A waste sorting process combining chemical composition analysis and the use of markers.

Abstract

The invention relates to a method for sorting objects comprising the steps of: depositing objects onto a belt conveyor (BCV); acquiring images of a first zone (Z1) of the belt; acquiring material and / or color detection signals for adjacent cells (CL) of a second zone (Z2) of the belt; processing the detection signals to determine detected attributes; detecting and decoding markers in the images to determine specified identifiers and attributes; determining a first instruction for each cell associated with an object identifier; determining a second instruction for each cell associated with material and / or color attributes; and controlling a sorting unit (BLS) to direct each object on the belt to an output (S0, S1) defined by sorting decisions determined from the first and second instructions. Figure 1

Description

Title of the invention: Waste sorting method combining chemical composition analysis and the use of markers. Technical field

[0001] The present invention relates to the field of waste sorting, in particular of the type of packaging made of plastic or fibrous material, on the basis of different criteria such as material, color, shape, use, viscosity, and the presence of carbon of biological origin and recycled material. State of the art

[0002] Generally, waste sorting relies on various technologies for the direct detection of the chemical composition of the objects to be sorted. These technologies employ different detection tools that are often combined for more precise diagnosis. These tools may, for example, include spectrometers in the near- or mid-infrared range for the molecular analysis of organic products (plastics, cellulosic or biological products), color cameras or spectrometers in the visible range for analyzing the color of objects; inductive detectors characterizing the presence of metals, X-ray detectors, or laser-induced breakdown spectroscopy (LIBS) for analyzing atomic composition.

[0003] Image processing systems also exist that include pattern recognition algorithms, particularly those using artificial intelligence. However, such systems prove poorly suited to processing waste that may be highly degraded, for example, deformed and contaminated.

[0004] Despite the existence of a wide variety of detection tools, it is not always possible to determine other properties important for recycling, such as the food or non-food use of the object, the presence of hazardous content, the presence of a layer partially or totally masking the object (in the case of multi-layer packaging), the type and shape of the object, the presence of additives in the material constituting the object, the viscosity index, particularly in the case where the object is made of HDPE (high-density polyethylene), the rate of recycled material and the proportion of biogenic carbon contained in the object.

[0005] It has already been proposed to add chemical tracers to the objects to be sorted in order to characterize a desired property. This would allow for indirect detection of the property based on a declarative principle. However, the use of such tracers has drawbacks. Indeed, the meaning of such tracers requires the agreement of a convention between the parties involved. The association between the Trackers and objects raise risks of error or fraud. Encoding capacity is limited, typically 1 bit of information per tracker. Trackers must ultimately be removed from objects during recycling to avoid compromising the subsequent sorting / recycling cycle.

[0006] The international barcode system is also known, which assigns a unique identifier to each commercial packaging reference. This identifier provides access to all the product's technical data, and therefore potentially to all attributes relevant for recycling. However, reading a barcode requires orienting the barcode towards a reading device. This marking technique is therefore not suitable for the automatic sorting of waste presented randomly on a conveyor. A new version of barcodes currently being standardized, based on QR codes, presents the same drawback of being present in only one location on the packaging.

[0007] RFID chip marking systems are also known, which can assign a unique identifier to each product. A global read is possible without orienting the product. However, RFID chips have a significant cost compared to the cost of packaging, and do not allow for precise localization of the object on the sorting belt.

[0008] In the 2010s, a new type of marker was proposed for packaging. These are digital watermarks, referred to as "markers" hereafter. They consist of adding a printed or embossed (molded or engraved) pattern to a label or the packaging of the object. Whether printed or engraved, these patterns have a very high resolution, on the order of 75 to 150 dpi, or pixels of 0.1 to 0.2 mm on a side. The variation in gray level of the print or the depth of the embossing is calculated so that the marker is imperceptible to the human eye, but is systematically visible to a high-speed camera with appropriate lighting (pulsed or non-pulsed, monochrome or white).

[0009] Since 2020, the European consortium Holy Grail 2.0 has launched an industrial validation program for the use of such markers on packaging in Europe. This program relies on technologies developed by industrial players such as Digimarc® and Filigrade®.

[0010] Compared to chemical tracers, markers require no external input of material and leave no trace during the recycling phase. Furthermore, their information richness is unparalleled: a pattern 1 to 2 cm on a side can contain 10 to 50 bits of information depending on the technological solutions chosen. In comparison, systems with three different chemical tracers, equivalent to 3 bits, only allow for the encoding of seven different situations of objects thus marked (eight combinations are possible, but total absence, coded 0,0,0, does not allow for distinguishing between marked and unmarked objects is woefully inadequate given the number of object types that need marking. The information contained in these markers is therefore comparable to that of a barcode. Unlike barcodes, these markers are formed in numerous locations on the object's surface, or even across its entire surface, so that they can be read automatically without requiring a specific face of the object to be presented to the reading device.

[0011] They therefore remain visible regardless of the object's orientation and condition, even when crushed, partially obscured, or soiled. These properties make it possible to consider using such markers for optical sorting prior to recycling. Summary

[0012] The present invention proposes to create a detection tunnel based on a row of cameras, placed above a sorting conveyor, which is combined with a conventional optical sorting system, using physical sensors such as spectrometers in the near-infrared (NIR) and / or visible ranges, to determine the composition of the material.

[0013] Thus, the present invention proposes a method for sorting marked and unmarked objects in a single operation, combining direct detection and indirect detection by detecting markers that provide information undetectable by direct detection. Indeed, it is desirable to be able to sort objects such as packaging for recycling based on complex combinations of criteria such as material, color, shape, use, viscosity, and the presence of bio-based carbon and recycled material, given that the markers are not necessarily present on the objects to be sorted, or if they are present, they can only be detected on a portion of the objects' surface.

[0014] Embodiments relate to a method for sorting objects comprising the steps of: depositing objects to be sorted onto a belt of a conveyor belt; acquiring an image stream of objects present in a first zone of the belt extending over a width of the belt; acquiring material and / or color detection signals for each cell of a set of adjacent cells located in a second zone extending over the width of the belt; for each cell, processing the detection signals to determine detected material and / or color attributes; detecting markers in the image stream of the first zone; for each detected marker, decoding the marker to determine an object identifier; for each decoded marker, assigning the object identifier determined by decoding the marker to the cells covered by the decoded marker;determine specified attributes for each object identifier determined from a decoded marker; for each cell associated with an object identifier, determine a first sorting instruction based on sorting criteria and the specified attributes; for each cell, dice; complete a second sorting instruction based on the sorting criteria and detected attributes; for each cell, determine a combined sorting decision based on the cell's first and second sorting instructions and a set of combination rules; according to a set of extension rules, extend the combined sorting decision of cells associated with an object identifier to neighboring cells not associated with an object identifier; and command a sorting device to direct each object present on the tape to a selected output based on the combined sorting decisions of the cells facing the sorting device.

[0015] In this way, it is possible to sort a stream of objects comprising marked objects mixed with unmarked objects, by applying sorting criteria that can combine several values ​​of specified object attributes, which can be obtained from object identifiers resulting from the decoding of markers present in the acquired image stream and from material and / or color detection signals. The combination of marker decoding, material detection of the objects to be sorted, and the extension of the combined sorting decision to neighboring cells not associated with marker detection offers numerous advantages, particularly in terms of the accuracy of the sorting unit's control. Indeed, in most cases, the detected markers do not completely cover an object.This is particularly the case when objects are not marked across their entire surface, when the label is partially torn off, or when the algorithm fails to detect all markers (computation times are too long, the marked surface is too damaged or dirty, the object is tilted, etc.). The precision achieved in the sorting unit's command applies regardless of the sorting system output selected for each marker, ensuring that the sorting command applied to all cells corresponding to an entire object is consistent and thus improving the purity of the sort.

[0016] Furthermore, the detected material may not correspond to that declared by the markers, for example, when the same mold is used for several materials, or in the event of a printing error on the markers. In case of contradiction, priority is given to the material and / or color detection signals, the measurement of which is actual, and not declarative, unlike the data obtained from decoding a marker.

