A method and system for identifying vehicles with black smoke on the road

Abstract

The present invention is applicable to the technical field of black smoke vehicle identification, and provides a method and system for identifying black smoke vehicles on the road. The present invention selects multiple public auxiliary vehicles; performs positioning and start-stop identification, selects a target auxiliary vehicle; receives monitoring and shooting clips, extracts representative detection images; performs grayscale processing, obtains grayscale statistical data; calculates the suspicious range ratio, and when the suspicious range ratio is greater than the preset standard range ratio, performs vehicle identification, and obtains black smoke vehicle information. It is possible to select a target auxiliary vehicle from multiple public auxiliary vehicles, receive monitoring and shooting clips, extract representative detection images, perform grayscale processing and analysis, calculate the suspicious range ratio, and identify black smoke vehicle information when the suspicious range ratio is greater than the preset standard range ratio. There is no need to install monitoring equipment on the monitoring pole or gantry on the road, which effectively increases the monitoring and identification range of black smoke vehicles and greatly reduces the cost of identifying black smoke vehicles on the road.

Description

Technical Field

[0001] The invention belongs to the technical field of black smoke vehicle identification, and in particular relates to a method and system for identifying black smoke vehicles on roads. Background Art

[0002] Black smoke vehicles refer to motor vehicles that emit visible pollutants such as black smoke or whose smoke density exceeds the standard. They are usually related to the diesel vehicle's engine being overloaded, the amount of fuel injected being too large, and the amount of air intake being too small. Black smoke vehicles not only pollute the air quality, but may also affect people's health.

[0003] Road black smoke vehicle identification uses technical means to automatically detect and record motor vehicles that emit black smoke and other visible pollutants.

[0004] In the prior art, the identification of vehicles with black smoke on the road requires the installation of monitoring equipment on monitoring poles or gantries on the road to capture real-time monitoring videos of the road and then identify the vehicles with black smoke. This fixed-position black smoke vehicle identification has a limited monitoring and identification range for black smoke vehicles and requires the deployment of a large number of monitoring equipment. The cost of identifying vehicles with black smoke on the road is extremely high. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for identifying vehicles with black smoke on the road, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0006] The embodiment of the present invention is implemented as follows:

[0007] A method for identifying vehicles with black smoke on the road, the method comprising the following steps:

[0008] Broadcasting a public auxiliary signal, receiving a plurality of broadcast feedback information, selecting a plurality of public auxiliary vehicles, and obtaining detection auxiliary permissions for the plurality of said public auxiliary vehicles;

[0009] Obtaining navigation positioning data and start / stop status data of a plurality of the public auxiliary vehicles, performing positioning identification and start / stop identification, and selecting a target auxiliary vehicle from the plurality of the public auxiliary vehicles;

[0010] Sending a black smoke monitoring instruction to the target auxiliary vehicle, receiving the monitoring shooting clips fed back by the target auxiliary vehicle, and extracting a representative detection image;

[0011] grayscale the representative detection image to generate a representative grayscale image, and perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data;

[0012] The suspicious range ratio is calculated according to the grayscale statistical data, and when the suspicious range ratio is greater than the preset standard range ratio, vehicle recognition is performed on the representative detection image to obtain black smoke vehicle information.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the broadcasting of the public auxiliary signal, receiving a plurality of broadcast feedback information, selecting a plurality of public auxiliary vehicles, and obtaining the detection auxiliary authority of the plurality of public auxiliary vehicles specifically include the following steps:

[0014] generating a common auxiliary signal, and broadcasting and sending the common auxiliary signal;

[0015] Receive multiple broadcast feedback information, analyze the feedback intention, and select multiple intended assistance vehicles with public assistance intentions;

[0016] Acquiring vehicle function information of a plurality of the intended auxiliary vehicles;

[0017] Analyze the functions and orientations of the photographed vehicle function information, and select a plurality of public auxiliary vehicles from the plurality of intended auxiliary vehicles;

[0018] Perform authority interaction with the plurality of the public auxiliary vehicles to obtain detection assistance authorities of the plurality of the public auxiliary vehicles.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the obtaining of navigation positioning data and start-stop status data of the plurality of public auxiliary vehicles, performing positioning identification and start-stop identification, and selecting a target auxiliary vehicle from the plurality of public auxiliary vehicles specifically comprises the following steps:

[0020] Acquiring navigation and positioning data of a plurality of said public auxiliary vehicles;

[0021] According to the plurality of navigation positioning data, selecting a plurality of outdoor auxiliary vehicles located on the outer roads of the city from the plurality of public auxiliary vehicles;

[0022] Acquiring start / stop status data of a plurality of said outdoor auxiliary vehicles;

[0023] According to the plurality of start-stop status data, a target auxiliary vehicle in a queue start state is selected from the plurality of outdoor auxiliary vehicles.

