CN113083701A - Automatic garbage classification and sorting method based on outdoor garbage image big data analysis - Google Patents

Abstract

The invention discloses a garbage automatic classification and sorting method based on video image analysis of big data, which comprises the following steps of S10: acquiring a video screen picture of a garbage stacking area, intercepting a plurality of images of garbage from the video screen picture, and entering the intercepted images into an area to be analyzed; s20: the method comprises the steps that a training server identifies images of an area to be analyzed, a plurality of images are analyzed and identified in sequence through the server, the image with the largest number of single junk individuals identified by the server is obtained, the obtained image with the largest number of junk individuals is a clear image, and the obtained images enter the analysis area; the method effectively and comprehensively identifies and processes the garbage according to the big data, the garbage is subjected to screen viewing and image acquisition through the big data, then a plurality of garbage individuals in each image are identified and separated, the server is ensured to know the data information of the garbage individuals through big data comparison, and the garbage is conveyed to a garbage sorting area through mechanical parts, so that the method is simple to use.

Description

Automatic garbage classification and sorting method based on outdoor garbage image big data analysis

Technical Field

The invention belongs to the technical field of image analysis, and particularly relates to an automatic garbage classification and sorting method based on outdoor garbage image big data analysis.

Background

With the improvement of the living standard and the consumption standard of people, daily garbage is generated more and more while a large amount of resources are consumed and the production scale is improved. The traditional garbage treatment method is only simple stacking or landfill, and the treatment method can cause bad smell, deterioration of sanitation, soil pollution and water quality pollution, further influences the living environment and the body health of people, and has unreasonable consequences.

The means for harmlessly treating garbage include deep landfilling, high-temperature incineration, composting and the like, but the cost for treating one ton of garbage is about several hundred yuan, so the cost for harmlessly treating garbage is high. In the face of the situation that garbage is growing day by day and the environment is worsening day by day, how to further utilize recoverable garbage through scientific management and scientific treatment of garbage classification, recycle garbage resources to the maximum extent, save garbage treatment cost, reduce harm of harmful garbage and improve living environment quality is one of the urgent problems which are commonly concerned by countries in the world at present.

The existing garbage sorting method is not comprehensive enough, most of the existing garbage sorting method is that environment-friendly personnel in a community classify and sort garbage manually, but when the garbage is transported, the garbage after the classification is finished can be mixed together uniformly, the classification sorting does not play a role, meanwhile, the garbage can be sorted secondarily, the classification sorting workload of the secondary garbage is large, meanwhile, various garbage is mixed together in an aggregation mode, the classification sorting work difficulty is large, the operation is complex, the work physical strength is greatly consumed, the normal processing of the garbage is not facilitated, and therefore the automatic garbage sorting method based on the video image analysis of big data is provided.

Disclosure of Invention

The invention aims to provide a garbage automatic classifying and sorting method based on video image analysis of big data, which aims to solve the problems that the existing garbage sorting methods proposed in the background technology are not comprehensive enough, most of the existing garbage sorting methods are used for classifying and sorting garbage manually by environment-friendly personnel in a cell, but during transportation, the classified garbage is mixed together uniformly, so that the classifying and sorting do not have an effect, meanwhile, the garbage is subjected to secondary classifying and sorting, the workload of the secondary garbage classifying and sorting is large, and the like.

In order to achieve the purpose, the invention provides the following technical scheme: an automatic garbage classifying and sorting method based on outdoor garbage image big data analysis comprises the following steps,

s10: acquiring a video screen picture of a garbage stacking area, intercepting a plurality of images of garbage from the video screen picture, and entering the intercepted images into an area to be analyzed;

s20: the method comprises the steps that a training server identifies images of an area to be analyzed, a plurality of images are analyzed and identified in sequence through the server, the image with the largest number of single junk individuals identified by the server is obtained, the obtained image with the largest number of junk individuals is a clear image, and the obtained images enter the analysis area;

s30: acquiring data information of the image in the analysis area, identifying the junk individual on the image entering the sub-clear area through big data, and then performing a training area on the image after identifying the junk individual;

s40: manually identifying the training area image by a worker, and verifying the data information of image identification in the analysis area by the worker;

s50: training a server to identify an analysis area, and entering a garbage classification and sorting area when the accuracy of the server to identify images in the training area is more than ninety percent;

s60: inputting garbage sorting area data, inputting the position and the number of garbage stacked areas, wherein the sorting areas are a plurality of mother sets, and the plurality of identified garbage individuals are a plurality of subsets;

s70: acquiring a clamping device, clamping the plurality of identified subsets through the clamping device, and then moving according to an input instruction of the server to enable the plurality of subsets to move to the top of the mother set;

s80: loosening the clamping device to enable the subset at the bottom of the clamping device to fall into the mother set, and finishing garbage sorting.

