CN112916416A - Building rubbish letter sorting system - Google Patents
Building rubbish letter sorting system Download PDFInfo
- Publication number
- CN112916416A CN112916416A CN202110288473.6A CN202110288473A CN112916416A CN 112916416 A CN112916416 A CN 112916416A CN 202110288473 A CN202110288473 A CN 202110288473A CN 112916416 A CN112916416 A CN 112916416A
- Authority
- CN
- China
- Prior art keywords
- construction waste
- data
- sorting system
- construction
- waste
- 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.)
- Pending
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
- B07C5/04—Sorting according to size
- B07C5/10—Sorting according to size measured by light-responsive means
-
- 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
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- 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
- B07C5/16—Sorting according to weight
Landscapes
- Processing Of Solid Wastes (AREA)
Abstract
Aiming at the defects of the prior art, the invention designs a construction waste sorting system, which relates to the technical field of binocular stereo vision, machine learning and density measurement, and adopts a method of combining visual identification and density measurement, utilizes the visual identification technology to obtain the type information of the construction waste, then utilizes the binocular stereo vision technology to obtain the volume data of the construction waste and combine the waste quality data obtained by a quality perception module to calculate the average density data of the waste, compares the average density data with the preset density of common construction materials to finally obtain the variety data of the construction waste, and sorts various types of construction waste by utilizing the motion of a mechanical arm, thereby realizing the automation and the intellectualization of the sorting of the construction waste, improving the sorting efficiency, saving manpower and material resources, and simultaneously adopting the method of combining machine vision and density measurement, the building rubbish identification model is simpler to establish, meanwhile, the sorting basis of the building rubbish is more reasonable, the result is more reliable, and the building rubbish identification model is beneficial to further recovery processing and recycling.
Description
Technical Field
The invention relates to the technical field of binocular stereoscopic vision, machine learning and density measurement, in particular to a design of a construction waste sorting system.
Background
Building rubbish that produces when building construction or demolition, if not in time clearance, not only can cause harmful effects to natural environment, also can lead to the waste of resource, consequently need in time clear up building rubbish, nevertheless because at construction site, building rubbish's quantity is a lot of, when the manual work is cleared up building rubbish, can consume a large amount of time energy, is unfavorable for the progress of engineering, also probably has the condition such as the clearance is incomplete, consequently has the improvement space. Moreover, because the variety of the materials of the construction waste is various, and the same type of materials can derive various different construction materials, such as reinforced concrete bricks and iron-based concrete bricks, common glass and organic glass, polystyrene plastics and polyvinyl chloride plastics, and the like, the difference of the materials on the appearance material is not large, and the density of the materials has obvious difference, which lays a theoretical foundation for the design of the invention.
In the prior art, a scheme of identifying construction waste on a construction site by using a construction sorting robot and automatically planning an action route to pick up the construction waste exists, but the scheme has the problems of huge data set, high difficulty in identifying model training, repeated back and forth movement of the robot and low working efficiency of the robot, so that the construction waste is transported by adopting a mode of combining machine vision identification and density measurement and a conveyor belt mode, the difficulty in establishing a vision identification model can be reduced, the construction waste can be more reasonably classified, the sorting efficiency is improved, and the subsequent recovery treatment and reutilization are facilitated.
Disclosure of Invention
The invention aims to provide a construction waste sorting system which can work on a construction site and sort construction waste on the construction site, provides a simpler and more reasonable sorting scheme and solves the defects of the prior technical scheme to a certain extent.
The above object of the present invention is achieved by the following technical solutions:
the utility model provides a building rubbish letter sorting system, building rubbish letter sorting system includes the letter sorting system body, the letter sorting system body includes following module:
mechanical arm: for completing the actions of picking up and sorting the construction waste;
a driving module: for driving the movement of the moving parts;
a collecting device: the sorting box is used for storing various sorted building wastes, and the main body of the sorting box is a sorting box;
an image acquisition module: the construction waste sorting system is used for collecting image data of the construction waste in real time, and the main body of the construction waste sorting system is a binocular camera;
a quality perception module: the construction waste sorting system is used for sensing the quality data of the construction waste, and the main body of the construction waste sorting system is a force sensor;
a transport module: the conveying belt is used for conveying the unsorted construction waste and the sorted construction waste, and the main body of the conveying belt is a conveying belt;
a control module: and automatically identifying the position information of the construction waste in the image data, controlling a mechanical arm to grab the construction waste, comprehensively judging the type information of the construction waste according to the visual identification result and the calculated density data of the construction waste, and sorting the construction waste to a preset position in the collection module.