[0024] As a further limitation of the technical solution of the embodiment of the present invention, the sending of the black smoke monitoring instruction to the target auxiliary vehicle, receiving the monitoring shooting clip fed back by the target auxiliary vehicle, and extracting the representative detection image specifically include the following steps:

[0025] generating and sending a black smoke monitoring instruction to the target auxiliary vehicle;

[0026] receiving monitoring footage fed back by the target auxiliary vehicle;

[0027] Processing the monitoring shot segment frame by frame to obtain a plurality of frame-by-frame shot images;

[0028] A representative detection image is selected from the plurality of images captured frame by frame.

[0029] As a further limitation of the technical solution of the embodiment of the present invention, the grayscale processing of the representative detection image to generate a representative grayscale image, and the grayscale value statistics of the representative grayscale image are performed to obtain grayscale statistical data specifically including the following steps:

[0030] Reading the three-color values ​​of pixels in the representative detection image to obtain three-color value data;

[0031] According to the three-color value data, the representative detection image is subjected to a sensitivity-weighted grayscale processing to generate a representative grayscale image;

[0032] Perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data.

[0033] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula for performing sensitivity-weighted grayscale processing on the representative detection image according to the three-color value data is:

[0034] P(x,y)=k1*R(x,y)+k2*G(x,y)+k3*B(x,y);

[0035] Among them, (x,y) represents the coordinates of the pixel point, P(x,y) is the grayscale value of the pixel point (x,y), R(x,y) is the red value of the pixel point (x,y), k1 is the red value coefficient, G(x,y) is the green value of the pixel point (x,y), k2 is the green value coefficient, B(x,y) is the blue value of the pixel point (x,y), and k3 is the blue value coefficient.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the calculation of the suspicious range ratio according to the grayscale statistical data, and when the suspicious range ratio is greater than the preset standard range ratio, the vehicle recognition is performed on the representative detection image to obtain the black smoke vehicle information specifically includes the following steps:

[0037] Calculate the suspicious range ratio according to the grayscale statistical data and the preset suspicious grayscale value interval;

[0038] Comparing the suspicious range ratio with a preset standard range ratio;

[0039] When the proportion of the suspicious range is greater than the proportion of the standard range, intercepting a vehicle license plate image and a vehicle logo image from the representative detection image;

[0040] The vehicle license plate image and the vehicle logo image are identified to obtain black smoke vehicle information.

[0041] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of the suspicious range ratio is:

[0042]

[0043] Among them, R is the proportion of suspicious range, N is the total number of pixels, and the suspicious gray value interval is [P a , P b ], Q i is the number of grayscale values ​​of i.

[0044] A road smoky vehicle identification system, the system comprises an auxiliary vehicle selection module, a positioning start-stop identification module, a shooting clip receiving module, a grayscale processing statistics module and a proportion analysis processing module, wherein:

[0045] An auxiliary vehicle selection module, used for broadcasting a public auxiliary signal, receiving a plurality of broadcast feedback information, selecting a plurality of public auxiliary vehicles, and obtaining detection auxiliary permissions of the plurality of said public auxiliary vehicles;

[0046] A positioning start-stop identification module is used to obtain navigation positioning data and start-stop status data of a plurality of the public auxiliary vehicles, perform positioning identification and start-stop identification, and select a target auxiliary vehicle from the plurality of the public auxiliary vehicles;

[0047] A shooting clip receiving module is used to send a black smoke monitoring instruction to the target auxiliary vehicle, receive the monitoring shooting clips fed back by the target auxiliary vehicle, and extract a representative detection image;

[0048] A grayscale processing and statistics module is used to perform grayscale processing on the representative detection image to generate a representative grayscale image, and perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data;

[0049] The proportion analysis processing module is used to calculate the suspicious range proportion according to the grayscale statistical data, and when the suspicious range proportion is greater than the preset standard range proportion, perform vehicle recognition on the representative detection image to obtain black smoke vehicle information.

[0050] As a further limitation of the technical solution of the embodiment of the present invention, the proportion analysis processing module specifically includes:

[0051] A range ratio calculation unit, used for calculating the suspicious range ratio according to the grayscale statistical data and a preset suspicious grayscale value interval;

[0052] A range proportion comparison unit, used for comparing the suspicious range proportion with a preset standard range proportion;

[0053] An image capture unit, configured to capture a vehicle license plate image and a vehicle logo image from the representative detection image when the proportion of the suspicious range is greater than the proportion of the standard range;

[0054] The image recognition unit is used to recognize the vehicle license plate image and the vehicle logo image to obtain black smoke vehicle information.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The embodiment of the present invention selects a plurality of public auxiliary vehicles; performs positioning and start-stop identification, selects a target auxiliary vehicle; receives monitoring and shooting clips, extracts representative detection images; performs grayscale processing, obtains grayscale statistical data; calculates the suspicious range ratio, and when the suspicious range ratio is greater than the preset standard range ratio, performs vehicle identification, and obtains black smoke vehicle information. It is possible to select a target auxiliary vehicle from a plurality of public auxiliary vehicles, receive monitoring and shooting clips, extract representative detection images, perform grayscale processing and analysis, calculate the suspicious range ratio, and identify black smoke vehicle information when the suspicious range ratio is greater than the preset standard range ratio. There is no need to install monitoring equipment on monitoring poles or gantry frames on the road, which effectively increases the monitoring and identification range of black smoke vehicles and greatly reduces the cost of identifying black smoke vehicles on the road. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flow chart of a method for identifying vehicles with black smoke on the road provided by an embodiment of the present invention is shown;

