CN110653169B - Garbage treatment method and device and terminal equipment - Google Patents
Garbage treatment method and device and terminal equipment Download PDFInfo
- Publication number
- CN110653169B CN110653169B CN201910721012.6A CN201910721012A CN110653169B CN 110653169 B CN110653169 B CN 110653169B CN 201910721012 A CN201910721012 A CN 201910721012A CN 110653169 B CN110653169 B CN 110653169B
- Authority
- CN
- China
- Prior art keywords
- garbage
- image data
- odor
- category
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0054—Sorting of waste or refuse
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0063—Using robots
Landscapes
- Image Analysis (AREA)
Abstract
The application is applicable to the technical field of software application, and provides a garbage treatment method, a garbage treatment device and terminal equipment, wherein the method comprises the following steps: acquiring image data obtained by collecting garbage through a camera and odor data obtained by collecting garbage through an odor sensor; processing the image data and the odor data to obtain size information, garbage categories and putrefaction types of all garbage; and determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, and controlling a mechanical arm to process the garbage according to the sorting scheme. The garbage collection and treatment device can solve the problems that in the prior art, garbage in the garbage treatment station is collected and treated in a manual sorting mode, the treatment efficiency is low, and adverse effects are easily caused to the bodies of workers.
Description
Technical Field
The application belongs to the technical field of software application, and particularly relates to a garbage treatment method and device and terminal equipment.
Background
Along with the development of science and technology, more and more garbage is generated in the production and living processes of people, and the treatment pressure of a garbage treatment station is higher and higher.
After entering the garbage disposal station, the garbage needs to be stored in a garbage storage box and then subjected to subsequent treatment, such as incineration, landfill, and the like. At present in the refuse treatment station, mainly accomodate the processing through the mode of manual sorting rubbish, the treatment effeciency is slow to operational environment is abominable, easily causes adverse effect to staff's health.
Disclosure of Invention
In view of this, embodiments of the present application provide a garbage disposal method, an apparatus, and a terminal device, so as to solve the problems that in the prior art, garbage in a garbage disposal station is stored and disposed in a manual sorting manner, the disposal efficiency is slow, and adverse effects are easily caused to the bodies of workers.
A first aspect of an embodiment of the present application provides a method for processing garbage, including:
acquiring image data obtained by collecting garbage through a camera and odor data obtained by collecting garbage through an odor sensor;
processing the image data and the odor data to obtain size information, garbage categories and putrefaction types of all garbage;
and determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, and controlling a mechanical arm to process the garbage according to the sorting scheme.
A second aspect of an embodiment of the present application provides a garbage disposal apparatus, including:
the data acquisition module is used for acquiring image data obtained by acquiring the garbage through the camera and odor data obtained by acquiring the garbage through the odor sensor;
the data processing module is used for processing the image data and the odor data to obtain the size information, the garbage category and the putrefaction type of each garbage;
and the garbage treatment module is used for determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, and controlling the mechanical arm to treat the garbage according to the sorting scheme.
A third aspect of the embodiments of the present application provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method when executing the computer program.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, implements the steps of the method as described above.
A fifth aspect of embodiments of the present application provides a computer program product, which, when run on a terminal device, causes the terminal device to perform the steps of the method as described above.
Compared with the prior art, the embodiment of the application has the advantages that:
in the refuse treatment scheme of this application, gather the image data and the smell data of rubbish thing through camera and smell sensor, handle image data and smell data, can obtain the size information of each rubbish thing, rubbish classification and corruption type, according to the size information of each rubbish thing, the letter sorting scheme of rubbish thing can be confirmed to rubbish classification and corruption type, handle rubbish thing according to letter sorting scheme control robotic arm, realize that the automatic sorting of rubbish thing is accomodate, need not artifical the participation, improve the treatment effeciency of rubbish thing, the mode of having solved among the prior art through artifical letter sorting is accomodate the processing to rubbish in the refuse treatment station, the treatment effeciency is slow, easily cause the problem of adverse effect to staff's health.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a system diagram of a garbage disposal system according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a garbage disposal method according to an embodiment of the present application;
FIG. 3 is a schematic view of a garbage disposal apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a terminal device provided in an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
In addition, in the description of the present application, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a schematic diagram of a system applicable to the embodiment of the present application. The system comprises: camera 101, arm 102, smell sensor, refuse handling installation 103. The camera 101, the mechanical arm 102 and the odor sensor communicate with the garbage disposal apparatus 103 through a wired and/or wireless network.