By adopting the technical scheme, the transport module conveys the unsorted construction waste into the detectable range of the sorting system, the control module on the sorting system body can analyze and process the image data obtained by the image acquisition module to obtain the position information of the construction waste, thereby controlling the mechanical arm to pick up the construction waste, then, the volume data of the construction waste calculated according to the image data obtained by the image acquisition module and the quality data obtained by the quality perception module calculate the density data of the picked construction waste and combine the visually recognized type information of the construction waste to ensure that the material type of the construction waste is accurate to a certain type, and in view of the above, the construction waste is more reasonably classified and stored, and the construction waste in the collecting device reaches a certain amount, so that the sorted construction waste is transported away through the transportation module. According to the technical scheme, on one hand, the sorting automation of the construction waste can be realized, and the manpower and material resources are saved; on the other hand, the construction waste can be classified more reasonably by combining machine vision and density measurement, and the subsequent further recycling treatment of the construction waste is facilitated.
The invention is further configured to: the control module realizes the sorting function of the construction waste by adopting the following method steps:
s1: if the image data is acquired, identifying the construction waste, the type information of the construction waste and the position of the construction waste from the image data;
s2: controlling the mechanical arm to pick up the construction waste, and meanwhile, acquiring quality data of the construction waste through a quality sensing module positioned on the mechanical arm;
s3: measuring the volume of the construction waste by a binocular vision technology, combining the previously obtained quality data to obtain the density data of the construction waste, and combining the previously obtained construction waste type information to judge the type information of the construction waste;
s4: and controlling the mechanical arm to place the picked construction waste at a corresponding position of the collecting device according to the type information of the construction waste.
The invention is further configured to: step S1 includes:
s11: processing the image data by using a building rubbish recognition model obtained by pre-training;
s12: and acquiring the type information and the position information of the construction waste according to the processing result.
By adopting the technical scheme, the construction waste recognition model is trained in advance, and the type information and the position information of the construction waste can be recognized from the image data after the control module acquires the image data, so that the control module can control the picking action of the mechanical arm according to the position information of the construction waste. The building rubbish identification model only needs to identify the type of the building rubbish, the required data set is relatively small, and the model building difficulty is low.
The invention is further configured to: step S2 includes:
s21: according to the position information of the construction waste, sending a corresponding picking action command to a mechanical arm to pick up the construction waste;
s22: and acquiring the quality data of the picked construction waste through a force sensor arranged on the mechanical arm.
By adopting the technical scheme, the building rubbish picking function is realized, the quality information of the building rubbish is obtained, and a foundation is laid for subsequent building rubbish type judgment.
The invention is further configured to: step S3 includes:
s31: acquiring the image of the construction waste by using a binocular camera, and solving volume data of the construction waste;
s32: calculating the average density of the construction waste according to the obtained data of the mass and the volume of the construction waste;
s33: and comparing the average density of the construction waste with the density of each material according to the preset density of the common construction waste material and each material and the previously obtained construction waste type information, and finally obtaining the category information of the construction waste.
By adopting the technical scheme, the volume data of the construction waste is obtained by adopting a binocular stereoscopic vision technology, the construction waste quality data obtained before are combined, the average density of the construction waste is further calculated, the construction waste type information is combined, the average density of the construction waste is compared with the density of each material under the type, and the construction waste is classified according to the average density and the density of each material under the type, so that the construction waste can be more reasonably classified, and the subsequent recycling treatment and reutilization are facilitated.