[0058] Figure 2 A flowchart of selecting a public auxiliary vehicle in a method provided by an embodiment of the present invention is shown;

[0059] Figure 3 A flowchart of selecting a target auxiliary vehicle in a method provided by an embodiment of the present invention is shown;

[0060] Figure 4 A flowchart of extracting a representative detection image in a method provided by an embodiment of the present invention is shown;

[0061] Figure 5 A flow chart of obtaining grayscale statistical data in a method provided by an embodiment of the present invention is shown;

[0062] Figure 6 A flow chart of range proportion analysis processing in the method provided in an embodiment of the present invention is shown;

[0063] Figure 7The application architecture diagram of the road black smoke vehicle identification system provided by the embodiment of the present invention is shown;

[0064] Figure 8 The structure block diagram of the proportion analysis processing module in the system provided by the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] It is understandable that in the prior art, the identification of vehicles with black smoke on the road requires the installation of monitoring equipment on monitoring poles or gantries on the road to capture real-time monitoring videos of the road before the identification of vehicles with black smoke. This fixed-position black smoke vehicle identification has a limited monitoring and identification range for black smoke vehicles and requires the deployment of a large number of monitoring equipment. The cost of identifying vehicles with black smoke on the road is extremely high.

[0067] To solve the above problems, an embodiment of the present invention discloses a method and system for identifying vehicles with black smoke on the road. The method and system broadcast a public auxiliary signal, receive multiple broadcast feedback information, select multiple public auxiliary vehicles, and obtain detection auxiliary permissions for multiple public auxiliary vehicles; obtain navigation positioning data and start-stop status data of multiple public auxiliary vehicles, perform positioning identification and start-stop identification, and select a target auxiliary vehicle from multiple public auxiliary vehicles; send a black smoke monitoring instruction to the target auxiliary vehicle, receive the monitoring and shooting clips fed back by the target auxiliary vehicle, and extract a representative detection image; grayscale the representative detection image to generate a representative grayscale image, and perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data; calculate the suspicious range ratio based on the grayscale statistical data, and when the suspicious range ratio is greater than the preset standard range ratio, perform vehicle identification on the representative detection image to obtain black smoke vehicle information. It can select a target auxiliary vehicle from multiple public auxiliary vehicles, receive monitoring footage, extract representative detection images, perform grayscale processing and analysis, calculate the suspicious range ratio, and identify the black smoke vehicle information when the suspicious range ratio is greater than the preset standard range ratio. There is no need to install monitoring equipment on monitoring poles or gantries on the road, which effectively improves the monitoring and identification range of black smoke vehicles and greatly reduces the cost of identifying black smoke vehicles on the road.

[0068] Specifically, Figure 1 A flow chart of a method for identifying vehicles with black smoke on the road provided by an embodiment of the present invention is shown.

[0069] In a preferred embodiment of the present invention, a method for identifying vehicles with black smoke on the road is provided, and the method specifically comprises the following steps:

[0070] Step S101: broadcast a public auxiliary signal, receive a plurality of broadcast feedback information, select a plurality of public auxiliary vehicles, and obtain detection auxiliary permissions of the plurality of public auxiliary vehicles.

[0071] In an embodiment of the present invention, a public auxiliary signal is generated, broadcasted to public social vehicles, and broadcast feedback information from multiple public social vehicles is received, and feedback intention analysis is performed on the multiple broadcast feedback information, public social vehicles without public assistance intention are eliminated, and public social vehicles with public assistance intention are selected and marked as intended auxiliary vehicles, thereby determining multiple intended auxiliary vehicles, obtaining vehicle function information of multiple intended auxiliary vehicles, and performing function and orientation analysis on the multiple vehicle function information, screening out intended auxiliary vehicles with vehicle front side camera function from multiple intended auxiliary vehicles, and marking them as public auxiliary vehicles, thereby obtaining multiple public auxiliary vehicles, and obtaining detection auxiliary permissions for multiple public auxiliary vehicles after multiple public auxiliary vehicles agree to the auxiliary permission applications.

[0072] It is understandable that there is no public assistance intention, including refusal of assistance and no feedback.

[0073] Specifically, Figure 2 A flow chart of selecting a public auxiliary vehicle in the method provided by an embodiment of the present invention is shown.

[0074] Among them, in the preferred embodiment provided by the present invention, the broadcasting of the public auxiliary signal, receiving multiple broadcast feedback information, selecting multiple public auxiliary vehicles, and obtaining the detection auxiliary authority of the multiple public auxiliary vehicles specifically include the following steps:

[0075] Step S1011: Generate a common auxiliary signal, and broadcast the common auxiliary signal.

[0076] Step S1012: receiving a plurality of broadcast feedback information, performing feedback intention analysis, and selecting a plurality of intended assistance vehicles having public assistance intentions.