The system can be provided with one or more cameras 101, the cameras 101 can be digital cameras and/or analog cameras, the appearances of the cameras 101 can be gunplanes, dome cameras and the like, and specific setting schemes can be selected according to actual conditions.
The system can be provided with one or more odor sensors for collecting odor data of garbage, the odor sensors can be fixedly arranged (for example, one odor sensor can be arranged at the bottom of the garbage stacking platform at fixed intervals), or movably arranged (for example, a probe integrated with the odor sensor can be arranged on a mechanical arm), and the specific arrangement scheme can be selected according to actual conditions.
The mechanical arm 102 may be a multi-joint mechanical arm, a rectangular coordinate system mechanical arm, a spherical coordinate system mechanical arm, a polar coordinate mechanical arm, a cylindrical coordinate mechanical arm, or the like.
The garbage disposal device 103 is used for making a garbage sorting scheme according to image data and odor data obtained by collecting garbage through the camera 101 and the odor sensor, and controlling the mechanical arm 102 to dispose the garbage according to the garbage sorting scheme.
The following embodiments of the present application mainly take the system scenario shown in fig. 1 as an example, and describe a garbage disposal method, a garbage disposal apparatus, and a terminal device provided in the embodiments of the present application.
The first embodiment is as follows:
referring to fig. 2, a garbage disposal method according to a first embodiment of the present application is described below, where the garbage disposal method according to the first embodiment of the present application includes:
step S201, acquiring image data obtained by collecting garbage through a camera and odor data obtained by collecting garbage through an odor sensor;
in the daily life scenario, after collecting garbage from each garbage collection point in a city, a garbage truck needs to be transported to a garbage disposal station for disposal, and the garbage disposal station needs to store the garbage into a garbage storage box and then perform subsequent disposal on the garbage in one box, such as landfill, incineration power generation, and the like.
After garbage truck transported rubbish to rubbish collection depot, at present mainly accomodate rubbish to rubbish containing box through the mode of manual sorting, the treatment effeciency is low, and operational environment is abominable, easily causes adverse effect to staff's health.
In the garbage disposal method, the camera can be used for collecting the image data of the garbage, and the odor sensor is used for collecting the odor data of the garbage.
After the image data of the garbage is collected by the camera, due to the influence of factors such as illumination and imaging angles, the image data collected by the camera may have problems such as backlight, edge blurring and camera shaking. Therefore, in some possible implementation manners, the image data may be denoised to obtain the denoised image data, so as to improve the quality of the image data, and the specific denoising processing method includes:
the image data collected by the camera can be expressed as:
H(x)=F(x)e-rd(x)+A(1-e-rd(x))
wherein x is the space coordinate of each pixel point in the image data, H (x) is the image data collected by the camera, F (x) is the image data after de-noising, r represents the atmospheric scattering coefficient, d represents the depth of the scenery, A is the global atmospheric light constant, F (x) e-rd(x)Representing image data, A (1-e), acquired by a camera after the reflected light from the scene surface has been attenuated by scattering or the like as it propagates through the medium-rd(x)) Representing ambient light or an atmospheric light curtain that causes shifts in image color and brightness in the image data.
The ambient light is denoted as l (x):
L(x)=A(1-e-rd(x))
the image data collected by the camera can be expressed as:
transforming the above formula, the expression of the denoising process can be obtained as follows:
and denoising the image data acquired by the camera according to the formula, so that the interference of noise is reduced, the denoised image data is obtained, and the quality of the image data is improved.
Step S202, processing the image data and the odor data to obtain size information, garbage categories and corruption types of various garbage;
after the image data and the odor data are obtained, the image data and the odor data can be processed to obtain the size information, the garbage category and the putrefaction type of each garbage, and the size information, the garbage category and the putrefaction type are used as the formulation basis of the sorting scheme of the garbage.
In some possible implementation manners, a harris corner detection algorithm may be used to perform corner detection on the image data to obtain a corner detection result, and then size information of each junk in the image data is calculated according to the corner detection result.
In the image data, inside a homogeneous region (an image region corresponding to the same object), the gray scale changes in different directions are small, at the edge of the homogeneous region, only the gray scale changes in the directions perpendicular to the edge ridge are large, but at the corner point of the homogeneous region, the gray scale changes in multiple directions are large, so that the corner point detection can be performed on the image data accordingly.
