SE1150288A1 - Process and system for identifying waste containers based on pattern - Google Patents

Abstract

Please send them a Phoenix message.

Description

METHOD AND SYSTEM FOR IDENTIFYING WASTE CONTAINERS BASEDON PATTERN Technical field The present document relates to a method for identifying and sorting wastecontainers provided with a pattern. The document also relates to anarrangement for sorting waste containers according to the method.

Backgroundln recent years an automated sorting of domestic waste, sorted at source, into different fractions has become more and more important in orderto increase the efficiency of the waste handling facilities and in order to beable to take care of the ever growing amounts of waste produced by thehouseholds.

There are a number of different methods and systems available todayto perform this type of sorting.

WO95/32062 discloses an arrangement for sorting differently colouredwaste sacks which occur in random distributions and contain different types ofwaste sorted at source. This arrangement comprises sorting stations, whichby means of a colour analysis as disclosed in WO9622512 identify and thenseparate waste sacks of a predetermined color, which are conveyed on aconveyor belt. ln EP 1 583 618 the refuse sacks are provided with a means ofidentification, in this case the entire bag is provided with a specific colour, andthe sorting is performed at_at least one sorting station, which is able to identifyat least two means of identification, this method and arrangement thus furtherenhances the accuracy of the sorting.

As the amounts of domestic waste continues to increase there is aneed for efficient sorting, and also a sorting that can take into account thewish that it should be possible to make use of the different fractions of thewaste, for instance in biogas production of organic waste. The demands forspecificity in the sorting for this type of waste are high, as plastics and otherunwanted materials can clog the production of biogas and even in a worstcase scenario render the entire biogas facility unuseable. 2 Sorting waste in bags having different colours is advantageous in that itis pedagogic, i.e. the user can easily decide which bag to use for a particulartype of waste, and that all the waste bags may be placed in one and the samewaste container, which makes it easy when the waste is to be collected. Oneproblem with having coloured bags is however that waste sorting can betedious and if the bag is coloured the user may experience a sense that itdoesn't matter if he puts something in the wrong bag, or if he does not sortthe waste at all. There is thus a need for a solution in which the user caneasily see what the bag is supposed to contain and the personnel at thewaste handling facility may visually inspect to see that nothing has beenwrongfully placed in the bag. One way of solving this problem is to make atransparent bag. lt must however still be possible for the user to determinewhat type of waste he bag is meant to be filled and to sort the bag in aconvenient and most of all accurate manner at the waste handling facility.

Summarylt is an object of the present disclosure, to provide an improved method and arrangement for sorting waste bags, which eliminates or alleviates atleast some of the disadvantages of the prior art and which allows for animproved sorting quality, especially in sorting of domestic waste.

The invention is defined by the appended independent claims.Embodiments are set forth in the appended dependent claims and in thefollowing description and drawings.

According to a first aspect, there is provideda method for identifying andsorting randomly distributed waste containers containing different types ofrefuse sorted at source, wherein the identification is based on an imageanalysis of a pattern arranged on each container. The method for identifyingand sorting comprises the following steps: capturing at least one image ofeach container, analyzing the image by determining following Characteristics:a shade and/or color of the pattern; a type of the pattern arranged on thecontainer; and calculating a sorting value based on the determinedCharacteristics. The calculated sorting value is compared to a predeterminedlimit value or predetermined range of sorting values in order to classify thetype of refuse contained in the container for sorting thereof.

The “type of pattern” may be determined by assigning a shape factorto the pattern. By “shape factor” is meant that if the pattern is in the 3 predetermined form of a dot the shape factor 1 would represent a perfectcircle and an ellipse would for instance represent the shape factor 0,6.

This means that each bag is assigned a “sorting value” by the analysis,i.e. a number calculated from determining the different Characteristics of thepattern on the bag, which is compared to a predetermined limit value or apredetermined range of sorting values and which sorting value is decisive fordetermining what the contents of the container such that it can subsequentlybe sorted into a correct vessel in the waste sorting facility.

