A data sampling and processing method and device for carbon emissions

Abstract

The present application discloses a data sampling and processing method and device for carbon emissions. This solution uses a first camera on a highway to shoot, so as to obtain a highway image, wherein the highway image contains at least one vehicle target object; the vehicle type of the vehicle target object in the highway image is identified to obtain a vehicle type identification result; according to the vehicle type identification result, the corresponding carbon emission estimation model is obtained from the first database, wherein the carbon emission estimation model is a mapping relationship model between vehicle speed and carbon emissions; after obtaining the speed of the vehicle target object, the carbon emissions of the highway area are determined according to the obtained vehicle speed and the carbon emission estimation model. It can be seen that this can not only greatly save the purchase cost of the equipment, but also help to improve the accuracy of carbon emission detection.

Description

Technical Field

[0001] The present invention relates to data collection and processing technology, and in particular to a data sampling and processing method and device for carbon emissions. Background Art

[0002] Road transportation is the main source of carbon emissions in my country, so accurately understanding the carbon emission level of road transportation is of great significance to the implementation of the "dual carbon" strategy and the formulation of green transportation development strategies. In order to accurately understand the carbon emission level of road transportation, it is necessary to sample the carbon emissions of road transportation, so that the corresponding road carbon emissions can be obtained after analyzing and processing the sampled data.

[0003] At present, in order to realize the collection of carbon emission data of road traffic, two methods are mainly used: the first one is that since the carbon emission level of road traffic is mainly affected by the greenhouse gases emitted by automobile exhaust, and there is an inevitable relationship between the fuel consumption of automobiles and the greenhouse gases emitted, a sensor detection device will be added to the automobile to directly detect and calculate the fuel consumption in real time, or a sensor detection device will be added to directly detect the exhaust gas emitted by the automobile in real time, so as to understand the carbon emission situation of road traffic through the collected data. However, this method has some disadvantages. For example, adding additional detection sensors to the vehicle will increase the cost of the vehicle, and the detection sensor is generally fixed at a certain position of the exhaust port, so the exhaust gas detected in real time is not accurate. The release may be only local, so the collected data cannot accurately represent the actual carbon emissions, that is, the detection accuracy of this method is low; the second method is to set up greenhouse gas detection devices on the side of the road, and use the data detected by them to monitor carbon emissions. However, since this method requires the deployment of corresponding greenhouse gas detection devices at a certain interval, its purchase cost is also high, and these devices are set on the roadside, which is easy to be affected by factors such as air pressure, wind speed, and vibration, resulting in detection errors. This leads to low accuracy in carbon emission monitoring. In order to ensure that there is no problem with the detection accuracy of the equipment, it is necessary to regularly invite professionals to the site to calibrate and adjust the equipment, which is time-consuming and labor-intensive. It can be seen that the existing data collection, processing and monitoring solutions for carbon emissions have problems such as high cost and difficulty in ensuring accuracy. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a data sampling and processing method for carbon emissions and a related device.

[0005] In a first aspect, an embodiment of the present application provides a data sampling and processing method for carbon emissions, the method comprising:

[0006] Acquire a highway image captured by a first camera, wherein the highway image contains at least one vehicle target object;

[0007] Performing vehicle type recognition on vehicle target objects in the highway image to obtain a vehicle type recognition result;

[0008] According to the vehicle type recognition result, a corresponding carbon emission estimation model is obtained from the first database, wherein the carbon emission estimation model is a mapping relationship model between vehicle speed and carbon emission;

[0009] After the vehicle speed of the target vehicle is obtained, the carbon emissions of the highway area are determined based on the obtained vehicle speed and the carbon emissions estimation model.

[0010] In some embodiments, the vehicle type recognition result includes a driving type of a vehicle target object, and the driving type includes a fuel driving type, a pure electric driving type, and a hybrid driving type. The corresponding carbon emission estimation model is obtained from the first database according to the vehicle type recognition result, which specifically includes:

[0011] When the driving type is a fuel driving type, obtaining a first carbon emission estimation model from a first database; and / or,

[0012] When the driving type is a hybrid driving type, the current driving mode of the vehicle target object is obtained from the information access port of the vehicle system; when it is determined that the current driving mode is a fuel driving mode, the second carbon emission estimation model is obtained from the first database.

[0013] In some embodiments, the vehicle type recognition result further includes the vehicle model of the vehicle target object, and the first carbon emission estimation model is obtained from the first database, which is specifically:

[0014] According to the vehicle model of the vehicle target object, obtaining a first carbon emission estimation model corresponding to the vehicle model from a first database;

[0015] The second carbon emission estimation model is obtained from the first database, which is specifically:

[0016] According to the vehicle model of the vehicle target object, a second carbon emission estimation model corresponding to the vehicle model is acquired from a first database.