The corner detection method comprises the following steps:
detecting first-order partial derivatives of an input image in an x-axis direction and a y-axis direction:
where I is an input image, in this embodiment, I represents image data for performing corner detection, IxAnd IyIs the first order partial derivative of I.
Smoothing the first-order partial derivatives of the input image by using an isotropic Gaussian kernel, and constructing an autocorrelation matrix M:
wherein G is an isotropic Gaussian kernel function,andis the first-order partial derivative of I after isotropic Gaussian kernel function smoothing treatment, sigma is a Gaussian smooth scale,for the convolution operator, M is the autocorrelation matrix.
Calculating the characteristic value of an autocorrelation matrix M, and calculating a corner response value R according to the characteristic value of the autocorrelation matrix M:
R=αβ-k(α+β)2
alpha and beta are characteristic values of the autocorrelation matrix M, k is an error corner response suppression constant, and the value of k is (0, 0.1) generally.
And determining the corner of the image data center according to the numerical value of R and a preset corner threshold value to obtain a corner detection result.
After the result of detecting the corner point is obtained, the side length and the included angle of each side of the junk can be calculated to obtain the geometric size information of the junk, for example, the coordinates of the corner point 1 of the junk 1 are (x1, y1), the coordinates of the corner point 2 are (x2, y2), and the side length L between the corner point 1 and the corner point 2 is:
because the garbage is not necessarily in a regular shape and can also be in a curve shape, the shape of the garbage can be determined according to the included angle between each adjacent side of the garbage, for example, if the included angle between each adjacent side of the garbage is less than or equal to 90 degrees, the garbage is represented to be in a regular shape, the garbage can be fitted into a cuboid, and the length, the width and the height of the garbage can be calculated through interpolation fitting; if the angle between each adjacent side of the garbage is mostly greater than 90 degrees, it means that the shape of the garbage may be a curved shape, for example, it may be a plastic bag filled with garbage, at this time, the garbage may be interpolated and fitted to a spherical shape, the radius of the garbage may be calculated, or the garbage may be fitted to an ellipsoid shape, and the major and minor diameters of the garbage may be calculated.
In some possible implementations, the image data may be input into a trained garbage recognition neural network model to obtain garbage categories of respective garbage.
The garbage recognition neural network model can be a convolutional neural network model, and the training process of the garbage recognition neural network model can be as follows:
1.1, shooting images of common garbage by using a camera to construct a sample set;
1.2, selecting a preset number of sample images from a sample set, wherein the sample images are respectively an image (recorded as class C0) of solid garbage (such as construction garbage), an image (recorded as class C1) of bagged garbage (such as plastic bagged garbage), an image (recorded as class C2) of bulk garbage (such as scattered pop-top cans, plastic bottles and the like), and respectively labeling class labels for the sample images;
1.3, taking a part (for example, 90%) of the selected sample image as a training sample image, and taking the rest (for example, 10%) of the selected sample image as a verification sample image;
1.4, training a training sample image after being randomly disturbed and inputting the training sample image into an untrained garbage recognition neural network model, wherein Keras can be selected as a framework building platform of the garbage recognition neural network model, a convolutional neural network model (CNN) is used as the garbage recognition neural network model, a sequential model for garbage recognition is created, a loss function can use a cross entropy (elementary _ entropy) loss function during training, an optimization function can use an adadelta function, the iteration round of training can be set according to the actual situation, for example, the iteration round can be set to 45 rounds, and GPU parallel operation can be used during training to accelerate the convergence speed of convolution calculation and the network model;
and 1.5, after the training is finished, using a verification set to verify the trained garbage recognition neural network model, if the accuracy is higher than a preset accuracy threshold, finishing the training, and storing the trained garbage recognition neural network model.
In some possible implementations, the convolutional neural network model may include: the multilayer structure comprises a first coiling layer, a first active layer, a second coiling layer, a second active layer, a first pooling layer, a third coiling layer, a third active layer, a second pooling layer, a flat (Flat) layer, a first full-connection layer, a fourth active layer, a Dropout layer, a second full-connection layer and a fifth active layer, wherein the first coiling layer, the first active layer, the second coiling layer, the second active layer, the first pooling layer, the third coiling layer, the third active layer, the second pooling layer, the flat (Flat) layer, the first full-connection layer, the fourth active layer, the Dropout layer, the second full-connection layer and the fifth active layer are sequentially connected.