Since the bags are classified according to both color and/or shade andthe shape or type of pattern there is provided a sorting and identificationmethod which is able to, with a great certainty and precision, classify and sortthe containers correctly. This sorting method is much safer and more precisethan prior art sorting methods based on e.g. the color of the container only.

Even further the method allows for the use of a transparent containeror bag, in which material sorted therein could have the same color or beingthe same type of pattern as the pattern printed on the bag as the identificationof the bag is dependent on the integer of several characteristics and not onlythe color of the pattern.

Further as the transparent container allows for a visual inspection ofthe refuse contained therein, the sorting can be supervised by e.g. wastefacility personnel which allows for the sorting to be even more accurate. Theuse of transparent containers may also reduce the tendency of the user tocheat when sorting the waste at source.

The color of the pattern can be used for the identification of what thebag is intended to be filled with by the consumer. This means that a greenpattern may be used for organic waste, a red pattern may be used for papermaterial, a black pattern may be used for plastics material etc. The color mayalso simply be black, and the other characteristics of the pattern may then bedecisive for the type of container.

This method allows for the identification of a container, such as aplastic bag, filled with material, where the pattern at some portions thereofmay have been stretched out, or even lost. That means that the bag can beidentified and sorted independently from outer phenomena and objects 4 contained in the bag. By outer phenomena is meant for instance that acontainer or bag from a specific store may have a color, or even a print thatcould confuse the sorting. This method may allow for such disturbances of thesorting to be reduced as a bag not presenting all the Characteristics neededfor the analysis, or a bag presenting Characteristics which do not comply withthe predetermined limit value or range of sorting values of the sorting valuecalculated in the analysis, will be classified as “other waste” and can beproperly handled by the waste handling system as such.

By capturing at least one image, usually at least 10 images of thesame container as it passes by the sensor or camera, and comparing theimage analysis of each of these images an even more precise identificationmay be achieved, the pattern or object may thus be analyzed from severaldifferent angles and images.

According to the first aspect the pattern may comprise at least onewell-defined object.

This means that the identification is based on identifying that one point,that could be a dot, a square , a triangle, a line, a bent line, a curved line etc.and determining its color, and the type of pattern thereof.

According to one alternative of the first aspect the pattern maycomprise a plurality of well-defined objects, wherein the objects form acluster.

According to the first aspect the method may further compriseanalyzing the image by determining the following characteristics: the numberof objects within the cluster; distances between the objects of the cluster; anda size of each individual object .

By “distances between the objects” is meant that the distancesbetween the points within the cluster are measured in a predeterminedmanner and thus a mutual relationship between the points can bedetermined _ The analysis based on a plurality of objects in a cluster may evenfurther increase the specificity of the identification as it is possible to providethe bag with a very specific pattern which cannot easily be confused with or 5 mistaken for some other type of print or contents of the bag, that could lead toan incorrect identification.

The method allows for the use of a transparent bag, in which materialsorted therein could have the same color as the pattern printed on the bag asthe identification of the bag is dependent on the total sum of severalCharacteristics and not only the color of the pattern.

Further as the transparent container allows for a visual inspection ofthe refuse contained therein, the sorting can be supervised by e.g. wastefacility personnel which allows for the sorting to be even more accurate.

The cluster may be arranged in the shape of a logo, a letter, or anumber. The pattern could thus be arranged as a further guidance to theconsumer in that the container could be marked with a pattern forming theletters for what is intended to be in the container. lt is further conceivable that instead of having different colors on thebag the pattern cluster could be identified by the logo, letters or number whichthe cluster forms.

That means that the letter “P” could for instance be arranged as theidentifiable pattern, but also as an indication to the consumer that thecontainer is to be filled with e.g. paper.

According to yet an alternative the method may further compriseanalyzing the image by determining the following characteristic: a surfacearea of the pattern.

By determining a surface area of the pattern and comparing this to apredetermined surface area it is even further possible to discriminate betweenthe desired pattern for sorting and some other type of pattern printed on thebag.

The container may be provided with a color, and wherein the color ofthe container is different from the color of the pattern.

According to one embodiment the pattern may be arranged on at leastone well-defined portion of the container.