[0017] Even if marker technology is adopted on a large scale, there will always be unmarked products present in a stream of marked objects to be sorted. By using a material detection device, it is possible to make combined sorting decisions on these objects. For example, sorting criteria can be configured to purify a stream of marked objects of contaminants consisting of unmarked objects.

[0018] This combination also reduces redundancy and the computing power required. Indeed, the algorithms used to detect and decode the Markers use high redundancy between successive images, resulting in significant computing power. By reducing the image acquisition frequency while ensuring the decoding of at least one marker per object, and by using material and / or color detection signals to complete the object mapping, it is possible to achieve equally high sorting efficiency despite a reduced image acquisition frequency.

[0019] According to one embodiment, according to the set of combination rules, the combined sorting decision for a cell is: compliant with one of the first and second sorting instructions for the cell if these are identical; assigned to one of the outputs of the sorting system in case of contradiction between the first and second sorting instructions for the cell, the output of the sorting system being determined according to the sorting criteria; compliant with the first sorting instruction of the cell if the second sorting instruction is indeterminate due to a lack of significant material and / or color detection in the cell; compliant with the second sorting instruction of the cell if the second sorting instruction of the cell is determined and if the sorting criteria, taking into account the detected attributes, specify that the second sorting instruction takes precedence; and determined according to the sorting criteria and the combined sorting decision of an adjacent cell.if the first sorting instruction is indeterminate due to the absence of a marker detection in the cell.

[0020] Thus, all cases of values ​​of the first and second sorting instructions are treated taking into account the specificities of the detection modes by image capture and processing and by material and / or color detection.

[0021] According to one embodiment, the method includes a first extension operation comprising steps of: selecting at least one cell of a first extension rank, not associated with an object identifier, for which the sorting criteria assign a priority to the first instruction, and which is adjacent to a core of at least one cell associated with an object identifier, for which the sorting criteria assign a priority to the first instruction, and for which the material specified by the marker corresponds to the material detected by the sensor set for the adjacent cell and the selected cell; and assigning to the combined sorting decision of each selected cell a value equal to that of a cell of the core.

[0022] Such an extension operation makes it possible to increase the number of cells concerned by the sorting commands to be activated for an object to be sorted, and therefore to improve the accuracy of the sorting commands, and thus to reduce sorting command errors.

[0023] According to one embodiment, the method includes a subsequent extension operation comprising steps of: selecting at least one cell belonging to a higher extension rank, not associated with an object identifier, for which the sorting criteria assign priority to the first instruction, and which is adjacent to at least one cell belonging to a lower extension rank, and for which the material detected by the sensor set corresponds to that of the selected cell; and assign to the combined sorting decision of each cell selected for the higher extension rank a value equal to that of the cell belonging to the lower extension rank.

[0024] This provision makes it possible to further increase the number of cells concerned by the sorting commands to be activated for an object to be sorted, for a better precision of the sorting command and therefore a better efficiency of the sorting of the object to be sorted.

[0025] According to one embodiment, several extension operations are performed up to a maximum number of extension operations defined for each output of the sorting system.

[0026] This provision makes it possible to further increase the number of cells concerned by the sorting commands to be activated for an object to be sorted, for a better efficiency of sorting the object to be sorted, while limiting the risk of overflowing onto adjacent objects to be sorted which could lead to a sorting error.

[0027] According to one embodiment, the maximum number of extension operations is defined for each identifier or each value of a specified attribute.

[0028] According to one embodiment, the method comprises the implementation of a detection table comprising, for each cell: - the first sorting instruction, - the second sorting instruction, - the combined sorting decision, - the extension rank, and - the object identifier resulting from a marker decoding.

[0029] According to one embodiment, the determination of the specified attributes from each object identifier determined using a decoded marker, includes a step of searching for the object identifier in a local database storing object identifiers that can be extracted from the markers and the specified attributes associated with each object identifier.

[0030] According to one embodiment, the method comprises steps consisting of: receiving sorting criteria; and updating a database storing object identifiers that can be extracted from the specified markers and attributes associated with each object identifier, the updating of the database comprising determining a sorting instruction for each object identifier based on the specified sorting criteria and attributes associated with the object identifier, the first sorting instruction for each cell associated with an object identifier being the sorting instruction associated with the object identifier in the database.

[0031] Thanks to the implementation of a database of marked objects, it is possible to determine the first sorting instruction and the specified attributes determined using an object identifier by a simple read from the database.

[0032] According to one embodiment, the process includes steps consisting of: deleting from the database the object identifiers which, for a certain period, have not been read to determine the first sorting instruction.

[0033] This provision makes it possible to lighten the operations of searching for objects in the database, from their identifiers to retrieve the associated sorting instruction and to update the sorting instructions stored in the database according to the sorting criteria.

[0034] According to one embodiment, the sorting criteria relate to one or more of the following specified or detected attributes: the nature of the material, the color, the shape, the use, the viscosity of the material, a percentage of biogenic material in the object, a percentage of recycled material in the object.

[0035] Thus, many sorting criteria can be taken into account, allowing for complex sorting.

[0036] According to one embodiment, the image stream is acquired by illuminating the first area of ​​the strip alternately under two lighting colors, so that each point of object moving through the first area is illuminated at least once by each of the lighting colors, the two lighting colors being located respectively at the two ends of the visible spectrum.

[0037] In this way, most of the markers present on product packaging can be detected regardless of the color of the packaging with lighting that is simpler to construct and more powerful for the same total number of sources (LEDs) than if three colors of lighting had to be provided.

[0038] According to one embodiment, the images of the image stream are acquired alternately under two different lighting colors, so that each cell is illuminated successively under the two lighting colors.

[0039] According to one embodiment, one of the two lighting colours has a wavelength less than 460 nm and the other of the two lighting colours has a wavelength greater than 630 nm.

[0040] Embodiments may also relate to a sorting system, comprising: a belt conveyor including a belt on which objects to be sorted are placed, an array of cameras for acquiring an image stream of objects present in a first zone of the belt extending over a width of the belt, an array of sensors for acquiring material and / or color detection signals for each cell of a set of adjacent cells located in a second zone extending over the width of the belt, an image processing unit for detecting markers in the image stream, a signal processing unit for determine detected attributes determined from material and / or color detection signals, a sorting device to direct each object present on the belt to an output of the sorting system, and a sorting control unit configured to implement the process defined above.

[0041] According to one embodiment, the system includes a lighting system comprising two sets of monochrome sources alternately illuminating the first zone. Brief description of the figures

[0042] The present invention will be better understood with the aid of the following description of exemplary embodiments with reference to the accompanying figures, in which identical reference signs correspond to structurally and / or functionally identical or similar elements.

[0043] [Fig-1] Figure 1 is a schematic profile view of an object sorting system, according to one embodiment,

[0044] [Fig.2] Figure 2 is a schematic view of a detection and analysis device of the sorting system, according to one embodiment,

[0045] [Fig. 3] Figure 3 is a schematic view of an image of objects detected on a conveyor belt of the sorting system, according to one embodiment,

[0046] [Fig. 4] Figure 4 is a schematic view of an image of objects detected on the conveyor belt of the sorting system, according to one embodiment,

[0047] [Fig. 5] Figure 5 represents the contents of a sorting table at one stage of a sorting process, according to one embodiment,

[0048] [Fig. 6] Figure 6 shows an example of the contents of the sorting table at another stage of the sorting process, according to one embodiment,

[0049] [Fig.7] Figure 7 represents the contents of the sorting table at a subsequent stage of the sorting process, according to one embodiment,

[0050] [Fig.8] Figure 8 represents the contents of the sorting table at a subsequent stage of the sorting process, according to one embodiment,

[0051] [Fig.9] Figure 9 represents the contents of the sorting table at a subsequent stage of the sorting process, according to one embodiment,

[0052] [Fig. 10] Figure 10 represents another example of a control table for a sorting device, according to one embodiment,

[0053] [Fig. 11] Figure 11 is a schematic profile view of an object sorting system, according to another embodiment. Detailed description

[0054] Figure 1 shows an object sorting system according to one embodiment. The sorting system comprises a BCV belt conveyor including a B1 belt on Objects OB to be sorted are deposited on the belt. The B1 belt is driven in translation in a DI direction to convey the objects into a tunnel formed by a roof T1 positioned above the B1 belt. The sorting system also includes a DTD detection device comprising an IS1-IS6 camera array and an IVS sensor array for material and / or color detection. The DTD detection device is positioned to observe an area of ​​the B1 belt downstream of an ZO area where the objects to be sorted OB are deposited. The IS1-IS6 camera array can be combined with VL1 and VL2 lighting devices, which can be focused, to illuminate an area ZI of the B1 belt observed by the cameras at different wavelengths. The IVS sensor array observes an area Z2 of the B1 belt downstream of the ZI area. The sorting system also includes a BLS sorting unit located at one end of the BCV conveyor's exit.The BLS sorting unit includes, for example, a plurality of compressed air ejection nozzles, aligned along a direction L1 perpendicular to the direction DI and parallel to the plane of the belt Bl, each nozzle being controlled by a respective solenoid valve. When one of these valves is opened, the air ejected by the nozzle thus opened pushes the object located above the nozzle towards the outlet SI; otherwise, the objects arriving at the outlet end of the conveyor BCV fall (under the effect of gravity) towards the outlet SO.