Wherein the first convolution layer may comprise 4 convolution kernels, each convolution kernel having a size of 5 x 5; the activation function of the first activation layer is a Relu function; the second convolutional layer may be a layer containing 8 convolutional layers, each convolutional core having a size of 3 x 3; the activation function of the second activation layer is a Relu function; the first pooling layer is the maximum pooling layer, and down-sampling factors in the vertical and horizontal directions are respectively taken as (2, 2); the third convolutional layer may contain 16 convolutional kernels, each of which has a size of 3 x 3; the activation function of the third activation layer is a Relu function; the second pooling layer is the maximum pooling layer, and down-sampling factors in the vertical and horizontal directions are respectively (2, 2); the flat layer is used for converting the multi-dimensional input into a one-dimensional feature vector; the number of output nodes of the first full-connection layer is 128, and the initialization method is a normal method; the activation function of the fourth activation layer is a Relu function; the Dropout layer is used for randomly disconnecting the input neurons to prevent overfitting, and the connection proportion of the input neurons disconnected immediately can be set to be 0.3; the output node of the second fully-connected layer is 3; the activation function of the fifth activation layer is a softmax function, and the probabilities of the three category labels are output.
In some possible implementation manners, the odor data may be input into a preset odor model to obtain the putrefaction information of each trash, for example, odor data of a plurality of putrefactive odors may be set in the preset odor model, if the odor data acquired by the odor sensor matches the odor data of any putrefactive odor, the putrefaction information of the trash is determined to be putrefactive, and if the odor data acquired by the odor sensor does not match the odor data of any putrefactive odor, the putrefaction information of the trash is determined to be not putrefactive.
Step S203, determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, and controlling a mechanical arm to process the garbage according to the sorting scheme.
After the size information, the garbage category and the putrefaction information of each garbage are obtained, a sorting scheme of the garbage can be determined, and the mechanical arm is controlled to process the garbage according to the sorting scheme.
In some possible implementations, the priority of each trash item may be determined according to a preset priority policy, and the robot arm is controlled to sort the trash items into the trash receptacles in order of the priority from high to low.
The pre-set priority policy may be: the putrefactive information is preferentially processed into putrefactive garbage, so that the putrefactive garbage is prevented from accelerating the putrefactive garbage.
In order to ensure that the garbage storage box can contain more garbage, the priority of each garbage category is bulk garbage > bagged garbage > solid garbage, the compression space of the bulk garbage is the largest, and the compression space of the solid garbage is the smallest.
Among the garbage objects with the same corruption information and the same category, the priority can be determined according to the size information, the garbage with small volume can be treated preferentially, and the storage capacity of the garbage storage box can be improved.
After the size information, the garbage category and the putrefaction information of each garbage are obtained, the priority of each garbage can be determined according to a preset priority policy, so that the sorting scheme of the garbage can be determined, for example, if there are five garbage, the putrefaction information of the garbage 1 and the garbage 3 is putrefactive, and the putrefaction information of the garbage 2, 4 and 5 is putrefaction-free, the priority of the garbage 1 and 3 is higher than that of the garbage 2, 4 and 5; the garbage category of the garbage 1 is bagged garbage, and the garbage category of the garbage 3 is bulk garbage, so that the priority of the garbage 3 is higher than that of the garbage 1; the garbage category of the garbage 2 is solid garbage, the garbage categories of the garbage 4 and 5 are bagged garbage, and the priority of the garbage 4 and 5 is higher than that of the garbage 2; the volume of the garbage 4 is larger than that of the garbage 5, so that the priority of the garbage 5 is higher than that of the garbage 4; according to the above contents, if the priority of each garbage is sequentially garbage 3, garbage 1, garbage 5, garbage 4 and garbage 2, the sorting scheme is to control the mechanical arm to sort the garbage into the garbage storage boxes according to the priority from high to low.
In other possible implementation manners, the preset garbage throwing strategy requires that garbage of different garbage types is placed in different garbage storage boxes, a sorting scheme of the garbage can be determined according to the size information, the garbage category and the putrefaction information of each garbage and the preset garbage throwing strategy, and the mechanical arm is controlled to process the garbage according to the sorting scheme of the garbage.
In some possible implementations, the camera may be used to capture image data of the trash receptacle, process the image data of the trash receptacle, calculate the remaining storage space of the trash receptacle, stop the movement of the robotic arm if the remaining storage space of the trash receptacle is smaller than the volume of the next trash to be stored, replace the trash receptacle, and then start the robotic arm to continue the trash storage process.