[0017] In some embodiments, the vehicle type recognition of the vehicle target object in the highway image to obtain the vehicle type recognition result specifically includes:

[0018] According to the usage status of the second database and the third database, the vehicle type is identified by using the license plate number, and / or the vehicle type is identified by combining the license plate color, vehicle shape and logo.

[0019] In some embodiments, the selection of using the license plate number recognition method to identify the vehicle type specifically includes:

[0020] Recognize the license plate number of the vehicle target object in the highway image;

[0021] According to the identified license plate number, querying from a second database to obtain a vehicle model corresponding to the license plate number;

[0022] A driving type of the vehicle target object is determined according to the vehicle model.

[0023] In some embodiments, the selection utilizes a combination of license plate color, vehicle outline, and vehicle logo recognition to identify the vehicle type, which specifically includes:

[0024] Identify the license plate color, vehicle outline and vehicle logo of the vehicle target object in the highway image;

[0025] Filtering a number of preliminary selected vehicle models corresponding to the recognized license plate color from a third database;

[0026] Selecting a plurality of candidate vehicle models corresponding to the identified vehicle logo from a plurality of preliminary selected vehicle models;

[0027] After calculating the similarity between the recognized vehicle outline and the vehicle outlines corresponding to several candidate vehicle models, the vehicle model corresponding to the highest similarity is used as the final vehicle model;

[0028] The driving type of the vehicle target object is determined according to the final vehicle model.

[0029] In some embodiments, the mapping relationship model between vehicle speed and carbon emissions is constructed based on the mapping relationship between vehicle speed and fuel consumption.

[0030] In some embodiments, after the step of determining the carbon emissions of the highway area, the following steps are also included:

[0031] After obtaining the current carbon emission standard document in real time, the carbon emission standard recorded in the carbon emission standard document is compared with the carbon emission of the highway area to determine whether the carbon emission of the highway area exceeds the standard;

[0032] When it is determined that the carbon emissions in the highway area exceed the standard, the vehicle driving condition of the vehicle that is not in the minimum carbon emissions state is identified, and the optimal vehicle speed of the vehicle that is not in the minimum carbon emissions state is determined according to the vehicle driving condition identification result;

[0033] The optimal vehicle speed is sent to the vehicle system of the vehicle that is not in the minimum carbon emission state through the information access port of the vehicle system for display.

[0034] In a second aspect, an embodiment of the present application provides a data sampling and processing device for carbon emissions, the device comprising:

[0035] A first camera is used to capture images of the road;

[0036] A processing system, comprising at least one processor, for executing the steps of implementing the above-mentioned first aspect method embodiment;

[0037] The first camera is communicatively connected to the processing system.

[0038] In some embodiments, the apparatus further comprises:

[0039] An information access port of a database, used for mutual information transmission between a plurality of databases and the processing system;

[0040] An information access port of the vehicle-mounted system, used for mutual information transmission between the vehicle-mounted system and the processing system;

[0041] The information access port of the database and the information access port of the vehicle-mounted system are both connected to the processing system.

[0042] The present application can achieve at least one of the following technical effects: the present application scheme uses the first camera currently set on the highway to shoot, so as to obtain a highway image, wherein the highway image contains at least one vehicle target object, and then performs vehicle type recognition on the vehicle target object in the highway image to obtain a vehicle type recognition result, and then obtains the corresponding carbon emission estimation model from the first database according to the vehicle type recognition result, wherein the carbon emission estimation model is a mapping relationship model between vehicle speed and carbon emissions, and finally obtains the vehicle speed of the vehicle target object, and then determines the carbon emissions of the highway area according to the obtained vehicle speed and the carbon emission estimation model. It can be seen that the use of the present application scheme to realize the carbon emission data collection and detection of the highway area can minimize the additional equipment and greatly reduce the investment cost of carbon emission collection and detection. In addition, the present scheme also obtains the corresponding carbon emission estimation model according to the identified vehicle type to obtain the carbon emission situation detection of different vehicle types, so as to finally obtain the overall carbon emission situation of the highway area, which greatly improves the accuracy of highway carbon emission collection and detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments.

[0044] Figure 1 A schematic diagram of the steps of a data sampling and processing method for carbon emissions is provided for an embodiment of the present application;

[0045] Figure 2 A schematic diagram of the mapping relationship between the license plate color, vehicle shape profile information, vehicle logo information, and vehicle model stored in the third database is provided for the embodiment of the present application;