The pattern may, according to yet an alternative, be arranged on aplurality of locations on the container. 6 By arranging the pattern on more than one portion of the bag, i.e.spread out over the bag it is possible to provide an even more accurateidentification and sorting, as the likelihood of there being a "perfect" patternsomewhere on the container or bag is increased. The pattern may also bearranged to cover substantially the entire container or bag. ln order to allow for the visual inspection of the container it couldhowever be appropriate that these plurality of locations are arranged to allowor seeing through the bag.

The pattern may comprise two or more different colors.

By having a pattern that comprises two or more colors the identification may be even further improved.

The waste container may essentially consist of a thin-walled bag offlexible material.

According to a second aspect there is provided an arrangement forsorting a plurality of waste containers designed to receive a quantity of waste,and wherein the containers are provided with at least one well-definedpattern. The arrangement comprises a conveyor arranged to transport thewaste containers, at least one first sensor arranged for analysing a patternarranged on a container, arranged to emit a signal when a waste containertransported on the conveyor is recorded by said at least one first sensor, andmeans for sorting the waste containers based on the signal from the firstsensor. The first sensor is arranged analyze the pattern arranged on thewaste containers according to the first aspect.

According to one alternative of the second aspect the arrangementmay further comprise at least one second sensor for analyzing a pattern of awaste container according to the first aspect, and for emitting a second signalin response to the second sensor recording the pattern on the wastecontainer provided with said pattern transported on the conveyor, wherein thepattern analysed by the second sensor may be the same or different as thepattern analysed by the first sensor and wherein said sorting means arearranged to sort the waste containers based also on said second signal.

According to a third aspect there is provided an arrangement for thesorting of waste containers comprising a transporting arrangement designedto transport randomly distributed waste containers containing different typesof waste sorted at source, each waste container having a predetermined 7 pattern for the type of waste in the container, a number of successivelyarranged sorting stations each comprísing at least one sensor selectivelysensitive to the respective patterns and designed to emit a signal when awaste container passes which has a pattern predetermined for the sensor andto which the sensor is sensitive, and separating elements designed, inresponse to a signal from the sensor, to undertake separation of the wastecontainer in question from the transporting arrangement, wherein at least onesensing arrangement is sensitive to at least one further predetermined patternon waste containers containing another type of waste. The sensors arearranged to analyze the pattern provided on the containers based on themethod as according to the first aspect.

By having at least one sensor it is further possible to adapt the sortingstations to detect not only a pattern but also a color of the container at thesame sorting station as a double detection system for each sorting station. ltis of course also conceivable that a single sensor is able to detect andanalyze not only the pattern arranged on the container but also the color orshade of the entire container.

According to one alternative of the second and third aspect the sensormay be an optical camera for capturing at least one image of each wastecontainer passing by the sensor.

Brief Description of the Drawinqs Embodiments of the present solution will now be described, by way ofexample, with reference to the accompanying schematic drawings.

Figs 1a-1d are a schematic top views of a flattened out containersprovided with different embodiments of patterns.

Fig. 2 is a schematic plan view from above showing one embodimentof an arrangement for sorting waste containers.

Fig. 3 is a schematic plan view from above showing one embodimentof an arrangement for sorting waste conatiners.

Description of Embodiments Figs 1 a-c shows a flatted out waste container 1, which may consist of a thin-walled bag 1 of a flexible material, such as plastic, paper, metal or a 8 combination thereof. The bag 1 can have a closure 5 to prevent waste in thebag 6 from being spread outside the bag. The bag or container is providedwith, in the flattened out state, a well-defined pattern 2. ln the below the word container and bag will be used interchangingly,however the term “container” is not to be interpreted to being limited to aplastic bag only.

The bag may be transparent, but according to one alternative it mayalso be provided with a color or a shade, which may still allow for the bag tobe transparent, i.e. have a low opacity in the visible light spectra. The color orshade of the bag may in this alternative embodiment be the same or differentas the color of the pattern.

According to yet an alternative the container may be completelycolored, i.e. does not allow to be seen through, and according to thisembodiment the color or shade of the bag is different from the color or shadeof the pattern. The color of the bag can according to this embodiment be afurther way to analyse and identify the bag.