In some possible implementations, the system further includes a garbage compressing device, where the garbage compressing device is configured to compress the volume of the garbage in the garbage storage box, and the garbage compressing device may be controlled to compress the garbage in the garbage storage box every preset time (e.g., every 30 seconds) or every preset number of the garbage (e.g., every 10 garbage) to make the garbage storage box vacate more remaining storage space and store more garbage.
In the garbage disposal method provided by the embodiment, the image data and the odor data of the garbage are collected through the camera and the odor sensor, the image data and the odor data are processed, the size information, the garbage category and the putrefaction type of each garbage can be obtained, the sorting scheme of the garbage can be determined according to the size information, the garbage category and the putrefaction type of each garbage, the garbage is processed by controlling the mechanical arm according to the sorting scheme, the garbage is automatically sorted and stored without manual participation, the garbage disposal efficiency is improved, the problem that in the prior art, the garbage in a garbage disposal station is stored and processed in a manual sorting mode is solved, the disposal efficiency is low, and adverse effects are easily caused to the bodies of workers is solved.
When the image data and the odor data are processed, a harris corner detection algorithm can be used for detecting the corner detection result of each garbage in the image data, and the size information of the garbage is calculated according to the corner detection result; the trained garbage recognition neural network model can be used for recognizing the image data to obtain the garbage category of each garbage; the spoilage information of each trash can be identified using a preset odor model.
After the size information, the garbage category and the putrefaction type of each garbage are obtained, the priority of each garbage can be determined according to a preset priority strategy, and the mechanical arm is controlled to sort the garbage into the garbage containing boxes from high to low according to the priority, so that the automatic containing of the garbage is realized.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Example two:
in the second embodiment of the present application, a garbage disposal apparatus is provided, and for convenience of description, only a part related to the present application is shown, as shown in fig. 3, the garbage disposal apparatus includes: a processor, wherein the processor is configured to execute the following program modules stored in the memory:
the data acquisition module 301 is used for acquiring image data obtained by acquiring trash with a camera and odor data obtained by acquiring trash with an odor sensor;
a data processing module 302, configured to process the image data and the odor data to obtain size information, a garbage category, and a corruption type of each garbage;
and the garbage disposal module 303 is configured to determine a sorting scheme for the garbage according to the size information, the garbage category, and the spoilage information of each garbage, and control the mechanical arm to dispose the garbage according to the sorting scheme.
Further, the data processing module 302 includes:
the corner detection submodule is used for carrying out corner detection on the image data by using a harris corner detection algorithm to obtain a corner detection result;
and the size information submodule is used for calculating the size information of each junk in the image data according to the corner detection result.
Further, the data processing module 302 includes:
and the garbage classification submodule is used for inputting the image data into the trained garbage recognition neural network model to obtain the garbage classification of each garbage.
Further, the data processing module 302 includes:
and the corruption type submodule is used for inputting the odor data into a preset odor model to obtain the corruption types of the garbage.
Further, the apparatus further comprises:
and the image denoising module is used for denoising the image data to obtain denoised image data.
Further, the garbage disposal module 303 includes:
the priority submodule is used for determining the priority of each junk according to the size information, the junk category, the corruption information and a preset priority strategy of each junk;
and the sequential sorting submodule is used for controlling the mechanical arm to sort the garbage to the garbage containing boxes according to the sequence from high to low in priority.
Further, the garbage recognition neural network model is specifically a convolutional neural network model.
It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.
Example three:
fig. 4 is a schematic diagram of a terminal device provided in the third embodiment of the present application. As shown in fig. 4, the terminal device 4 of this embodiment includes: a processor 40, a memory 41 and a computer program 42 stored in said memory 41 and executable on said processor 40. The processor 40, when executing the computer program 42, implements the steps in the above-mentioned garbage disposal method embodiment, such as the steps S201 to S203 shown in fig. 2. Alternatively, the processor 40, when executing the computer program 42, implements the functions of each module/unit in each device embodiment described above, for example, the functions of the modules 301 to 303 shown in fig. 3.