[0046] Figure 3 A schematic diagram of the structure of a data sampling and processing device for carbon emissions provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described through the implementation method with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0048] The main source of carbon emissions from highway traffic comes from greenhouse gases emitted by vehicles traveling on the road. Therefore, in order to accurately grasp the level of carbon emissions from highway traffic, so as to facilitate the formulation of subsequent green transportation development strategies, such as the formulation of planting layout strategies for green plants on both sides of the road, the installation layout of traffic lights and their switching time interval strategies, it is necessary to detect and collect data on greenhouse gases emitted by vehicles traveling on highway traffic roads, so as to have a good understanding of the level of carbon emissions from highway traffic. At present, the detection method for greenhouse gases emitted by vehicles mainly involves additionally setting up detection sensors to collect corresponding data, thereby realizing the detection of automobile carbon emissions. For example, detection sensors are set at appropriate locations of automobile exhaust emissions, or corresponding greenhouse gas detection devices are arranged at intervals at appropriate locations beside the highway. It can be seen that the additional setting of detection sensors will greatly increase the investment cost of the detection scheme, and for the former, the corresponding detection sensors are added to the vehicle, which requires business negotiations with various car manufacturers, and can only be installed and set up with their permission. The process is cumbersome and is very unfavorable for the promotion and use of the scheme. In addition, the use of the above-mentioned additional detection sensor to detect carbon emissions is easily affected by external environmental factors and / or the stability of the equipment itself, resulting in reduced detection accuracy, and additional manpower is required to perform regular calibration and maintenance of the detection equipment on site, further increasing the investment cost of the solution. In view of this, a carbon emission data collection and detection processing solution that can reduce investment costs and improve accuracy is a solution that urgently needs to be studied and designed.

[0049] In the process of research and design of the scheme, it was found that there is a connection between the vehicle's driving speed and fuel consumption, and there is an inevitable connection between fuel consumption and carbon emissions. Therefore, the detection of vehicle carbon emissions is achieved by detecting the vehicle's driving speed, which is a feasible solution. Moreover, from the current monitoring methods of the driving conditions of vehicles on traffic roads, it can be known that the images taken by the camera can be used for image recognition to identify the corresponding driving status of the vehicle, such as the vehicle speed. Therefore, the algorithm model of the mapping relationship between vehicle speed and carbon emissions and the combination of software and hardware between the cameras installed on the road can well realize the information collection and monitoring of carbon emissions in highway traffic.

[0050] Reference Figure 1 The present application provides a data sampling and processing method for carbon emissions, and the specific implementation steps include the following.

[0051] S1. Acquire a highway image captured by a first camera, wherein the highway image contains at least one vehicle target object, and the first camera is a camera set on a traffic highway.

[0052] Specifically, for the first camera mentioned above, the hardware can be directly implemented by using cameras that are already installed on the highway and have road monitoring functions. Of course, on this basis, if more cameras are needed for certain sections of the highway to monitor the carbon emissions of highway traffic, the same equipment as the existing cameras can be directly used. It can be seen that compared with the traditional solution, this solution can reduce the equipment purchase investment cost in terms of hardware, and given that the current camera installation and deployment methods on traffic roads are very mature, this solution can be used to reduce the design and manpower investment required for the addition of cameras.

[0053] S2. Perform vehicle type recognition on the vehicle target object in the highway image to obtain a vehicle type recognition result.

[0054] Specifically, different types of vehicles have different architectures, functions, drive types and other attributes, so the mapping relationship between the speed and fuel consumption of different types of vehicles will be different, which will lead to different mapping relationships between the vehicle's driving speed and carbon emissions. In addition, for the increasingly common new energy vehicles (including pure electric vehicles and hybrid vehicles), they cannot directly call the carbon emission estimation model of fuel vehicles for use. It can be seen that it is necessary to identify the type of vehicle captured in the image, so that the corresponding carbon emission estimation model can be accurately and appropriately called later to calculate the carbon emissions of different types of vehicles, thereby obtaining the carbon emissions of the highway area.

[0055] Step S2—performing vehicle type recognition on the vehicle target object in the highway image to obtain a vehicle type recognition result may specifically include the following steps.

[0056] S201. According to the usage status of the second database and the third database, select to identify the vehicle type by using the license plate number, and / or select to identify the vehicle type by combining the license plate color, vehicle shape and logo.

[0057] Specifically, for the above-mentioned second database, it is a professional database, which mainly stores the license plate number and the vehicle registration information corresponding to the license plate number, wherein the vehicle registration information includes the vehicle model. Since this professional database is generally a database that can only be held by an official agency or a third-party agency with permission, the validity of the access certificate of the database is affected by the official agency or the third-party agency, so when implementing this solution, the professional database may appear unusable. In addition, for this professional database, it may be called and queried by other different business end equipment / devices / servers due to the needs of different businesses / transactions. At this time, it is easy to cause the information query processing to be slow due to busy business queries, or even the situation of query failure (this situation can also be understood as an unusable state), which will reduce the data processing efficiency. Therefore, although the identified license plate number is used to realize the identification of the vehicle type, its implementation steps and the recognition algorithm of the license plate number are relatively simple, but its stability and reliability are slightly lacking.

[0058] In view of this, in order to ensure the processing efficiency and stability of this solution, in addition to the information access port of the second database, the processing system will also be provided with an information access port of the third database, so as to query and match the corresponding information from the third database to realize the identification of the vehicle type. Figure 2 For the third database, it mainly stores the mapping relationship between license plate color, vehicle shape profile information (mainly shape profile feature matrix), vehicle logo information, and vehicle model, so that matching can be performed one by one based on the above three elements, so as to obtain the vehicle type corresponding to the vehicle target object according to the final vehicle model.