[0077] Step S1013: Obtain vehicle function information of the plurality of intended auxiliary vehicles.

[0078] Step S1014: Analyze the functions and orientations of the photographed vehicle function information, and select a plurality of public auxiliary vehicles from the plurality of intended auxiliary vehicles.

[0079] Step S1015: Perform authority interaction with the plurality of public auxiliary vehicles to obtain detection auxiliary authorities of the plurality of public auxiliary vehicles.

[0080] Furthermore, the method for identifying vehicles with black smoke on the road also includes the following steps:

[0081] Step S102: Obtain navigation positioning data and start / stop status data of a plurality of the public auxiliary vehicles, perform positioning identification and start / stop identification, and select a target auxiliary vehicle from the plurality of the public auxiliary vehicles.

[0082] In an embodiment of the present invention, under the condition of having detection assistance authority for multiple public auxiliary vehicles, navigation positioning data of multiple public auxiliary vehicles are obtained, and by analyzing the multiple navigation positioning data, multiple public auxiliary vehicles that are in the process of navigation driving and are on urban external roads such as expressways, main roads, secondary roads and branch roads are screened from the multiple public auxiliary vehicles, and are marked as outdoor auxiliary vehicles. Then, start-stop status data of multiple outdoor auxiliary vehicles are obtained, and by analyzing the multiple start-stop status data, outdoor auxiliary vehicles that are currently in a queuing start state are screened from the multiple outdoor auxiliary vehicles, and are marked as target auxiliary vehicles.

[0083] It can be understood that urban external roads refer to urban roads that do not have vehicle driving privacy requirements, such as expressways, main roads, secondary roads, branch roads and elevated roads, rather than internal roads such as residential areas, work areas, entertainment areas, etc. that have vehicle driving privacy requirements.

[0084] It can be understood that the platoon start state refers to the state in which the target auxiliary vehicle is in navigation driving with other vehicles on the outer roads of the city and is currently in the state of starting after stopping; the platoon start state is widely present in accident congestion queues and traffic light queues.

[0085] It is understandable that since the black smoke emission of a black smoke vehicle is most obvious when starting, it is most appropriate to detect whether there is a black smoke vehicle ahead by using a target auxiliary vehicle when the platoon is started.

[0086] Specifically, Figure 3 A flow chart of selecting a target auxiliary vehicle in the method provided by an embodiment of the present invention is shown.

[0087] Among them, in the preferred embodiment provided by the present invention, the obtaining of navigation positioning data and start-stop status data of a plurality of the public auxiliary vehicles, performing positioning identification and start-stop identification, and selecting a target auxiliary vehicle from the plurality of the public auxiliary vehicles specifically comprises the following steps:

[0088] Step S1021, obtaining navigation positioning data of a plurality of the public auxiliary vehicles.

[0089] Step S1022: Filter a plurality of outdoor auxiliary vehicles located on the outer roads of the city from the plurality of public auxiliary vehicles according to the plurality of navigation positioning data.

[0090] Step S1023, obtaining the start / stop status data of the plurality of outdoor auxiliary vehicles.

[0091] Step S1024: Filter a target auxiliary vehicle in a queue start state from among the plurality of outdoor auxiliary vehicles according to the plurality of start-stop status data.

[0092] Furthermore, the method for identifying vehicles with black smoke on the road also includes the following steps:

[0093] Step S103: sending a black smoke monitoring instruction to the target auxiliary vehicle, receiving the monitoring shooting clip fed back by the target auxiliary vehicle, and extracting a representative detection image.

[0094] In an embodiment of the present invention, a black smoke monitoring instruction is generated and sent to a target auxiliary vehicle. After receiving the black smoke monitoring instruction, the target auxiliary vehicle needs to shoot in the forward direction of the vehicle during startup, and upload the captured monitoring footage for feedback. By receiving the monitoring footage and vehicle startup data fed back by the target auxiliary vehicle, the monitoring footage is processed frame by frame to obtain a plurality of frame-by-frame images. According to the vehicle startup data, the plurality of frame-by-frame images are corresponded to the vehicle startup speed. From the plurality of frame-by-frame images, the frame-by-frame image corresponding to the vehicle startup speed of 5 km / h is selected and marked as a representative detection image.

[0095] Specifically, Figure 4 A flow chart of extracting a representative detection image in the method provided by an embodiment of the present invention is shown.

[0096] Among them, in the preferred embodiment provided by the present invention, the sending of the black smoke monitoring instruction to the target auxiliary vehicle, receiving the monitoring shooting clip fed back by the target auxiliary vehicle, and extracting the representative detection image specifically include the following steps:

[0097] Step S1031: Generate and send a black smoke monitoring instruction to the target auxiliary vehicle.

[0098] Step S1032: receiving the monitoring and shooting clips fed back by the target auxiliary vehicle.

[0099] Step S1033: perform frame-by-frame processing on the monitoring and shooting segment to obtain a plurality of frame-by-frame shooting images.