The invention is further configured to: step S31 includes:
s311: obtaining left and right image difference information by adopting a semi-global stereo matching (SGM) method;
s312: reconstructing three-dimensional information of all points in the camera view by using the parallax information;
s313: the construction waste is divided into a plurality of parts, the volume of each part is obtained by utilizing the thought of integral, and finally the total volume of the construction waste is obtained.
By adopting the technical scheme, the images of the construction waste are collected by using the binocular camera, the parallax information of the left and right images is obtained through stereo matching, the three-dimensional information of all points in the field of view of the camera is reconstructed by using the parallax information, the construction waste is divided into a plurality of parts, the volume of each part is obtained by using the thought of integral, and finally the total volume of the construction waste is obtained.
The invention is further configured to: step S4 includes:
s41: dividing corresponding construction waste storage areas in the collection device in advance according to the quantity of the category information, and marking each construction waste storage area according to the category information;
s42: when the mechanical arm picks up the construction waste, the construction waste is stored into the construction waste storage area corresponding to a collecting device according to the type information corresponding to the construction waste.
Through adopting above-mentioned technical scheme, set up the storage area who corresponds with each kind of information in collection device in advance, when can sorting the building rubbish of building site, the building rubbish that will pick up and sort is placed in the region that collection device corresponds, helps subsequent recovery and recycle.
Preferably, the control module further comprises a control system consisting of the following modules:
the image identification control module is used for acquiring the image data;
the quality perception control module is used for acquiring the quality data;
the motion control module is used for generating and sending a motion command to the driving module according to the image data and the type information, so that the driving module drives the sorting mechanical arm to finish picking and sorting actions according to the motion command;
and the collection module is used for dividing the building garbage storage areas and marking the position of each building garbage storage area.
By adopting the technical scheme, the control module combines the collection of data, the motion control of the mechanical arm, the identification of images and the judgment of the construction waste type information, so that the mechanical arm and the construction waste type information are integrated, and the efficiency and the stability of a control system are improved.
In conclusion, the beneficial technical effects of the invention are as follows:
from the discernment of building rubbish to the letter sorting of building rubbish, the overall process realizes automation and intellectuality, has improved the letter sorting efficiency of building rubbish greatly, has also saved manpower and materials simultaneously.
The method combining machine vision and density measurement is adopted, firstly, the type information and the position of the construction waste are identified through the acquired image and the construction waste identification model acquired through pre-training, then the average density of the construction waste is calculated according to the collected construction waste quality data and volume data, the average density of the construction waste is compared with the density of each material under the type by combining the construction waste type information, and the information is used as the basis for judging the type information of the construction waste, so that the problem that the construction waste classification is wrong due to the fact that the visual identification result is deviated because the construction waste materials are various and the appearance difference of the construction waste made of the same type of materials is not large is solved, the difficulty in building the construction waste identification model is reduced, meanwhile, the sorting basis of the construction waste is more reasonable, and the result is more reliable, beneficial to further recovery processing and reuse.
Drawings
Fig. 1 is a flowchart of a method for identifying construction waste and construction waste type information performed by a control module according to a second embodiment of the present invention;
fig. 2 is a flowchart of the implementation of step S1 in the method for identifying construction waste and the type information of construction waste performed by the control module according to the second embodiment of the present invention;
fig. 3 is a flowchart of the implementation of step S2 in the method for identifying construction waste and the type information of construction waste performed by the control module according to the second embodiment of the present invention;
fig. 4 is a flowchart of the implementation of step S3 in the method for identifying construction waste and the type information of construction waste performed by the control module according to the second embodiment of the present invention;
fig. 5 is a flowchart of the implementation of step S31 in the method for identifying construction waste and the type information of construction waste performed by the control module according to the second embodiment of the present invention;
fig. 6 is a flowchart of the implementation of step S4 in the method for identifying construction waste and the type information of construction waste performed by the control module according to the second embodiment of the present invention;
FIG. 7 is a functional block diagram of the modules of the control system in the third embodiment of the present invention;
table 1 shows the type information, the category information, and the density of the common building materials preset in the method for identifying the construction waste and the construction waste category information by the control module in the second embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The first embodiment is as follows:
the invention discloses a construction waste sorting system, which comprises: the sorting mechanical arm body comprises a mechanical arm, a driving module, an image acquisition module, a quality perception module, a collecting device, a transportation module and a control module.
