Automatic classification method and system for construction waste

Abstract

The invention discloses an automatic classification method and system for construction waste, and the method comprises the steps: obtaining first image data of a to-be-detected target object, determining a corresponding garbage type according to an image recognition result, and carrying out the recognition of the garbage type according to the recognized garbage type, the sorting device is controlled to place the corresponding to-be-detected target objects on the corresponding carrying trolleys, and weight sensors are arranged on the carrying trolleys and used for detecting first weight values of the to-be-detected target objects placed on the carrying trolleys; when the first weight value is greater than or equal to a first weight threshold value, enabling the carrying trolley to transport the to-be-measured target object to a corresponding object placing area for placing; and the number of transportation times and the transportation weight of the carrying trolley are sent to a central server so as to determine the needed carrying trolley. By using the scheme, reasonable arrangement, allocation and management of transportation resources can be facilitated, the waste treatment efficiency is improved, and the classification accuracy is improved.

Description

Technical Field

[0001] The present invention relates to object classification and processing technology, and in particular to an automatic classification method and system for construction waste. Background Art

[0002] With the rapid development of urbanization, more and more construction work is being done. Whether it is the construction of new buildings or the renovation of old buildings, a large amount of construction waste will be generated during the construction process. If these large amounts of construction waste are discarded, it will not only cause a waste of resources, but also require special arrangements for the land to place these wastes. However, land resources are also limited. In the long run, there will be no suitable land space to place these wastes. For this reason, it is necessary to consider the issue of resource recycling of construction waste.

[0003] In order to recycle waste resources, waste is classified at the construction site into three categories: recyclable waste, non-recyclable waste and hazardous waste. This makes it easier to transport different types of waste to corresponding places for treatment. For example, recyclable waste is transported to resource recycling factories for treatment, non-recyclable waste is transported to landfills for landfilling, and hazardous waste is transported to special places for special treatment. However, in the current classification scheme for construction sites, it is difficult to allocate the corresponding number and specifications of transport vehicles to transport them because the output of each type of waste cannot be determined. This will lead to low efficiency in transportation and processing, and is not conducive to the management and allocation of transportation resources. Summary of the invention

[0004] In view of this, 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 an automatic classification method and system for construction waste to improve processing efficiency and facilitate the management and allocation of transportation resources.

[0005] In a first aspect, an embodiment of the present application provides a method for automatically classifying construction waste, the method comprising the following steps:

[0006] S1. Acquire first image data of a target object to be measured, wherein the first image data is obtained by photographing the target object to be measured by a first camera device;

[0007] S2. Identifying the type of garbage to which the target object to be detected belongs according to the first image data;

[0008] S3, according to the identified garbage type, controlling the sorting device to place the corresponding target object to be measured on the corresponding transport trolley, wherein the transport trolley is provided with a weight sensor, and the weight sensor is used to detect a first weight value of the target object to be measured placed on the transport trolley;

[0009] S4. When the first weight value is greater than or equal to the first weight threshold, the transport vehicle is instructed to transport the target object to be measured to a corresponding storage area for placement; wherein the number of the storage areas is the same as the number of garbage types;

[0010] S6. Send the number of transportations and the transportation weight of the transport vehicle to the central server, so that the central server can determine the number and type of transport vehicles required according to the number of transportations and the transportation weight.

[0011] In some embodiments, the method further comprises the following steps:

[0012] S5. When the first weight value is less than the first weight threshold and there is no target object to be measured of the garbage type corresponding to the transport vehicle, the transport vehicle is ordered to transport the target object to be measured to the corresponding storage area for placement.

[0013] In some embodiments, when the number of the weight sensor is 1, the step of confirming the first weight value includes:

[0014] A plurality of weight data are collected within a preset time period, and the first weight value is obtained by calculating an average value of the plurality of weight data.

[0015] In some embodiments, when the number of the weight sensors is 3, the layout shape of the 3 weight sensors at the bottom of the transport cart is an equilateral triangle.

