A method and system for analyzing waste incineration process based on video recognition
By using video recognition technology to identify and track abnormal areas in the incinerator, the instability of calorific value and humidity parameters of different batches of waste has been resolved, thereby improving the stability and efficiency of the incineration process.
Patent Information
- Application Number
- CN202410348984.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-26
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-03-26
Smart Images

Figure CN118172702B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a method and system for analyzing a waste incineration process based on video recognition. Background Art
[0002] During the garbage incineration process, it is necessary to ensure that the garbage is put into the furnace loosely, in small quantities and continuously, so as to minimize the disturbance to the furnace. As for the research and development of the furnace body, it has shifted from grate furnace to incinerator. The garbage in the incinerator circulates in the furnace body and can have more sufficient contact with the air, so that the garbage can be fully burned.
[0003] However, it should be considered here that the feeding amount is also related to the combustion process, because the feeding amount is directly related to the internal temperature of the furnace and the garbage circulation process. In order to keep the incinerator running smoothly, the feeding process needs to be controlled. The main influencing factors of this process are the calorific value of the garbage and the combustion process.
[0004] In this case, there are sensor distance measurement and binocular vision distance measurement methods to control the feeding amount to achieve a stable incineration process. There are also irregular pile volume measurement methods to match materials, but these methods cannot achieve the linkage management of garbage calorific value and combustion process. Specifically, the calorific value, humidity and other parameters of different batches of garbage are different, so the feeding amount needs to be adjusted each time according to the combustion process. How to achieve this process requires further research. Summary of the invention
[0005] The present application provides a method and system for analyzing a waste incineration process based on video recognition, which provides adjustment parameters for batch materials by analyzing the degree of combustion of materials during the incineration stage, so that the materials can be burned as fully and stably as possible.
[0006] The above-mentioned purpose of the present application is achieved through the following technical solutions:
[0007] In a first aspect, the present application provides a method for analyzing a waste incineration process based on video recognition, comprising:
[0008] Obtaining a video stream of a coverage area and dividing the coverage area to obtain multiple analysis areas;
[0009] Divide the video stream according to the division method of the analysis area to obtain multiple sub-video streams, each of which corresponds to an analysis area;
[0010] Obtain an abnormal area in the analysis area and track the movement process of the abnormal area;
[0011] Statistics on the activities of all abnormal areas in the coverage area, including the area and the length of the moving path;
[0012] Use activity conditions to give the waste incineration results per unit time length;
[0013] Among them, multiple binocular vision camera modules are used to obtain video streams of the same coverage area.
[0014] In a possible implementation manner of the first aspect, obtaining an abnormal region in an analysis region includes:
[0015] Performing multiple grayscale screening processes on the image in the sub-video stream to obtain multiple suspected abnormal regions and merging the suspected abnormal regions to obtain a suspected grayscale region;
[0016] Merging the suspected grayscale areas obtained by multiple binocular vision camera modules to obtain overlapping areas; and
[0017] The obtained overlapping area is regarded as the abnormal area;
[0018] Each portion in the overlapping area appears in at least two suspected grayscale areas.
[0019] In a possible implementation manner of the first aspect, the method further includes screening the suspected abnormal area and discarding the bottom area of the normal incineration area.
[0020] In a possible implementation manner of the first aspect, screening the suspected abnormal area includes:
[0021] Obtain the flame area in the sub-video stream and depict the edge of the flame area;
[0022] Determine at least one highest position according to the edge of the flame area, and record the highest position as the vertex;
[0023] Use auxiliary rays to determine the coordinates of the vertices;
[0024] According to the vertex, a part of the edges associated with the vertex is filtered out from the edges of the flame area;
[0025] constructing the influence region of the vertex using the vertex and the portion of the edges associated with the vertex; and
[0026] The suspected abnormal areas within the affected area will be discarded.
[0027] In a possible implementation manner of the first aspect, tracking the movement process of the abnormal area includes:
[0028] Determine a plurality of auxiliary observation points belonging to the abnormal region using auxiliary rays, wherein the auxiliary observation points are all located inside the abnormal region; and
[0029] Use auxiliary observation points to form a tracking graph;
[0030] The tracking process of an abnormal area is divided into multiple time periods, and there is a blank time period between any two adjacent time periods.