The mechanical arm is controlled by the control module and can pick up and sort the construction waste in the construction site according to the instruction sent by the control module.
The driving module is controlled by the control module and can drive the mechanical arm to complete corresponding actions according to instructions sent by the control module.
The image acquisition module may send the acquired image data to the control module, and in this embodiment, the main body of the image acquisition module is a binocular camera. The image acquisition module can acquire image data of a construction site (containing construction waste to be sorted) in real time and send the image data to the control module for processing and calculation.
The quality perception module can send the acquired construction waste quality data to the control module, in this embodiment, the main body of the quality perception module is a force sensor, and the quality perception module can acquire the quality data of construction waste picked up by the current mechanical arm and send the data to the control module for processing and calculation.
The collecting device is used for storing construction waste picked by the mechanical arm, wherein the collecting device is one of areas of a construction site in the movable range of the mechanical arm, and the position of the area on the construction site can be known by the sorting mechanical arm body.
The transportation module is used for transporting unsorted construction waste to a detectable range of the sorting system, transporting the sorted construction waste away, and carrying out next-step recycling treatment.
Example two:
in the first embodiment, the control module identifies the construction waste and judges the type information of the construction waste by adopting the following method steps to finish the sorting and collection of the construction waste:
s1: if the image data is acquired, identifying the construction waste, the type information of the construction waste and the position of the construction waste from the image data;
in the present embodiment, the image data refers to data of an image of a construction site collected in real time. Construction waste refers to waste generated when a building is constructed or dismantled in a construction site, wherein the construction waste includes, but is not limited to, screws, stones, wood boards, other waste and the like. The type information of the construction waste refers to the type of the construction waste material, as shown in table one.
Specifically, a model capable of identifying construction waste and type information corresponding to the construction waste from an image is provided in the control module in advance, and after image data of a construction site photographed by the image acquisition module is acquired, the position of the construction waste at the construction site and the type information corresponding to each identified construction waste are acquired in the graphic data using the model.
S2: controlling the mechanical arm to pick up the construction waste, and meanwhile, acquiring quality data of the construction waste through a quality sensing module positioned on the mechanical arm;
in this embodiment, the instruction for controlling the robot arm is sent by the control module, and the specific pickup instruction is an operation instruction for controlling each joint of the robot arm to rotate so that the robot arm approaches the construction waste and for clamping, picking and sorting the robot arm. The quality data refers to the mass of the construction waste picked up at present, and is mainly that the acting force data on the mechanical arm is obtained through the force sensor and is sent to the control module, and the mass of the construction waste is obtained through a series of calculations.
S3: measuring the volume of the construction waste by a binocular vision technology, combining the previously obtained quality data to obtain the density data of the construction waste, and combining the previously obtained construction waste type information to judge the type information of the construction waste;
in this embodiment, the volume of the construction waste refers to the total volume of the construction waste picked up by the mechanical arm at this time; the density data refers to the average density of the construction waste; the type information of construction waste refers to the type of construction material to which the material constituting the construction waste belongs.
S31: acquiring the image of the construction waste by using a binocular camera, and solving volume data of the construction waste;
specifically, step S31 is to obtain the volume data of the construction waste by the following method steps:
s311: obtaining left and right image difference information by adopting a semi-global stereo matching (SGM) method;
specifically, in the SGM algorithm, a winner-take-all algorithm is used for the parallax calculation, and each pixel selects a parallax value corresponding to the minimum aggregate cost value as the final parallax. After obtaining the disparity map, a further disparity optimization process is needed, and the invention adopts a left-right consistency method (L-R-Check) which is based on the uniqueness constraint of the disparity, namely that each pixel has at most one correct disparity, and simultaneously, a small communication area is removed and a uniqueness detection method is combined to remove the wrong disparity, thereby obtaining the disparity map and the left-right image difference information.