[0016] In some embodiments, step S6 specifically includes:

[0017] S601, when the target object to be measured placed in the placement area contains solid material, obtaining shape information of the target object to be measured;

[0018] S602: Send the shape information, the number of transportations of the transport vehicle, and the transportation weight to the central server, so that the central server determines the number and type of transport vehicles required according to the shape information, the number of transportations, and the transportation weight.

[0019] In some embodiments, the first camera device is a 3D camera, and the 3D camera is a camera installed on a sorting device or on an unmanned aerial vehicle.

[0020] In some embodiments, the sorting device or unmanned aerial vehicle is also equipped with a near-infrared transmitting and receiving device.

[0021] In some embodiments, the step S2 specifically includes:

[0022] S201, obtaining image features of a target object to be measured in first image data;

[0023] S202, obtaining first near-infrared spectrum data, wherein the first near-infrared spectrum data is data obtained after spectral analysis processing of a first near-infrared light signal, and the first near-infrared light signal is a near-infrared light signal reflected by the target object to be measured and received after the near-infrared transmitting and receiving device transmits near-infrared light to the target object to be measured;

[0024] S203: After the image features and the first near-infrared spectrum data form a data input matrix, the data input matrix is ​​input into a deep learning training model for processing to obtain the garbage type to which the target object to be tested belongs.

[0025] In a second aspect, an embodiment of the present application provides an automatic classification system for construction waste, the system comprising:

[0026] A first camera device, used to photograph the target object to be measured;

[0027] A weight sensor, used for detecting a first weight value of a target object to be measured placed on the transport trolley;

[0028] A first processing system, comprising at least one processor, for executing the steps of the method for automatically classifying construction waste;

[0029] The sorting device is controlled by the first processing system to perform a sorting operation on the target object to be detected.

[0030] In some embodiments, the system further comprises:

[0031] A transport trolley, controlled by the first processing system, for placing the target object to be measured and transporting the target object to be measured to the storage area; and / or,

[0032] The near-infrared transmitting and receiving device is used to transmit near-infrared light to the target object to be measured, receive the near-infrared light signal reflected by the target object to be measured, and send the received near-infrared light signal to the first processing system.

[0033] The present application can achieve the following technical effects: after the present application scheme identifies the type of construction waste (i.e., the target object to be measured), the sorting device is used to place different types of waste on the corresponding transport cart, and the weight sensor on the transport cart can detect the weight currently placed on the transport cart. When the current load-bearing capacity is greater than the acceptable range (i.e., the first weight threshold), the transport cart is ordered to transport the target object to be measured to the corresponding storage area for placement, and finally the number of transportations and the weight of the transport cart are sent to the central server, so that the central server can determine the number and type of transport vehicles required according to the number of transportations and the weight of the transportation. It can be seen that by using this scheme, the real-time production of each type of waste can be tracked in real time. In this way, according to the current transportation demand and the current transportation resource capacity, the corresponding transport vehicle can be reasonably arranged to transport the required type of waste to the construction site and transport it to the corresponding treatment site, ensuring the rational use and management of transportation resources. In addition, the present scheme has classified different types of waste and placed them in the corresponding storage area, so that the transport vehicle can quickly transport the corresponding waste when it arrives at the construction site, greatly improving the processing efficiency of the transportation work. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] 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.

[0035] Figure 1 A schematic diagram of the structure of an automatic classification system for construction waste provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of the steps of a method for automatically classifying construction waste provided in an embodiment of the present application;

[0037] Figure 3 A distribution diagram of weight sensors disposed at the bottom of a transport trolley is provided for an embodiment of the present application.

[0038] Figure numerals: 1. Weight sensor. DETAILED DESCRIPTION

[0039] 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.