[0031] In a possible implementation manner of the first aspect, the method further includes:
[0032] When tracking the same abnormal area in the next time period, auxiliary observation points are placed in the area where the abnormal area last appeared.
[0033] Determine whether all auxiliary observation points are located within the abnormal area;
[0034] When all auxiliary observation points are located within the abnormal area, the abnormal area is tracked for the next time period. When there are auxiliary observation points located outside the abnormal area, all auxiliary observation points are adjusted to be located within the abnormal area before tracking the abnormal area for the next time period.
[0035] In a possible implementation of the first aspect, the adjustment includes proportionally reducing the auxiliary observation point composition tracking graph and moving the auxiliary observation point composition tracking graph. In a second aspect, the present application provides a waste incineration process analysis device based on video recognition, comprising:
[0036] A first area division unit is used to obtain a video stream of a coverage area and divide the coverage area to obtain a plurality of analysis areas;
[0037] A second area division unit is used to divide the video stream according to the division method of the analysis area to obtain multiple sub-video streams, each sub-video stream corresponds to an analysis area;
[0038] A tracking unit, used for obtaining an abnormal area in an analysis area and tracking the movement process of the abnormal area;
[0039] A statistical unit is used to count the activities of all abnormal areas in the coverage area, including the area and the length of the moving path;
[0040] An evaluation unit, used to use the activity situation to give the waste incineration result per unit time length;
[0041] Among them, multiple binocular vision camera modules are used to obtain video streams of the same coverage area.
[0042] In a third aspect, the present application provides a waste incineration process analysis system based on video recognition, the system comprising:
[0043] one or more memories for storing instructions; and
[0044] One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.
[0045] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising:
[0046] Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.
[0047] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.
[0048] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.
[0049] The chip system may be composed of chips, or may include chips and other discrete devices.
[0050] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 It is a schematic diagram of a waste incineration process provided by this application.
[0052] Figure 2 It is a schematic flowchart of the steps of a method for analyzing a waste incineration process provided in this application.
[0053] Figure 3 This is a schematic diagram of a process for screening suspected abnormal areas provided by the present application.
[0054] Figure 4 This is a schematic diagram of the principle of using vertices and partial edges associated with the vertices to construct the influence area of the vertex provided by the present application.
[0055] Figure 5 This is a schematic diagram of the locations of the first auxiliary observation points and abnormal areas provided in this application. DETAILED DESCRIPTION
[0056] In order to more clearly understand the technical solution in this application, the relevant technology is first introduced.
[0057] The garbage incineration process analysis method disclosed in the present application mainly observes the combustion conditions in the incinerator. In the feeding stage, the crushed garbage is fed into the incinerator. In the high temperature environment, this part of the garbage begins to burn, and the volume and weight of the garbage fragments begin to decrease. With the help of circulating air, the garbage fragments that meet the requirements enter the circulating flow state until they are completely burned.
[0058] In some processes, the garbage will be preheated. Theoretically, most of the water in the garbage has been removed at this time, but it is also necessary to consider the influence of actual factors such as the proportion of each component in the garbage, the preheating temperature, and the thickness of the garbage, which leads to fluctuations in the proportion of the combustion area in the garbage. When this kind of garbage is fed into the incinerator, the temperature and combustion conditions in the incinerator will fluctuate. Therefore, it is necessary to dynamically control the feeding process, and adjust the feeding time and feeding amount in the specific control process.
[0059] See also Figure 1 After the garbage is sent into the incinerator, it begins to burn. The garbage participating in the cycle circulates in the incinerator and the separator. The separator outputs high-temperature gas and dust at the same time. The high-temperature gas uses heat exchange to recover heat, and the dust enters the dust removal process for treatment. The slag produced during the combustion process is discharged from the bottom of the incinerator.
[0060] The garbage entering the incinerator will first fall to the bottom. For the convenience of description, the bottom area is divided into a combustion area and a non-combustion area. When the proportion of the combustion area is too low, the temperature of the combustion stage will be reduced. At the same time, there is a risk of insufficient combustion. On the one hand, the calorific value of the garbage cannot be fully utilized, and on the other hand, the emission of pollutants such as nitrogen oxides and dioxins is increased.
[0061] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.
[0062] This application discloses a method for analyzing the waste incineration process based on video recognition. Figure 2 In some examples, the method for analyzing a waste incineration process based on video recognition disclosed in the present application includes the following steps:
[0063] S101, obtaining a video stream of a coverage area and dividing the coverage area to obtain multiple analysis areas;
[0064] S102, dividing the video stream according to the division method of the analysis area to obtain multiple sub-video streams, each sub-video stream corresponds to an analysis area;
[0065] S103, obtaining an abnormal area in the analysis area and tracking the movement process of the abnormal area;
[0066] S104, counting the activities of all abnormal areas in the coverage area, the activities including the area and the length of the moving path;
[0067] S105, using the activity status to provide the waste incineration result per unit time length;
[0068] Among them, multiple binocular vision camera modules are used to obtain video streams of the same coverage area.
[0069] First of all, it should be explained that the garbage incineration process analysis method based on video recognition disclosed in this application is applied to a set of analysis systems. The analysis system (hereinafter referred to as the system) consists of a binocular vision camera module and an analyzer. The binocular vision camera module is responsible for collecting the final images of the preheating stage in the incinerator, and the analyzer is responsible for analyzing the collected images. The corresponding adjustment means for the analysis results include adjusting the feed amount and moving speed, etc. This part will be further introduced in the subsequent content.
[0070] At the same time, in the present application, multiple binocular vision camera modules are used to obtain video streams of the same coverage area. Multiple binocular vision camera modules can obtain images from different angles, which helps to reduce the negative impact of image distortion caused by high temperature on process analysis.
[0071] In step S101, the video stream of the coverage area is obtained and the coverage area is divided to obtain multiple analysis areas. At the same time, the video stream is divided to obtain multiple sub-video streams, each of which corresponds to an analysis area, which is the content in step S102.
[0072] The contents of step S101 and step S102 are to enable the video to match the position. The purpose of regional division is mainly to take into account that the performance of materials in different areas is different during the movement of materials. Using the regional division method, there is no need to adjust the binocular vision camera module to move with the material, because the binocular vision camera module needs to continuously acquire images over a period of time.
[0073] At the same time, it is also necessary to consider that the binocular vision camera module needs to be cooled down every time it works for a period of time. The zoned working method can enable the binocular vision camera module to quickly enter the image acquisition process.
[0074] In step S103, an abnormal area in the analysis area is obtained and the movement process of the abnormal area is tracked. The abnormal area here mainly refers to the area without combustion. Then in step S104, the activities of all abnormal areas in the coverage area are counted, and the activities include area and moving path length.
[0075] Generally speaking, the area of the abnormal area should continue to shrink as the garbage moves. At the end of the coverage area, the abnormal area should disappear or its area should shrink to the allowable range. The moving path length refers to the length of the abnormal area in the coverage area, or it can also be considered as the appearance time of the abnormal area in the coverage area.
[0076] At the end of the coverage area, the sum of the areas of all abnormal areas should be within the allowable range, and abnormal areas exceeding the allowable area are not allowed to appear.
[0077] For the moving path length, reference should be made to the description of the sum of the areas of all abnormal areas. When the moving path lengths of all abnormal areas are short, it means that the material temperature at the end of the preheating stage is too high or the material thickness is insufficient. At this time, the process parameters need to be adjusted.
[0078] If the material temperature is too high, the drying temperature of the front section should be lowered; if the material thickness is insufficient, the feed amount should be increased.
[0079] In step S105, the activity status is used to give the waste incineration result per unit time length. The above content is the process parameter adjustment based on the waste incineration result, which will not be repeated here.
[0080] In some examples, obtaining an abnormal region in an analysis region includes:
[0081] S201, performing multiple grayscale screening processes on the image in the sub-video stream to obtain multiple suspected abnormal regions and merging the suspected abnormal regions to obtain a suspected grayscale region;
[0082] S202, merging the suspected grayscale areas obtained by multiple binocular vision camera modules to obtain overlapping areas; and
[0083] S203, taking the obtained overlapping area as an abnormal area;
[0084] Each portion in the overlapping area appears in at least two suspected grayscale areas.
[0085] In step S201, the image in the sub-video stream is subjected to multiple grayscale screening processes, and multiple suspected abnormal regions are obtained. These obtained suspected abnormal regions need to be merged.
[0086] Grayscale screening refers to processing an image using a grayscale value range, and all elements in the image outside the grayscale value range are discarded. The purpose of performing multiple grayscale screening processes is that some image elements will be lost during a grayscale screening process, because the colors of suspected grayscale areas are not consistent. For a fixed grayscale range, only a part of the suspected grayscale area can be obtained.
[0087] For the suspected grayscale areas obtained by multiple binocular vision camera modules, it is necessary to continue the merging process. The merging process here is mainly to take into account that the surface of the abnormal area is not on a single plane, but is composed of multiple small planes.
[0088] For a binocular vision camera module, it is highly unlikely that all these small planes can be obtained at the same time. Therefore, it is necessary to merge the suspected grayscale areas obtained by multiple binocular vision camera modules. The condition for the merging is that each part in the overlapping area appears in at least two suspected grayscale areas.
[0089] See also Figure 3 At the same time, it is also necessary to screen the suspected abnormal areas and discard the bottom areas of the normal burning areas. Because the bottom areas of some normal burning areas may also be screened out in multiple grayscale screening processes, these bottom areas will directly affect the final results.
[0090] For the screening of suspected abnormal areas, the specific steps are as follows:
[0091] S301, obtaining a flame area in a sub-video stream and depicting the edge of the flame area;
[0092] S302, determining at least one highest position according to the edge of the flame area, and recording the highest position as a vertex;
[0093] S303, using auxiliary light to determine the coordinates of the vertex;
[0094] S304, filtering out a portion of edges associated with the vertex from the edges of the flame area according to the vertex;
[0095] S305, constructing an influence area of the vertex using the vertex and a portion of the edges associated with the vertex; and
[0096] S306: discard the suspected abnormal area in the affected area.
[0097] In step S301 to step S306, the edge of the flame area is first determined, and then at least one highest position is determined based on the edge of the flame area. It should be noted here that the edge of the flame area refers to the flame area in the entire coverage area (the entire analysis area), and the highest position is also located in the entire coverage area (the entire analysis area).
[0098] Then, auxiliary light is used to determine the coordinates of the vertex. The auxiliary light is generated by a laser generator. The reason for using auxiliary light here is that there is a lack of reference objects in the coverage area, and the binocular vision camera module has a natural deficiency in determining the distance of the flame. The direction and angle of the auxiliary light are known parameters. By crossing multiple auxiliary lights, the coordinates of the vertex can be easily calculated.
[0099] Then, according to the vertex, the edge associated with the vertex is filtered out from the edge of the flame area. The specific method is to filter out a partial edge associated with the coordinates of the vertex according to the color difference. At this time, two situations will occur:
[0100] The first is that some edges of the transfer station associated with the vertex can reach or approach the surface of the material, such as Figure 4 As shown on the left;
[0101] The second is that some edges associated with the vertex are still some distance away from the surface of the material, such as Figure 4 Shown on the right.
[0102] For the second case, the predicted extension method is used to make the extension of the part of the edge associated with the vertex reach or approach the surface of the material. The predicted extension is mainly based on the edge trend of the flame. Figure 4 The dashed line on the right.
[0103] Then, the vertex and the part of the edge associated with the vertex are used to construct the influence area of the vertex and the suspected abnormal area in the influence area is discarded. The discarding process can discard the bottom area of the normal burning area.
[0104] In some examples, tracking the movement of the abnormal area includes the following steps:
[0105] S401, using auxiliary light to determine a plurality of auxiliary observation points belonging to the abnormal area, wherein the auxiliary observation points are all located inside the abnormal area; and
[0106] S402, using auxiliary observation points to form a tracking graph;
[0107] The tracking process of an abnormal area is divided into multiple time periods, and there is a blank time period between any two adjacent time periods.
[0108] In step S401 and step S402, auxiliary light is used to determine multiple auxiliary observation points belonging to the abnormal area, see Figure 5 ,This method is designed to facilitate tracking of abnormal areas, and use ,auxiliary observation points to form tracking graphics.
[0109] It should be understood that the difficulty of tracking auxiliary observation points is significantly lower than directly tracking the abnormal area, because this involves the influence of actual factors such as material surface flow and flames. Using auxiliary observation points located inside the abnormal area can effectively reduce the difficulty of tracking the abnormal area.
[0110] Since the moving direction of the abnormal area does not change substantially, the method of using auxiliary observation points is obviously easier to implement.
[0111] In addition, the tracking process of an abnormal area is divided into multiple time periods, and there is a blank time period between any two adjacent time periods. That is, in this application, a discontinuous tracking method is used for the abnormal area.
[0112] This is mainly due to the limitations of the camera coverage area. The image quality at the edge of the coverage area is low and there is a distortion problem. The camera needs to move within the coverage area to achieve the image acquisition task of the coverage area.
[0113] Furthermore, the following steps are added:
[0114] S501, when tracking the same abnormal area in the next time period, placing auxiliary observation points in the area where the abnormal area last appeared calculated;
[0115] S502, determining whether all auxiliary observation points are located in the abnormal area;
[0116] When all auxiliary observation points are located within the abnormal area, the abnormal area is tracked for the next time period. When there are auxiliary observation points located outside the abnormal area, all auxiliary observation points are adjusted to be located within the abnormal area before tracking the abnormal area for the next time period.
[0117] The contents of step S501 and step S502 are mainly to determine the combustion status of the material based on the prediction. The specific method is to place auxiliary observation points in the area where the last abnormal area appeared when tracking the same abnormal area in the next time period, and then determine whether all the auxiliary observation points are located in the abnormal area.
[0118] When all the auxiliary observation points are located within the abnormal area, it means that the abnormal area has not changed. Of course, the auxiliary observation point composition graph can also be processed by proportional reduction. Proportional reduction is a set parameter given based on experience.
[0119] Whether all the graphics composed of auxiliary observation points after proportional reduction are located within the abnormal area indicates that the disappearance speed of the abnormal area is in line with expectations.
[0120] When there are auxiliary observation points outside the abnormal area, it means that the disappearance speed of the abnormal area is inaccurate, and active intervention is required to make all auxiliary observation points located in the abnormal area before tracking the abnormal area for the next time period.
[0121] There are two ways of active intervention: the first is to move all auxiliary observation points, the second is to scale down the auxiliary observation point composition graph, or a combination of the two methods. Movement means that the thickness of the garbage at the bottom of the incinerator is decreasing, and proportional reduction means that the abnormal area is shrinking at a certain speed.
[0122] For abnormal areas, there are two modes: disappearance and decline. Both modes indicate that the garbage at the bottom of the incinerator is in a state of consumption. Therefore, these two factors need to be considered at the same time. When the area of the abnormal area does not shrink but the height decreases, the abnormal area is also considered to be in the process of change.
[0123] A weighted calculation is performed for the area change and height drop, and then the feeding process is adjusted based on the comparison of the result with the set value. The weighting is set based on the empirical value of the specific usage, and this application does not limit it.
[0124] The present application also provides a garbage incineration process analysis device based on video recognition, comprising:
[0125] A first area division unit is used to obtain a video stream of a coverage area and divide the coverage area to obtain a plurality of analysis areas;
[0126] A second area division unit is used to divide the video stream according to the division method of the analysis area to obtain multiple sub-video streams, each sub-video stream corresponds to an analysis area;
[0127] A tracking unit, used for obtaining an abnormal area in an analysis area and tracking the movement process of the abnormal area;
[0128] A statistical unit is used to count the activities of all abnormal areas in the coverage area, including the area and the length of the moving path;
[0129] An evaluation unit, used to use the activity situation to give the waste incineration result per unit time length;
[0130] Among them, multiple binocular vision camera modules are used to obtain video streams of the same coverage area.
[0131] Furthermore, it also includes:
[0132] A first image processing unit is used to perform multiple grayscale screening processes on the image in the sub-video stream to obtain multiple suspected abnormal regions and merge the suspected abnormal regions to obtain a suspected grayscale region;
[0133] A second image processing unit is used to merge the suspected grayscale areas obtained by the multiple binocular vision camera modules to obtain an overlapping area; and
[0134] A third image processing unit, used for taking the obtained overlapping area as an abnormal area;
[0135] Each portion in the overlapping area appears in at least two suspected grayscale areas.
[0136] Furthermore, it also includes screening the suspected abnormal areas and discarding the bottom area of the normal incineration area.
[0137] Furthermore, it also includes:
[0138] The third four-image processing unit is used to obtain the flame area in the sub-video stream and depict the edge of the flame area;
[0139] A position determination unit, used to determine at least one highest position according to the edge of the flame area, the highest position being recorded as a vertex;
[0140] A coordinate determination unit, for determining the coordinates of the vertices using auxiliary rays;
[0141] An edge determination unit, used for screening out a portion of edges associated with the vertex from the edges of the flame area according to the vertex;
[0142] an area determination unit, configured to construct an influence area of a vertex using the vertex and a portion of edges associated with the vertex; and
[0143] The screening unit is used to discard suspected abnormal areas within the affected area.
[0144] Furthermore, it also includes:
[0145] an auxiliary determination unit, configured to determine a plurality of auxiliary observation points belonging to the abnormal region using auxiliary light, wherein the auxiliary observation points are all located inside the abnormal region; and
[0146] A tracking graph generating unit, used for forming a tracking graph using auxiliary observation points;
[0147] The tracking process of an abnormal area is divided into multiple time periods, and there is a blank time period between any two adjacent time periods.
[0148] Furthermore, it also includes:
[0149] The first tracking unit is used to place auxiliary observation points to the calculated last appearance area of the abnormal area when tracking the same abnormal area in the next time period;
[0150] A determination unit, used to determine whether all auxiliary observation points are located in the abnormal area;
[0151] The second tracking unit is used to track the abnormal area for the next time period when all the auxiliary observation points are located within the abnormal area, and to adjust all the auxiliary observation points to be located within the abnormal area before tracking the abnormal area for the next time period when there are auxiliary observation points located outside the abnormal area.
[0152] Furthermore, it also includes:
[0153] A first calculation unit, used to calculate the waiting time when all auxiliary observation points are located in the abnormal area and to calculate the average waiting time of the waiting time in the coverage area;
[0154] A second calculation unit is used to calculate the actual flow speed of the material according to the average waiting time;
[0155] A third calculation unit is used to calculate the thickness drop speed according to the movement amount of the auxiliary observation point perpendicular to the material flow direction;
[0156] The correction calculation unit is used to perform correction calculation on the actual flow speed of the material using the thickness drop speed.
[0157] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
[0158] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).
[0159] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.
[0160] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0161] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0163] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0164] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.
[0165] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.
[0166] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0167] The present application also provides a waste incineration process analysis system based on video recognition, the system comprising:
[0168] one or more memories for storing instructions; and
[0169] One or more processors are used to call and run the instructions from the memory to execute the method as described above.
[0170] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the waste incineration process analysis system performs operations of the waste incineration process analysis system corresponding to the above method.
[0171] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.
[0172] The chip system may be composed of chips, or may include chips and other discrete devices.
[0173] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.
[0174] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.
[0175] Optionally, the computer instructions are stored in a memory.
[0176] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.
[0177] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.
[0178] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.
[0179] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.
[0180] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.