[0055] The IVS sensor assembly may include at least one of the following devices: a spectrometer operating in the near or mid-infrared wavelength range and / or in the visible range, a LIBS spectrometer, one or more color cameras for detecting the colors of objects in the Bl band, or more generally for recognizing the appearance of objects (shape, texture, color...), inductive detectors to characterize the presence of metals, an X-ray emitter / detector assembly, and a profilometry or laser triangulation system to detect black objects or objects insensitive to the previously mentioned detection technologies.

[0056] The sorting system may also include a BL turbine to drive air over the Bl belt at a speed substantially corresponding to the speed of movement of the Bl belt in the Dl direction, so that the lightest OB objects deposited on the belt are also driven in the Dl direction at the same speed. The air supplied by the BL turbine is guided into the tunnel formed by the TL roof.

[0057] Figure 2 shows the DTD detection device associated with an analysis device of the sorting system, according to one embodiment. Figure 2 shows the IVS sensor assembly, the IS1-IS6 camera assembly, the associated VL1 and VL2 lighting devices, and the Bl belt exit area with the BLS sorting unit. comprising the NZ nozzles and their respective EV solenoid valves. Figure 2 shows in particular the field observed by each of the IS1-IS6 cameras along the B1 band width (L1 direction). As illustrated, the areas of the B1 band observed by the IS1-IS6 cameras slightly overlap. Each IS1-IS6 camera is connected to a PC1-PC6 image processing unit.

[0058] The IVS sensor assembly is connected to a PCS signal processing unit. The PC1-PC6 and PCS processing units communicate via an NS network with an MPC sorting control unit. A TL terminal can be used to control the MPC control unit. The VL1 and VL2 lighting devices include, for example, light-emitting diode (LED) bars positioned on either side of the detection axes of the IS1-IS6 cameras.

[0059] According to a known technique, the IS1-IS6 cameras are monochrome, and the LED bars comprise two or three sets of monochrome LEDs, each covering a specific color in the visible spectrum. The lights are switched on sequentially, following a cycle controlled by a specially designed LM electronic unit. Image acquisition is synchronous between all the IS1-IS6 cameras and also synchronous with one of the colors of the lighting, the whole system being controlled by the LM unit. The image acquisition rate is adjustable between 30 and 300 fps (frames per second). This refers to the total number of images, all colors combined. By successively activating three colors at the same frequency, 100 images per second are obtained in each color at 300 fps. The use of different colors maximizes contrast for marker detection on objects detected in the B1 band.For example, if a marker is printed in yellow on a white background, it is barely visible to the naked eye, but under blue light, it appears black on a white background with a monochrome camera. Decoding the markers does not require knowing the color that illuminated the detected object.

[0060] According to another known technique, the illumination of the ZI zone observed by the IS1-IS6 cameras can be achieved using white LEDs, pulsed or non-pulsed, and the IS1-IS6 cameras used are RGB color cameras, i.e., three-channel cameras (red, green, and blue). Each image capture therefore provides three monochrome sub-images, one per channel. This solution allows for a higher acquisition frequency per color channel, but at the cost of lower spatial resolution, because the pixels of each channel are juxtaposed on the readout circuit and thus shared between the three channels.

[0061] The inventors observed that two different colors of illumination are sufficient to detect all the markers appearing on product packaging. Furthermore, measurements show that the best contrasts are obtained by alternately using colors of illumination at the two ends of the visible spectrum, namely blue illumination for the lower limit (at a wavelength below 460 nm), and a Red or near-infrared lighting is used for the upper limit (at a wavelength above 630 nm). Using any other color of lighting does not provide a significant benefit. In one embodiment, marker detection is performed by alternately illuminating the ZI zone with blue and red or near-infrared lighting. This solution is highly advantageous because the lighting power of an LED bar can be distributed between two colors instead of three. This ensures 50% more power per color for the same number of light sources.

[0062] In the example shown in Figure 2, the camera array comprises six IS1-IS6 cameras for a bandwidth B1 of 1.2 m. Each camera has a field of view at the bandwidth of 23 cm along the L1 axis by 14 cm along the D1 axis. Each camera is connected to its respective PC1-PC6 image processing unit. Of course, other configurations are possible, depending in particular on the computing power of the image processing units. Thus, for example, several processing units can be connected to one camera, or conversely, several cameras can be connected to one processing unit.

[0063] Each PC1-PC6 image processing unit is configured to analyze the images provided by the IS1-IS6 camera to which it is connected, in order to detect object markers present in each image. The PC1-PC6 image processing units do not communicate with each other, but transmit messages to the MPC sorting control unit at the end of each image processing cycle.

[0064] According to one embodiment, each of the messages thus transmitted to the MPC control unit comprises: - a moment of image capture, - the coordinates (X, Y) in the image of each marker detected in the image, and - an identifier corresponding to each of the detected markers.

[0065] The IVS sensor assembly is, for example, equipped with a scanner that periodically scans the entire width of the B1 band (along the L1 direction) in the Z2 area. The PCS processing unit connected to the IVS sensor assembly periodically provides data in the form of an acquisition area divided into one or more lines (along the L1 direction) of a few hundred adjacent rectangular cells. Thus, an acquisition line comprises, for each cell, a number indicating the cell's position (along the L1 width of the B1 band) (and optionally an acquisition line number), and a code indicating a classification of the detected attribute, for example, a material, a color, etc. The resolution of the IVS sensor assembly can be coarser than that of the IS1-IS6 cameras, since the cells of the IVS sensor assembly can be several millimeters on a side.However, this resolution is sufficient to create a "chemical image" where . The color of each point can represent a given family of objects. Furthermore, this resolution is not necessarily related to the number of solenoid valves (EVs) in the BLS sorting unit. The scanning period of the IVS sensor array is independent of that of the IS1-IS6 cameras.

[0066] Alternatively, the IVS sensor assembly may include a hyperspectral camera visualizing the entire Bl bandwidth, without physical movement to scan a detection line extending across the bandwidth. Nevertheless, each line is acquired at a constant acquisition time, providing data for each cell.

[0067] The PC1-PC6 and PCS processing units and the MPC control unit can be synchronized using known protocols such as, for example, TCP / IP or UDP, with sub-millisecond precision. Furthermore, since the workload of the MPC control unit is relatively low, it is conceivable that the processing performed by the PCS processing unit and the MPC control unit could be handled by a single processing unit.

[0068] The image processing and marker detection algorithms implemented in the PC1-PC6 processing units require relatively significant computing power due to the high number of images to be processed per second and the high resolution of each of these images. Even though these processes can be optimized by parallelizing the calculations using specialized processors (such as GPUs), the marker decoding time can still be long depending on the image. Consequently, it may be possible for the detection algorithm not to necessarily decode all the markers in an image, but to stop at the first marker found and decoded in the image, or at the first marker found in a predefined sub-region of the image.