[0040] In order to achieve resource recovery and reuse of construction waste, it is necessary to classify the waste on the construction site, generally into three categories: recyclable waste, non-recyclable waste and hazardous waste, and then transport the classified waste of different types to the corresponding treatment site for treatment. In view of this, it is currently achieved by using a waste sorting device set up at the construction site. The general process is that after the transport vehicle arrives at the construction site, the sorting device starts to sort the waste, and then the sorted waste is directly placed on the transport vehicle. When the weight of the materials undertaken by the transport vehicle has reached the upper limit, these materials are transported to the corresponding treatment site. It can be seen that if there are fewer transport vehicles arranged at this time, it will lead to the inability to transport all the waste away at one time. If there are more transport vehicles arranged at this time, it will cause a waste of transportation resources. In view of this, the embodiment of the present application provides an automatic classification scheme for construction waste, which can improve the rationality of transportation resource allocation and improve the efficiency of overall transportation work.

[0041] First of all, it should be noted that the target object to be detected described in the embodiments of the present application mainly refers to construction waste, which can also be understood as building garbage. Among them, the classification of construction waste is as follows.

[0042] ①Recyclable garbage

[0043] Recyclable garbage may include scrap steel, scrap wood, scrap bricks, concrete, glass, etc. They are basically solid materials that can be reused after processing. For example, scrap steel can be re-melted into new steel, which can reduce the production of new steel, and it can be reused in the construction field. Generally, the new steel re-melted from scrap steel is of high quality and can be used to make heavy-duty equipment, heavy machinery, etc., while the steel with average quality can be used in the fields of reinforced concrete, etc. The same is true for other waste wood, waste bricks, waste glass, etc. That is, they are generally transported to factories for reprocessing.

[0044] ② Non-recyclable garbage

[0045] Non-recyclable garbage may include garbage sludge, sand, soil, ceramics, etc., which are generally transported to landfills for disposal.

[0046] ③. Hazardous waste

[0047] Hazardous waste may include lead paint, contaminated cement, chemical waste, etc. They have adverse effects on the environment and people and should be transported to corresponding special treatment sites for treatment.

[0048] It can be seen that for the above three types of waste, their shapes, materials, textures, chemical compositions, etc. are all different, so they can be classified into corresponding types of garbage based on their characteristics.

[0049] Reference Figure 1 An automatic classification system for construction waste includes: a first camera device, a weight sensor, a first processing system and a sorting device, wherein the first camera device, the weight sensor and the sorting device are all communicatively connected to the first processing system.

[0050] The first camera device is mainly used to photograph the target object to be measured.

[0051] Specifically, for the first camera device, it can be a 3D camera, such as a laser three-dimensional camera, etc., which can be installed on a sorting device or on an unmanned aerial vehicle. When it is installed on the sorting device, the target object to be measured is photographed at the material taking port, and then the processing system performs image recognition on it, and the sorting device sorts it according to the result of image recognition and places it on the corresponding transport trolley; or, when it is installed on an unmanned aerial vehicle, the unmanned aerial vehicle can be used to bypass the waste, so that the first camera device can take a photo of the waste, and then the processing system performs image recognition on it, and then the sorting device can use its own installed automatic pick-up and placement components (such as automatic clamping devices such as mechanical arms) to take the corresponding waste and place it on the corresponding transport trolley. It can be seen that the internal sorting structure of the sorting device of the former scheme is more complicated than the internal structure of the sorting device of the latter scheme, but the latter scheme requires the purchase of an additional unmanned aerial vehicle, which is more expensive. Therefore, the installation implementation method of the first camera device can be selected and designed according to actual needs, and is not specifically limited in this embodiment.

[0052] The weight sensor is used to detect a first weight value of a target object to be measured placed on the transport trolley.

[0053] Specifically, for the weight sensor, there is at least one, and when there are more than two, it is necessary to arrange them at the bottom of the transport vehicle in a certain manner to improve their detection accuracy. In this embodiment, they can be arranged and installed as required, and are not specifically limited.

[0054] The first processing system includes at least one processor for executing the steps of the method for automatically classifying construction waste. The steps of the method will be described in detail below.

[0055] The sorting device is controlled by the first processing system to perform a sorting operation on the target object to be detected.

[0056] Specifically, the sorting device mainly performs corresponding operations according to the control instruction transmitted by the first processing system. The control instruction is determined by the first processing system according to the recognition result obtained after recognizing the first image data. In addition, the sorting device may include a pick-up and place component, a feed port, a sorting structure, and a discharge port.

[0057] In some embodiments, the system of the present application also includes a transport vehicle and a near-infrared transmitting and receiving device, which are described in detail as follows.

[0058] For the transport trolley, it can be a manually operated transport structure, and such a structure has low cost, but it requires construction personnel to manually confirm whether the transport trolley can be pushed to the storage area and requires manpower to push it, that is, this is a non-automatic transport trolley. Alternatively, it can be an automatic transport trolley, which is controlled by the first processing system and is used to place the target object to be tested, and when receiving the trigger instruction from the first processing system, the automatic navigation function is turned on to transport the target object to be tested to the storage area. Among them, there are three storage areas, namely, storage area A, which is used to place recyclable garbage; storage area B, which is used to place non-recyclable garbage; storage area C, which is used to place hazardous waste. They are all divided out on demand on the construction site, and according to the different types of garbage, their area sizes and the containers / appliances configured in the area to assist in the placement of materials are also different, which can be configured accordingly according to actual needs.

[0059] The near-infrared transmitting and receiving device is used to transmit near-infrared light to the target object to be measured, receive the near-infrared light signal reflected by the target object to be measured, and send the received near-infrared light signal to the first processing system.

[0060] Specifically, the near-infrared emitting device is mainly provided to realize the function of near-infrared spectral analysis. Since the near-infrared spectral analysis method is a non-destructive testing technology, it can be applied to a variety of different material components for detection. Therefore, by emitting a near-infrared light signal to the target object to be measured and receiving the near-infrared light signal reflected from the target object to be measured, the spectrum of the absorbed spectrum of the substance can be obtained by spectral analysis, and then the composition and properties of the substance can be identified according to the obtained spectral analysis results, so as to determine what kind of substance is on the target object to be measured. If the target object to be measured has harmful chemical substances and is too invasive to be removed, and the amount is relatively large, then even though the target object to be measured is actually scrap steel, waste wood, etc. in recyclable garbage, it should also be identified as hazardous waste. Therefore, adding a near-infrared emitting and receiving device to enable the system to realize the near-infrared spectral analysis function can further accurately classify construction waste.

[0061] Reference Figure 2 For the first processing system mentioned above, the program is loaded to execute the steps of the automatic classification method for construction waste, and its specific steps are as follows.

[0062] S1. Acquire first image data of a target object to be measured, wherein the first image data is obtained by photographing the target object to be measured by a first camera device.

[0063] Specifically, the first camera device may be a 2D camera device or a 3D camera device. Compared with a 2D camera device, the image data captured by a 3D camera device can also identify the shape information of the target object to be measured, which is more conducive to the subsequent accurate determination of the type and number of transport vehicles. Therefore, preferably, the first camera device uses a 3D camera, and as mentioned above, the 3D camera is a camera installed on a sorting device or an unmanned aerial vehicle. The 3D camera can be a laser three-dimensional scanning camera, which can provide effective laser point cloud data for subsequent laser point cloud three-dimensional modeling by emitting and receiving laser information.

[0064] S2. Identify the type of garbage to which the target object to be detected belongs according to the first image data. The types of garbage are recyclable garbage, non-recyclable garbage and hazardous garbage.

[0065] Specifically, based on the above, these three types of garbage are different in their form (such as solid materials, which have a clear shape and edges, while the shape of liquids is the same as their containers), materials, textures (liquid textures are smoother than those of solid materials), and colors (for example, the colors of steel, wood, rotors, and chemical liquids are also different from each other). Therefore, by identifying the image features such as the shape, color, and texture of the target object to be tested in the first image data, and then inputting the identified image features into the trained deep learning training model for processing, the type of garbage to which the target object to be tested belongs can be obtained.

[0066] In some embodiments, based on the above description, in order to further identify the type of garbage and avoid judging steel full of harmful substances as recyclable garbage, a consideration factor is added to the input data of the training model, namely, the material composition information of the target object to be measured, and this information can be obtained by performing spectral analysis on the received signal after the near-infrared transmitting device transmits and receives the signal to the target object to be measured, and the near-infrared spectrum data is obtained, and the near-infrared spectrum data is used to represent the material composition information. Therefore, for step S2, it can specifically include the following steps.

[0067] S201, obtaining image features of a target object to be measured in first image data, wherein the image features include shape, texture and color features of the target object to be measured.

[0068] S202, obtaining first near-infrared spectrum data, wherein the first near-infrared spectrum data is data obtained after spectral analysis processing is performed on a first near-infrared light signal, and the first near-infrared light signal is a near-infrared light signal reflected by a target object to be measured and received after a near-infrared transmitting and receiving device transmits near-infrared light to the target object to be measured.

[0069] S203: After the image features and the first near-infrared spectrum data form a data input matrix, the data input matrix is ​​input into a deep learning training model for processing to obtain the garbage type to which the target object to be tested belongs.

[0070] It can be seen that the garbage type of the target object to be detected can be further accurately identified through the implementation method of the above embodiment.

[0071] S3. According to the identified garbage type, control the sorting device to place the corresponding target object to be measured on the corresponding transport cart, wherein the transport cart is provided with a weight sensor, and the weight sensor is used to detect a first weight value of the target object to be measured placed on the transport cart.

[0072] Specifically, through the above steps, it is possible to detect in real time how much waste material is currently carried on the transport cart. In this embodiment, a type of garbage is placed on a corresponding transport cart. For example, if the current transport cart a is used to carry recyclable garbage, then other types of waste materials will not be placed on this transport cart a. It can be seen that usually, for the same type of waste materials, the number of times they are transported and the weight of each transportation are summarized and counted, and the total output of recyclable waste materials currently placed on the storage area A can be calculated (the output is expressed by weight in this embodiment), that is, Among them, W k It is represented by the total weight of the kth type of target object to be tested, that is, the total weight of the kth type of waste. For example, the first type is the total weight of recyclable waste, the second type is the total weight of non-recyclable waste, etc. m represents the total number of target object types to be tested, that is, there are m types in total; w i represents the single weight of the kth type of waste transported for the ith time, and n is the total number of times the kth type of waste has been transported by the transport vehicle.

[0073] In some embodiments, in order to further improve the accuracy of the first weight value, the specific acquisition and confirmation steps may include:

[0074] A plurality of weight data are collected within a preset time period, and the first weight value is obtained by calculating an average value of the plurality of weight data.

[0075] Specifically, since the weight value detected by the weight sensor may be larger due to the kinetic energy of the material when it is placed on the transport cart, the discreteness of the collected weight data will be relatively large. In fact, when the discreteness of the weight data tends to be flat, the calculated value is close to the actual weight value. Therefore, further: when the variance of the weight data collected within the preset time period is less than the first threshold, the average value of the weight data is calculated to obtain the first weight value. In this way, the collected weight data can be determined to be valid data, which is closer to the actual material weight, and the confirmation accuracy of the first weight value is further improved.

[0076] In some embodiments, reference Figure 3 When the number of the weight sensors 1 is 3, the layout shape of the 3 weight sensors 1 at the bottom of the transport trolley is an equilateral triangle. Since the shapes of most solid materials are irregular, the pressures they exert on the bottom plate of the transport trolley will be different, which will cause uneven force. If there is only one weight sensor, it will easily cause the problem of the detected weight being too large or too small. For this reason, the weight sensors are arranged in an equilateral triangle at the bottom of the transport trolley, with one weight sensor at each corner, for a total of 3 weight sensors. Then, the bottom of the transport trolley, that is, the center of gravity of the bottom plate, is the same as the center of gravity of the equilateral triangle. In this way, the first initial weight values ​​detected by the 3 weight sensors can be averaged and the average value can be used as the final first weight value.

[0077] Of course, for the first initial weight value collected by any of the above weight sensors, the above steps are the same, a plurality of weight data are collected within a preset time period, and the first initial weight value is obtained after the average value of the plurality of weight data is calculated. Then, the average value of the first initial weight values ​​collected by the three weight sensors is calculated, and the average value is used as the final first weight value.

[0078] S4. When the first weight value is greater than or equal to the first weight threshold, instruct the transport vehicle to transport the target object to be measured to a corresponding storage area for placement; wherein the number of the storage areas is the same as the number of garbage types.

[0079] Specifically, the first weight threshold refers to the maximum weight that the transport cart can bear. When it is detected that the weight currently borne by the transport cart is greater than or equal to the first weight threshold, the transport cart is ordered to transport the target object to be tested to the corresponding storage area for placement. For example, if the material currently transported by the transport cart is material a, it is placed in storage area A.

[0080] S5. When the first weight value is less than the first weight threshold and there is no target object to be measured of the garbage type corresponding to the transport vehicle, the transport vehicle is triggered to transport the target object to be measured to the corresponding storage area for placement.

[0081] Specifically, when the weight currently borne by the transport cart has not reached the maximum weight it can bear, but the garbage type corresponding to the transport cart (for example, the garbage type of the waste currently carried by the transport cart O is a), such as garbage type a, has been sorted, that is, there is no waste of this type, then the transport cart cannot carry waste of other types of garbage at this time, but can only carry the waste currently carried to the corresponding storage area for placement. This can further ensure that the output of the waste currently placed in the storage area can be accurately calculated later.

[0082] S6. Send the number of transportations and the transportation weight of the transport vehicle to the central server, so that the central server can determine the number and type of transport vehicles required according to the number of transportations and the transportation weight.

[0083] Specifically, after the number of times the transport carts corresponding to the type of garbage and the weight of each transport are sent to the central server, the central server can calculate the output of a type of waste currently placed in the storage area based on these two parameters. Since the type of waste is also known, it can determine how many transport vehicles should be arranged and what type of transport vehicles should be arranged based on the output and current transportation resources, so as to ensure that the waste currently placed in the storage area can be transported to the corresponding treatment site at one time. It can be seen that this can ensure the reasonable arrangement and management of transportation resources and improve treatment efficiency.

[0084] In some embodiments, solid materials mainly refer to recyclable garbage. Since their shapes are basically irregular, the space required for placing regular-shaped solid materials is smaller than the space required for placing irregular-shaped solid materials under the same weight. In other words, in order to further improve the rationality and accuracy of transportation resources, the shape of the target object to be measured also needs to be considered. Therefore, step S6 may specifically include the following steps.

[0085] S601. When the target object to be measured placed in the placement area contains solid material, shape information of the target object to be measured is obtained.

[0086] S602: Send the shape information, the number of transportations of the transport vehicle, and the transportation weight to the central server, so that the central server determines the number and type of transport vehicles required according to the shape information, the number of transportations, and the transportation weight.

[0087] Specifically, if the shapes of solid materials are all regular, the required placement space, that is, the accommodating space of the transport vehicle, is V0. If the shapes of solid materials are irregular, the accommodating space of the transport vehicle is increased, that is, V1=d*V0, wherein V1 is the accommodating space of the transport vehicle required when the shapes of solid materials are irregular, d is the empirical coefficient, 1<d≤1.5, and the greater the proportion of irregular shapes, the greater the value of d. After V1 is determined, you can directly consider arranging a transport vehicle with an accommodating space of V1, or arranging several transport vehicles, and their total accommodating space is V1. This can be actually arranged and deployed according to the actual situation of transportation resources, and is not specifically limited here.

[0088] In some embodiments, the near-infrared transmitting and receiving device is installed on the sorting device or the unmanned aerial vehicle.

[0089] It can be seen that by adopting the above scheme, waste can be accurately classified by garbage type, and it can be conducive to the reasonable arrangement, deployment and management of transportation resources, greatly improving the efficiency of waste treatment. Moreover, the above-mentioned transport trolley for building materials is an existing equipment in the current building materials field, but it is generally used to transport available building materials. If it is applied to this scheme, it will not only improve the automatic intelligence of the above-mentioned classification scheme, but also make full use of this transport trolley to achieve the effect of maximizing resource utilization.