[0059] It can be seen that the above step S201 may specifically include:

[0060] S2011, determining whether the second database is in an available state, if not, selecting to use a recognition method combining the license plate color, the vehicle shape and the vehicle logo to perform vehicle type recognition, if yes, executing step S2012;

[0061] S2012. Determine whether the total number M of vehicle target objects that currently need to be identified by vehicle type exceeds a first threshold. If not, select the method of using the license plate number to identify the vehicle type. If so, for the first number m1 of vehicle target objects, select the method of using the license plate number to identify the vehicle type. For the second number m2 of vehicle target objects, select the method of using a combination of the license plate color, the vehicle's outer contour, and the vehicle logo to identify the vehicle type. Among them, m1 is greater than m2, and M=m1+m2.

[0062] It can be seen that when the second database is unavailable, only the third database can be used to realize vehicle type identification. When the second and third databases are both available, if the number of vehicle target objects that need to be identified is small, the information in the second database can be directly used to realize vehicle information identification. On the contrary, if the number is large, the quantity is allocated and the second and third databases are used at the same time to perform vehicle type identification, thereby greatly improving processing efficiency.

[0063] The steps of the above embodiment are implemented on the premise that the third database is in a usable state. If both the second database and the third database are detected to be in an unusable state, an early warning message needs to be sent to the back-end staff for timely maintenance and adjustment.

[0064] In addition, the above vehicle type recognition result specifically includes the driving type of the vehicle target object, and the driving type includes a fuel driving type, a pure electric driving type, and a hybrid driving type.

[0065] In some embodiments, in the above step S201, the selection of using the license plate number recognition method to identify the vehicle type specifically includes the following steps.

[0066] A1. Recognize the license plate number of the vehicle target object in the highway image.

[0067] Specifically, for the recognition of license plate numbers, the main algorithm steps are license plate positioning, character segmentation and character recognition, and the specific recognition algorithm can be implemented using an existing algorithm, and no limitation is made in this embodiment.

[0068] A2. According to the identified license plate number, the vehicle model corresponding to the license plate number is queried from the second database, that is, the mapping relationship between the license plate number and the vehicle model is stored in the second database.

[0069] A3. Determine the driving type of the vehicle target object according to the vehicle model.

[0070] Specifically, the second database can also store a mapping relationship between vehicle models and drive types, so that when the vehicle model is determined, the drive type corresponding to the vehicle model can be directly obtained from the second database, so that the drive type of the vehicle target object can be obtained. Of course, if the second database does not store the mapping relationship between the vehicle model and the drive type, then the vehicle model can be directly used to identify and match the corresponding drive type in other public automobile information databases.

[0071] In some embodiments, in the above step S201, the selection of vehicle type recognition by combining license plate color, vehicle outline and vehicle logo recognition specifically includes the following steps.

[0072] B1. Identify the license plate color, vehicle outline and vehicle logo of the vehicle target object in the highway image.

[0073] B2. Filtering out several preliminary selected vehicle models corresponding to the recognized license plate color from the third database.

[0074] B3. Selecting a number of candidate vehicle models corresponding to the identified vehicle logo from the number of initially selected vehicle models.

[0075] B4. After calculating the similarity between the identified vehicle outline and the vehicle outlines corresponding to several candidate vehicle models, the vehicle model corresponding to the highest similarity is used as the final vehicle model.

[0076] B5. Determine the driving type of the target vehicle object according to the final vehicle model.

[0077] Specifically, since the license plate color of fuel vehicles is blue and the license plate color of new energy vehicles is green, the vehicle models belonging to fuel vehicles or new energy vehicles can be screened out using the identified license plate color to achieve rough screening; then, the vehicle models belonging to fuel vehicles or new energy vehicles can be further screened using the identified vehicle logo, which can reduce the number of vehicle contour matching and identification required; finally, based on the matching of the identified vehicle contour with the vehicle contour stored in the database, the vehicle contour with the highest matching degree (i.e., the highest similarity) can be identified; finally, based on the vehicle contour with the highest matching degree, the final vehicle model can be determined, thereby obtaining the drive type corresponding to the vehicle model, i.e., the drive type of the vehicle target object. It can be seen that by screening based on the license plate color, vehicle logo, and vehicle contour step by step, the drive type of the vehicle target object can be quickly and accurately identified.

[0078] In addition, it should be noted that if the above steps B2 and / or B3 are reduced, and the vehicle shape contour of the vehicle target object is directly used to match and identify with several vehicle shape contours pre-stored in the third database, although the corresponding vehicle model can be obtained in the end, compared with the matching and identification of license plate color and vehicle logo, the algorithm of vehicle shape contour is the most complicated, and in this field, vehicles of different brands may have very similar shape contours, or fuel vehicles and new energy vehicles of the same brand may have very similar shape contours. Therefore, only using the vehicle shape contour to identify and match the shape contour with the highest similarity may result in multiple recognition results. It can be seen that the implementation method of reducing the above steps B2 and / or B3 will have low efficiency and accuracy.