Illustratively, the computer program 42 may be partitioned into one or more modules/units that are stored in the memory 41 and executed by the processor 40 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 42 in the terminal device 4. For example, the computer program 42 may be divided into a data collection module, a data processing module, and a garbage processing module, and each module has the following specific functions:
the data acquisition module is used for acquiring image data obtained by acquiring the garbage through the camera and odor data obtained by acquiring the garbage through the odor sensor;
the data processing module is used for processing the image data and the odor data to obtain the size information, the garbage category and the putrefaction type of each garbage;
and the garbage treatment module is used for determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, and controlling the mechanical arm to treat the garbage according to the sorting scheme.
The terminal device 4 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 40, a memory 41. Those skilled in the art will appreciate that fig. 4 is merely an example of a terminal device 4 and does not constitute a limitation of terminal device 4 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the terminal device may also include input-output devices, network access devices, buses, etc.
The Processor 40 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 41 may be an internal storage unit of the terminal device 4, such as a hard disk or a memory of the terminal device 4. The memory 41 may also be an external storage device of the terminal device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal device 4. The memory 41 is used for storing the computer program and other programs and data required by the terminal device. The memory 41 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (9)
1. A method of waste disposal, comprising:
acquiring image data obtained by collecting garbage through a camera and odor data obtained by collecting garbage through an odor sensor;
denoising the image data to obtain denoised image data; the denoising processing expression is as follows:wherein, f (x) is the image data after de-noising, h (x) is the image data collected by the camera, l (x) is the ambient light or the atmospheric light curtain, and l (x) is a (1-e)-rd(x)) R represents the atmospheric scattering coefficient, d represents the scene depth, and a is the global atmospheric light constant;
processing the image data and the odor data to obtain size information, garbage categories and putrefaction types of all garbage;
determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, and controlling a mechanical arm to automatically sort the garbage according to the sorting scheme;
the step of determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, wherein the step of controlling a mechanical arm to automatically sort the garbage according to the sorting scheme comprises the following steps:
determining the priority of each junk according to the size information, the junk category, the corruption information and a preset priority strategy of each junk; the preset priority policy comprises: the method comprises the steps of preferentially treating garbage with putrefactive information, wherein the priority of each garbage category is bulk garbage, bagged garbage and solid garbage from high to low in the garbage with the same putrefactive information, and the priority is determined according to size information in the garbage with the same putrefactive information and the same category, so that the garbage with small volume is preferentially treated;
controlling the mechanical arm to sort the garbage into the garbage containing boxes according to the sequence of the priorities from high to low;
the step of processing the image data and the odor data to obtain the size information, the garbage category and the putrefaction type of each garbage comprises the following steps:
performing corner detection on the image data by using a harris corner detection algorithm to obtain a corner detection result;
and calculating the side length and the included angle of each side of each garbage object in the image data according to the angular point detection result, fitting the garbage objects into a cuboid if the included angle of each adjacent side of the garbage objects is less than or equal to 90 degrees, calculating the length, the width and the height of the garbage objects through interpolation fitting, interpolating and fitting the garbage objects into a spherical shape if most of the included angle of each adjacent side of the garbage objects is greater than 90 degrees, calculating the radius of the garbage objects, or fitting the garbage objects into an ellipsoidal shape, and calculating the long diameter and the short diameter of the garbage objects.
2. A method of waste management as claimed in claim 1 wherein said processing said image data and said odor data to obtain size information, waste category and spoilage type of each waste item comprises:
and inputting the image data into the trained garbage recognition neural network model to obtain the garbage category of each garbage.
3. A method of waste management as claimed in claim 1 wherein said processing said image data and said odor data to obtain size information, waste category and spoilage type of each waste item comprises:
and inputting the odor data into a preset odor model to obtain the putrefaction type of each garbage.
4. The garbage disposal method of claim 2, wherein the garbage recognition neural network model is specifically a convolutional neural network model.
