Road congestion detection method, device and equipment
By using the data collected from the capture equipment to detect road congestion, the problem of high cost of deploying sensors in the prior art is solved, and low-cost and accurate road congestion detection is achieved.
Patent Information
- Application Number
- CN202310952191.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-28
- Publication Date
- 2025-02-14
AI Technical Summary
The prior art requires additional deployment of sensors when detecting road congestion, resulting in higher deployment costs.
By obtaining the capture data of the first and second capture devices on the road to be detected within a specified time period, the vehicle's attribute information is detected based on the images in each frame of these data, and the detection sequence overlap of each attribute information is calculated. Then determine whether the road is congested.
This enables road congestion detection without additional deployment of other equipment, reducing costs, and accurately determining road congestion conditions.
Smart Images
Figure CN119445816A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent transportation technology, and in particular to a road congestion detection method, device and equipment. Background Art
[0002] In recent years, with the continuous improvement of social and economic levels, the number of vehicles has increased year by year, and traffic safety issues have received more and more attention and attention from people. How to detect road congestion has become a problem that needs to be solved urgently.
[0003] At present, road congestion is mainly detected by sensors installed on both sides of the road. When this method is used to detect road congestion, additional sensors need to be deployed, and the deployment cost is relatively high. Summary of the invention
[0004] In view of this, the present application provides a road congestion detection method, device and equipment to reduce the cost of road congestion detection.
[0005] Specifically, the present application is implemented through the following technical solutions:
[0006] A first aspect of the present application provides a road congestion detection method, the method comprising:
[0007] Acquire first captured data of a first captured device on the road to be detected within a first specified time period, and second captured data of a second captured device on the road to be detected within a second specified time period;
[0008] Detecting at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtaining a first detection sequence for each attribute information and a second detection sequence for each attribute information; wherein the first detection sequence corresponds to the first captured data, and the second detection sequence corresponds to the second captured data;
[0009] Determine the overlap degree of the first detection sequence of each item of attribute information and the second detection sequence of each item of attribute information to obtain the overlap degree of each item of attribute information;
[0010] Whether the road to be detected is congested is determined based on the overlap degree of each item of attribute information.
[0011] A second aspect of the present application provides a road congestion detection device, the device comprising an acquisition module, a detection module, a calculation module and a processing module; wherein:
[0012] The acquisition module is used to acquire first captured data of a first captured device on the road to be detected within a first specified time period, and second captured data of a second captured device on the road to be detected within a second specified time period;
[0013] The detection module is used to detect at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtain a first detection sequence for each attribute information and a second detection sequence for each attribute information; wherein the first detection sequence corresponds to the first captured data, and the second detection sequence corresponds to the second captured data;
[0014] The calculation module is used to determine the overlap between the first detection sequence of each item of attribute information and the second detection sequence of each item of attribute information, so as to obtain the overlap between each item of attribute information;
[0015] The processing module is used to determine whether the road to be detected is congested based on the overlap of each item of attribute information.
[0016] The third aspect of the present application provides a road congestion detection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods provided in the first aspect of the present application are implemented.
[0017] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods provided in the first aspect of the present application.
[0018] The road congestion detection method, device and equipment provided by the present application obtains the first captured data of the first captured device on the road to be detected within the first specified time period, and the second captured data of the second captured device on the road to be detected within the second specified time period, and then detects at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtains the first detection sequence of each attribute information and the second detection sequence of each attribute information, thereby determining the first detection sequence of each attribute information and the overlap degree of the second detection sequence of each attribute information, and obtaining the overlap degree of each attribute information, and then judging whether the road to be detected is congested based on the overlap degree of each attribute information. In this way, the first detection sequence is obtained through the first captured data, the second detection sequence is obtained through the second captured data, and the overlap degree of the first detection sequence of each attribute information and the second detection sequence of each attribute information is calculated, and then judging whether the road to be detected is congested based on the overlap degree, and road congestion detection can be performed based on the captured data collected by the captured device, without the need to deploy other equipment additionally, and the cost is low. In addition, the congestion situation of the road to be detected can be accurately determined through this method. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1A flowchart of a first embodiment of a road congestion detection method provided by the present application;
[0020] Figure 2 A flowchart of a second embodiment of the road congestion detection method provided by the present application;
[0021] Figure 3 A flowchart of a third embodiment of the road congestion detection method provided by the present application;
[0022] Figure 4 A diagram showing the relationship between the acquisition order and the vehicle color according to an exemplary embodiment of the present application;
[0023] Figure 5 A diagram showing the relationship between the acquisition order and the vehicle color according to another exemplary embodiment of the present application;
[0024] Figure 6 A flowchart of a fourth embodiment of the road congestion detection method provided by the present application;
[0025] Figure 7 A flowchart of a fifth embodiment of a road congestion detection method provided by the present application;
[0026] Figure 8 A hardware structure diagram of a road congestion detection device in which the road congestion detection device provided in this application is located;
[0027] Fig. 9 The figure is a schematic structural diagram of a road congestion detection device according to an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0028] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0029] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0030] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0031] The present application provides a road congestion detection method, device and equipment to reduce the cost of road congestion detection.