[0079] As for the recognition algorithm of the license plate color, vehicle outline and vehicle logo, it can be implemented by using existing algorithms, and no limitation is made in this embodiment.

[0080] S3. According to the vehicle type recognition result, a corresponding carbon emission estimation model is obtained from the first database, wherein the carbon emission estimation model is a mapping relationship model between vehicle speed and carbon emissions.

[0081] Specifically, since the vehicle type identification result includes the drive type of the vehicle target object, and the drive type includes a fuel drive type, a pure electric drive type and a hybrid drive type, the step S3—obtaining the corresponding carbon emission estimation model from the first database according to the vehicle type identification result, may specifically include the following steps.

[0082] S301, when the driving type is a fuel driving type, obtaining a first carbon emission estimation model from a first database; and / or,

[0083] S302: When the driving type is a hybrid driving type, the current driving mode of the vehicle target object is obtained from the information access port of the vehicle system; when it is determined that the current driving mode is a fuel driving mode, a second carbon emission estimation model is obtained from the first database.

[0084] Specifically, vehicles with pure electric drive technology and / or in electric drive mode basically do not emit greenhouse gases. Therefore, in this embodiment, the carbon emissions of fuel vehicles and vehicles in fuel driving mode are mainly estimated and summarized. Therefore, when the driving type of the vehicle target object is identified as a fuel driving type, or the vehicle target object is in fuel driving mode, it is necessary to obtain the corresponding carbon emission estimation model from the first database for estimation. In addition, for the above-mentioned first carbon emission estimation model and the second carbon emission estimation model, they can be determined to be the same or different according to the function obtained by curve fitting based on the actual measurement situation.

[0085] Of course, for vehicles with pure electric drive technology and / or in electric drive mode, although they basically do not emit greenhouse gases, they can also apply the above steps. For example, when the drive type is pure electric drive technology and / or the current driving mode is in electric drive mode, the third carbon emission estimation model is obtained from the first database. At this time, the third carbon emission estimation model can be 0, or if the corresponding third carbon emission estimation model can still be obtained after actual measurement, it can be directly substituted into the above steps.

[0086] Furthermore, in view of the fact that there are always technical differences between vehicles of different models, the carbon emission estimation model can be further refined to measure the actual situation for different vehicle models on the basis that the vehicle type is a fuel vehicle type, and then further obtain the mapping relationship between the vehicle model and the carbon emission estimation model. Therefore, for the vehicle type identification result, it can also include the vehicle model of the vehicle target object. In this way, the first carbon emission estimation model is obtained from the first database in step S301, which is specifically: according to the vehicle model of the vehicle target object, the first carbon emission estimation model corresponding to the vehicle model is obtained from the first database. And the second carbon emission estimation model is obtained from the first database in step S302, which is specifically: according to the vehicle model of the vehicle target object, the second carbon emission estimation model corresponding to the vehicle model is obtained from the first database.

[0087] It can be seen that by adopting the above embodiment, a carbon emission estimation model corresponding to a specific vehicle model can be obtained, which can more accurately estimate the carbon emission of the vehicle target object and further improve the accuracy.

[0088] As for the method of obtaining the vehicle model, it can be obtained from steps A1-A3 and / or B1-B5, which will not be elaborated here.

[0089] In some partial embodiments, the mapping relationship model between vehicle speed and carbon emissions is constructed based on the mapping relationship between vehicle speed and fuel consumption.

[0090] Specifically, after research and testing, it was found that the relationship function between driving speed and fuel consumption per 100 kilometers is as follows:

[0091] y=av 2 +bv+c

[0092] Wherein, y represents the fuel consumption per 100 kilometers, in L / (100km); v represents the speed of the vehicle, in km / h; a, b, and c are coefficients obtained after curve fitting, all of which are constants. The a, b, and c corresponding to different drive types and different vehicle models will be different, and are not specifically limited here. They can be obtained by testing according to actual conditions. In some specific embodiments, the value range of a is [0.002, 0.003], the value range of b is [-0.3, -0.2], and the value range of c is [30, 33].

[0093] The relationship function between fuel consumption per 100 kilometers and carbon emissions is as follows:

[0094]

[0095] Where, E represents the carbon emissions per 100 kilometers, in mg / (100km); ρ is the density of the fuel liquid, in kg / L; Q is the default net calorific value of the fuel, in MJ / kg; F i is the emission factor based on net calorific value, in mg / MJ; I i is the characteristic factor. n is the total number of emission factors and characteristic factors based on net calorific value.