5. A waste disposal device, comprising:
the data acquisition module is used for acquiring image data obtained by acquiring the garbage through the camera and odor data obtained by acquiring the garbage through the odor sensor;
the image denoising module is used for denoising the image data to obtain denoised image data; the denoising processing expression is as follows:wherein, f (x) is the image data after de-noising, h (x) is the image data collected by the camera, l (x) is the ambient light or the atmospheric light curtain, and l (x) is a (1-e)-rd(x)) R represents the atmospheric scattering coefficient, d represents the scene depth, and a is the global atmospheric light constant;
the data processing module is used for processing the image data and the odor data to obtain the size information, the garbage category and the putrefaction type of each garbage;
the garbage treatment module is used for determining a sorting scheme of the garbage according to the size information, the garbage category and the putrefaction information of each garbage, and controlling the mechanical arm to automatically sort the garbage according to the sorting scheme;
the garbage disposal module comprises:
the priority submodule is used for determining the priority of each junk according to the size information, the junk category, the corruption information and a preset priority strategy of each junk; the preset priority policy comprises: the method comprises the steps of preferentially treating garbage with putrefactive information, wherein the priority of each garbage category is bulk garbage, bagged garbage and solid garbage from high to low in the garbage with the same putrefactive information, and the priority is determined according to size information in the garbage with the same putrefactive information and the same category, so that the garbage with small volume is preferentially treated;
the sequential sorting submodule is used for controlling the mechanical arm to sort the garbage into the garbage containing boxes from high to low in priority;
the data processing module comprises:
the corner detection submodule is used for carrying out corner detection on the image data by using a harris corner detection algorithm to obtain a corner detection result;
and the size information submodule is used for calculating the side length and the included angle of each side of each rubbish object in the image data according to the angular point detection result, fitting the rubbish objects into a cuboid if the included angle of each adjacent side of the rubbish objects is smaller than or equal to 90 degrees, calculating the length, the width and the height of the rubbish objects through interpolation fitting, and interpolating and fitting the rubbish objects into a sphere if most of the included angle of each adjacent side of the rubbish objects is larger than 90 degrees, calculating the radius of the rubbish objects, or fitting the rubbish objects into an ellipsoid, and calculating the long diameter and the short diameter of the rubbish objects.
6. The garbage disposal device of claim 5, wherein the data processing module comprises:
and the garbage classification submodule is used for inputting the image data into the trained garbage recognition neural network model to obtain the garbage classification of each garbage.
7. The garbage disposal device of claim 5, wherein the data processing module comprises:
and the corruption type submodule is used for inputting the odor data into a preset odor model to obtain the corruption types of the garbage.
8. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 4 when executing the computer program.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910721012.6A CN110653169B (en) | 2019-08-06 | 2019-08-06 | Garbage treatment method and device and terminal equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910721012.6A CN110653169B (en) | 2019-08-06 | 2019-08-06 | Garbage treatment method and device and terminal equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110653169A CN110653169A (en) | 2020-01-07 |
CN110653169B true CN110653169B (en) | 2022-01-14 |
Family
ID=69036423
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910721012.6A Active CN110653169B (en) | 2019-08-06 | 2019-08-06 | Garbage treatment method and device and terminal equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110653169B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113510132A (en) * | 2020-04-10 | 2021-10-19 | 广东鸿山环境集团有限公司 | Intelligent garbage treatment and classification system |
CN113788245A (en) * | 2020-06-17 | 2021-12-14 | 北京京东尚科信息技术有限公司 | Package recovery device and package recovery method |
CN112849815A (en) * | 2020-12-30 | 2021-05-28 | 深兰人工智能芯片研究院(江苏)有限公司 | Control method and device of manipulator, intelligent garbage can and storage medium |
CN113932393B (en) * | 2021-10-12 | 2023-03-21 | 青岛海尔空调器有限总公司 | Method and device for controlling air conditioner, air conditioner and storage medium |
CN114089656B (en) * | 2021-10-27 | 2023-08-08 | 广州大学 | Ocean garbage recycling planning method and system based on machine vision and reinforcement learning |
CN114289343A (en) * | 2021-12-29 | 2022-04-08 | 张祥森 | Garbage classification processing method and system |
CN115185187B (en) * | 2022-08-16 | 2023-06-20 | 哈尔滨工业大学 | Mechanical arm limited time tracking control method based on type-II ellipsoidal fuzzy neural network |