The pattern may have a color that predetermingly correponds, e.g. asan information to the user, to the type of waste to be placed in the container.Alternatively the color or shade of the pattern for all types of waste is thesame, according to such an embodiment it is to be understood that thepattern instead has a shape that corresponds to the type of waste to beplaced in the container.

The pattern may be one object 2, such as a triangle, dot or squarearranged on a well-defined portion of the bag (se Fig. 1d).

The pattern may further be a plurality of objects 3 in a cluster, arrangedon at least one portion of the container (Fig. 1b).

As such the object or objects may toghether as a cluster or individuallyhave the shape of a circle, a dot (i.e a filled circle), a square, a triangle, anoval or any other type of shape (see e.g. Fig 1b).

According to the method of the present disclosure the pattern 2 isanalysed by image analysis. A sensor, such as an optical camera maycapture at least one image of the container as it passes by the sensor and adetermination of several Characteristics of the pattern may be performed.Based on these different chararcteristics a sorting value for the patternprovided on the container is calculated, either as a total or for each of theindividual characteristcs. This sorting value or values may then be comparedto a pretermined sorting value or a predetermined range of sorting values to 9 determine if the pattern, and thus the container, is the desired pattern orcontainer for that sensor or sorting station. The sorting value is thus a functionof the Characteristics determined by the analysis. Each of theseCharacteristics may be compared with predetermined values which enables aClassification of the pattern. The pattern itself may thus be a guide to the userregarding what to put in the container, e.g. a circle may be biodegradablewaste, a triangle may be metal waste, and an unspecified pattern may thusmean that the bag cannot be classified.

The characterstics that are determined and analysed comprises, theshade and/or color of the pattern itself, the type of the pattern arranged on thecontainer, which may be determined by assigning a shape factor to thepattern.

According to one embodiment, if the object is a dot, the shape factor 1would represent a perfect circle and an ellipse would for instance representthe shape factor 0,6.

The type of pattern may also be characterized and determined by othertypes of analysis which are readily conceivable by the skilled person.

According to alternative embodiments further Characteristics that maybe determined by the image analysis are the number of objects 3 within thecluster, and the size of each individual object 3.

The predetermined sorting value for the size of each individual object 3may be defined as an interval or as a definite value. By the size of eachobject is meant the area or surface area of each individual object. The totalsum of all areas of the objects within the pattern or cluster may also bedetermined as a total surface area of the objects (as opposed to the term totalsurface area of the pattern, which also takes into account the area and spacebetween the objects). The method can thus take into account certaindeviations for certain objects in the cluster and still be able to determine if the analyzed pattern is the desired or correct pattern or not. ln Fig. 1c a detail 4 of the bag shown in Fig 1a, and the measurementsof distances d1-7 between different objects in the cluster, which is also onecharaceteristic that may be detemined by the image analysis.

The distances may be e.g. measured from the center of one object to the center of an adjacent object in an X-Y cooridnate system, where the principal point of each object is the center of the object. Fig. 1c illustratesdifferent types of distances that can be measured. lt is also possible tomeasure other distances not shown in the figures. That means that if oneportion of the objects are arranged as forming parts of the corners of a squarethe distances between the objects are measured in a number of differentways and compared to the predetermined limit value or range (max/min) of distances.

The distances may thus be measured in a precice manner to take intoaccount for when the pattern, or cluster of objects, have been streched out oreven destroyed at a portion of the total surface area of the pattern.

According to yet an alternative the surface area of the pattern is alsodetermined. This means that if the pattern does not cover the predeterminedsurface area the container may be sorted as “other waste" or as one of thedesired fractions depending on the sorting value calculated from the otherCharacteristics as well. Through the present method it should thus still bepossible to correctly sort the container even though the pattern for somereason is not visible on the entire surface area as it should be, e.g. hiddenbehind something that is stuck on the container or it has been disrupted ordestroyed. lt could also be that a container could be provided with a pattern similarto the desired pattern, but which covers more or less of the bag than thepredetermined surface area of the desired and correct pattern does, thesorting method should then provide for a determination that the containerdoes not comprise the correct pattern and thus sort the container as “otherwaste”. This is even further facilitated by the fact that several images, of thesame container, may be compared with each other in the analysis.

The pattern may be analysed by the aid of sensors such as opticalcameras connected to computers, and the method and analysis may thus be fully automated.

Fig. 2 is a simplified view of a sorting arrangement 10 for wastecontainers 1. The sorting arrangement comprises a feed input 11, which maybe a conveyor belt, or a chute from which waste containers 1 to be sorted istransported. The feed input conveyor transports the containers to a secondconveyor 12. ln Fig 2 two parallel conveyor belts 12a, 12b lead to a series of 11 sorting stations. A first sorting station 14a, 14b is provided with a sensorarranged for analyzing a pattern 2 provided on the waste containers 1according to the above described method. Based on the analysis the sortingstation provides a signal when the correct pattern is identified which allows fora sorting means (not shown) to remove the container, provided with thedetected pattern, from the conveyor belt into some type of vessel for storingthe waste containers. ln the arrangement 10 shown in Fig 2 the wastecontainers pass three different sorting stations 14a, 15a, 16a, which may bearranged to detect the same or different type of patterns. The sorting stationmay also be provided with sensors that allow for an identification of severaltypes of patterns and sort those bags into one or more vessels. This meansthat the arrangement allows for the sorting of containers each provided withdifferent patterns.

The waste container can also pass a sorting station provided with asensor of the type which is disclosed in SE8901046-6, WO9306945A1 andEP0759816B1 and which identifies a colour or a shade of the passing wastecontainer, a second signal representing said colour or shade being sent to thecontrol unit. The sensors can be arranged in any relative order. Thus it neednot be important which sensor records the waste container 1 first.

Sorting means (not shown) are arranged to selectively strike or push awaste container 1 away from the conveyor belt 12a, 12b, so that the wastecontainer gets into a collecting vessel (not shown). The control unit can bearranged to produce control signals to the sorting means based on the time ofarrival of the signals from the sensors of the sorting stations 14a, 14b, 15a,15b and knowledge of the transport speed of the conveyor. This results insorting of the waste container in collecting vessels, which, for example, canbe intended to contain biodegradable and combustible waste respectively. lt will be appreciated that the sorting arrangement, the conveyor andthe sorting means can be designed in various ways. Conveyors of differenttypes can be used, such as belt conveyors, screw conveyors, overhead con-veyors, chain conveyors etc. Also pipes in which the waste containers aremade to be transported under the action of excess pressure, negativepressure and/or gravity may constitute conveyors. Also the number of col-lecting vessels can be varied according to the number of sorting fractions thatare desired.

Also the sorting means can be arbitrarily designed. 12 Fig. 3 illustrates one sorting arrangement for the sorting of threedifferent randomly distributed fractions of waste containers. The wastecontatiners are feed to the arrangement by three parallell feed inputs 11a,11b, 11c. Through the feed inputs the randomly distrubuted waste containersare transported along three parallell conveyors 12a, 12b, 12c, with a certaininterval between the individual waste containers, in order for the wastecontainers to be sorted at sorting stations 14a-c, 15a-c, 16a-c,17a-c, 18a-c,19a-c that are arranged in series one after the other. The individual wastecontainers may all be provided with specific patterns p1, p2, p3 to be detectedby corresponding sensors at the sorting stations. The containers providedwith the first pattern p1 are identified and separated at the first two sortingstations 14a-c, 15a-c, the containers provided with the second pattern p2 are Isorted at the two followning sorting stations 16a-c, 17a-c, and the containers _ provided with the third pattern p3, alternativley no pattern or alteratively all patterns at all, i.e. “other waste”, are sorted at the two last sorting stations18a-c, 19a-c. Separation of containers identifieable by the same pattern atmultiple succeeding sorting stations in this way increases the capacity butalso the accuracy of the sorting. This arrangement may also be constructedina number of different ways, e.g. such as those disclosed in EP 1 583 618B1. lt is also possible to combine sorting based on pattern as disclosed in thepresent application with the color coded sorting disclosed in EP 1 583 618 B1.