Preferably, the video images acquired in S10 are four-view videos, which are a front view, a left view, a right view and a top view of the garbage stacking area.

Preferably, the images captured in S10 are multiple groups of images, and the number of each group of images is four, and the images are captured at the same time in videos with four viewing angles respectively.

Preferably, in S20, multiple groups of images are identified, and a demand image is obtained from the multiple groups of images, where the demand image is one of the images with the largest number of garbage individuals and the clearest image.

Preferably, the characteristics of the big data identification spam individuals in S30 are as follows: the garbage can be recovered and the garbage can not be recovered.

Preferably, the recyclable garbage comprises four characteristics of number, type, style and dryness and the non-recyclable garbage comprises four characteristics of number, type, style and dryness.

Preferably, when the data information identified by the big data in the analysis area is consistent with the information verified by the staff member in the step S40, the server saves the data; and when the data information identified by the big data in the analysis area is inconsistent with the information verified by the staff, the staff modifies the real information data, and the server stores the modified data of the staff after marking red.

Preferably, in S60, when the accuracy of the server recognizing the training area image is less than ninety percent, the server returns to S10 to continue the recognition and detection.

In S60, the number of the mother sets is greater than four, and the number of the subsets is greater than five.

Preferably, after the plurality of subsets are placed in the mother set, the method further comprises the step of garbage full load early warning, and the method comprises the following steps:

preferably, the height of the subset in the parent set is detected, and when the height of the subset is higher than a set height, early warning information is sent out, and the subset is stopped to be thrown.

Compared with the prior art, the invention has the beneficial effects that:

the method effectively and comprehensively identifies and processes the garbage according to the big data, the garbage is viewed through the big data, images are obtained, then a plurality of garbage individuals in each image are identified and separated, the server is ensured to know the data information of the garbage individuals through big data comparison, so whether the garbage is recoverable garbage or not is ensured, the garbage is characterized by the number, the type, the style and the like, the garbage is conveyed to a garbage sorting area through mechanical parts, the method is simple to use, the physical strength of workers is saved, the workers are prevented from working in a severe working environment, meanwhile, the classification and sorting work is relatively easy, the degree of mechanization is high, and the garbage separation and the processing are facilitated.

Drawings

FIG. 1 is a schematic structural view of the present invention;

FIG. 2 is a schematic structural view of the present invention;

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1 and fig. 2, the present invention provides a technical solution: an automatic garbage classifying and sorting method based on outdoor garbage image big data analysis comprises the following steps,

s10: acquiring a video screen picture of a garbage piling area, wherein the acquired video images are four visual angle videos which are respectively a main view, a left view, a right view and a top view of the garbage piling area, so that the intercepted images are a plurality of groups of images, the number of each group of images is four, the images are respectively intercepted at the same time in the four visual angle videos, for example, the intercepted image in the first video is 3:42 seconds, the intercepted image in the rest three visual angles is also 3:42 seconds, the images of a plurality of garbage are intercepted from the rest three visual angles, and the intercepted images enter an area to be analyzed;

s20: the method comprises the steps that a training server identifies images of an area to be analyzed, a plurality of images are analyzed and identified in sequence through the server, information data identification and analysis are carried out on the images through the server, a required image is obtained from a plurality of groups of images, the required image is one with the largest number of garbage individuals and the clearest image, and the plurality of images obtained, identified and analyzed enter an analysis area;

s30: acquiring data information of the image in the analysis area, identifying the junk individual on the image entering the sub-clear area through big data, and then performing a training area on the image after identifying the junk individual;

s40: manually identifying the training area image by a worker, and verifying the data information of image identification in the analysis area by the worker;

s50: training a server to identify an analysis area, and entering a garbage classification and sorting area when the accuracy of the server to identify images in the training area is more than ninety percent;

s60: inputting garbage sorting area data, inputting the position and the number of the garbage stacked areas, wherein the sorting areas are a plurality of mother sets, and the plurality of identified garbage individuals are a plurality of subsets;

s70: acquiring a clamping device, clamping the plurality of identified subsets through the clamping device, and then moving according to an input instruction of the server to enable the plurality of subsets to move to the top of the mother set;

s80: loosening the clamping device to enable the subset at the bottom of the clamping device to fall into the mother set, and finishing garbage sorting.

In this embodiment, preferably, the characteristics of the big data identifying spam individuals in S30 are as follows: the garbage recycling device comprises recyclable garbage and non-recyclable garbage, wherein the recyclable garbage comprises four characteristics of number, type, style and dryness and the non-recyclable garbage comprises four characteristics of number, type, style and dryness.