[0032] The road congestion detection method, device and equipment provided by the present application obtains the first captured data of the first captured device on the road to be detected within the first specified time period, and the second captured data of the second captured device on the road to be detected within the second specified time period, and then detects at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtains the first detection sequence of each attribute information and the second detection sequence of each attribute information, and further determines the overlap between the first detection sequence of each attribute information and the second detection sequence of each attribute information, and obtains the overlap between each attribute information, and then determines whether the road to be detected is congested based on the overlap between each attribute information. In this way, the first detection sequence is obtained through the first captured data, the second detection sequence is obtained through the second captured data, and the overlap between the first detection sequence of each attribute information and the second detection sequence of each attribute information is calculated, and then determines whether the road to be detected is congested based on the overlap, and the road congestion detection can be performed based on the captured data collected by the capture device, without the need to deploy other equipment, and the cost is low. In addition, the congestion situation of the road to be detected can be accurately determined by this method.
[0033] Specific embodiments are given below to introduce the technical solution of the present application in detail.
[0034] Figure 1 This is a flow chart of the first embodiment of the road congestion detection method provided by this application. Please refer to Figure 1 , the method provided in this embodiment may include:
[0035] S101, obtaining first captured data of a first captured device on a road to be detected within a first specified time period, and second captured data of a second captured device on the road to be detected within a second specified time period.
[0036] Specifically, the first capture device and the second capture device are shooting devices used to capture vehicle conditions on the road. For example, the first capture device and / or the second capture device may be a surveillance camera installed on a road or at an intersection. For another example, the first capture device and / or the second capture device may be a remote sensing satellite or an aerial drone.
[0037] Specifically, the distance between the first capture device and the second capture device is equal to the preset distance, and according to the driving direction of the vehicle, the second capture device is located behind the first capture device. It should be noted that the specific value of the preset distance is set according to actual needs and is not limited in this embodiment. For example, in one embodiment, the preset distance is 3 kilometers.
[0038] Furthermore, the first designated time period is set according to actual needs. In this embodiment, the first designated time period is not limited. For example, the first designated time period may be half an hour before the current time. Specifically, for example, in one embodiment, the current time is 10:00 and the first designated time period is 9:30-10:00.
[0039] Furthermore, the second designated time period may be a time period after the first designated time period and a preset time period from the first designated time period. It should be noted that the preset time period is equal to the ratio of the distance between the first capture device and the second capture device to the reference speed, wherein the reference speed may be the speed of a vehicle traveling on the road to be detected when the road to be detected is not congested. For example, in one embodiment, when the distance between the first capture device and the second capture device is 3 kilometers, the preset time period is 8 minutes. Further, in combination with the above example, when the first designated time period is 9:30-10:00, at this time, the second designated time period is 9:38-10:08.
[0040] Further, the first captured data is all image data captured by the first captured device within the first specified time period. For example, the first captured data may be a video. For another example, the first captured data may be a plurality of pictures.
[0041] Similarly, the second captured data is all the image data captured by the second captured device within the second specified time period. For example, the second captured data may be a video. For another example, the second captured data may be a plurality of pictures.
[0042] S102. Detect at least one attribute information of the vehicle based on each frame image in the first snapshot data and the second snapshot data, and obtain a first detection sequence for each attribute information and a second detection sequence for each attribute information; wherein the first detection sequence corresponds to the first snapshot data, and the second detection sequence corresponds to the second snapshot data.
[0043] Specifically, the attribute information of the vehicle may include at least one of the following information: vehicle color, license plate, and vehicle model. The following description will be made by taking the vehicle attribute information being the license plate as an example.
[0044] For example, in one embodiment, the first captured data and the second captured data each include 8 frames of images, and all passing vehicles and the license plates of all passing vehicles are detected from each frame of the first captured data and the second captured data in the order from the front to the back of the shooting time, and then based on the first captured data, a first detection sequence corresponding to the license plate is obtained; similarly, based on the second captured data, a second detection sequence corresponding to the license plate is obtained. For example, Table 1 shows the first detection sequence and the second detection sequence corresponding to the license plate shown in an exemplary embodiment of the present application:
[0045] Table 1 The first detection sequence and the second detection sequence corresponding to the license plate
[0046] Collection order First detection sequence Second detection sequence 1 Guangdong B12345 Guangdong B12345 2 Guangdong C23456 Guangdong C23456 3 Guangdong D34567 Guangdong D12321 4 Guangdong E45678 Guangdong E45678 5 Guangdong F56789 Guangdong F56789 6 Guangdong G67890 Guangdong G67890 7 Guangdong H78901 Guangdong H78901 8 Guangdong J89012 Guangdong J89012
[0047] S103: Determine the degree of overlap between the first detection sequence corresponding to each item of attribute information and the second detection sequence corresponding to each item of attribute information, and obtain the degree of overlap between each item of attribute information.
[0048] Specifically, a relevant coincidence calculation algorithm can be used to calculate the coincidence between the first detection sequence and the second detection sequence corresponding to each attribute information. The specific implementation principle of the coincidence calculation algorithm can be referred to the description in the relevant technology, which will not be repeated here.
[0049] For example, in one embodiment, in combination with the above example, please refer to Table 1, the license plate of the third vehicle in the first detection sequence is different from that in the second detection sequence, and the calculated overlap degree between the first detection sequence and the second detection sequence is 88%.
[0050] S104: Determine whether the road to be detected is congested based on the overlap of each item of attribute information.
[0051] In a specific implementation, in a possible implementation mode, when the attribute information is one item, when the overlap degree of the attribute information is greater than the congestion threshold, it is determined that the road to be detected is congested, otherwise it is determined that the road to be detected is unobstructed.
[0052] The specific value of the congestion threshold is set according to actual needs and is not limited in this embodiment. For example, in one embodiment, the congestion threshold is 80%.
[0053] Specifically, the higher the overlap between the first detection sequence and the second detection sequence, the less the change in the order of vehicles on the road to be detected or the lower the proportion, that is, the higher the congestion level of the road to be detected. Conversely, the lower the overlap between the first detection sequence and the second detection sequence, the greater the probability of vehicles interweaving on the road to be detected and the greater the difference in the order of vehicles, that is, the lower the congestion level of the road to be detected.
[0054] In combination with the above example, the overlap between the first detection sequence and the second detection sequence is 88%, which is greater than the congestion threshold. It can be considered that the road to be detected is in a congested state at this time.
[0055] Furthermore, when there are multiple pieces of attribute information, it is possible to determine whether the road to be detected is congested based on the overlap of these pieces of attribute information. For example, in one embodiment, the determination can be made in the following manner:
[0056] (1) For each item of attribute information, determine the judgment result corresponding to the attribute information (the judgment result is congestion or unobstructed traffic).
[0057] Specifically, for the overlap degree of each attribute information, when the overlap degree is greater than the congestion threshold of the attribute information, the judgment result corresponding to the attribute information is determined to be congested; otherwise, the judgment result corresponding to the attribute information is determined to be unblocked.
[0058] (2) Among all the judgment results, the judgment result with the largest proportion is confirmed as the congestion state of the road to be detected at this time.
[0059] For example, in one embodiment, the attribute information includes vehicle color, license plate and vehicle model. The judgment result corresponding to the vehicle color is determined to be congested, the judgment result corresponding to the license plate is determined to be unobstructed, and the judgment result corresponding to the vehicle model is determined to be unobstructed. At this time, among all the judgment results, the proportion of unobstructed is relatively large, confirming that the road to be inspected is unobstructed at this time.
[0060] The road congestion detection method provided in this embodiment obtains the first captured data of the first captured device on the road to be detected within the first specified time period and the second captured data of the second captured device on the road to be detected within the second specified time period, and then detects at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtains the first detection sequence corresponding to each attribute information and the second detection sequence corresponding to each attribute information, thereby determining the first detection sequence of each attribute information and the overlap degree of the second detection sequence of each attribute information, and obtaining the overlap degree of each attribute information, and then judging whether the road to be detected is congested based on the overlap degree of each attribute information. In this way, the first detection sequence is obtained through the first captured data, the second detection sequence is obtained through the second captured data, and the overlap degree of the first detection sequence of each attribute information and the second detection sequence of each attribute information is calculated, and then judging whether the road to be detected is congested based on the overlap degree, and road congestion detection can be performed based on the captured data collected by the captured device, without the need to deploy other additional equipment, and the cost is low. In addition, the congestion situation of the road to be detected can be accurately determined through this method.
[0061] Figure 2 This is a flow chart of the second embodiment of the road congestion detection method provided by this application. Please refer to Figure 2 The method provided in this embodiment, based on the above embodiment, determines the overlap between the first detection sequence of each item of attribute information and the second detection sequence of each item of attribute information, and obtains the overlap between each item of attribute information, which may include:
[0062] S201. According to a preset conversion relationship between attribute information values and digital information values, convert each attribute information value in the first detection sequence and the second detection sequence into a digital information value to obtain a first digital sequence corresponding to the first detection sequence and a second digital sequence corresponding to the second detection sequence.
[0063] Specifically, the conversion relationship between the preset attribute information value and the digital information value is set according to actual needs. In this embodiment, the conversion relationship between the preset attribute information value and the digital information value is not limited. For example, in one embodiment, when the attribute information is a vehicle model, Table 2 is a conversion relationship between a preset vehicle model value and a digital information value shown in an exemplary embodiment of the present application.
[0064] Table 2 Conversion relationship between preset vehicle model value and digital information value
[0065]
[0066]
[0067] For example, in one embodiment, in combination with the above example, the first detection sequence is A, B, C, D, E, F, G, and in combination with Table 2, after converting each attribute information value, the obtained digital information values are 1, 2, 3, 4, 5, 6, 7 respectively; similarly, the second detection sequence is A, B, C, A, E, F, G, and after converting each attribute information value, the obtained digital information values are 1, 2, 3, 1, 5, 6, 7 respectively. Based on these two sets of digital information values, the corresponding first digital sequence is 1234567, and the second digital sequence is 1231567.
[0068] S202: Calculate the degree of coincidence between the first digital sequence and the second digital sequence, and determine the calculated degree of coincidence as the degree of coincidence of each item of information.
[0069] Specifically, a relevant coincidence calculation algorithm can be used to calculate the coincidence between the first digital sequence and the second digital sequence. The specific implementation principle of the coincidence calculation algorithm can be referred to the description in the relevant technology, which will not be repeated here.
[0070] For example, in one embodiment, in combination with the above example, the coincidence degree of the first digital sequence 1234567 and the second digital sequence 1231567 is calculated, and the coincidence degree of the first digital sequence and the second digital sequence is 86%.
[0071] The road congestion detection method provided by the present application obtains the first captured data of the first captured device on the road to be detected within the first specified time period, and the second captured data of the second captured device on the road to be detected within the second specified time period, and then detects at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtains the first detection sequence of each attribute information and the second detection sequence of each attribute information, thereby determining the overlap between the first detection sequence of each attribute information and the second detection sequence of each attribute information, obtaining the overlap of each attribute information, and then judging whether the road to be detected is congested based on the overlap of each attribute information. In this way, road congestion detection can be performed based on the captured data collected by the captured device, without the need to deploy other additional equipment, and the cost is low. In addition, the congestion situation of the road to be detected can be accurately determined through this method.
[0072] Figure 3 This is a flow chart of the third embodiment of the road congestion detection method provided by this application. Please refer to Figure 3 , the method provided in this embodiment may include:
[0073] S301 , obtaining first captured data of a first captured device on a road to be detected within a first specified time period, and second captured data of a second captured device on the road to be detected within a second specified time period.
[0074] The specific implementation principle and implementation process of step S301 can be found in the description of the above embodiment, which will not be repeated here.
[0075] S302. Detect at least one attribute information of the vehicle based on each frame image in the first snapshot data and the second snapshot data, and obtain a first detection sequence for each attribute information and a second detection sequence for each attribute information; wherein the first detection sequence corresponds to the first snapshot data, and the second detection sequence corresponds to the second snapshot data.
[0076] For example, in one embodiment, the attribute information of the vehicle is the vehicle color, and the first captured data and the second captured data obtained include 10 frames of images respectively. According to the order from the front to the back of the shooting time, the vehicle color of the vehicle is detected from each frame of the first captured data to obtain the first detection sequence corresponding to the vehicle color; the vehicle color of the vehicle is detected from each frame of the second captured data to obtain the second detection sequence corresponding to the vehicle color. For example, Table 3 shows the first detection sequence and the second detection sequence corresponding to the vehicle color shown in an exemplary embodiment of the present application:
[0077] Table 3 The first detection sequence and the second detection sequence corresponding to the vehicle color
[0078]
[0079]
[0080] S303: According to a preset conversion relationship between attribute information values and digital information values, convert each attribute information value in the first detection sequence and the second detection sequence into a digital information value to obtain a first digital sequence corresponding to the first detection sequence and a second digital sequence corresponding to the second detection sequence.
[0081] For example, in one embodiment, in combination with the above example, the detected attribute information is vehicle color. Table 4 is a conversion relationship between a preset vehicle color value and a digital information value shown in an exemplary embodiment of the present application.
[0082] Table 4 Conversion relationship between preset vehicle color value and digital information value
[0083] Vehicle color value Digital information value blue 1 green 2 White 3 black 4 yellow 5 …… ……
[0084] Furthermore, the first detection sequence is yellow, green, black, blue, blue, white, green, black, yellow, green. Combined with Table 4, after converting the attribute information values, the digital information values obtained are 5, 2, 4, 1, 1, 3, 2, 4, 5, 2. Similarly, the second detection sequence is yellow, green, black, blue, green, white, green, black, yellow, green. Combined with Table 4, after converting the attribute information values, the digital information values obtained are 5, 2, 4, 1, 2, 3, 2, 4, 5, 2. Based on these two sets of digital information values, the corresponding first digital sequence is 5241132452, and the second digital sequence is 5241232452.
[0085] S304: construct a relationship diagram between the collection order and the attribute information with the collection order of each digital information value in the first digital sequence as the horizontal coordinate and the digital information values as the vertical coordinate, to obtain a first relationship diagram corresponding to the first digital sequence.
[0086] Further, in combination with the above example, for the first digital sequence, the collection order of each digital information value in the first digital sequence is used as the horizontal coordinate and the first digital information value is used as the vertical coordinate to construct a relationship diagram between the collection order and the attribute information, and obtain a first relationship diagram corresponding to the first digital sequence. The first relationship diagram is as follows: Figure 4 As shown in Figure A ( Figure 4 A relationship diagram between the collection order and the vehicle color is shown as an exemplary embodiment of the present application).
[0087] S305 , constructing a relationship diagram between the collection order and the attribute information with the collection order of each digital information value in the second digital sequence as the horizontal coordinate and the digital information values as the vertical coordinate, to obtain a second relationship diagram corresponding to the second digital sequence.
[0088] The explanation of this step can be found in the previous step, and will not be repeated here. The final second relationship diagram is as follows: Figure 4 As shown in Figure B.
[0089] S306: Calculate the overlap degree between the first relationship graph and the second relationship graph, and determine the calculated overlap degree as the overlap degree of each item of attribute information.
[0090] Specifically, a relevant overlap calculation algorithm can be used to calculate the overlap between the relationship graphs. The specific implementation principle of the overlap calculation algorithm can be referred to the description in the relevant technology, which will not be repeated here.
[0091] Combining the above example, for example, in Figure 4In the example shown, the overlap between the relationship graph corresponding to the first digital sequence and the relationship graph corresponding to the second digital sequence is 90%. At this time, the overlap between the two is high, and it can be considered that the road is congested at this time.
[0092] S307: Determine whether the road to be detected is congested based on the overlap of each item of attribute information.
[0093] Specifically, the specific implementation principle of step S307 can be found in the description of the above embodiment, which will not be repeated here.
[0094] For another example, in another embodiment, the first captured data and the second captured data each include 10 frames of images, and the vehicle colors of all vehicles are detected from each frame of the first captured data and the second captured data in order from the front to the back of the shooting time, thereby obtaining the first detection sequence and the second detection sequence corresponding to the vehicle color. For example, Table 5 is a first detection sequence and a second detection sequence corresponding to the vehicle color shown in another exemplary embodiment of the present application:
[0095] Table 5 The first detection sequence and the second detection sequence corresponding to the vehicle color
[0096] Collection order First detection sequence Second detection sequence 1 yellow green 2 green yellow 3 black black 4 blue green 5 blue blue 6 White White 7 green green 8 black yellow 9 yellow black 10 green yellow
[0097] Further, the first detection sequence is yellow, green, black, blue, blue, white, green, black, yellow, green. Combined with Table 4, after converting the attribute information values, the corresponding digital information values are 5, 2, 4, 1, 1, 3, 2, 4, 5, 2; similarly, the second detection sequence is green, yellow, black, green, blue, white, green, yellow, black, yellow. Combined with Table 4, after converting the attribute information values, the corresponding digital information values are 2, 5, 4, 2, 1, 3, 2, 5, 4, 5. Based on these two sets of digital information values, the corresponding first digital sequence is 5241132452, and the second digital sequence is 2542132545.
[0098] Further, for each digital sequence, a relationship diagram between the collection order and the attribute information is constructed with the collection order of each digital information value in the digital sequence as the horizontal axis and the digital information value as the vertical axis to obtain a relationship diagram corresponding to the digital sequence. The relationship diagram is as follows: Figure 5 As shown ( Figure 5 This is another relationship diagram between the acquisition order and the vehicle color shown in an exemplary embodiment of the present application). Please refer to Figure 5 , Figure 5 Figure A in is the relationship diagram corresponding to the first digital sequence. Figure 5 Figure B in is the relationship diagram corresponding to the second digital sequence.
[0099] Further, in Figure 5 In the example shown, the overlap between the relationship graph corresponding to the first digital sequence and the relationship graph corresponding to the second digital sequence is 40%. At this time, the overlap between the two is low, and it can be considered that the road is unblocked at this time.
[0100] The road congestion detection method provided in this embodiment can perform road congestion detection based on the captured data collected by the capture device, without the need to deploy other additional equipment, and has low cost. In addition, through this method, the congestion situation of the road to be detected can be accurately determined.
[0101] Figure 6 This is a flow chart of the fourth embodiment of the road congestion detection method provided by this application. Please refer to Figure 6 The method provided in this embodiment, based on the above embodiment, when the attribute information is multiple, the step of judging whether the road to be detected is congested based on the overlap of each attribute information may include:
[0102] S601. Obtain a comprehensive degree of coincidence based on a weight associated with each item of attribute information and a degree of coincidence of each item of attribute information.
[0103] Specifically, the specific value of the weight associated with each item of attribute information is set according to actual needs. In this embodiment, the specific value of the weight associated with each item of attribute information is not limited.
[0104] For example, in one embodiment, the attribute information includes vehicle color, vehicle model and license plate. The weight associated with vehicle color can be set to 10%, the weight associated with vehicle model can be set to 20%, and the weight associated with license plate can be set to 70%.
[0105] Furthermore, the overlap degree of each item of attribute information is weighted by the weight associated with each item of attribute information, and the weighted processing result is determined as the comprehensive overlap degree.
[0106] S602: When the comprehensive overlap is greater than a preset threshold, determine that the road to be detected is congested.
[0107] Specifically, the specific value of the preset threshold is set according to actual needs. In this embodiment, the specific value of the preset threshold is not limited. For example, in one embodiment, the preset threshold is 60%. At this time, when performing road congestion detection and judgment, when the comprehensive overlap is greater than 60%, it is determined that the road to be detected is congested.
[0108] S603: When the comprehensive overlap is less than or equal to a preset threshold, determine that the road to be detected is unobstructed.
[0109] In combination with the above example, the preset threshold is 60%. At this time, when performing road congestion detection and judgment, when the comprehensive overlap is less than or equal to 60%, it is determined that the road to be detected is unobstructed.
[0110] The road congestion detection method provided in this embodiment, when there are multiple pieces of attribute information, when judging whether the road to be detected is congested based on the overlap of each piece of attribute information, firstly obtains the comprehensive overlap based on the weight associated with each piece of attribute information and the overlap of each piece of attribute information, and then determines that the road to be detected is congested when the comprehensive overlap is greater than a preset threshold, and determines that the road to be detected is unobstructed when the comprehensive overlap is less than or equal to the preset threshold. In this way, based on the weights pre-set for each piece of attribute information, the overlap of each piece of attribute information is combined to perform road congestion detection, which can improve the accuracy of detection.
[0111] Figure 7 This is a flow chart of the fifth embodiment of the road congestion detection method provided by this application. Please refer to Figure 7 The method provided in this embodiment, based on the above embodiment, after determining that the road to be detected is congested, the method may further include:
[0112] S701. Determine the congestion level corresponding to the comprehensive overlap based on a preset correspondence between the comprehensive overlap and the congestion level.
[0113] The correspondence between the preset comprehensive overlap and the congestion level is set according to actual needs. For example, in one embodiment, different colors are used to represent different congestion levels. Table 6 shows a correspondence between the preset comprehensive overlap and the congestion level in an exemplary embodiment of the present application.
[0114] Table 6 Correspondence between preset comprehensive overlap and congestion level
[0115] Comprehensive overlap Congestion level Characterizing Color 0％-30％ Smooth green 30％-60％ Basic smooth Light Green 60％-70％ Mild congestion Light yellow 70％-80％ Moderate congestion yellow 80％-100％ Severe congestion red
[0116] Please refer to Table 6. In the example shown in Table 6, the road congestion level is divided into five levels, corresponding to the five colors of green, light green, light yellow, yellow and red. The greener the road, the smoother the road, and the redder the road, the more congested the road. Further, after obtaining the comprehensive overlap, the congestion level corresponding to the comprehensive overlap can be found based on Table 6.
[0117] S702: Determine the congestion level as the current congestion level of the road to be detected.
[0118] For example, in one embodiment, combined with the above example, the currently calculated comprehensive overlap is 48%. Combined with Table 6, at this time, the corresponding congestion level is basically unobstructed, and the current congestion level of the road to be detected is determined to be basically unobstructed, and is represented by light green.
[0119] For another example, in another embodiment, combined with the above example, the currently calculated comprehensive overlap is 84%. Combined with Table 6, at this time, the corresponding congestion level is severe congestion, and the current congestion level of the road to be detected is determined to be severe congestion, and is represented by red.
[0120] The road congestion detection method provided in this embodiment determines the congestion level corresponding to the comprehensive overlap based on the preset corresponding relationship between the comprehensive overlap and the congestion level, and then determines the congestion level as the current congestion level of the road to be detected. In this way, not only can it be determined whether the road is congested, but also the corresponding congestion level can be given.
[0121] Corresponding to the aforementioned embodiment of a road congestion detection method, the present application also provides an embodiment of a road congestion detection device.
[0122] The embodiment of a road congestion detection device of the present application can be applied to a road congestion detection device. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, the processor of the road congestion detection device in which it is located reads the corresponding computer program instructions in the non-volatile memory into the memory and runs them. From the hardware level, if Figure 8 As shown, it is a hardware structure diagram of the road congestion detection device where the road congestion detection device of the present application is located, except Figure 8 In addition to the processor, memory, network interface, and non-volatile memory shown, the road congestion detection device in the embodiment where the device is located may also include other hardware according to the actual function of the road congestion detection device, which will not be described in detail.
[0123] Fig. 9 This is a schematic diagram of a road congestion detection device according to an exemplary embodiment of the present application. Fig. 9 The device provided in this embodiment may include an acquisition module 910, a detection module 920, a calculation module 930 and a processing module 940; wherein,
[0124] The acquisition module 910 is used to acquire first captured data of a first captured device on the road to be detected within a first specified time period, and second captured data of a second captured device on the road to be detected within a second specified time period;
[0125] The detection module 920 is used to detect at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtain a first detection sequence of each attribute information and a second detection sequence of each attribute information; wherein the first detection sequence corresponds to the first captured data, and the second detection sequence corresponds to the second captured data;
[0126] The calculation module 930 is used to determine the overlap between the first detection sequence of each item of attribute information and the second detection sequence of each item of attribute information, and obtain the overlap between each item of attribute information;
[0127] The processing module 940 is used to determine whether the road to be detected is congested based on the overlap of each item of attribute information.
[0128] The device of this embodiment can be used to perform Figure 1 The steps, specific implementation principles and implementation processes of the method embodiment shown are similar and will not be repeated here.
[0129] Optionally, the calculation module 930 is specifically configured to convert each attribute information value in the first detection sequence and the second detection sequence into a digital information value according to a preset conversion relationship between the attribute information value and the digital information value, so as to obtain a first digital sequence corresponding to the first detection sequence and a second digital sequence corresponding to the second detection sequence;
[0130] The calculation module 930 is further specifically configured to calculate the degree of overlap between the first digital sequence and the second digital sequence, and determine the calculated degree of overlap as the degree of overlap of each item of attribute information.
[0131] Optionally, the calculation module 930 is specifically configured to construct a relationship diagram between the collection order and the attribute information by taking the collection order of each digital information value in the first digital sequence as the horizontal coordinate and the each digital information value as the vertical coordinate, so as to obtain a first relationship diagram corresponding to the first digital sequence;
[0132] The calculation module 930 is further specifically configured to construct a relationship diagram between the collection order and the attribute information with the collection order of each digital information value in the second digital sequence as the horizontal coordinate and the digital information value as the vertical coordinate, so as to obtain a second relationship diagram corresponding to the second digital sequence;
[0133] The calculation module 930 is further specifically configured to calculate the overlap between the first relationship graph and the second relationship graph, and determine the calculated overlap as the overlap of each item of attribute information.
[0134] Optionally, the processing module 940 is specifically configured to obtain a comprehensive degree of coincidence based on a weight associated with each item of attribute information and a degree of coincidence of each item of attribute information;
[0135] The processing module 940 is further specifically used to determine that the road to be detected is congested when the comprehensive overlap is greater than a preset threshold, and to determine that the road to be detected is unobstructed when the comprehensive overlap is less than or equal to the preset threshold.
[0136] Optionally, the processing module 940 is specifically used to determine the congestion level corresponding to the comprehensive overlap based on a preset correspondence between the comprehensive overlap and the congestion level, and determine the congestion level as the current congestion level of the road to be detected.
[0137] Optionally, the attribute information includes at least one of the following information: vehicle color, license plate, and vehicle model.
[0138] Please continue to refer to Figure 8 The present application also provides a road congestion detection device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods provided in the first aspect of the present application are implemented.
[0139] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of any one of the methods provided in the present application are implemented.
[0140] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.
[0141] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.
[0142] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.
Claims
1. A road congestion detection method, characterized in that: The method comprises: Acquire first captured data of a first captured device on the road to be detected within a first specified time period, and second captured data of a second captured device on the road to be detected within a second specified time period; Detecting at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtaining a first detection sequence for each attribute information and a second detection sequence for each attribute information; wherein the first detection sequence corresponds to the first captured data, and the second detection sequence corresponds to the second captured data; Determine the overlap degree of the first detection sequence of each item of attribute information and the second detection sequence of each item of attribute information to obtain the overlap degree of each item of attribute information; Whether the road to be detected is congested is determined based on the overlap degree of each item of attribute information.
2. The method according to claim 1, characterized in that The determining the coincidence degree between the first detection sequence of each item of attribute information and the second detection sequence of each item of attribute information to obtain the coincidence degree of each item of attribute information includes: According to a preset conversion relationship between attribute information values and digital information values, each attribute information value in the first detection sequence and the second detection sequence is converted into a digital information value to obtain a first digital sequence corresponding to the first detection sequence and a second digital sequence corresponding to the second detection sequence; The degree of coincidence between the first digital sequence and the second digital sequence is calculated, and the calculated degree of coincidence is determined as the degree of coincidence of each item of attribute information.
3. The method according to claim 2, characterized in that The calculating the degree of coincidence between the first digital sequence and the second digital sequence includes: A relationship diagram between the collection order and the attribute information is constructed with the collection order of each digital information value in the first digital sequence as the horizontal coordinate and the digital information values as the vertical coordinate, to obtain a first relationship diagram corresponding to the first digital sequence; A relationship diagram between the collection order and the attribute information is constructed with the collection order of each digital information value in the second digital sequence as the horizontal coordinate and the digital information values as the vertical coordinate, to obtain a second relationship diagram corresponding to the second digital sequence; The overlap degree between the first relationship graph and the second relationship graph is calculated, and the calculated overlap degree is determined as the overlap degree of each item of attribute information.
4. The method according to any one of claims 1 to 3, characterized in that: When the attribute information is multiple, judging whether the road to be detected is congested based on the overlap of each item of attribute information includes: Obtaining a comprehensive degree of coincidence based on the weight associated with each item of attribute information and the degree of coincidence of each item of attribute information; When the comprehensive overlap is greater than a preset threshold, determining that the road to be detected is congested; When the comprehensive overlap is less than or equal to a preset threshold, it is determined that the road to be detected is unobstructed.
5. The method according to any one of claims 1 to 4, characterized in that: After determining that the road to be detected is congested, the method further includes: Based on a preset correspondence between the comprehensive overlap and the congestion level, determining the congestion level corresponding to the comprehensive overlap; The congestion level is determined as the current congestion level of the road to be detected.
6. The method according to claim 1, characterized in that The attribute information includes at least one of the following information: vehicle color, license plate, and vehicle model.
7. A road congestion detection device, characterized in that: The device includes an acquisition module, a detection module, a calculation module and a processing module; wherein, The acquisition module is used to acquire first captured data of a first captured device on the road to be detected within a first specified time period, and second captured data of a second captured device on the road to be detected within a second specified time period; The detection module is used to detect at least one attribute information of the vehicle based on each frame image in the first captured data and the second captured data, and obtain a first detection sequence for each attribute information and a second detection sequence for each attribute information; wherein the first detection sequence corresponds to the first captured data, and the second detection sequence corresponds to the second captured data; The calculation module is used to determine the overlap between the first detection sequence of each item of attribute information and the second detection sequence of each item of attribute information, so as to obtain the overlap between each item of attribute information; The processing module is used to determine whether the road to be detected is congested based on the overlap of each item of attribute information.
8. The device according to claim 7, characterized in that The calculation module is specifically configured to convert each attribute information value in the first detection sequence and the second detection sequence into a digital information value according to a preset conversion relationship between the attribute information value and the digital information value, so as to obtain a first digital sequence corresponding to the first detection sequence and a second digital sequence corresponding to the second detection sequence; The calculation module is further specifically used to calculate the overlap degree between the first digital sequence and the second digital sequence, and determine the calculated overlap degree as the overlap degree of each item of attribute information.
9. A road congestion detection device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 6 when executing the program.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.