[0069] Thus, regardless of the specifics of the marker decoding software's operation, not all markers are always decoded. Figure 3 shows an image of the Bl strip, objects Cl, C2 detected by the PC1-PC6 processing units, M1 markers represented as crosses associated with a sort command to output SI, M2 markers represented as circles associated with a sort command to output S0, and M3 markers represented as diamonds that have not been decoded. Thanks to redundancy between successive images, the undecoded M3 markers can be decoded during the processing of subsequent images.

[0070] It turns out that the execution time of an image processing algorithm can be variable. The total time between acquisition and the delivery of a result by each PC1-PC6 processing unit can fluctuate, for example, between 20 and 300 ms. If the distance between the IS1-IS6 cameras and the NZ nozzle bar with the EV solenoid valves is fixed at a value between 1 and 2 m, and the speed of movement of the If the B1 band is located between 2 and 5 m / s, it is possible that an image processing result may be delivered too late to the MPC control unit to be usable. If this occurs, a non-blocking error message may be issued by the PCS control unit.

[0071] The MPC sorting control unit combines the data received from the PC1-PC6 image processing units and the PCS processing unit, and controls the BLS sorting device. To do this, the MPC control unit stores the received data in a detection table containing all the information necessary to combine the data and control the BLS sorting device. The MPC control unit performs image processing to improve the sorting process and derives sorting commands from this data, which it then sends to the EV solenoid valves. The detection table can be saved to a file for later analysis.

[0072] The MPC sorting control unit also includes a user interface accessible from the TL terminal, and presenting a set of menus for configuring the sorting criteria, including for example: - a menu for selecting sorting attributes, - a menu for adjusting the sorting of marked objects, - a menu for adjusting object families, and - optionally, a graphical display of a sorting trial, in the form of a map representing the detection table.

[0073] The information encoded in the markers can be of two types, depending on the marker's encoding capacity. If the markers' encoding capacity is limited (10 to 15 bits per marker), it is possible to directly encode a list of sorting and recycling attributes, that is, the few properties to be used to determine sorting instructions. For example, the property "food use" or not can be encoded on 1 bit, the property "viscosity level" (MFI) can be encoded on 2 bits for "very low", "low", "medium", and "high", and a material code (plastic resins) can be encoded from 1 to 7, on 3 bits.

[0074] If the encoding capacity of the markers is sufficient, for example 42 bits as with barcodes, or more, it is more advantageous to encode a unique object identifier, also called a SKU (Store Keeping Unit). The object identifiers used can be those standardized by the GTIN (Global Trade Identification Number) and used by the international barcode system. Of course, other options are possible, provided they uniquely identify the objects. This object identifier serves as the entry key to access a complete technical data sheet for the object. This data sheet can be accessed via a remote information system, for example via the Internet, and provides, in particular, a list of sorting / recycling attributes.

[0075] When an OB object passes over the Bl strip, only a few milliseconds are available between its detection and the sorting decision. The available time may therefore be insufficient to access remote information and make the sorting decision.

[0076] According to one embodiment, the sorting system comprises a local database SD connected to the sorting control unit MPC and providing a sorting instruction for each marked object ID to be sorted, for example, output S0 / output SI. The local database SD can also store a list of specified object attribute values ​​for each object ID, the sorting instruction being modifiable and determined according to sorting criteria stored by the sorting control unit MPC and selected by the user.

[0077] Each time a marker is decoded, the object identifier extracted from the marker is used to access the local database SD. If this identifier is not already present in the local database, a remote database is queried to obtain, within a few seconds or minutes, the list of specified object attributes corresponding to the extracted identifier. The local database SD is then updated with the identifier, the specified object attributes obtained, and optionally the sorting instruction determined based on the sorting criteria stored by the sort control unit MPC. Thus, the first object(s) associated with an identifier not present in the local database SD are not sorted (sent to output S0), but subsequent objects associated with that identifier can be sorted correctly.

[0078] If the object identifier extracted from the marker is present in the local SD database, a corresponding sorting instruction is read and compared to the sorting instruction resulting from the analysis of the signals from the IVS sensor assembly. A combined sorting decision is established based on these two sorting instructions by the MPC processing unit, which controls the EV solenoid valves. Thus, access to the SD database only needs to be performed once for a given sorting recipe, and only to read the ejection instructions. This arrangement avoids unnecessary calculations or disk accesses.

[0079] According to one embodiment, object identifiers that have not been searched for a certain period to determine the first sorting instruction are deleted from the SD database. This arrangement simplifies the operations of searching for objects in the database, using their identifiers to retrieve the associated sorting instruction, and updating the sorting instructions stored in the database according to the sorting criteria. To this end, a read occurrence counter can be associated with each object identifier stored in the database. This counter can be incremented by one for each object that its identifier is searched in the database to determine the first sorting instruction. This counter can be reset from time to time, by For example, at regular intervals (e.g., weekly). Objects with a zero occurrence counter before being reset are deleted from the SD database.

[0080] According to one embodiment, the object attribute selection menu is displayed on the TL terminal screen. An example of such a menu is shown in the following Table 1:

[0081] [Tables 1] Attribute Selection Material Yes / No Color Yes / No Shape Yes / No Use Yes / No Viscosity Yes / No % Biogenic Yes / No % Recycled Yes / No

[0082] The possible values ​​for each object attribute are predefined. An example of these possible values ​​is shown in the following Table 2:

[0083] [Tables2] Attribute Values ​​Material PET / Sleeved PET / PE / HDPE / LDPE / Rigid PP / PP Film / PS / PVC / Cardboard / Tetra Pak / Other Color Clear / Colored / All Shape Bottle / Tray or Jar / Tube / Hose / All Use Food / Cosmetic / Detergent / All Viscosity Low / Medium / High / All % Biogenic 0-9% / 10%-29% / 30%-49% / 50%-89% / 90-100% / All % Recycled 0-9% / 10%-29% / 30%-49% / 50%-89% / 90-100% / All

[0084] Following the validation of the selections made in Table 1, the "Marked Objects" menu for selecting materials determined by a marker is displayed. The columns of the "Marked Objects" menu are selected from the sorting attribute selection menu (Table 1) and include an additional "Output" column that allows specifying a sorting instruction based on the attributes specified in the other columns. The "Marked Objects" menu is, for example, as shown in the following Table 3:

[0085] [Tables3] Material Colour r Shape Use e Viscosity % biogenic. % recycled Output e PET (1) (2) (3) (4) (5) (5) n / a 1 PET sleeved (1) (2) (3) (4) (5) (5) n / a 1 PE (1) (2) (3) (4) (5) (5) n / a 1 HDPE (1) (2) (3) (4) (5) (5) n / a 1 PELD (1) (2) (3) (4) (5) (5) n / a 1 rigid PP (1) (2) (3) (4) (5) (5) n / a 1 PP film (1) (2) (3) (4) (5) (5) n / a 1 PS (1) (2) (3) (4) (5) (5) n / a 1 PVC (1) (2) (3) (4) (5) (5) n / a 1 Cardboard / Paper (1) (2) (3) (4) (5) (5) n / a 1 Tetra (1) (2) (3) (4) (5) (5) n / a 1

[0086] (1), (2), (3), (4), (5): the cells of table 3 thus referenced contain all the possible choices for the value of the corresponding attribute appearing in the header of the corresponding column, these choices being listed in table 2. Table 3 is displayed when the attributes "Color", "Shape", "Use", "Viscosity", "% biogenic" and "% recycled" have been selected in the attribute selection table (table 1).

[0087] It is possible to duplicate a line from the "marked products" menu following the selection in a cell belonging to the line and to one of the columns "Color", "Shape", "Use", "Viscosity", "% biogenic" and "% recycled" with a value other than "All", to allow specifying another sorting instruction for the same material but having other values ​​for the attributes thus selected.

[0088] According to one embodiment, upon validation of the "marked products" menu, each of the first sorting instructions specified in the "Output" column is written to the local SD database for each marked object ID corresponding to the attribute values ​​indicated in the table row corresponding to the sorting instruction. It is therefore not necessary to reread the choices made in the menus during sorting; only the local SD database is consulted based on the object ID resulting from the decoding of a marker in an image.

[0089] The "object families" menu for selecting materials and colors, detected by the IVS sensor set, includes for each material indicated in the "Material" row of table 2, and possibly each color indicated in the "Color" row of table 2, a set of sorting criteria allowing a sorting instruction to be determined.

[0090] An example of the "object families" menu is shown in the following table 4:

[0091] [Tables4] Material detected Color detected Priority marker Output * PET Clear / Colored / All yes / no S0 / S1 Sleeved PET Clear / Colored / All yes / no S0 / S1 PET Clear / Colored / All yes / no S0 / S1 PE Clear / Colored / All yes / no S0 / S1 HDPE Clear / Colored / All yes / no S0 / S1 LDPE Clear / Colored / All yes / no S0 / S1 Rigid PP Clear / Colored / All yes / no S0 / S1 PP film Clear / Colored / All yes / no S0 / S1 PS Clear / Colored / All yes / no S0 / S1 PVC Clear / Colored / All yes / no S0 / S1 Cardboard / Paper Clear / Colored / All yes / no S0 / S1 Tetra Particle Clear / Colored / All yes / no S0 / S1

[0092] * if the marker is non-priority or if no marker is detected

[0093] If the "color" attribute is not selected in the object attribute selection menu (table 1), the "Color detected" column of the "object families" menu is not displayed.

[0094] The user is invited to select one of the alternatives indicated in each The "Color Detected," "Priority Marker," and "Output" columns of the "Object Family" menu are selected. When a color is set to "Light" or "Colored" in a row, that row is duplicated to allow for specifying a different sorting instruction for the same material but with a different "Color" attribute value. This allows for different sorting instructions to be specified for two object families made of the same material, for example, two PET families such as "Light PET" and "Colored PET." If the "Priority Marker" checkbox is selected (set to "Yes"), the combined sorting decision is determined by the first instruction specified in the "Output" column of the "Marked Objects" menu. The sorting instruction specified in the "Output" checkbox of the "Object Family" menu determines the combined sorting decision in cases where no marker has been detected and the "Priority Marker" checkbox contains the value "No."

[0095] According to one embodiment, the detection table is configured to map the entire space between the area observed by the IS1-IS6 cameras and the ejection line at the downstream end of the Bl strip. The detection table is in the form of a two-dimensional array, consisting of records, each representing a rectangular cell whose height (along the Dl direction) is related to a time increment dependent on the acquisition time of a cell line of the IVS sensor assembly. For example, if a cell line is acquired every 4 ms, and the strip moves at a speed of 3 m / s, the cells in the table have a height of 12 mm. However, the choice of the time increment can also be determined by the ejection technology. The width of each cell represented by the detection table is chosen so that the cells have a shape close to a square.This width can also be related to the spacing between the NZ ejection nozzles of the BLS sorting unit. The position of the objects to be sorted in the detection table is updated at each time increment, according to a circular buffer scheme. The principle of a circular buffer is known to those skilled in the art and is not explained again here.

[0096] The detection table accumulates and combines the results from all IS1-IS6 cameras and all marker images, applying a logical OR to all results provided by the PC1-PC6 and PCS processing units, except in the specific case where contradictory results appear in the same recording. With significant redundancy between images depending on the frame rate, the same cell can be designated multiple times. Each record in the detection table can account for these redundancies. In the event of contradictory results, it is possible, for example, to invalidate the cell for any future action and record a negative redundancy value to track the event.

[0097] Considering the width in the Dl direction of the images taken by the IS1-IS6 cameras, the image acquisition rate and the translation speed of the Bl strip, A point on the strip can be seen multiple times. Such redundancy creates a significant computational load. It is therefore desirable to limit this redundancy without substantially reducing the detected areas. Furthermore, if the cells corresponding to the records in the detection table are more widely spaced than the markers, each cell can contain several markers, which can lead to different sorting commands. In one embodiment, one of the SO or SI outputs—for example, the SI output—is intended to receive selected objects, while the other SO output receives all unselected objects. In case of conflict, the SO output is preferred to avoid polluting the objects sent to the SI output.

[0098] According to one embodiment, each record in the detection table stores the following parameters: - an initial sorting instruction (towards the SO / SI output) determined based on the detected and decoded markers, - a second sorting instruction (towards the SO / SI output) determined on the basis of detected attributes (material, color, ...), obtained by processing the signals from the IVS sensor assembly, - a combined sorting decision (towards the SO / SI output), - an extension rank, - an object identifier obtained from marker decoding,

[0099] - detected attribute values ​​(material, color), and

[0100] - a redundancy count value of detected markers.

[0101] The values ​​of the detected attributes, provided by the PCS processing unit, and the corresponding second sorting instruction, are stored in the records of the detection table taking into account the number of rows in the table corresponding to the distance between the observation area of ​​the IS1-IS6 cameras and the observation area of ​​the IVS sensor assembly.

[0102] Combining data from the PC1-PC6 image processing units and data from the PCS signal processing unit of the IVS sensor assembly allows for the detection of marking errors. Indeed, the material detected by the IVS sensor assembly for a cell in the detection table may not correspond to that deduced from the decoded markers. This situation can occur, for example, if the same mold is used for several materials, or if there have been printing errors in the markers. In case of discrepancy, priority can be given to the IVS sensor assembly, whose measurement is actual and not declarative.

[0103] Combining data from the PC1-PC6 image processing units and data from the PCS processing unit improves the determination of the surfaces to be ejected and therefore the EV solenoid valves to be controlled for sorting each object. Indeed, in many cases, the detected markers do not completely cover the object. This occurs when objects are not marked across their entire surface, or when the label is partially torn off. It also occurs when image processing fails to detect all the markers (computation times are too long, the marked surface is too damaged or dirty, the object is tilted, etc.). In this case, the object's surface area considered for ejection can be extended to all the cells covered by the object detected by the IVS sensor array, starting from cell nuclei centered on the decoded markers. Positive extensions are thus defined around nuclei containing markers specifying object ejection. Similarly, negative extensions are defined around nuclei containing markers specifying not to eject the object.The EV solenoid valves will be activated on all cells covered by an object if the extension is positive, and will not be activated on all cells covered by the object if the extension is negative.

[0104] Combining data from the PC1-PC6 image processing units and data from the PCS processing unit also allows for the sorting of unmarked objects. Even if marker technology is adopted on a large scale, there will always be unmarked products mixed with marked objects. Using the IVS sensor assembly, combined sorting decisions can be made for these objects. Furthermore, a stream of marked objects can be purified of contaminants consisting of unmarked objects.

[0105] Combining data from the PC1-PC6 image processing units with data from the PCS processing unit also reduces redundancy and the required computing power. Indeed, working at a rate of 300 images per second requires significant downstream computing power. By decoding at least one marker per object and entrusting the PCS processing unit with the task of completing the object mapping, it is possible to achieve equally high sorting efficiency despite the reduced frame rate.

[0106] According to one embodiment, the MPC control unit is configured to determine the first and second sort instructions for each cell from the data provided in the messages transmitted by the PC1-PC6 and PCS processing units. For example, the first and second sort instructions can take the values ​​1 (sort to output SI), -1 (sort to output S0), or 0 if no data has been provided for the cell by the PC1-PC6 and PCS processing units. The MPC control unit is then configured to determine the combined sort decision for each cell based on the combination of the first and second sort instructions determined for that cell. For this purpose, the MPC control unit can use the following instruction merge table:

[0107] [Tables5] Instruction 2 Instruction 1 Priority marker: YES Priority marker: NO No detection Compliant product Non-compliant product IF SO SI SO SI X(S1) X(S1) Y (S0) A (SI) C(S0) E(S1) SO O(S0) O(S0) Y (S0) A (SI) C(S0) F (S0) No marker N (SI) M (S0) B (SI) D (S0) • (S0)

[0108] Table 5 provides possible values ​​for the combined sorting decision for a cell in the form of codes, depending on the first sorting instruction (instruction 1) and the second sorting instruction (instruction 2), as well as the criteria selected in the "object families" menu (Table 4). Table 5 also distinguishes between cases where the material and / or color detected for a cell by the IVS sensor assembly is consistent or inconsistent ("Conforming Product" / "Non-Conforming Product") with the material and / or color specified by the marker detected for the cell. Output S0 is selected (no opening of the corresponding EV solenoid valve(s)) in the absence of data that would lead to selecting output SLA. Note that the various codes indicated in Table 5 are intended, in particular, to provide additional information on the value of the combined sorting decision that can be used for statistical purposes.