[0100] Step S1034: Select a representative detection image from the plurality of images captured frame by frame.

[0101] Furthermore, the method for identifying vehicles with black smoke on the road also includes the following steps:

[0102] Step S104: grayscale the representative detection image to generate a representative grayscale image, and perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data.

[0103] In an embodiment of the present invention, the representative detection image is analyzed, the three-color values ​​of the pixels in the representative detection image are read, and the three-color value data are obtained. Then, according to the three-color value data, the representative detection image is subjected to sensitivity-weighted grayscale processing to generate a representative grayscale image. Then, grayscale value statistics are performed on the representative grayscale image to obtain the number of pixels corresponding to each grayscale value and obtain grayscale statistical data. Specifically, according to the three-color value data, the calculation formula for performing sensitivity-weighted grayscale processing on the representative detection image is:

[0104] P(x,y)=k1*R(x,y)+k2*G(x,y)+k3*B(x,y);

[0105] Among them, (x,y) represents the coordinates of the pixel point, P(x,y) is the grayscale value of the pixel point (x,y), R(x,y) is the red value of the pixel point (x,y), k1 is the red value coefficient, G(x,y) is the green value of the pixel point (x,y), k2 is the green value coefficient, B(x,y) is the blue value of the pixel point (x,y), and k3 is the blue value coefficient.

[0106] Specifically, Figure 5 A flow chart of obtaining grayscale statistical data in the method provided by an embodiment of the present invention is shown.

[0107] Among them, in the preferred embodiment provided by the present invention, the grayscale processing is performed on the representative detection image to generate a representative grayscale image, and grayscale value statistics are performed on the representative grayscale image. The grayscale statistical data are obtained specifically including the following steps:

[0108] Step S1041 , reading the three-color values ​​of the pixels in the representative detection image to obtain three-color value data.

[0109] Step S1042: Perform sensitivity-weighted grayscale processing on the representative detection image according to the three-color value data to generate a representative grayscale image.

[0110] Step S1043: Perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data.

[0111] Furthermore, the method for identifying vehicles with black smoke on the road also includes the following steps:

[0112] Step S105: Calculate the suspicious range ratio according to the grayscale statistical data, and when the suspicious range ratio is greater than the preset standard range ratio, perform vehicle recognition on the representative detection image to obtain black smoke vehicle information.

[0113] In an embodiment of the present invention, the suspicious range ratio is calculated according to the grayscale statistical data and the preset suspicious grayscale value interval, and then the suspicious range ratio is compared with the preset standard range ratio to determine whether the suspicious range ratio is greater than the standard range ratio. When the suspicious range ratio is greater than the standard range ratio, the vehicle license plate image and the vehicle logo image are intercepted from the representative detection image, and the vehicle license plate information is obtained by performing vehicle license plate recognition on the vehicle license plate image, and then the vehicle logo recognition is performed on the vehicle logo image to obtain the vehicle logo information, and the black smoke vehicle information is obtained by combining the vehicle license plate information and the vehicle logo information. Specifically, the calculation formula of the suspicious range ratio is:

[0114]

[0115] Among them, R is the proportion of suspicious range, N is the total number of pixels, and the suspicious gray value interval is [P a , P b ], Q i is the number of grayscale values ​​of i.

[0116] Specifically, Figure 6 A flow chart of range proportion analysis processing in the method provided in an embodiment of the present invention is shown.

[0117] Among them, in the preferred embodiment provided by the present invention, the suspicious range ratio is calculated according to the grayscale statistical data, and when the suspicious range ratio is greater than the preset standard range ratio, the representative detection image is subjected to vehicle identification, and the black smoke vehicle information is obtained, which specifically includes the following steps:

[0118] Step S1051: Calculate the suspicious range ratio according to the grayscale statistical data and the preset suspicious grayscale value interval.

[0119] Step S1052: compare the suspicious range ratio with a preset standard range ratio.

[0120] Step S1053: When the proportion of the suspicious range is greater than the proportion of the standard range, a vehicle license plate image and a vehicle logo image are captured from the representative detection image.

[0121] Step S1054: Identify the vehicle license plate image and the vehicle logo image to obtain black smoke vehicle information.

[0122] Furthermore, Figure 7 The application architecture diagram of the road smoky vehicle identification system provided by an embodiment of the present invention is shown.

[0123] Among them, in another preferred embodiment provided by the present invention, a road smoky vehicle identification system includes:

[0124] The auxiliary vehicle selection module 101 is used to broadcast a public auxiliary signal, receive a plurality of broadcast feedback information, select a plurality of public auxiliary vehicles, and obtain detection auxiliary permissions of the plurality of public auxiliary vehicles.