In this embodiment, preferably, in S40, when the data information identified by the big data in the analysis area is consistent with the information verified by the staff member, the server saves the data; and when the data information identified by the big data in the analysis area is inconsistent with the information verified by the staff, the staff modifies the real information data, and the server stores the modified data of the staff after marking red.

In this embodiment, preferably, in S60, when the accuracy of the server recognizing the training area image is less than ninety percent, the server returns to S10 to continue the recognition and detection.

In this embodiment, preferably, in S60, the number of the mother sets is greater than four, and the number of the subset sets is greater than five.

In this embodiment, preferably, after the plurality of subsets are placed in the mother set, the method further includes a step of performing garbage full load warning, which includes:

and detecting the height of the subset in the master set, and sending out early warning information to stop throwing the subset when the height of the subset is higher than a set height.

This gives: through the server, big data add and hold, when improving work efficiency, the condition of staff's work in adverse circumstances has been avoided, the effect of protecting has been played to staff's physical and mental health, big data discerns rubbish simultaneously, it is relatively accurate to handle, ensure that the server knows the individual data information of rubbish, and carry rubbish to rubbish letter sorting region through mechanical component, high durability and convenient use, the physical power of staff has been saved, the staff has been avoided working in adverse circumstances, the letter sorting work of while classification is light relatively, the degree of mechanization is higher, the separation and the processing of the rubbish of being convenient for.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The above description is only for the purpose of illustrating the technical solutions of the present invention and not for the purpose of limiting the same, and other modifications or equivalent substitutions made by those skilled in the art to the technical solutions of the present invention should be covered within the scope of the claims of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. An automatic garbage classification and sorting method based on outdoor garbage image big data analysis is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,

s10: acquiring a video screen picture of a garbage stacking area, intercepting a plurality of images of garbage from the video screen picture, and entering the intercepted images into an area to be analyzed;

s20: the method comprises the steps that a training server identifies images of an area to be analyzed, a server sequentially analyzes and identifies a plurality of images, the server identifies and analyzes information data of the images, and a plurality of images obtained after identification and analysis enter an analysis area;

s30: acquiring data information of the image in the analysis area, identifying the junk individual on the image entering the sub-clear area through big data, and then performing a training area on the image after identifying the junk individual;

s40: manually identifying the training area image by a worker, and verifying the data information of image identification in the analysis area by the worker;

s50: training a server to identify an analysis area, and entering a garbage classification and sorting area when the accuracy of the server to identify images in the training area is more than ninety percent;

s60: inputting garbage sorting area data, inputting the position and the number of garbage stacked areas, wherein the sorting areas are a plurality of mother sets, and the plurality of identified garbage individuals are a plurality of subsets;

s70: acquiring a clamping device, clamping the plurality of identified subsets through the clamping device, and then moving according to an input instruction of the server to enable the plurality of subsets to move to the top of the mother set;

s80: loosening the clamping device to enable the subset at the bottom of the clamping device to fall into the mother set, and finishing garbage sorting.

2. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 1, characterized in that: the video images acquired in the step S10 are videos with four viewing angles, which are respectively a front view, a left view, a right view and a top view of the garbage stacking area.

3. The automatic garbage classification and sorting method based on the outdoor garbage image big data analysis as claimed in claim 2, wherein: the images captured in the S10 are multiple groups of images, and the number of each group of images is four, and the images are captured at the same time in the videos with four viewing angles.

4. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 1, characterized in that: and S20, performing information data identification and analysis on the multiple groups of images, and acquiring a demand image from the multiple groups of images, wherein the demand image is the image with the largest number of garbage individuals and the clearest image.

5. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 1, characterized in that: the characteristics of the big data identification junk individual in the S30 are as follows: the garbage can be recovered and the garbage can not be recovered.

6. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 5, characterized in that: the recyclable garbage comprises four characteristics of number, type, style and dryness and wetness, and the unrecoverable garbage comprises four characteristics of number, type, style and dryness and wetness.

7. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 1, characterized in that: when the data information identified by the big data in the analysis area is consistent with the information verified by the staff, the server saves the data in S40; and when the data information identified by the big data in the analysis area is inconsistent with the information verified by the staff, the staff modifies the real information data, and the server stores the modified data of the staff after marking red.

8. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 1, characterized in that: in S60, when the accuracy of the server recognizing the training area image is less than ninety percent, the server returns to S10 to continue the recognition and detection.

9. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 1, characterized in that: in S60, the number of the mother sets is greater than four, and the number of the subsets is greater than five.

10. The automatic garbage classification and sorting method based on outdoor garbage image big data analysis according to claim 1, characterized in that: after a plurality of subsets are placed in the mother set, the method further comprises the step of garbage full-load early warning, and the method comprises the following steps:

and detecting the height of the subset in the master set, and sending out early warning information to stop throwing the subset when the height of the subset is higher than a set height.

Images