S312: reconstructing three-dimensional information of all points in the camera view by using the parallax information;
specifically, by using the parallax principle and the similar triangle principle, each pixel point on the parallax map is traversed sequentially, the Z coordinate of each pixel point under the world coordinate system can be obtained, and then the complete three-dimensional coordinate of each pixel point under the world coordinate system can be obtained, namely the three-dimensional information of all the points is obtained.
S313: dividing the construction waste into a plurality of parts, and calculating the volume of each part by using the thought of integral, and finally calculating the total volume of the construction waste;
specifically, the lower left corner of the screen is used as the origin of the world coordinate system, and a new three-dimensional coordinate, i.e., a depth map, of each point in the world coordinate system is obtained. Setting a sliding window with the side length n x n, enabling the sliding window to sequentially traverse the whole depth map, respectively calculating the areas of the quadrangles corresponding to the four vertexes of the quadrangle surrounded by the sliding window by using the coordinates of the four vertexes of the quadrangle, taking the average value of the three-dimensional coordinate Z values corresponding to the four vertexes of the quadrangle as the height of the corresponding quadrangle, thus obtaining the volume of each quadrangular prism, and accumulating the quadrangular prisms to obtain the total volume of the construction waste.
S32: calculating the average density of the construction waste according to the obtained data of the mass and the volume of the construction waste;
specifically, according to the construction waste quality data M obtained by the quality perception module and the construction waste volume data V measured by the binocular vision technology, the formula is used
Calculating the average density of the construction waste
。
S33: and comparing the average density of the construction waste with the density of each material according to the preset density of the common construction waste material and each material and the previously obtained construction waste type information, and finally obtaining the category information of the construction waste.
In this embodiment, the common construction waste material refers to various materials constituting construction waste on a construction site, including various organic materials, inorganic materials, metal materials, and non-metal materials; comparing the average density of the construction waste with the density of each material means that the calculated average density of the construction waste is compared with the density of each type of construction material under the type of the construction material, and the error between the calculated average density of the construction waste and the density of each type of construction material is within a certain range, so that the construction waste can be judged to be formed by the construction material.
Specifically, the detailed data of the type, type and density of the common construction waste materials are shown in table one. According to the type information of the construction waste materials obtained before, the material types of the construction waste are limited within one type, the calculated average density of the construction waste is compared with the density of each construction material type under the type, and the type information of the construction waste can be judged if the density error of the two types is less than 10%.
S4: and controlling the mechanical arm to place the picked construction waste at a corresponding position of the collecting device according to the type information of the construction waste.
In this embodiment, step S4 specifically includes the following steps:
s41: dividing corresponding construction waste storage areas in the collection device in advance according to the quantity of the category information, and marking each construction waste storage area according to the category information;
in the present embodiment, the construction waste storage area refers to an area for storing picked-up construction waste.
Specifically, according to the number of categories in the category data, namely how many kinds of construction wastes can be sorted in total, according to the number of categories, a corresponding number of areas are divided in the collection device to serve as construction waste storage areas, and each construction waste storage area is marked according to the category data.
S42: when the mechanical arm picks up the construction waste, the construction waste is stored into the construction waste storage area corresponding to a collecting device according to the type information corresponding to the construction waste.
Specifically, when the mechanical arm picks up the construction waste, the construction waste is stored into the construction waste storage area corresponding to the collecting device according to the type information corresponding to the construction waste.
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 invention.
Example three:
in the first embodiment, a control system of a construction waste sorting system is provided, wherein each module of the control system identifies the position of construction waste, determines the type information of the construction waste by combining machine vision and density measurement, and performs one-to-one correspondence between the picking and collecting processes of the construction waste. The control system comprises a motion control module 10, a quality perception control module 20, an image recognition control module 30 and a collection module 40. The functional modules are explained in detail as follows:
and the motion control module 10 is configured to generate and send a motion command to the mechanical arm or the driving module according to the position of the construction waste and the position data of each region of the collection module, so as to complete the picking and sorting actions of the construction waste.
And the quality perception control module 20 is used for acquiring the acting force data when the mechanical arm picks up the construction waste and calculating the quality data of the construction waste according to the acting force data.
And the image identification control module 30 is configured to acquire the image data, identify the position and type information of the construction waste from the image data, and calculate volume data of the construction waste.
And the collection module 40 is used for dividing the construction waste storage areas and marking the position of each construction waste storage area.
Preferably, the quality-aware control module 20 includes:
the acting force acquisition module 21 is used for acquiring acting force data acquired by the force sensor;
and the quality calculation module 22 is used for calculating the quality data of the construction waste according to the acting force data and the stress analysis condition.
Preferably, the image recognition control module 30 includes:
the image processing submodule 31 is used for preprocessing the image data to obtain a required processing result;
the image identification submodule 32 is used for acquiring the position and type information of the construction waste according to a preset construction waste identification model;
and the volume calculation module 33 is configured to process the image data obtained by the binocular camera and calculate the total volume of the construction waste.
Preferably, the collection module 40 comprises:
the classification submodule 41 is configured to divide corresponding construction waste storage areas in the collection module according to the quantity of the category information in advance, and mark each construction waste storage area according to the category information;
and the positioning storage submodule 42 is used for acquiring the position of each construction waste storage area and recording the quantity of the construction waste stored in each storage area in real time.
For specific limitations of the control system, reference may be made to the above embodiments for identifying construction waste and category information, and limitations of a method for picking up and collecting construction waste, which are not described herein again. The various modules in the control system described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Watch I (plucking from the building engineering materials handbook)
Claims (11)
1. The utility model provides a building rubbish letter sorting system, building rubbish letter sorting system includes the letter sorting system body, the letter sorting system body includes following module:
mechanical arm: for completing the actions of picking up and sorting the construction waste;
a driving module: for driving the movement of the moving parts;
a collecting device: the sorting box is used for storing various sorted building wastes, and the main body of the sorting box is a sorting box;
an image acquisition module: the construction waste sorting system is used for collecting image data of the construction waste in real time, and the main body of the construction waste sorting system is a binocular camera;
a quality perception module: the construction waste sorting system is used for sensing the quality data of the construction waste, and the main body of the construction waste sorting system is a force sensor;
a transport module: the conveyor belt is used for uniformly conveying the unsorted construction waste and the sorted construction waste, and the main body of the conveyor belt is a conveyor belt;
a control module: and automatically identifying the position information of the construction waste in the image data, controlling a mechanical arm to grab the construction waste, comprehensively judging the type information of the construction waste according to the visual identification result and the calculated density data of the construction waste, and sorting the construction waste to a preset position in the collection module.
2. The construction waste sorting system of claim 1, wherein the control module identifies the waste and the category information by:
s1: if the image data is acquired, identifying the construction waste, the type information of the construction waste and the position of the construction waste from the image data;
s2: controlling the mechanical arm to pick up the construction waste, and meanwhile, acquiring quality data of the construction waste through a quality sensing module positioned on the mechanical arm;
s3: measuring the volume of the construction waste by a binocular vision technology, combining the previously obtained quality data to obtain the density data of the construction waste, and combining the previously obtained construction waste type information to judge the type information of the construction waste;
s4: and controlling the mechanical arm to place the picked construction waste at a corresponding position of the collecting device according to the type information of the construction waste.
3. The construction waste sorting system of claim 2, wherein step S1 includes:
s11: processing the image data by using a building rubbish recognition model obtained by pre-training;
s12: and acquiring the type information and the position information of the construction waste according to the processing result.
4. The construction waste sorting system of claim 2, wherein step S2 includes:
s21: according to the position information of the construction waste, sending a corresponding picking action command to a mechanical arm to pick up the construction waste;
s22: and acquiring the quality data of the picked construction waste through a force sensor arranged on the mechanical arm.
5. The construction waste sorting system of claim 2, wherein step S3 includes:
s31: acquiring the image of the construction waste by using a binocular camera, and solving volume data of the construction waste;
s32: calculating the average density of the construction waste according to the obtained data of the mass and the volume of the construction waste;
s33: and comparing the average density of the construction waste with the density of each material according to the preset density of the common construction waste material and each material and the previously obtained construction waste type information, and finally obtaining the category information of the construction waste.
6. The construction waste sorting system of claim 2, wherein step S31 includes:
s311: obtaining left and right image difference information by adopting a semi-global stereo matching (SGM) method;
s312: reconstructing three-dimensional information of all points in the camera view by using the parallax information;
s313: the construction waste is divided into a plurality of parts, the volume of each part is obtained by utilizing the thought of integral, and finally the total volume of the construction waste is obtained.
7. The construction waste sorting system of claim 2, wherein step S4 includes:
s41: dividing corresponding construction waste storage areas in the collection device in advance according to the quantity of the category information, and marking each construction waste storage area according to the category information;
s42: when the mechanical arm picks up the construction waste, the construction waste is stored into the construction waste storage area corresponding to a collecting device according to the type information corresponding to the construction waste.
8. The construction waste sorting system of claim 1, wherein the control module further comprises a control system consisting of:
the image identification control module is used for acquiring the image data;
the quality perception control module is used for acquiring the quality data;
the motion control module is used for generating and sending a motion command to the driving module according to the image data and the type information, so that the driving module drives the sorting mechanical arm to finish picking and sorting actions according to the motion command;
and the collection module is used for dividing the waste storage areas and marking the position of each waste storage area.
9. The construction waste sorting system of claim 1, wherein the image recognition control module comprises:
the image processing submodule is used for preprocessing the image data to obtain a required processing result;
the image recognition submodule acquires the position and type information of the construction waste according to a preset construction waste recognition model;
and the volume calculation module is used for processing the image data obtained by the binocular camera and calculating the total volume of the construction waste.
10. The construction waste sorting system of claim 1, wherein the quality-aware control module comprises:
the acting force acquisition module is used for acquiring acting force data by using the force sensor;
and the quality calculation module is used for calculating the quality data of the construction waste according to the acting force data and the stress analysis condition.
11. The construction waste sorting system of claim 1, wherein the collection module comprises:
the classification submodule is used for dividing corresponding construction waste storage areas in the collection module in advance according to the quantity of the category information and marking each construction waste storage area according to the category information;
and the positioning storage submodule is used for acquiring the position of each construction waste storage area and recording the quantity of the construction waste stored in each storage area in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110288473.6A CN112916416A (en) | 2021-03-18 | 2021-03-18 | Building rubbish letter sorting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110288473.6A CN112916416A (en) | 2021-03-18 | 2021-03-18 | Building rubbish letter sorting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112916416A true CN112916416A (en) | 2021-06-08 |
Family
ID=76175845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110288473.6A Pending CN112916416A (en) | 2021-03-18 | 2021-03-18 | Building rubbish letter sorting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112916416A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538845A (en) * | 2021-07-12 | 2021-10-22 | 武汉市佳梦科技有限公司 | Building construction site safety production real-time monitoring and early warning method based on remote video monitoring and analyzing technology |
| CN113640177A (en) * | 2021-06-29 | 2021-11-12 | 阿里巴巴新加坡控股有限公司 | Cargo density measuring method and system and electronic equipment |
| CN113911586A (en) * | 2021-12-09 | 2022-01-11 | 四川大学 | Intelligent garbage sorting system and sorting method |
| CN114345892A (en) * | 2021-12-24 | 2022-04-15 | 苏州嘉诺智能装备有限公司 | Garbage classification processing system and method |
| CN114511748A (en) * | 2022-04-19 | 2022-05-17 | 山东第一医科大学附属省立医院(山东省立医院) | Information scanning system and method of PCR (polymerase chain reaction) shelter waste material storage device |
| CN116921247A (en) * | 2023-09-15 | 2023-10-24 | 北京安麒智能科技有限公司 | Control method of intelligent garbage sorting system |
-
2021
- 2021-03-18 CN CN202110288473.6A patent/CN112916416A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113640177A (en) * | 2021-06-29 | 2021-11-12 | 阿里巴巴新加坡控股有限公司 | Cargo density measuring method and system and electronic equipment |
| CN113640177B (en) * | 2021-06-29 | 2024-06-14 | 阿里巴巴创新公司 | Cargo density measuring method and system and electronic equipment |
| CN113538845A (en) * | 2021-07-12 | 2021-10-22 | 武汉市佳梦科技有限公司 | Building construction site safety production real-time monitoring and early warning method based on remote video monitoring and analyzing technology |
| CN113538845B (en) * | 2021-07-12 | 2022-07-12 | 中铁建网络信息科技有限公司 | Building construction site safety production real-time monitoring and early warning method based on remote video monitoring and analyzing technology |
| CN113911586A (en) * | 2021-12-09 | 2022-01-11 | 四川大学 | Intelligent garbage sorting system and sorting method |
| CN114345892A (en) * | 2021-12-24 | 2022-04-15 | 苏州嘉诺智能装备有限公司 | Garbage classification processing system and method |
| CN114511748A (en) * | 2022-04-19 | 2022-05-17 | 山东第一医科大学附属省立医院(山东省立医院) | Information scanning system and method of PCR (polymerase chain reaction) shelter waste material storage device |
| CN114511748B (en) * | 2022-04-19 | 2022-06-24 | 山东第一医科大学附属省立医院(山东省立医院) | Information scanning system and method of PCR (polymerase chain reaction) shelter waste material storage device |
| CN116921247A (en) * | 2023-09-15 | 2023-10-24 | 北京安麒智能科技有限公司 | Control method of intelligent garbage sorting system |
| CN116921247B (en) * | 2023-09-15 | 2023-12-12 | 北京安麒智能科技有限公司 | Control method of intelligent garbage sorting system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112916416A (en) | Building rubbish letter sorting system | |
| JP5969685B1 (en) | Waste sorting system and sorting method | |
| JP5458885B2 (en) | Object detection method, object detection apparatus, and robot system | |
| CN110544293B (en) | Building scene recognition method through visual cooperation of multiple unmanned aerial vehicles | |
| CN111445368B (en) | Garbage classification method, device and equipment based on machine vision and deep learning | |
| CN111360780A (en) | Garbage picking robot based on visual semantic SLAM | |
| CN110743818A (en) | Garbage sorting system and garbage sorting method based on vision and deep learning | |
| JP2017109197A (en) | Waste screening system and screening method therefor | |
| CN108182689A (en) | The plate workpiece three-dimensional recognition positioning method in polishing field is carried applied to robot | |
| CN111974704A (en) | Garbage classification detection system and method based on computer vision | |
| CN111993418B (en) | Multi-target multi-mechanical-arm collaborative sorting system and sorting strategy for coal and gangue sorting robot | |
| CN110516625A (en) | A kind of method, system, terminal and the storage medium of rubbish identification classification | |
| CN103198477A (en) | Apple fruitlet bagging robot visual positioning method | |
| CN113289925A (en) | Intelligent sorting system and method for sundries in coal based on deep learning | |
| CN113643280A (en) | Plate sorting system and method based on computer vision | |
| CN116277025A (en) | Object sorting control method and system of intelligent manufacturing robot | |
| CN113240798B (en) | Intelligent material integrity detection and configuration method based on digital twinning and AR | |
| CN113469264A (en) | Construction method of automatic garbage classification model, garbage sorting method and system | |
| JP2021030219A (en) | Article sorting apparatus and article sorting method | |
| CN113982690A (en) | Control method, device and system based on anchoring and protecting operation and tunneling, anchoring and protecting all-in-one machine | |
| CN114004814A (en) | Coal gangue identification method and system based on deep learning and gray scale third moment analysis | |
| CN113920142A (en) | Sorting manipulator multi-object sorting method based on deep learning | |
| WO2022241597A1 (en) | Ai intelligent garbage identification and classification system and method | |
| JP7299570B2 (en) | Soil foreign matter removal device and soil foreign matter removal method | |
| Reiterer et al. | A 3D optical deformation measurement system supported by knowledge-based and learning techniques |
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 |