[0090] Since the first processing system of the system embodiment includes at least one processor for executing the steps of the above method embodiment, the beneficial effects of the system of the present embodiment are the same as those of the above method embodiment and will not be elaborated in detail here.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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 method for automatically classifying construction waste, characterized in that: The method comprises the following steps: S1. Acquire first image data of a target object to be measured, wherein the first image data is obtained by photographing the target object to be measured by a first camera device; S2. Identifying the type of garbage to which the target object to be detected belongs according to the first image data; S3, according to the identified garbage type, controlling the sorting device to place the corresponding target object to be measured on the corresponding transport trolley, wherein the transport trolley is provided with a weight sensor, and the weight sensor is used to detect a first weight value of the target object to be measured placed on the transport trolley; S4. When the first weight value is greater than or equal to the first weight threshold, the transport vehicle is instructed to transport the target object to be measured to a corresponding storage area for placement; wherein the number of the storage areas is the same as the number of garbage types; S6. Send the number of transportations and the transportation weight of the transport vehicle to the central server, so that the central server can determine the number and type of transport vehicles required according to the number of transportations and the transportation weight.

2. The method according to claim 1, characterized in that The method further comprises the following steps: S5. When the first weight value is less than the first weight threshold and there is no target object to be measured of the garbage type corresponding to the transport vehicle, the transport vehicle is ordered to transport the target object to be measured to the corresponding storage area for placement.

3. The method according to claim 1, characterized in that When the number of the weight sensor is one, the step of confirming the first weight value includes: A plurality of weight data are collected within a preset time period, and the first weight value is obtained by calculating an average value of the plurality of weight data.

4. The method according to claim 3, characterized in that When the number of the weight sensors is 3, the layout shape of the 3 weight sensors at the bottom of the transport trolley is an equilateral triangle.

5. The method according to any one of claims 1 to 4, characterized in that: The step S6 specifically includes: S601, when the target object to be measured placed in the placement area contains solid material, obtaining shape information of the target object to be measured; S602: Send the shape information, the number of transportations of the transport vehicle, and the transportation weight to the central server, so that the central server determines the number and type of transport vehicles required according to the shape information, the number of transportations, and the transportation weight.

6. The method according to any one of claims 1 to 4, characterized in that: The first camera device is a 3D camera, and the 3D camera is a camera installed on a sorting device or an unmanned aerial vehicle.

7. The method according to claim 6, characterized in that The sorting device or the unmanned aerial vehicle is also equipped with a near-infrared transmitting and receiving device.

8. The method according to claim 7, characterized in that The step S2 specifically includes: S201, obtaining image features of a target object to be measured in first image data; S202, obtaining first near-infrared spectrum data, wherein the first near-infrared spectrum data is data obtained after spectral analysis processing of a first near-infrared light signal, and the first near-infrared light signal is a near-infrared light signal reflected by the target object to be measured and received after the near-infrared transmitting and receiving device transmits near-infrared light to the target object to be measured; S203: After the image features and the first near-infrared spectrum data form a data input matrix, the data input matrix is ​​input into a deep learning training model for processing to obtain the garbage type to which the target object to be tested belongs.

9. An automatic classification system for construction waste, characterized in that: The system includes: A first camera device, used to photograph the target object to be measured; A weight sensor, used for detecting a first weight value of a target object to be measured placed on the transport trolley; A first processing system, comprising at least one processor, for executing the method steps according to any one of claims 1 to 8; The sorting device is controlled by the first processing system to perform a sorting operation on the target object to be detected.

10. The system according to claim 9, characterized in that The system also includes: A transport trolley, controlled by the first processing system, for placing the target object to be measured and transporting the target object to be measured to the storage area; and / or, The near-infrared transmitting and receiving device is used to transmit near-infrared light to the target object to be measured, receive the near-infrared light signal reflected by the target object to be measured, and send the received near-infrared light signal to the first processing system.

Images