Claims (14)

1. Method for identifying and sorting randomly distributed waste containers (1)containing different types of refuse sorted at source, wherein the identificationis based on an image analysis of a pattern (2) arranged on each container (1) characterized inthat the method for identifying and sorting comprises the following steps: capturing at least one image of each container (1) analyzing the image by determining following Characteristics: a shade and/or color of the pattern;a type of the pattern arranged on the Container; calculating a sorting value based on the determined Characteristics; comparing the calculated sorting value to a predetermined limit valueor predetermined range of sorting values in order to classify the type of refusecontained in the container for sorting thereof.

2. The method as claimed in claim 1, wherein the pattern (2) comprises at least one well-defined object (3).

3. The method as claimed in claim 1, wherein the pattern (2) comprisesa plurality of well-defined objects (3), wherein the objects (3) form a cluster.

4. The method as claimed in claim 3, further comprising analyzing theimage by determining the following Characteristics:the number of objects (3) within the Cluster;distances (d1, d2, d3) between the objects (3) of the Cluster; anda size of each individual object (3).

5. The method as claimed in any one of the preceding Claims, furthercomprising analyzing the image by determining the following Characteristic:a surface area of the pattern. 14

6. The method as claimed in any one of claims 1-5, wherein thecontainer is provided with a color, and wherein the color of the container is different from the color of the pattern.

7. The method as claimed in any one of the preceding claims, whereinthe pattern is arranged on at least one well-defined portion of the container.

8. The method as claimed in any one of claims 1-6, wherein the pattern is arranged on a plurality of locations on the container.

9. The method as claimed in any one of the preceding claims, wherein the pattern comprises two or more different colors.

10. The method as claimed in any one of claims 1-9, wherein the wastecontainer (1) essentially consists of a thin-walled bag (1) of flexible material.

11. An arrangement (10) for sorting a plurality of waste containers (1)designed to receive a quantity of waste, and wherein the containers areprovided with at least one well-defined pattern (2), comprising: a conveyor (12) arranged to transport the waste containers (1), at least one first sensor (14) arranged for analysing a pattern arrangedon a container (1), arranged to emit a signal when a waste container (1)transported on the conveyor (12) is recorded by the at least one first sensor(12), and means for sorting the waste containers (1 ) based on the signal fromthe first sensor (14), characterisedinthat the first sensor (14) is arranged analyze the pattern arranged on thewaste containers (1) according to the method in any one of claims 1-10.

12. The arrangement as claimed in claim 11, wherein the arrangementfurther comprises at least one second sensor (15, 16) for analyzing a patternof a waste container (1) according to the method in any one of claims 1-10,and for emitting a second signal in response to the second sensor (15, 16)recording the pattern on the waste container (1 ') provided with said patterntransported on the conveyor (11), wherein the pattern analysed by the second sensor (15, 16) may be the same or different as the pattern analysed by thefirst sensor (14) and wherein said sorting means are arranged to sort thewaste containers (1) based also on said second signal.

13. An arrangement (10) for the sorting of waste containers (1)comprising a transporting arrangement (12) designed to transport randomlydistributed waste containers (1) containing different types of waste sorted atsource, each waste container (1) having a predetermined pattern (2) for thetype of waste in the container, a number of successively arranged sortingstations (14, 15, 16) each comprising at least one sensor selectively sensitiveto the respective patterns (2) and designed to emit a signal when a wastecontainer (1) passes which has a pattern (2) predetermined for the sensorand to which the sensor is sensitive, and separating elements designed, inresponse to a signal from the sensor, to undertake separation of the wastecontainer (1) in question from the transporting arrangement (12), wherein atleast one sensing arrangement is sensitive to at least one furtherpredetermined pattern on waste containers (1) containing another type ofwaste, characterized in that the sensors are arranged to analyze the pattern (2) provided on thecontainers (1) based on the method as claimed in any one of claims 1- 10.

14. The arrangement as claimed in any one of claims 11-13, whereinthe sensor is an optical camera for capturing at least one image of eachwaste container passing by the sensor.