[0125] In an embodiment of the present invention, the auxiliary vehicle selection module 101 generates a public auxiliary signal, broadcasts the public auxiliary signal to public social vehicles, receives broadcast feedback information from multiple public social vehicles, and then analyzes the feedback intention of the multiple broadcast feedback information, eliminates public social vehicles without public auxiliary intention, selects public social vehicles with public auxiliary intention, and marks them as intended auxiliary vehicles, thereby determining multiple intended auxiliary vehicles. The auxiliary vehicle selection module 101 obtains vehicle function information of multiple intended auxiliary vehicles, and then performs function and orientation analysis of the multiple vehicle function information, selects intended auxiliary vehicles with vehicle front side camera function from multiple intended auxiliary vehicles, and marks them as public auxiliary vehicles, thereby obtaining multiple public auxiliary vehicles, and obtaining detection auxiliary permissions for multiple public auxiliary vehicles by sending auxiliary permission applications to multiple public auxiliary vehicles and after the multiple public auxiliary vehicles agree to the auxiliary permission applications.

[0126] The positioning start-stop identification module 102 is used to obtain navigation positioning data and start-stop status data of a plurality of the public auxiliary vehicles, perform positioning identification and start-stop identification, and select a target auxiliary vehicle from the plurality of the public auxiliary vehicles.

[0127] In an embodiment of the present invention, under the condition of having detection assistance authority for multiple public auxiliary vehicles, the positioning start-stop identification module 102 obtains the navigation positioning data of multiple public auxiliary vehicles, and by analyzing the multiple navigation positioning data, screens multiple public auxiliary vehicles that are in the process of navigation driving and are on urban external roads such as expressways, main roads, secondary roads and branch roads from the multiple public auxiliary vehicles, and marks them as outdoor auxiliary vehicles, and then obtains the start-stop status data of the multiple outdoor auxiliary vehicles, and by analyzing the multiple start-stop status data, screens the outdoor auxiliary vehicles that are currently in the queue start state from the multiple outdoor auxiliary vehicles, and marks them as target auxiliary vehicles.

[0128] The shooting clip receiving module 103 is used to send a black smoke monitoring instruction to the target auxiliary vehicle, receive the monitoring shooting clip fed back by the target auxiliary vehicle, and extract a representative detection image.

[0129] In an embodiment of the present invention, the shooting clip receiving module 103 generates a black smoke monitoring instruction and sends the black smoke monitoring instruction to the target auxiliary vehicle. After receiving the black smoke monitoring instruction, the target auxiliary vehicle needs to shoot in the forward direction of the vehicle during the startup process and upload the captured monitoring shooting clip for feedback. The shooting clip receiving module 103 receives the monitoring shooting clip and vehicle startup data fed back by the target auxiliary vehicle, and then processes the monitoring shooting clip frame by frame to obtain multiple frame-by-frame shooting images, and according to the vehicle startup data, the multiple frame-by-frame shooting images are corresponded to the vehicle startup speed, and from the multiple frame-by-frame shooting images, the frame-by-frame shooting image corresponding to the vehicle startup speed of 5km / h is selected, and it is marked as a representative detection image.

[0130] The grayscale processing and statistics module 104 is used to perform grayscale processing on the representative detection image to generate a representative grayscale image, and perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data.

[0131] In the embodiment of the present invention, the grayscale processing statistics module 104 analyzes the representative detection image, reads the pixel three-color values ​​in the representative detection image, obtains the three-color value data, and then performs sensitivity-weighted grayscale processing on the representative detection image according to the three-color value data to generate a representative grayscale image, and then performs grayscale value statistics on the representative grayscale image to obtain the number of pixels corresponding to each grayscale value to obtain grayscale statistical data. Specifically, the calculation formula for performing sensitivity-weighted grayscale processing on the representative detection image according to the three-color value data is:

[0132] P(x,y)=k1*R(x,y)+k2*G(x,y)+k3*B(x,y);

[0133] Among them, (x,y) represents the coordinates of the pixel point, P(x,y) is the grayscale value of the pixel point (x,y), R(x,y) is the red value of the pixel point (x,y), k1 is the red value coefficient, G(x,y) is the green value of the pixel point (x,y), k2 is the green value coefficient, B(x,y) is the blue value of the pixel point (x,y), and k3 is the blue value coefficient.

[0134] The proportion analysis processing module 105 is used to calculate the suspicious range proportion according to the grayscale statistical data, and when the suspicious range proportion is greater than the preset standard range proportion, perform vehicle recognition on the representative detection image to obtain black smoke vehicle information.

[0135] In the embodiment of the present invention, the proportion analysis processing module 105 calculates the proportion of the suspicious range according to the grayscale statistical data and the preset suspicious grayscale value interval, and then compares the suspicious range proportion with the preset standard range proportion to determine whether the suspicious range proportion is greater than the standard range proportion. When the suspicious range proportion is greater than the standard range proportion, the vehicle license plate image and the vehicle logo image are intercepted from the representative detection image, and the vehicle license plate information is obtained by performing vehicle license plate recognition on the vehicle license plate image, and then the vehicle logo recognition is performed on the vehicle logo image to obtain the vehicle logo information. The black smoke vehicle information is obtained by combining the vehicle license plate information and the vehicle logo information. Specifically, the calculation formula of the suspicious range proportion is:

[0136]

[0137] Among them, R is the proportion of suspicious range, N is the total number of pixels, and the suspicious gray value interval is [P a , P b ], Q i is the number of grayscale values ​​of i.

[0138] Specifically, Figure 8 It shows a structural block diagram of the proportion analysis processing module 105 in the system provided by an embodiment of the present invention.

[0139] Among them, in the preferred embodiment provided by the present invention, the proportion analysis processing module 105 specifically includes:

[0140] The range ratio calculation unit 1051 is used to calculate the suspicious range ratio according to the grayscale statistical data and the preset suspicious grayscale value interval.

[0141] The range ratio comparison unit 1052 is used to compare the suspicious range ratio with a preset standard range ratio.

[0142] The image capture unit 1053 is used to capture the vehicle license plate image and the vehicle logo image from the representative detection image when the proportion of the suspicious range is greater than the proportion of the standard range.

[0143] The image recognition unit 1054 is used to recognize the vehicle license plate image and the vehicle logo image to obtain black smoke vehicle information.

[0144] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0146] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for identifying vehicles with black smoke on the road, characterized in that: The method comprises the following steps: Broadcasting a public auxiliary signal, receiving a plurality of broadcast feedback information, selecting a plurality of public auxiliary vehicles, and obtaining detection auxiliary permissions for the plurality of said public auxiliary vehicles; By generating a public auxiliary signal, broadcasting the public auxiliary signal to public social vehicles, and receiving broadcast feedback information from multiple public social vehicles, and then analyzing the feedback intention of the multiple broadcast feedback information, public social vehicles without public auxiliary intention are eliminated, public social vehicles with public auxiliary intention are selected, and marked as intended auxiliary vehicles, thereby determining multiple intended auxiliary vehicles, by obtaining vehicle function information of multiple intended auxiliary vehicles, and then performing function and orientation analysis on the multiple vehicle function information, from the multiple intended auxiliary vehicles, the intended auxiliary vehicles with vehicle front side camera function are screened out, and marked as public auxiliary vehicles, thereby obtaining multiple public auxiliary vehicles, by sending auxiliary authority applications to multiple public auxiliary vehicles, and after the multiple public auxiliary vehicles agree to the auxiliary authority applications, obtaining detection auxiliary permissions for multiple public auxiliary vehicles; Obtaining navigation positioning data and start / stop status data of a plurality of the public auxiliary vehicles, performing positioning identification and start / stop identification, and selecting a target auxiliary vehicle from the plurality of the public auxiliary vehicles; Under the condition of having the detection assistance authority for multiple public auxiliary vehicles, the navigation positioning data of multiple public auxiliary vehicles are obtained, and by analyzing the multiple navigation positioning data, multiple public auxiliary vehicles that are in the process of navigation driving and are on the urban external roads such as expressways, main roads, secondary roads and branch roads are screened from the multiple public auxiliary vehicles, and they are marked as outdoor auxiliary vehicles, and then the start-stop status data of multiple outdoor auxiliary vehicles are obtained, and by analyzing the multiple start-stop status data, outdoor auxiliary vehicles that are currently in a platoon start state are screened from the multiple outdoor auxiliary vehicles, and they are marked as target auxiliary vehicles; the platoon start state refers to the target auxiliary vehicle being in the urban external roads, in the process of navigation driving with other vehicles, and currently in a state of starting after stopping; Sending a black smoke monitoring instruction to the target auxiliary vehicle, receiving the monitoring shooting clips fed back by the target auxiliary vehicle, and extracting a representative detection image; grayscale the representative detection image to generate a representative grayscale image, and perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data; The suspicious range ratio is calculated according to the grayscale statistical data, and when the suspicious range ratio is greater than the preset standard range ratio, vehicle recognition is performed on the representative detection image to obtain black smoke vehicle information.

2. The method for identifying vehicles with black smoke on the road according to claim 1, characterized in that: The sending of the black smoke monitoring instruction to the target auxiliary vehicle, receiving the monitoring shooting clip fed back by the target auxiliary vehicle, and extracting the representative detection image specifically comprises the following steps: generating and sending a black smoke monitoring instruction to the target auxiliary vehicle; receiving monitoring footage fed back by the target auxiliary vehicle; Processing the monitoring shot segment frame by frame to obtain a plurality of frame-by-frame shot images; A representative detection image is selected from the plurality of images captured frame by frame.

3. The method for identifying vehicles with black smoke on the road according to claim 1, characterized in that: The grayscale processing of the representative detection image to generate a representative grayscale image, and grayscale value statistics of the representative grayscale image to obtain grayscale statistical data specifically includes the following steps: Reading the three-color values ​​of pixels in the representative detection image to obtain three-color value data; According to the three-color value data, the representative detection image is subjected to a sensitivity-weighted grayscale processing to generate a representative grayscale image; Perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data.

4. The method for identifying vehicles with black smoke on the road according to claim 3, characterized in that: The calculation formula for performing sensitivity-weighted grayscale processing on the representative detection image according to the three-color value data is: P(x,y)=k1*R(x,y)+k2*G(x,y)+k3*B(x,y); Among them, (x, y) represents the coordinates of the pixel point, P(x, y) is the grayscale value of the pixel point (x, y), R(x, y) is the red value of the pixel point (x, y), k1 is the red value coefficient, G(x, y) is the green value of the pixel point (x, y), k2 is the green value coefficient, B(x, y) is the blue value of the pixel point (x, y), and k3 is the blue value coefficient.