CN115545441A (en) * | 2022-09-23 | 2022-12-30 | 中环洁集团股份有限公司 | Road garbage detection method, system, terminal and storage medium |
CN116720999B (en) * | 2023-08-07 | 2023-11-07 | 戈尔电梯(天津)有限公司 | Control method and device for intelligent community, electronic equipment and storage medium |
CN117540893A (en) * | 2024-01-10 | 2024-02-09 | 江西众加利高科技股份有限公司 | Intelligent processing method and device for garbage point data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011050949A (en) * | 2009-08-04 | 2011-03-17 | Nippon Steel Engineering Co Ltd | Method for collecting and sorting garbage, device for collecting and sorting garbage |
CN108971190A (en) * | 2018-06-25 | 2018-12-11 | 大连大学 | A kind of separating domestic garbage method based on machine vision |
CN109165811A (en) * | 2018-07-23 | 2019-01-08 | 星络科技有限公司 | Community's waste disposal method, system, terminal and computer readable storage medium |
CN109201514A (en) * | 2017-06-30 | 2019-01-15 | 京东方科技集团股份有限公司 | Waste sorting recycle method, garbage classification device and classified-refuse recovery system |
CN109201518A (en) * | 2018-08-15 | 2019-01-15 | 深圳市烽焌信息科技有限公司 | A kind of equipment and storage medium of periodic cleaning rubbish |
CN109261539A (en) * | 2018-08-17 | 2019-01-25 | 湖北文理学院 | A kind of garbage sorting system and method for view-based access control model identification and convolutional neural networks |
CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103552788B (en) * | 2013-11-07 | 2016-03-09 | 邱泽国 | Concentrating type rubbish identifies assembly and automatic sorting garbage bin thereof automatically |
-
2019
- 2019-08-06 CN CN201910721012.6A patent/CN110653169B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011050949A (en) * | 2009-08-04 | 2011-03-17 | Nippon Steel Engineering Co Ltd | Method for collecting and sorting garbage, device for collecting and sorting garbage |
CN109201514A (en) * | 2017-06-30 | 2019-01-15 | 京东方科技集团股份有限公司 | Waste sorting recycle method, garbage classification device and classified-refuse recovery system |
CN108971190A (en) * | 2018-06-25 | 2018-12-11 | 大连大学 | A kind of separating domestic garbage method based on machine vision |
CN109165811A (en) * | 2018-07-23 | 2019-01-08 | 星络科技有限公司 | Community's waste disposal method, system, terminal and computer readable storage medium |
CN109201518A (en) * | 2018-08-15 | 2019-01-15 | 深圳市烽焌信息科技有限公司 | A kind of equipment and storage medium of periodic cleaning rubbish |
CN109261539A (en) * | 2018-08-17 | 2019-01-25 | 湖北文理学院 | A kind of garbage sorting system and method for view-based access control model identification and convolutional neural networks |
CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN110653169A (en) | 2020-01-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110653169B (en) | Garbage treatment method and device and terminal equipment | |
WO2021022475A1 (en) | Refuse disposal method and apparatus, and terminal device | |
CN110321910B (en) | Point cloud-oriented feature extraction method, device and equipment | |
Muja et al. | Rein-a fast, robust, scalable recognition infrastructure | |
CN107292886B (en) | Target object intrusion detection method and device based on grid division and neural network | |
CN110163813A (en) | A kind of image rain removing method, device, readable storage medium storing program for executing and terminal device | |
CN111860060A (en) | Target detection method and device, terminal equipment and computer readable storage medium | |
CN110148117B (en) | Power equipment defect identification method and device based on power image and storage medium | |
CN111738403A (en) | Neural network optimization method and related equipment | |
KR20180123810A (en) | Data enrichment processing technology and method for decoding x-ray medical image | |
CN112580662A (en) | Method and system for recognizing fish body direction based on image features | |
CN113159064A (en) | Method and device for detecting electronic element target based on simplified YOLOv3 circuit board | |
CN110110829A (en) | A kind of two dimensional code processing method and processing device | |
CN113313688B (en) | Energetic material medicine barrel identification method and system, electronic equipment and storage medium | |
CN111353577B (en) | Multi-task-based cascade combination model optimization method and device and terminal equipment | |
CN113435466A (en) | Method, device, medium and terminal for detecting elevator door position and switch state | |
CN115760800A (en) | Aluminum product defect classification method and device based on Hash algorithm and Hash-AlexNet neural network | |
CN108665062B (en) | Neural network processing system for reducing IO (input/output) overhead based on wavelet transformation | |
CN116229262A (en) | Modeling method and device for building information model | |
CN112804446B (en) | Big data processing method and device based on cloud platform big data | |
CN113496139B (en) | Method and apparatus for detecting objects from images and training object detection models | |
US11645519B2 (en) | Filtering data in orthogonal directions through a convolutional neural network | |
CN113256556A (en) | Image selection method and device | |
Matsui et al. | Enhanced YOLO using Attention for Apple grading | |
CN116128734B (en) | Image stitching method, device, equipment and medium based on deep learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |