

[0187] Second, a large number of moving tracks in the same period are obtained.

[0188] In order to mine large-scale accurate cycle length of the traffic signal lamp, and make the mined cycle length of the traffic signal lamp match the actual cycle length of the cycle true value system, a large number of moving tracks can be obtained, for example, the driving tracks of different vehicle types (such as taxis, socialized management vehicles, buses, trucks, and small cars) can be obtained, and user UGC (User-generated Content, also known as UCC, User-created Content) tracks (such as user walking tracks, user cycling tracks, etc.) can be obtained.

[0189] Furthermore, each moving trajectory can be filtered based on its quality to retain high-quality moving trajectories. Then, based on the high-quality moving trajectories, effective switching points (i.e., the first switching point of each traffic light cycle, referred to as the target switching point in this disclosure) can be identified to avoid the problem of the cycle mining method not converging due to trajectory quality issues.

[0190] The third step is the principle of cycle duration mining: the deviation between the pairwise target switching points is learned through the least squares method, and the maximum likelihood method is used to estimate the cycle duration of the traffic light.

[0191] With a large number of effective switching points based on trajectory mining, the effective switching points can be sorted by time, and the deviation between each pair can be calculated. Then, the cycle duration can be modeled by the optimization method - least squares method. The solution is to minimize the error by traversing each candidate cycle duration. That is, from each candidate cycle duration, the candidate cycle duration with the smallest mean square error between each deviation can be found. Then, the found candidate cycle duration can be used as the cycle duration of the traffic light.

[0192] Considering that the candidate cycle length may differ from the actual cycle length of the traffic light, this disclosure allows for confidence selection of the candidate cycle length based on the deviation between adjacent timestamps, ultimately yielding the optimal cycle length.

[0193] Next, the actual cycle duration of the traffic lights can be obtained from the cycle truth system. The predicted cycle duration is compared with the actual cycle duration to determine if the prediction meets expectations. For example, if the difference between the predicted and actual cycle durations is relatively small, the prediction is considered to be successful; if the difference is relatively large, the prediction is considered unsuccessful. When the prediction fails to meet expectations, the algorithm parameters in the cycle duration mining method (such as those in maximum likelihood estimation) can be optimized, and / or the movement trajectories can be re-obtained from other data sources to improve the precision and recall of the cycle duration mining method. This process can be iterated continuously until convergence, at which point the optimized cycle duration mining method can be used to automatically generate batches of traffic light cycle durations on a large scale.

[0194] By means of big data mining method, large-scale output cycle mining value can be realized under the premise of ensuring prediction effect, so as to popularize intelligent traffic construction faster. Meanwhile, compared with the cost of self-driving car collection, the cost is significantly reduced, and compared with the coverage of existing signal control lights, large-scale batch coverage can be achieved. Compared with the distribution statistical method, the effect of the scheme is better. The problems of high error judgment based on trajectory graph and low coverage of self-driving car are solved. The inventor applies the method to real-time road condition products and traffic signal light countdown products, and applies it to the effect improvement of road condition congestion calling by 2.48%, and the accuracy rate of traffic signal light cycle length prediction reaches 95%+, which also verifies the confidence of the method from the test results.

[0195] The traffic signal light cycle length determination method provided by the above Figures 1 to 7 The embodiments provide a traffic signal light cycle length determination device, which corresponds to the traffic signal light cycle length determination method provided by the above Figures 1 to 7 The embodiments provide a traffic signal light cycle length determination device, which corresponds to the traffic signal light cycle length determination method provided by the above

[0196] Figure 9 The traffic signal light cycle length determination device provided by the above

[0197] As Figure 9 shown, the traffic signal light cycle length determination device 900 can include an acquisition module 901, a first determination module 902, and a second determination module 903.

[0198] The acquisition module 901 is configured to acquire target movement trajectories of a plurality of target objects in a set period.

[0199] The first determination module 902 is configured to determine switching points in the plurality of target movement trajectories according to coordinate positions and time stamps of each trajectory point in the plurality of target movement trajectories, wherein the switching point is a trajectory point at which the target object switches from a stop state to a movement state.

[0200] The second determination module 903 is configured to determine the cycle length of the traffic signal light according to a difference between time stamps of each switching point.

[0201] In a possible implementation manner of the embodiment of the present disclosure, the second determining module 903 is configured to: cluster the switching points according to the coordinate positions and the time stamps of the switching points, to obtain a plurality of first clusters; determine a target switching point from each first cluster according to the time stamps of the switching points in the first cluster; and determine the cycle length of the traffic signal lamp according to the differences between the time stamps of the target switching points.

[0202] In a possible implementation manner of the embodiment of the present disclosure, the second determining module 903 is configured to: cluster the target switching points according to the coordinate positions of the target switching points, to obtain at least one second cluster; for any second cluster, determine a first difference value between the time stamps of any two target switching points in the second cluster; for any candidate cycle length in a set of candidate cycle lengths, determine a first error between the candidate cycle length and the first difference values; determine a first target cycle length from the candidate cycle lengths according to the first errors of the candidate cycle lengths; and determine the cycle length of the traffic signal lamp matching the coordinate positions of the target switching points in the second cluster according to the first target cycle length.

[0203] In a possible implementation manner of the embodiment of the present disclosure, the second determining module 903 is configured to: cluster the target switching points according to the coordinate positions of the target switching points, to obtain at least one second cluster; for any second cluster, determine a first difference value between the time stamps of any two target switching points in the second cluster; divide a set of candidate cycle lengths to obtain a plurality of candidate cycle length sub-sets; determine a second target cycle length from each candidate cycle length sub-set according to the first difference values; and determine the cycle length of the traffic signal lamp matching the coordinate positions of the target switching points in the second cluster according to the second target cycle lengths.

[0204] In a possible implementation manner of the embodiment of the present disclosure, the second determining module 903 is configured to: for any candidate cycle length sub-set, determine a second error between any candidate cycle length in the candidate cycle length sub-set and the first difference values; and determine a second target cycle length from the candidate cycle lengths in the candidate cycle length sub-set according to the second errors of the candidate cycle lengths in the candidate cycle length sub-set.

[0205] In a possible implementation manner of the embodiment of the present disclosure, the second determining module 903 is configured to: sort the target switch points in the second cluster according to timestamps from early to late to obtain a sorted sequence; determine a difference between timestamps of adjacent target switch points in the sorted sequence to obtain at least one second difference value; determine a third error between any second target period length and each second difference value; determine a third target period length from the second target period lengths according to the third error of each second target period length; and determine a period length of the traffic signal lamp matching the coordinate position of each target switch point in the second cluster according to the third target period length.

[0206] In a possible implementation manner of the embodiment of the present disclosure, the acquisition module 901 is configured to: acquire candidate moving tracks of a plurality of target objects in a set period; for any candidate moving track in the plurality of candidate moving tracks, determine a difference between timestamps of adjacent track points in the candidate moving track according to the coordinate positions and the timestamps of the track points in the candidate moving track; filter the candidate moving track in response to the difference between the timestamps of the adjacent track points being greater than a set difference threshold; and determine the target moving track according to the retained candidate moving tracks.

[0207] In a possible implementation manner of the embodiment of the present disclosure, the acquisition module 901 is configured to: acquire candidate moving tracks of a plurality of target objects in a set period; for any candidate moving track in the plurality of candidate moving tracks, determine a total moving time length of a corresponding target object, and a first position where the corresponding target object stops moving and a first stop time length of the first position according to the coordinate positions and the timestamps of the track points in the candidate moving track; determine a total stop time length of the corresponding target object according to the first stop time lengths of the positions; filter the candidate moving track in response to a ratio between the total stop time length and the total moving time length being greater than a set proportion threshold, and / or there being at least one first stop time length greater than a set time threshold; and determine the target moving track according to the retained candidate moving tracks.

[0208] In a possible implementation manner of the embodiment of the present disclosure, the acquisition module 901 is configured to: acquire candidate moving tracks of a plurality of target objects in a set period; determine a second position and a target period according to the coordinate positions and the timestamps of the track points in the plurality of candidate moving tracks, wherein at least two target objects are in a stop state when the distance between the target objects and the second position is less than a set distance threshold in the target period; filter, from the plurality of candidate moving tracks, a candidate moving track that passes through the second position and has a moving speed greater than a set speed threshold in the target period; and determine the target moving track according to the retained candidate moving tracks.

[0209] The cycle time determination apparatus of the traffic signal light according to the embodiments of the present disclosure determines switching points in the target movement trajectories of the target objects in the set time period according to the coordinate positions and time stamps of the trajectory points in the target movement trajectories of the target objects, wherein the switching points are the trajectory points at which the target objects switch from the stop state to the movement state, and determines the cycle time of the traffic signal light according to the difference between the time stamps of the switching points. In this way, the cycle time of the traffic signal light is determined according to a large number of movement trajectories, which can improve the accuracy and reliability of the determination result.

[0210] To achieve the above-mentioned embodiments, the present disclosure further provides an electronic device, which can include at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the cycle time determination method of the traffic signal light according to any one of the above-mentioned embodiments of the present disclosure.

[0211] To achieve the above-mentioned embodiments, the present disclosure further provides a non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to perform the cycle time determination method of the traffic signal light according to any one of the above-mentioned embodiments of the present disclosure.

[0212] To achieve the above-mentioned embodiments, the present disclosure further provides a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the cycle time determination method of the traffic signal light according to any one of the above-mentioned embodiments of the present disclosure.

[0213] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program product.

[0214] Figure 10 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. The electronic device can include a server, a client in the above-mentioned embodiments. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0215] As Figure 10As shown, the electronic device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes in accordance with a computer program stored in a ROM (Read-Only Memory) 1002 or a computer program loaded into a RAM (Random Access Memory) 1003 from the storage unit 1008. Various programs and data required for the operation of the electronic device 1000 can also be stored in the RAM 1003. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An I / O (Input / Output) interface 1005 is also connected to the bus 1004.

[0216] A plurality of components in the electronic device 1000 are connected to the I / O interface 1005, including an input unit 1006 such as a keyboard, a mouse, and the like, an output unit 1007 such as various types of displays, a speaker, and the like, a storage unit 1008 such as a magnetic disk, an optical disk, and the like, and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1009 allows the electronic device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0217] The computing unit 1001 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 1001 performs various methods and processes described above, such as the above-mentioned traffic signal cycle length determination method. For example, in some embodiments, the above-mentioned traffic signal cycle length determination method can be implemented as a computer software program, which is tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded onto the RAM 1003 and executed by the computing unit 1001, one or more steps of the above-mentioned traffic signal cycle length determination method described above can be performed. Alternatively, in other embodiments, the computing unit 1001 can be configured to perform the above-mentioned traffic signal cycle length determination method by other any appropriate means, such as by means of firmware.

[0218] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a Field Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a System on a Chip (SOC), a Complex Programmable Logic Device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0219] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general or special purpose computer, such that the program code, when executed by the processor or controller, causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0220] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include a linearly-programmed electronic storage, a portable computer diskette, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory), or flash memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0221] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0222] The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0223] The computer system can include clients and servers. The clients and the servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service (Virtual Private Server). The server can also be a server of a distributed system, or a server combined with a blockchain.

[0224] It should be noted that artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) of people, which has both hardware and software technologies. Artificial intelligence hardware technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technology mainly includes computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc. several major directions.

[0225] Cloud computing refers to accessing elastic and scalable shared physical or virtual resource pools through a network, which can include servers, operating systems, networks, software, applications, and storage devices, and can deploy and manage resources in a demand-driven and self-service manner. Through cloud computing technology, efficient and powerful data processing capabilities can be provided for artificial intelligence, blockchain, and other technology applications and model training.

[0226] According to the technical scheme of the embodiment of the present disclosure, the switching points in the plurality of target moving tracks are determined according to the coordinate positions and time stamps of each track point in the target moving tracks of the plurality of target objects in a set period of time; wherein the switching point is a track point where the target object switches from a stop state to a moving state; and the cycle length of the traffic signal lamp is determined according to the difference between the time stamps of each switching point. Thus, the cycle length of the traffic signal lamp is determined according to a large number of moving tracks, which can improve the accuracy and reliability of the determination result.

[0227] It should be understood that various forms of the flow shown above can be used to reorder, add or delete steps. For example, each step described in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical scheme proposed in the present disclosure can be achieved, which is not limited herein.

[0228] The above detailed description does not limit the scope of the disclosure. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the disclosure shall be included in the scope of the disclosure.

Claims

1. A method for determining a cycle length of a traffic signal, the method comprising: obtaining target moving trajectories of a plurality of target objects within a set time period; determining switching points in the target moving trajectories according to coordinate positions and time stamps of each trajectory point in the target moving trajectories, wherein the switching points are trajectory points at which the target objects switch from a stop state to a moving state; determining the cycle length of the traffic signal according to a first error between a difference between time stamps of each of the switching points and a candidate cycle length; the obtaining of the target moving trajectories of the plurality of target objects within the set time period comprises: obtaining candidate moving trajectories of the plurality of target objects within the set time period; filtering the candidate moving trajectories according to coordinate positions and time stamps of each trajectory point in the candidate moving trajectories; determining the target moving trajectories according to each of the retained candidate moving trajectories.

2. The method of claim 1, wherein, the determining of the cycle length of the traffic signal according to the first error between the difference between time stamps of each of the switching points and the candidate cycle length comprises: clustering each of the switching points according to the coordinate positions and the time stamps of each of the switching points to obtain a plurality of first clusters; determining target switching points from each of the first clusters according to the time stamps of each of the switching points in each of the first clusters; determining the cycle length of the traffic signal according to the first error between the difference between time stamps of each of the target switching points and the candidate cycle length.

3. The method of claim 2, wherein, the determining of the cycle length of the traffic signal according to the first error between the difference between time stamps of each of the target switching points and the candidate cycle length comprises: clustering each of the target switching points according to the coordinate positions of each of the target switching points to obtain at least one second cluster; for any one of the second clusters, determining a difference between time stamps of any two target switching points in the second cluster to obtain at least one first difference value; for any one of a set of candidate cycle lengths, determining a first error between the candidate cycle length and each of the first difference values; determining a first target cycle length from each of the candidate cycle lengths according to the first error of each of the candidate cycle lengths; determining the cycle length of the traffic signal that matches the coordinate positions of each of the target switching points in the second cluster according to the first target cycle length.

4. The method of claim 2, wherein, the determining of the cycle length of the traffic signal according to the first error between the difference between time stamps of each of the target switching points and the candidate cycle length comprises: clustering each of the target switching points according to the coordinate positions of each of the target switching points to obtain at least one second cluster; for any one of the second clusters, determining a difference between time stamps of any two target switching points in the second cluster to obtain at least one first difference value; dividing a set of candidate cycle lengths to obtain a plurality of candidate cycle length sub-sets; determining a second target cycle length from each of the candidate cycle length sub-sets according to each of the first difference values; determining the cycle length of the traffic signal that matches the coordinate positions of each of the target switching points in the second cluster according to each of the second target cycle lengths.

5. The method of claim 4, wherein, The method further comprises: determining, for each of the candidate period time sub-sets, a second error between any candidate period time in the candidate period time sub-set and each of the first differences; determining, from each of the candidate period time sub-sets, a second target period time according to the second error of each candidate period time in the candidate period time sub-set.

6. The method of claim 4, wherein, The method further comprises: sorting, in time stamp order, each of the target switch points in the second cluster from early to late to obtain a sorted sequence; determining, for each of the target switch points in the second cluster, a second difference between time stamps of adjacent target switch points in the sorted sequence; determining, for each of the second target period times, a third error between the second target period time and each of the second differences; determining, from each of the second target period times, a third target period time according to the third error of each of the second target period times; determining, for each of the target switch points in the second cluster, a period time of a traffic signal lamp matching a coordinate position of the target switch point according to the third target period time.

7. The method of any one of claims 1-6, wherein, The method further comprises: determining, for each of the candidate moving trajectories, a difference between time stamps of adjacent trajectory points in the candidate moving trajectory according to the coordinate positions and time stamps of the trajectory points in the candidate moving trajectory; filtering the candidate moving trajectory in response to the difference between time stamps of the adjacent trajectory points being greater than a set difference threshold.

8. The method of any one of claims 1-6, wherein, The method further comprises: determining, for each of the candidate moving trajectories, a total moving time of a corresponding target object, and a first position where the corresponding target object stops moving and a first stop time of the first position according to the coordinate positions and time stamps of the trajectory points in the candidate moving trajectory; determining a total stop time of the corresponding target object according to the first stop time of each of the first positions; filtering the candidate moving trajectory in response to a ratio between the total stop time and the total moving time being greater than a set ratio threshold, and / or, there being at least one first stop time greater than a set time threshold.

9. The method of any one of claims 1-6, wherein, The method further comprises: determining, according to the coordinate positions and time stamps of the trajectory points in the plurality of candidate moving trajectories, a second position and a target period, wherein at least two target objects are in a stop state when a distance between the target objects and the second position is less than a set distance threshold in the target period; filtering, from the plurality of candidate moving trajectories, a candidate moving trajectory that passes through the second position and has a moving speed greater than a set speed threshold in the target period.

10. A device for determining a cycle length of a traffic signal, the device comprising: an obtaining module configured to obtain target moving tracks of a plurality of target objects in a set time period; a first determining module configured to determine switching points in the target moving tracks according to coordinate positions and time stamps of track points in the target moving tracks, wherein the switching points are track points at which the target objects switch from a stop state to a moving state; a second determining module configured to determine the cycle length of the traffic signal according to a first error between a difference of the time stamps of the switching points and a candidate cycle length; the obtaining module is specifically configured to obtain candidate moving tracks of the plurality of target objects in the set time period, filter the candidate moving tracks according to the coordinate positions and the time stamps of track points in the candidate moving tracks, and determine the target moving tracks according to the retained candidate moving tracks.

11. The apparatus of claim 10, wherein, the second determining module is configured to: cluster the switching points according to the coordinate positions and the time stamps of the switching points to obtain a plurality of first clusters; determine target switching points from each of the first clusters according to the time stamps of the switching points in each of the first clusters; and determine the cycle length of the traffic signal according to a first error between a difference of the time stamps of the target switching points and a candidate cycle length.

12. The apparatus of claim 11, wherein, the second determining module is configured to: cluster the target switching points according to the coordinate positions of the target switching points to obtain at least one second cluster; determine a difference of the time stamps of any two target switching points in the second cluster to obtain at least one first difference value for any of the second clusters; determine a first error between the candidate cycle length and the first difference values for any of a set of candidate cycle lengths; determine a first target cycle length from the candidate cycle lengths according to the first errors of the candidate cycle lengths; and determine the cycle length of the traffic signal that matches the coordinate positions of the target switching points in the second cluster according to the first target cycle length.

13. The apparatus of claim 11, wherein, the second determining module is configured to: cluster the target switching points according to the coordinate positions of the target switching points to obtain at least one second cluster; determine a difference of the time stamps of any two target switching points in the second cluster to obtain at least one first difference value for any of the second clusters; divide a set of candidate cycle lengths to obtain a plurality of candidate cycle length sub-sets; determine a second target cycle length from each of the candidate cycle length sub-sets according to the first difference values; and determine the cycle length of the traffic signal that matches the coordinate positions of the target switching points in the second cluster according to the second target cycle length.

14. The apparatus of claim 13, wherein, the second determining module is configured to: determine a second error between any of the candidate cycle length sub-sets and the first difference values for any of the candidate cycle length sub-sets; and determine a second target cycle length from each of the candidate cycle lengths in the candidate cycle length sub-set according to a second error of each of the candidate cycle lengths in the candidate cycle length sub-set.

15. The apparatus of claim 13, wherein, The second determining module is configured to: sort each of the target switching points in the second cluster according to timestamps from early to late to obtain a sorting sequence; determine a second difference value from a difference between timestamps of adjacent target switching points in the sorting sequence; determine a third error between any of the second target cycle lengths and each of the second difference values; determine a third target cycle length from each of the second target cycle lengths according to the third error of each of the second target cycle lengths; determine a cycle length of a traffic signal lamp matching the coordinate position of each of the target switching points in the second cluster according to the third target cycle length.

16. The apparatus of any one of claims 10-15, wherein, The obtaining module is configured to: for any of the plurality of candidate moving trajectories, determine a difference between timestamps of adjacent trajectory points in each of the trajectory points in the candidate moving trajectory according to the coordinate position and the timestamp of each of the trajectory points in the candidate moving trajectory; filter the candidate moving trajectory in response to the difference between the timestamps of the adjacent trajectory points being greater than a set difference threshold.

17. The apparatus of any one of claims 10-15, wherein, The obtaining module is configured to: for any of the plurality of candidate moving trajectories, determine a total moving time length of a corresponding target object, and a first position where the corresponding target object stops moving and a first stop time length of the first position according to the coordinate position and the timestamp of each of the trajectory points in the candidate moving trajectory; determine a total stop time length of the corresponding target object according to the first stop time length of each of the first positions; filter the candidate moving trajectory in response to a ratio between the total stop time length and the total moving time length being greater than a set proportion threshold, and / or, there being at least one of the first stop time lengths being greater than a set time threshold.

18. The apparatus of any one of claims 10-15, wherein, The obtaining module is configured to: determine a second position and a target period according to the coordinate position and the timestamp of each of the trajectory points in the plurality of candidate moving trajectories, wherein at least two target objects are in a stop state when a distance between the target objects and the second position is less than a set distance threshold in the target period; filter a candidate moving trajectory from the plurality of candidate moving trajectories, wherein the candidate moving trajectory passes through the second position and has a moving speed greater than a set speed threshold in the target period. 19.An electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the cycle length determination method of the traffic signal lamp according to any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the cycle length determination method of the traffic signal lamp according to any one of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method for determining the cycle length of a traffic light according to any one of claims 1-9.

Images