Claims
1. A method for analyzing a waste incineration process based on video recognition, characterized in that: include: Obtaining a video stream of a coverage area and dividing the coverage area to obtain multiple analysis areas; Divide the video stream according to the division method of the analysis area to obtain multiple sub-video streams, each of which corresponds to an analysis area; Obtain an abnormal region in an analysis region and track the movement process of the abnormal region; Statistics on the activities of all abnormal areas in the coverage area, including the area and the length of the moving path; Use activity conditions to give the waste incineration results per unit time length; Among them, multiple binocular vision camera modules are used to obtain the video stream of the same coverage area: The abnormal areas in an analysis area include: Performing multiple grayscale screening processes on the image in the sub-video stream to obtain multiple suspected abnormal regions and merging the suspected abnormal regions to obtain a suspected grayscale region; The suspected grayscale areas obtained by multiple binocular vision camera modules are merged to obtain overlapping areas; The obtained overlapping area is regarded as the abnormal area; Wherein, each portion in the overlapped region appears in at least two suspected grayscale regions; Tracking the movement of abnormal areas includes: A plurality of auxiliary observation points belonging to the abnormal area are determined by using auxiliary light, and the auxiliary observation points are all located inside the abnormal area; Use auxiliary observation points to form a tracking graph; The tracking process of an abnormal area is divided into multiple time periods, and there is a blank time period between any two adjacent time periods; When tracking the same abnormal area in the next time period, auxiliary observation points are placed in the area where the abnormal area last appeared. Determine whether all auxiliary observation points are located within the abnormal area; When all auxiliary observation points are located within the abnormal area, the abnormal area is tracked for the next time period. When there are auxiliary observation points located outside the abnormal area, all auxiliary observation points are adjusted to be located within the abnormal area before tracking the abnormal area for the next time period.
2. The method for analyzing the waste incineration process based on video recognition according to claim 1 is characterized in that: It also includes screening suspected abnormal areas and discarding the bottom area of the normal burning area.
3. The method for analyzing the waste incineration process based on video recognition according to claim 2 is characterized in that: Screening of suspected abnormal areas includes: Obtain the flame area in the sub-video stream and depict the edge of the flame area; Determine at least one highest position according to the edge of the flame area, and record the highest position as the vertex; Use auxiliary rays to determine the coordinates of the vertices; According to the vertex, a part of the edges associated with the vertex is filtered out from the edges of the flame area; constructing the influence region of the vertex using the vertex and the portion of the edges associated with the vertex; and The suspected abnormal areas within the affected area will be discarded.
4. The method for analyzing the waste incineration process based on video recognition according to claim 1 is characterized in that: The adjustment includes proportionally reducing the tracking graphics composed of the auxiliary observation points and moving the tracking graphics composed of the auxiliary observation points.
5. A garbage incineration process analysis device based on video recognition, characterized in that: include: A first area division unit is used to obtain a video stream of a coverage area and divide the coverage area to obtain a plurality of analysis areas; A second area division unit is used to divide the video stream according to the division method of the analysis area to obtain multiple sub-video streams, each sub-video stream corresponds to an analysis area; A tracking unit, used for obtaining an abnormal area in an analysis area and tracking the movement process of the abnormal area; A statistical unit is used to count the activities of all abnormal areas in the coverage area, including the area and the length of the moving path; An evaluation unit, used to use the activity situation to give the waste incineration result per unit time length; Among them, multiple binocular vision camera modules are used to obtain video streams of the same coverage area; A first image processing unit is used to perform multiple grayscale screening processes on the image in the sub-video stream to obtain multiple suspected abnormal regions and merge the suspected abnormal regions to obtain a suspected grayscale region; A second image processing unit is used to merge the suspected grayscale areas obtained by multiple binocular vision camera modules to obtain an overlapping area; A third image processing unit, used for taking the obtained overlapping area as an abnormal area; Wherein, each portion in the overlapped region appears in at least two suspected grayscale regions; an auxiliary determination unit, used to determine a plurality of auxiliary observation points belonging to the abnormal area using auxiliary light, wherein the auxiliary observation points are all located inside the abnormal area; A tracking graph generating unit, used for forming a tracking graph using auxiliary observation points; The tracking process of an abnormal area is divided into multiple time periods, and there is a blank time period between any two adjacent time periods; The first tracking unit is used to place auxiliary observation points to the calculated last appearance area of the abnormal area when tracking the same abnormal area in the next time period; A determination unit, used to determine whether all auxiliary observation points are located in the abnormal area; The second tracking unit is used to track the abnormal area for the next time period when all the auxiliary observation points are located within the abnormal area, and to adjust all the auxiliary observation points to be located within the abnormal area before tracking the abnormal area for the next time period when there are auxiliary observation points located outside the abnormal area.
6. A garbage incineration process analysis system based on video recognition, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 4 is executed.