[0109] In the representation of table 5:

[0110] The code "X" indicates that the corresponding cell is to be sorted towards the SI output because the material detected by the IVS sensor assembly is a material to be sorted with "Priority Marker" set to "yes" and the first sorting instruction indicates SI;

[0111] The code "Y" indicates that the corresponding cell should be sorted to output S0 because there is an inconsistency between the marking associated with the corresponding cell and the material or color detected by the IVS sensor assembly, whereas priority was given to marker detection, this inconsistency may result from a marking error;

[0112] The code "O" indicates that the combined sorting decision of the corresponding cell is determined solely on the basis of the first sorting instruction of the cell, which indicates the output S0, because the material detected by the IVS sensor assembly is a sortable material with "Priority Marker" set to "no";

[0113] The code "A" indicates that the corresponding cell is to be sorted to the IF output in reason for the priority given to detection by the IVS sensor assembly;

[0114] The code "B" indicates that no marker was detected in the corresponding cell, but that the IF output was selected by the second sort instruction;

[0115] The code "C" indicates that the corresponding cell is to be sorted to output S0 due to the priority given to detection by the IVS sensor assembly;

[0116] The code "D" indicates that no marker was detected in the corresponding cell, but that output S0 was selected by the second sorting instruction;

[0117] The code "E" indicates that the corresponding cell is to be sorted to the SI output because of the detected marker, the IVS sensor assembly having detected nothing, this situation being able to occur in the presence of a black object or a material or color detection hole;

[0118] The code "F" indicates that the corresponding cell is to be sorted to output S0 because of the detected marker, the IVS sensor assembly having detected nothing, this situation being able to occur in the presence of a black object or a material or color detection hole;

[0119] The codes "M" and "N" are to be used when priority has been given to the first sorting instruction and no marker has been detected in the corresponding cell. Thus, the code "N" is to be used if the second instruction for the cell selects output SI, and the code "M" is to be used if the second instruction for the cell selects output S0; and

[0120] The code indicates that nothing was detected in the corresponding cell, probably due to the absence of an object in the cell, with output S0 being selected by default.

[0121] The first step determines whether the material detected by the IVS sensor assembly is to be sorted according to the marker ("Priority Marker") or not, as specified for each detectable material by the "object family" menu. If the material is not to be sorted according to the marker, then the first instruction has no impact and the combined decision is equal to the decision of the second instruction. Thus, if the second instruction is SI and at least one marker has been detected (regardless of the first instruction), the combined sorting decision receives the code "A". If the second instruction is SI and no marker has been detected, the combined sorting decision receives the code "B".

[0122] If the second instruction is S0 and at least one marker has been detected (regardless of the first instruction), the combined sorting decision receives the code "C". If the second instruction is S0 and no marker has been detected, the combined sorting decision receives the code "D".

[0123] If the material is to be sorted according to the marker, then a conformity test is performed. This test consists of determining whether the material detected by the sensor assembly The IVS value for the cell corresponds to the material indicated by the detected marker for the cell. If the detected material and the material specified by the marker are inconsistent, there is a material non-conformity problem, and the combined sorting decision receives the code "Y". Conversely, if the material detected by the IVS sensor set is consistent with that specified by the marker, then the cell is considered compliant. In this case, the combined decision applied to the cell corresponds to the first setpoint. Thus, if the first setpoint is SI, then the combined sorting decision receives the code "X"; otherwise (first setpoint is SO), the combined sorting decision receives the code "O". If no marker has been detected, the second setpoint is applied, as it is the only one available: the combined sorting decision receives the code "N" if the second setpoint is SI, and the code "M" if the second setpoint is SO.

[0124] If no material has been detected by the IVS sensor assembly, then the combined sorting decision corresponds to the first setpoint: the combined sorting decision receives the code "E" if the first setpoint is SI, and the code "F" if the first setpoint is SO. If no material or marker has been detected for a cell, then no sorting information is available for the cell, so the combined sorting decision receives the code

[0125] In an example of a sorting recipe, the sorting criteria selected in the "object families" menu are presented in the following table 6:

[0126] [Tableauxô] Material detected Color detected Priority marker Output Clear PET Yes IF Colored PET No SO Sleeved PET All Yes SO Other plastics (PE, PP, PS, PVC) All No SO Fibrous (Cardboard, Tetra Pak) All No SO

[0127] The first row of Table 6 (after the header row) indicates that clear PETs, as detected by the IVS sensor set, are to be sorted according to the marker. The aim is to separate food-grade clear PET from non-food-grade clear PET, which can only be achieved using the attributes provided by the markers. Thus, the combined sorting decision will be determined by the marker for the "Clear PET" cells. The first row allows clear PETs to be sorted according to the markers and directed to the SI output when they are not marked, because they are assumed to be food-grade. The second row of Table 6 directs colored PET, with or without a marker, to the SO output, as these are considered contaminants. The third row of Table 6 sorts sleeved PET based on the presence of markers, since the color under the sleeve is not detectable by the IVS sensor array. The attributes provided by the marker direct the object to the SI output if it is clear food-grade PET, and otherwise to the SO output. If no marker is detected, the SO output is specified to consider the object as a contaminant. The fourth row of Table 6 directs other plastics, regardless of color, with or without a marker, to the SO output, as these are contaminants. The fifth row of Table 6 directs fibrous materials, regardless of color, with or without a marker, to the SO output, as these are contaminants.

[0128] In the example of the sorting recipe partly specified in Table 6, the sorting criteria selected in the "marked objects" menu are presented in the following Table 7:

[0129] [Tables?] Material (specified) Color (specified) Shape Use Outlet PET Clear Tray All SO PET Clear Detergent Bottle SO PET Clear Cosmetic Bottle SO PET Clear Food Bottle SI Sleeved PET All All Food SI Sleeved PET All All Detergent SO Sleeved PET All All Cosmetic SO

[0130] The sorting criteria thus selected allow the SI output to be selected for light-colored PET bottle-shaped food-grade objects and light-colored PET sleeve-type food-grade objects. All other combinations have their output specified as SO because they are considered contaminants.

[0131] Figure 5 illustrates an example of a detection table and shows in particular an example of the distribution of combined sorting decisions in the CL cells of the detection table. Figure 5 shows three objects more or less separated by "empty" codes, namely an OBI object to be sorted towards output SI (code "X") in the upper left, an OB2 object to be sorted towards output S0 (code "O") in the lower right, which touches the first object, and an unmarked OB3 object (code "N") and not contiguous with the OBI, OB2 objects, in the upper right.

[0132] In the OBI object, some cells received the code "X" due to detection of a marker consistent with the material or color detected for these cells by the IVS sensor array. The other cells of the object received the code "M" due to the absence of a marker in the corresponding cells; the material and / or color detected by the IVS sensor array in these cells is assigned to the SO output. In object OB3, the cells received the code "N" due to the absence of a marker in the corresponding cells; the material and / or color detected by the IVS sensor array in the cell is assigned to the SI output. In object OB2, some cells received the code "O," for example, because they contain non-food packaging and the sorting criteria specified that only food packaging should be sorted to the SO output.The other cells of the object were assigned the code "M" due to the absence of a marker in the corresponding cells, the material and / or color detected by the IVS sensor assembly in these cells being assigned to the SO output.

[0133] According to one embodiment, the MPC control unit executes an extension algorithm to expand the cell selection for each of the SO, SI outputs to the maximum number of cells covered by the objects, in order to improve the accuracy of the BLS sorting unit control. This algorithm processes only cells that have received the code "M" or "N", i.e., cells whose detected material is to be sorted according to the marker ("Priority Marker"), but for which no marker has been detected. Furthermore, these extensions are performed only on cells that are adjacent to a cell that has received the code "X" or "O" and if the material detected by the IVS sensor assembly for the cell with "N" or "M" is identical to that of the neighboring cell with "X" or "O".