5. The method for identifying vehicles with black smoke on the road according to claim 1, characterized in that: The method of calculating the suspicious range ratio according to the grayscale statistical data, and performing vehicle recognition on the representative detection image when the suspicious range ratio is greater than the preset standard range ratio, and obtaining the black smoke vehicle information specifically includes the following steps: Calculate the suspicious range ratio according to the grayscale statistical data and the preset suspicious grayscale value interval; Comparing the suspicious range ratio with a preset standard range ratio; When the proportion of the suspicious range is greater than the proportion of the standard range, intercepting a vehicle license plate image and a vehicle logo image from the representative detection image; The vehicle license plate image and the vehicle logo image are identified to obtain black smoke vehicle information.

6. The method for identifying vehicles with black smoke on the road according to claim 5, characterized in that: The calculation formula for the suspicious range ratio is: Among them, R is the proportion of suspicious range, N is the total number of pixels, and the suspicious gray value interval is [P a , P b ], Q i is the number of grayscale values ​​of i.

7. A road smoky vehicle identification system, characterized in that: The system includes an auxiliary vehicle selection module, a positioning start-stop recognition module, a shooting clip receiving module, a grayscale processing statistics module and a proportion analysis processing module, wherein: An auxiliary vehicle selection module, used for broadcasting a public auxiliary signal, receiving a plurality of broadcast feedback information, selecting a plurality of public auxiliary vehicles, and obtaining detection auxiliary permissions of the plurality of said public auxiliary vehicles; By generating a public auxiliary signal, broadcasting the public auxiliary signal to public social vehicles, and receiving broadcast feedback information from multiple public social vehicles, and then analyzing the feedback intention of the multiple broadcast feedback information, public social vehicles without public auxiliary intention are eliminated, public social vehicles with public auxiliary intention are selected, and marked as intended auxiliary vehicles, thereby determining multiple intended auxiliary vehicles, by obtaining vehicle function information of multiple intended auxiliary vehicles, and then performing function and orientation analysis on the multiple vehicle function information, from the multiple intended auxiliary vehicles, the intended auxiliary vehicles with vehicle front side camera function are screened out, and marked as public auxiliary vehicles, thereby obtaining multiple public auxiliary vehicles, by sending auxiliary authority applications to multiple public auxiliary vehicles, and after the multiple public auxiliary vehicles agree to the auxiliary authority applications, obtaining detection auxiliary permissions for multiple public auxiliary vehicles; A positioning start-stop identification module is used to obtain navigation positioning data and start-stop status data of a plurality of the public auxiliary vehicles, perform positioning identification and start-stop identification, and select a target auxiliary vehicle from the plurality of the public auxiliary vehicles; Under the condition of having the detection assistance authority for multiple public auxiliary vehicles, the navigation positioning data of multiple public auxiliary vehicles are obtained, and by analyzing the multiple navigation positioning data, multiple public auxiliary vehicles that are in the process of navigation driving and are on the urban external roads such as expressways, main roads, secondary roads and branch roads are screened from the multiple public auxiliary vehicles, and they are marked as outdoor auxiliary vehicles, and then the start-stop status data of multiple outdoor auxiliary vehicles are obtained, and by analyzing the multiple start-stop status data, outdoor auxiliary vehicles that are currently in a platoon start state are screened from the multiple outdoor auxiliary vehicles, and they are marked as target auxiliary vehicles; the platoon start state refers to the target auxiliary vehicle being in the urban external roads, in the process of navigation driving with other vehicles, and currently in a state of starting after stopping; A shooting clip receiving module is used to send a black smoke monitoring instruction to the target auxiliary vehicle, receive the monitoring shooting clips fed back by the target auxiliary vehicle, and extract a representative detection image; A grayscale processing statistics module is used to perform grayscale processing on the representative detection image to generate a representative grayscale image, and perform grayscale value statistics on the representative grayscale image to obtain grayscale statistical data; The proportion analysis processing module is used to calculate the suspicious range proportion according to the grayscale statistical data, and when the suspicious range proportion is greater than the preset standard range proportion, perform vehicle recognition on the representative detection image to obtain black smoke vehicle information.

8. The road smoky vehicle identification system according to claim 7, characterized in that: The proportion analysis processing module specifically includes: A range ratio calculation unit, used for calculating the suspicious range ratio according to the grayscale statistical data and a preset suspicious grayscale value interval; A range proportion comparison unit, used for comparing the suspicious range proportion with a preset standard range proportion; An image capture unit, configured to capture a vehicle license plate image and a vehicle logo image from the representative detection image when the proportion of the suspicious range is greater than the proportion of the standard range; The image recognition unit is used to recognize the vehicle license plate image and the vehicle logo image to obtain black smoke vehicle information.

Images