[0096] From the above, the functional expression of the mapping relationship model between the vehicle speed and the carbon emissions is specifically:

[0097] S4. After obtaining the speed of the vehicle target object, the carbon emissions of the highway area are determined according to the obtained speed and the carbon emissions estimation model.

[0098] Specifically, it can be seen from the above that for several vehicle target objects identified in the highway image, the pure electric vehicle target object can be ignored. Therefore, after obtaining the speed of a fuel vehicle and a hybrid vehicle in a fuel driving mode, it is substituted into the corresponding carbon emission estimation model for calculation, so that the carbon emissions of each monitored vehicle (mainly referring to a fuel vehicle and a hybrid vehicle in a fuel driving mode) can be obtained, and then the carbon emissions of the vehicles appearing in the highway area are summarized, so that the carbon emissions of the highway area can be obtained. For the acquisition of the above vehicle speed, in addition to using image recognition technology, the existing speed radar can also be used to obtain the vehicle speed, which can be selected according to the actual situation and is not limited here.

[0099] There are two ways to obtain the vehicle speed using image recognition technology: the first is to calculate the instantaneous speed of the vehicle target object by the position change of the vehicle target object in the image between the i-1th moment and the ith time; the second is to record the time from the first moment to the last moment when the vehicle target object is photographed. Since the length of the highway area photographed by the first camera is known, the length of the highway area and the above-mentioned recorded time can be used to obtain the average speed of the vehicle target object. As for the vehicle speed obtained in the above step S4, at least one of the above two acquisition methods can be selected according to actual needs.

[0100] In addition, since the vehicle may travel on an uphill or downhill road, step S4 may be specifically as follows: after obtaining the vehicle speeds of several of the vehicle target objects, determine the first carbon emissions of the highway area based on the obtained vehicle speeds and the carbon emission estimation model; then, determine whether the vehicle target object is traveling on an uphill or downhill road. When the vehicle target object is traveling on an uphill road, the first carbon emissions are increased and used as the final carbon emissions; when the vehicle target object is traveling on a downhill road, the first carbon emissions are reduced and used as the final carbon emissions.

[0101] After the carbon emissions of the highway area captured by the camera are estimated by using the above step S4, the following steps can be performed according to the obtained carbon emissions.

[0102] S5. After obtaining the current carbon emission standard document in real time, compare the carbon emission standard recorded in the carbon emission standard document with the carbon emission of the highway area to determine whether the carbon emission of the highway area exceeds the standard.

[0103] Specifically, the above-mentioned carbon emission standard document can be an official document specifically about the carbon emission standard, or it can be other standard documents involving carbon emission standard, such as environmental quality standard documents, etc. As for the carbon emissions of the highway area, it is mainly obtained by summarizing the carbon emissions of the vehicles photographed in the highway area. It can be seen that in the process of implementing this solution, not only the carbon emissions of each monitored vehicle can be obtained, but also the carbon emissions of the highway area obtained by statistics and summary in any time period. Among them, the time period can be in minutes, hours, days, and can be set according to actual needs.

[0104] In addition, since the proportion of each gas component in the greenhouse gas emitted by the vehicle, such as carbon monoxide, carbon dioxide, nitrogen oxides, etc., can be obtained through multiple tests, after obtaining the carbon emissions of the vehicle, the content of each corresponding greenhouse gas currently emitted can actually be calculated. Therefore, the above step S5 can specifically include the following steps:

[0105] S501. When the carbon emission standard document is a carbon emission standard for automobiles, after obtaining the current carbon emission standard document in real time, the emission standard of each gas is extracted from the carbon emission standard document, and the carbon emissions corresponding to the target vehicle are obtained, so as to obtain the proportion of each greenhouse gas cost in the carbon emissions. For example, if the proportion of carbon dioxide is 70%, then the proportion of carbon dioxide is the product of carbon emissions*70%; then the proportion of each greenhouse gas is compared with the emission standard of the extracted gas, so as to determine whether the carbon emissions emitted by the monitored target vehicle on the highway area exceed the standard; and / or,

[0106] S502. When the carbon emission standard document is an environmental quality standard document, after obtaining the current carbon emission standard document in real time, the emission standard of each gas is extracted from the carbon emission standard document, and the carbon emissions corresponding to the vehicle target object are used to obtain the proportion of each greenhouse gas in the carbon emissions. Then, according to the required time, the proportion of each greenhouse gas cost emitted by several vehicle target objects is statistically analyzed to obtain the total proportion of each greenhouse gas in the highway area in any time period; then, the total proportion is compared with the emission standard of each gas extracted one by one, so as to determine whether the carbon emissions of the highway area exceed the standard in any time period.

[0107] By adopting the above-mentioned embodiment, no matter when the relevant standards in the carbon emission standard document are updated, they can be compared with the latest standards, which greatly improves timeliness and also makes it convenient for subsequent professionals to quickly check whether the highway emissions exceed the standards.

[0108] In addition, in order to further facilitate quick reference, the following steps may also be included:

[0109] S503, extract the percentage exceeding the standard and the storage location of this data, and add these two data to the corresponding file template, so that professionals can quickly understand the current carbon emissions of road traffic by reading this document first.

[0110] S6. When it is determined that the carbon emissions in the highway area exceed the standard, a vehicle driving condition identification is performed on the vehicle that is not in the minimum carbon emissions state, and an optimal vehicle speed of the vehicle that is not in the minimum carbon emissions state is determined according to the vehicle driving condition identification result.

[0111] Specifically, since the carbon emissions of a vehicle are related to its speed, in order to make the carbon emissions in the highway area meet the standards as much as possible, it is possible to consider optimizing the vehicle speed and feeding back the recommended speed to the vehicle terminal to remind the user.

[0112] Furthermore, in order to take into account both the reduction of carbon emissions and driving safety, step S6 may specifically include the following steps:

[0113] S601. When it is determined that the carbon emissions in the highway area exceed the standard, the vehicle driving condition of the vehicles that are not in the minimum carbon emissions state is identified to obtain the front vehicle distance of the vehicle target object, and then the optimal speed of the vehicle that is not in the minimum carbon emissions state is determined based on the front vehicle distance (if there is no vehicle in front of the vehicle target object, that is, the front vehicle distance is 0 or positive infinity), as well as the traffic light conditions of the highway area (such as red light, green light, yellow light or no traffic light) and the maximum speed limit.

[0114] It should be noted that if the current speed of the vehicle that is not in the minimum carbon emission state is already the optimal speed, then the corresponding prompt information can be sent, such as "the current speed is already the optimal speed"; if it is not the optimal speed, the current distance to the vehicle in front, the traffic light conditions and the maximum speed limit of the current road section are used to determine the speed of the vehicle that is not in the minimum carbon emission state, so as to adjust it, such as increasing or decreasing it, so as to achieve the purpose of reducing the carbon emissions of the vehicle.

[0115] S7. Sending the optimal vehicle speed to the vehicle system of the vehicle that is not in the minimum carbon emission state through the information access port of the vehicle system for display.

[0116] As can be seen from the above, by using the present application scheme, the existing traffic monitoring system can realize the reuse of functions to achieve the purpose of cost reduction, and also obtain the corresponding carbon emission estimation model according to the identified vehicle type to obtain the carbon emission situation detection of different vehicle types, so as to finally obtain the overall carbon emission situation of the highway area, which greatly improves the accuracy of highway carbon emission collection and detection. In addition, the latest carbon emission standard documents can be obtained and the corresponding information can be extracted in real time, so that the judgment of whether the vehicle carbon emissions meet the standards can not only ensure accuracy, but also facilitate the subsequent personnel to consult, and the convenience of use is improved. Finally, the vehicle speed can also be adjusted based on the carbon emissions, which is very conducive to promoting the development of green transportation, and no additional hardware equipment investment is required, which not only achieves the purpose of green transportation development, but also has low cost and can reduce the complexity of the project implementation.

[0117] Reference Figure 3 The present application also provides a data sampling and processing device for carbon emissions, the device comprising:

[0118] The first camera is used to photograph the highway;

[0119] A processing system comprising at least one processor for executing the steps of the above method embodiment;

[0120] The first camera is communicatively connected to the processing system.

[0121] Furthermore, the device also includes:

[0122] The information access port of the database is used for information transmission between several databases and the processing system; the databases mentioned here include at least the first, second and third databases;

[0123] An information access port of the vehicle-mounted system, used for mutual information transmission between the vehicle-mounted system and the processing system;

[0124] The information access port of the database and the information access port of the vehicle-mounted system are both connected to the processing system.

[0125] Since the processing system of the present device embodiment includes at least one processor for executing the steps of the above method embodiment, the beneficial effects of the device are the same as those of the above method embodiment and will not be elaborated in detail here.

[0126] In addition, the present application also provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above method embodiment.

[0127] For the processors mentioned in the above storage medium embodiment and the system embodiment, the number can be at least 1, and at least any step in the above method embodiment can be executed. When the number is at least two, at least two processors can be connected to each other by communication, not limited to wired or wireless communication connection, and the at least one processor can be connected to various intelligent terminal devices by communication. In addition, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0128] Finally, it should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0129] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A data sampling and processing method for carbon emissions, characterized in that: The method includes: Acquire a highway image captured by a first camera, wherein the highway image contains at least one vehicle target object; Performing vehicle type recognition on vehicle target objects in the highway image to obtain a vehicle type recognition result; According to the vehicle type recognition result, a corresponding carbon emission estimation model is obtained from the first database, wherein the carbon emission estimation model is a mapping relationship model between vehicle speed and carbon emission; After obtaining the speed of the vehicle target object, the carbon emissions of the highway area are determined according to the obtained speed and the carbon emissions estimation model; The vehicle type recognition of the vehicle target object in the highway image to obtain a vehicle type recognition result specifically includes: S201, according to the usage status of the second database and the third database, select to use the license plate number recognition method to perform vehicle type recognition, and / or select to use the recognition method combining the license plate color, vehicle shape outline and vehicle logo to perform vehicle type recognition; The step S201 specifically includes: S2011, determining whether the second database is in an available state, if not, selecting to use a recognition method combining the license plate color, the vehicle outline and the vehicle logo to identify the vehicle type, if yes, executing step S2012; S2012, determine whether the total number M of vehicle target objects that need to be identified by vehicle type currently exceeds the first threshold value, if not, select the vehicle type identification method using the license plate number, if so, for the first number m1 of vehicle target objects, select the vehicle type identification method using the license plate number, and for the second number m2 of vehicle target objects, select the vehicle type identification method using the combination of license plate color, vehicle outline and vehicle logo, wherein m1 is greater than m2, M = m1 + m2; The selection utilizes a recognition method combining the license plate color, the vehicle shape and the vehicle logo to identify the vehicle type, which specifically includes the following steps: B1. Identify the license plate color, vehicle outline and vehicle logo of the vehicle target object in the highway image; B2, selecting a number of preliminary selected vehicle models corresponding to the recognized license plate color from the third database; B3, selecting a number of candidate vehicle models corresponding to the identified vehicle logo from a number of preliminary selected vehicle models; B4, after calculating the similarity between the identified vehicle outline and the vehicle outlines corresponding to several candidate vehicle models, the vehicle model corresponding to the highest similarity is used as the final vehicle model; B5. Determine the driving type of the target vehicle according to the final vehicle model; After the step of determining the carbon emissions of the highway area, the following steps are also included: S5. After obtaining the current carbon emission standard document in real time, compare the carbon emission standard recorded in the carbon emission standard document with the carbon emission of the highway area, so as to determine whether the carbon emission of the highway area exceeds the standard; S6. When it is determined that the carbon emissions in the highway area exceed the standard, a vehicle driving condition identification is performed on the vehicle that is not in the minimum carbon emissions state, and an optimal vehicle speed of the vehicle that is not in the minimum carbon emissions state is determined according to the vehicle driving condition identification result; S7, sending the optimal vehicle speed to the vehicle system of the vehicle that is not in the minimum carbon emission state through the information access port of the vehicle system for display; Wherein, step S6 comprises the following steps: When it is determined that the carbon emissions in the highway area exceed the standard, the vehicle driving condition of the vehicle that is not in the minimum carbon emissions state is identified to obtain the front vehicle distance of the vehicle target object, and then the optimal speed of the vehicle that is not in the minimum carbon emissions state is determined based on the front vehicle distance, combined with the traffic light conditions and the maximum speed limit of the highway area.

2. The method according to claim 1, characterized in that The vehicle type recognition result includes a driving type of the vehicle target object, and the driving type includes a fuel driving type, a pure electric driving type, and a hybrid driving type. The corresponding carbon emission estimation model is obtained from the first database according to the vehicle type recognition result, which specifically includes: When the driving type is a fuel driving type, obtaining a first carbon emission estimation model from a first database; and / or, When the driving type is a hybrid driving type, the current driving mode of the vehicle target object is obtained from the information access port of the vehicle system; when it is determined that the current driving mode is a fuel driving mode, the second carbon emission estimation model is obtained from the first database.

3. The method according to claim 2, characterized in that The vehicle type recognition result also includes the vehicle model of the vehicle target object. The first carbon emission estimation model obtained from the first database is specifically: According to the vehicle model of the vehicle target object, obtaining a first carbon emission estimation model corresponding to the vehicle model from a first database; The second carbon emission estimation model is obtained from the first database, which is specifically: According to the vehicle model of the vehicle target object, a second carbon emission estimation model corresponding to the vehicle model is acquired from a first database.

4. The method according to claim 1, characterized in that The method of selecting a vehicle type by using a license plate number recognition method specifically includes: Recognize the license plate number of the vehicle target object in the highway image; According to the identified license plate number, querying from a second database to obtain a vehicle model corresponding to the license plate number; A driving type of the vehicle target object is determined according to the vehicle model.

5. The method according to any one of claims 1 to 4, characterized in that: The mapping relationship model between vehicle speed and carbon emissions is constructed based on the mapping relationship between vehicle speed and fuel consumption.

6. A data sampling and processing device for carbon emissions, characterized in that: The device includes: A first camera is used to capture images of the road; A processing system, comprising at least one processor, for executing the method according to any one of claims 1 to 5; The first camera is communicatively connected to the processing system.

7. The device according to claim 6, characterized in that The device also includes: An information access port of a database, used for mutual information transmission between a plurality of databases and the processing system; An information access port of the vehicle-mounted system, used for mutual information transmission between the vehicle-mounted system and the processing system; The information access port of the database and the information access port of the vehicle-mounted system are both connected to the processing system.

Images