[0134] Two types of extensions are applied. In so-called "positive" extensions, the areas of cells that received the "X" code for selecting the SI output are enlarged by assigning a non-zero extension rank to cells that received the "N" or "M" code and are adjacent to a cell that received the "X" code. In so-called "negative" extensions, the areas of cells that received the "O" code for selecting the SO output are enlarged by assigning a non-zero extension rank to cells that received the "N" or "M" code and are adjacent to a cell that received the "O" code. Thus, the extension rank assigned to a cell that received the "X" or "O" code is always 0. The extension rank assigned to a cell adjacent to a cell that received the "X" or "O" code is 1. The extension rank assigned to a cell adjacent to a cell that received the "n" rank is n+1.The adjacency relationship applied here can be, for example, a 4-way connection (taking into account neighboring cells located above, below, to the left, and to the right of the cell considered) or an 8-way connection (also taking into account all neighboring cells located diagonally from the cell considered), depending on the number of cells considered adjacent to a cell located outside the edges of the zone. considered.

[0135] According to one embodiment, several extension iterations are performed by traversing the detection table at each iteration. Each iteration adds a new row of cells with an extension rank incremented by one around the already extended areas. Each time an extension rank is assigned to a cell, the detection table record corresponding to the cell can also receive the marker identifier of the cell with a lower extension rank to which it is adjacent.

[0136] If two objects of the same material are contiguous as illustrated in Figure 4, there is a risk that the extension ranks assigned by successive iterations will extend from a marked object into a neighboring unmarked object. Indeed, Figure 4 represents an image taken by the IS1-IS6 cameras containing a marked object C3 and an unmarked object C4. Assigning extension ranks to the marked object risks extending the area occupied by the marked object into that of the marked object, for example, up to the dashed line extending into object C4. As a result, cells covered by the unmarked object of object C4 will be ordered for sorting in the same way as those covered by the marked object C3. The unmarked object (C4) may therefore be mistakenly sent to the same output as the marked object (C3).

[0137] The concept of numbered extension ranks allows this risk to be controlled, and a maximum extension rank can be defined, for example, in one of the menus displayed by the TL terminal. This maximum extension rank can be different for positive and negative extensions. It can also be specific to each material detected or specified by the markers or to each marked product identifier. In this case, a column can be added to the "object family" menu and / or the "marked objects" menu to allow the specification of the maximum extension rank.

[0138] Each maximum extension rank thus defines the number of iterations to be executed for the corresponding extension type or product type. One of the menus displayed by the TL terminal can be used to specify that either output S0 or SI is preferred. Thus, if output S0 is preferred, negative extensions are performed before positive extensions at each iteration. It can be configured to prevent assigning a non-zero extension rank to a cell when the cell's identifier field is already filled. This ensures that the cell is assigned to the object of the same family whose marker is closest in the images.

[0139] Figure 6 illustrates the contents of the detection table after the execution of a first iteration of the extension algorithm on the table shown in Figure 5. In the representation in Figure 6, cells that have received the code "N" or "M" and the extension rank 1 are denoted by the code "#" if they are adjacent to a cell that has received the code "X" (positive extension) and by the code "e" if they are adjacent to a cell having received the code "O" (negative extension).

[0140] Figure 7 illustrates the content of the detection table after the execution of a second iteration of the extension algorithm on the table illustrated by Figure 6. In the representation of Figure 7, the cells having received the code "N" or "M" and the extension rank 2 are noted by the code "#2" if they are adjacent to a cell having received the code "#" and by the code "e2" if they are adjacent to a cell having received the code "e".

[0141] Figures 8 and 9 represent the contents of the detection table after the execution of a third and a fourth iteration of the extension algorithm on the table illustrated in Figure 7, in the case where the maximum rank is set to 2 for positive extensions, and at least 4 for negative extensions. In the representation in Figure 8, cells with the code "N" or "M" and an extension rank of 3 are denoted by the code "e3" if they are adjacent to a cell with the code "e2". In the representation in Figure 9, cells with the code "N" or "M" and an extension rank of 4 are denoted by the code "e4" if they are adjacent to a cell with the code "e3".

[0142] At the end of the execution of all the required iterations of the extension algorithm, the remaining cells assigned the code "N" or "M" belong to objects not containing markers, such as the OB3 object located in the upper right of Figures 5 to 9, and to areas of a marked object that have not been reached by the extension process. Indeed, cells assigned the code "N" or "M" located beyond the maximum extension rank relative to the "X" or "O" kernels do not receive a non-zero extension rank. Such an area appears in the lower left of the OBI object. However, a large majority of the surface of the OBI object is already selected for the SL output. The risk of sorting error is therefore low.

[0143] The choice of maximum extension ranks serves several purposes. First, it aims to ensure efficient sorting of objects to be directed to the SI output thanks to positive extensions. It also aims to prevent overflow onto neighboring unmarked objects, and thus avoid accidentally directing them to the wrong output. In the case of negative extensions, the aim is to prevent an object that should be sent to the S0 output, but which is not completely covered by the extensions, from being unintentionally directed to the SI output.

[0144] According to one embodiment, the MPC control unit is configured to successively read each line (extending along the L1 direction) of the detection table and to open the solenoid valves EV corresponding to the cells of the read line, associated with the combined sorting decisions set to "X", "N", "A", "B", "E", and the extension ranks "# <n>"(n=", 2, 3, ..., maximum positive extension rank), in order to send the corresponding object to the SI output, the corresponding EV solenoid valves to the cells of the row read, associated with the combined sorting decisions at "Y", "O", "M", "C", "D", "F", and the extension ranks "e <n>"(n=", 2, 3, maximum negative extension rank) remain closed. The cells whose EV solenoid valves will be opened successively line by line (extending along the L1 direction) are shown in gray in Figure 9. Figure 10 shows a sequence of EV solenoid valve control lines obtained from the extension table in Figure 9 by replacing the combined sorting decision codes with the corresponding output SI or S0, with output S0 being selected by default. The control table in Figure 10 indicates for each cell whether output SI is selected, with empty cells in the table indicating that output S0 is selected. If the number of cells in the width of the table in Figure 10 is equal to the number of EV solenoid valves in the BLS sorting unit, each cell in this table defines the control of one solenoid valve.

[0145] According to one embodiment, the MPC control unit is configured to archive the rows (extending along the L1 direction) of the detection table after reading and controlling the EV solenoid valves. Each archived row can be indexed by the time elapsed since the start of a sorting sequence following the definition of the sorting criteria. To limit the volume of data thus archived, it may be decided not to save rows of empty cells.

[0146] This archiving allows for a posteriori analysis of the performance of the sorting system.

[0147] Archiving the rows of the detection table can be used to determine the areas occupied by the objects sorted on the Bl strip by calculating the number of cells assigned to each marker identifier. This process can be used to estimate the number of different objects that have been processed. This estimate can be based on an average detected area recorded per object identifier (or SKU). This estimate can also be performed by analyzing the connectivity between cells corresponding to the same marker identifier. This estimate is more reliable the more detailed the marker identifiers are. However, errors can occur in the presence of a cluster of objects in contact with the same marker identifier, which may be interpreted as a single object.To limit the impact of these errors, a maximum area per object identifier can be defined, which makes it possible to deduce whether it is a cluster or a single object.

[0148] Furthermore, discontinuous object marking, which would not be compensated for by the extensions performed (discontinuity in marker detection and detection data from the IVS sensor array), may occur. The same object then appears as several clusters of cells. Conventional image processing algorithms, such as "closing," can be implemented to group the clusters if they are a single object.

[0149] It will be clear to a person skilled in the art that the present invention is capable of various embodiments and applications. In particular, the invention is not limited to a two-output sorting system but can also be applied to a system with three or more outputs. Thus, Figure 11 represents a sorting system that differs from the sorting system of Figure 1 in that it has three outputs SO, SI, S2, and a second sorting device BL1 located at one end of the BCV conveyor's output, which can be activated to direct an object to be sorted towards output S2. When both sorting devices BLS and BL1 are inactive, the objects to be sorted are directed towards output SO. In this case, the sorting criteria specification menus (Tables 3 and 4) and the merge table (Table 5) are adapted by introducing a third alternative value (S2) in the "Output" column.

[0150] Furthermore, other rules for combining the first and second sorting instructions to determine the combined sorting decision can be applied as needed. In particular, different priorities applied to the sorting instructions can be implemented without departing from the scope of the present invention.

[0151] The execution of the extension algorithm is also optional, given that this algorithm simply expands the areas subjected to the sorting commands and thus reduces sorting errors. Furthermore, the contours of objects present on the B1 band can be detected by implementing a known image processing method, for example, based on one or more artificial intelligence or neural network models. The extension algorithm can also be performed earlier on images from the IS1-IS6 cameras. It is also possible to use artificial intelligence software to recognize other aspects of objects such as shape, texture, color, etc.

[0152] The order of the two sensor sets described can be reversed. Indeed, the system can operate equally well with the IVS sensor set placed upstream in the direction of the Bl strip's movement, before the IS1-IS6 cameras placed downstream.

[0153] The implementation of the SD database is also optional, given that the determination of the first sorting instruction can be carried out without this local database, by accessing a remote database to determine the specified attributes (linked to the detected marking identifier) ​​and applying the sorting criteria to these attributes.

[0154] It should also be noted that the detection and decoding of markers using alternating illumination with only two colors located respectively at the extremes of the visible spectrum constitutes a separate invention distinct from the object sorting process. Thus, the present description also covers a method for reading markers on an object, comprising the steps of: illuminating the object alternately with two colors located respectively at the extremes of the visible spectrum, and acquiring images of the object when illuminated with each of the two colors. lighting colors, detect one or more markers on the object in images where the object is illuminated under one of the two lighting colors, and decode each detected marker.

[0155] Image acquisition can be carried out using an image sensor sensitive to both colors of illumination, or using two sensors sensitive respectively to the two colors of illumination.< / n> < / n>

Claims

Claims

1. 1. A method of sorting objects comprising steps of: place objects to be sorted on a belt (Bl) of a belt conveyor (BCV); acquiring a stream of images of objects present on a first zone (Zl) of the strip extending over a width of the strip; acquiring material and / or color detection signals for each cell of a set of adjacent cells (CL) located in a second zone (Z2) extending across the width of the strip; for each of the cells, process the detection signals to determine detected material and / or color attributes; detect markers in the image stream of the first zone; for each detected marker, decode the marker to determine an object identifier; for each decoded marker, assign the object identifier determined by the decoding of the marker to the cells covered by the decoded marker; determine specified attributes for each object identifier determined from a decoded marker; for each cell associated with an object identifier, determine a first sorting instruction based on sorting criteria and specified attributes; for each cell, determine a second sorting instruction based on the sorting criteria and the detected attributes; for each cell, determining a combined sorting decision based on the cell's first and second sorting instructions and a set of combination rules; according to a set of extension rules, extending the combined sorting decision of cells associated with an object identifier to neighboring cells not associated with an object identifier; and control a sorting device (BLS, BL1) to direct each object present on the strip towards an exit (SO, SI, S2) selected according to the combined sorting decisions of the cells opposite the sorting device.

2. 2. The method of claim 1, wherein, according to the set of combination rules, the combined sorting decision for a cell (CL) is: conforms to one of the first and second sorting instructions for the cell if these are identical, assigned to one of the outputs (SO, SI, S2) of the sorting system in the event of a contradiction between the first and second sorting instructions for the cell, the output of the sorting system being determined according to the sorting criteria, in accordance with the first sorting instruction of the cell if the second sorting instruction is undetermined due to an absence of significant detection of material and / or color in the cell, in accordance with the second sorting instruction of the cell, if the second sorting instruction of the cell is determined and if the sorting criteria taking into account the detected attributes specify that the second sorting instruction has priority, and determined according to the sorting criteria and the combined sorting decision of an adjacent cell, if the first sorting instruction is undetermined due to an absence of detection of a marker in the cell.

3. 3. A method according to claim 1 or 2, comprising a first extension operation comprising steps consisting in: selecting at least one cell (CL) of a first extension rank, not associated with an object identifier, for which the sorting criteria assign a priority to the first instruction, and which is adjacent to a core of at least one cell associated with an object identifier, for which the sorting criteria assign a priority to the first instruction, and for which the material specified by the marker corresponds to the material detected by the sensor assembly (IVS) for the adjacent cell and the selected cell; and assigning to the combined sorting decision of each selected cell a value equal to that of a cell of the core.

4. 4. A method according to claim 3, comprising an operation of further extension comprising steps consisting in: selecting at least one cell (CL) belonging to a higher extension rank, not associated with an object identifier, for which the sorting criteria assign a priority to the first instruction, and which is adjacent to at least one cell belonging to a lower extension rank, and for which the material detected by the sensor assembly (IVS) corresponds to that of the selected cell; and assigning to the combined sorting decision of each cell selected for the higher extension rank a value equal to that of the cell belonging to the lower extension rank.

5. 5. Method according to claim 4, in which several extension operations are carried out up to a maximum number of extension operations defined for each output (S0, SI, S2) of the sorting system.

6. 6. The method of claim 5, wherein the maximum number of extension operations is defined for each identifier or each value of a specified attribute.

7. Method according to one of claims 3 to 6, comprising the implementation of a detection table comprising for each cell: - the first sorting instruction, - the second sorting instruction, - the combined sorting decision, - the extension rank, and - the object identifier resulting from a marker decoding.

8. Method according to one of claims 1 to 7, in which the determination of the specified attributes from each object identifier determined using a decoded marker, comprises a step of searching for the object identifier in a local database (SD) storing object identifiers capable of being extracted from the specified markers and attributes associated with each object identifier.

9. A method according to one of claims 1 to 8, comprising steps of: receiving sorting criteria; and updating a database (SD) storing object identifiers capable of being extracted from the specified markers and attributes associated with each object identifier, the updating of the database comprising determining a sorting instruction for each object identifier based on the sorting criteria and the specified attributes associated with the object identifier, the first sorting instruction for each cell (CL) associated with an object identifier being the sorting instruction associated with the object identifier in the database.

10. 10. Method according to claim 8 or 9, comprising steps consisting of: deleting from the database (SD) the object identifiers which, during a certain period, have not been read to determine the first sorting instruction.

11. 11. Method according to one of claims 1 to 10, in which the sorting criteria relate to one or more of the following specified or detected attributes: the nature of the material, the color, the shape, the use, the viscosity of the material, a percentage of biogenic material in the object, a percentage of recycled material in the object.

12. Method according to one of claims 1 to 11, in which the image stream is acquired by illuminating the first area of ​​the strip (Bl) alternately under two lighting colors, so that each point of the object moving through the first area is illuminated at least once by each of the lighting colors, the two lighting colors being located respectively at the two ends of the visible spectrum.

13. 13. Method according to one of claims 1 to 12, in which the images of the image stream are acquired alternately under two different lighting colors, so that each cell (CL) is illuminated successively under the two lighting colors.

14. The method of claim 13, wherein one of the two illumination colors has a wavelength less than 460 nm and the other of the two illumination colors has a wavelength greater than 630 nm.

15. 15. Sorting system, comprising: a belt conveyor (BCV) comprising a belt on which objects to be sorted (OB1, OB2, OB3) are deposited, a set of cameras (IS1-IS6) for acquiring a stream of images of objects present on a first zone (Z1) of the belt extending over a width of the belt, a set of sensors (IVS) for acquiring material and / or color detection signals for each cell of a set of adjacent cells (CL) located in a second zone (Z2) extending over the width of the belt, an image processing unit (PC1-PC6) for detecting markers in the stream of images, a signal processing unit (PCS) for determining detected attributes determined from the material and / or color detection signals, a sorting member (BLS, BL1) for directing each object present on the belt towards an outlet (S0, SI, S2) of the sorting system,and a sorting control unit (MPC) configured to implement the method according to one of claims 1 to 9.,

16. 16. A sorting system according to claim 15, comprising a system lighting system comprising two sets of monochrome sources (VL1, VL2) alternately illuminating the first zone (Zl).

Images