EP3887069B1 - System and method for characterizing and sorting waste, in particular packaging waste - Google Patents

Description

The present invention relates to the field of characterization and sorting of waste and more particularly packaging, in particular packaging made of glass, metal, plastic, paper, cardboard.

A first type of technology used for automated sorting relies on optical sorting machines, which generally use light spectrometry to characterize the material of objects in a waste stream. According to this technology, objects are irradiated by a light spectrum, generally in infrared lengths, sometimes supplemented by additional analyses, and a sensor records the reflected spectrum, to compare it with spectra recorded in a database. spectra, which makes it possible to identify the material of irradiated objects. Such a process is for example described in the application WO2013/027083 . However, the discrimination performance between different materials is not completely satisfactory, particularly in the field of plastic, where new complex flows have been placed on the market (multilayer type, complex assemblies, new opaque resins, etc.) which are not always well recognized or in the case of buyers requiring high purity rates (sometimes well above 95%), required for the recycling of certain plastics.

Also recently, systems using visible image analysis have emerged, notably thanks to the development of artificial intelligence, and algorithms developed using learning methods using image banks ( “deep learning” in English) in order to recognize the object itself (by its shape, its appearance, etc.) and no longer the material making up an object. The recognition of objects to be sorted by waste sorting robots (or simply to be characterized), currently on the market, is generally based on a system of online waste characterization arches allowing the analysis of images obtained by illumination under light white and detection in the visible spectrum. Typically, the flow of objects (bottles, bowls, trays, cans, boxes, films, pieces of paper or cardboard, etc.) is illuminated by white light, and the images are captured by a camera (active in visible light), images which are then analyzed using using algorithms to identify/characterize flow objects.

However, the performance of these visible detection systems is still lower than operators' expectations (to date, around 85% recognition rate on average) and the qualities of the products after sorting by the robots do not meet generally not meeting the criteria of buyers of secondary raw materials, requiring the addition of human sorters in addition to robots.

This low level of performance of the object recognition system is notably due to the fact that the analysis is currently carried out only with white light and with a camera in the visible: there are therefore few contrasts and discriminating factors for the 'identification. In particular, transparent objects are barely visible, superimposed objects can be misidentified (a transparent bottle above a colored bottle is generally considered to be a colored bottle for example) and nested objects are misidentified (in particularly, PET (polyethylene terephthalate) bottles nested in an aluminum can). We can also mention the problem of discrimination between opaque PET and HDPE (high density polyethylene), two plastics used for the manufacture of milk bottles: opaque PET is currently considered a contaminant of HDPE, it is therefore appropriate to reduce to minimum the opaque PET content of HDPE batches, but current automatic sorting systems only provide mediocre performance for the moment.

We know in particular the document WO 2015/063300 relating to a system for characterizing objects in a flow of objects to be sorted.

There is therefore a need for an automated waste sorting process and system, which is more discriminating while being simple to implement and if possible with little additional cost compared to the systems currently on the market.

Summary of the invention

The applicant has demonstrated that the use of lights of different types to irradiate a waste stream makes it possible to obtain more contrasting images, facilitating image analysis and resulting in better discrimination of waste according to their material.

It will be noted that the invention applies not only to the characterization and sorting of waste, but to the characterization and sorting of any object in general.

• Un organe d'acquisition d'image dans le spectre visible installé de sorte à pouvoir acquérir au moins une image d'une portion du flux d'objets à trier, l'organe d'acquisition d'image couvrant visuellement une zone appelée zone d'identification des objets à trier;
• Une première source lumineuse, émettant dans le spectre visible, installée en surplomb et éclairant ladite portion de flux d'objets à trier dont ladite au moins une image est acquise par l'organe d'acquisition d'image 8 ;
• Un organe de caractérisation apte à caractériser les objets de ladite portion du flux d'objets à trier en fonction de ladite au moins une image acquise ;
• Une deuxième source lumineuse, de nature distincte de la première source lumineuse, permettant l'apparition d'informations visuelles supplémentaires dans le spectre visible sur ladite au moins une image acquise ;

l'organe de caractérisation étant en outre adapté pour caractériser lesdits objets de ladite portion du flux d'objets en fonction desdites informations visuelles supplémentaires.Thus, an object of the invention relates firstly to a system for characterizing objects from a flow of objects to be sorted, the flow of objects to be sorted being installed on a conveyor device, comprising:

• An image acquisition member in the visible spectrum installed so as to be able to acquire at least one image of a portion of the flow of objects to be sorted, the image acquisition member visually covering an area called zone d identification of objects to be sorted;
• A first light source, emitting in the visible spectrum, installed overhead and illuminating said portion of flow of objects to be sorted of which said at least one image is acquired by the image acquisition member 8;
• A characterization unit capable of characterizing the objects of said portion of the flow of objects to be sorted as a function of said at least one acquired image;
• A second light source, of a nature distinct from the first light source, allowing the appearance of additional visual information in the visible spectrum on said at least one acquired image;

the characterization member being further adapted to characterize said objects of said portion of the flow of objects as a function of said additional visual information.

The appearance of this additional visual information, whether color reflection and/or fluorescence, allows the addition of additional discriminating pixels in the acquired image to improve the characterization of the objects in the image.

Advantageously and in a non-limiting manner, said at least one second light source emits ultraviolet light allowing the appearance of fluorescence in the visible spectrum when an object in the object flow portion reacts to ultraviolet.

Advantageously and in a non-limiting manner, said at least one second light source emits light in the visible spectrum, of distinct color and/or distinct intensity from the first light source, and oriented so as to illuminate at a lighting angle distinct from the first light source the objects of the object flow portion illuminated by the first light source. This makes it possible to better highlight the contours of objects in the flow of objects.

Advantageously and in a non-limiting manner, said at least one second light source is installed so as to define a main lighting axis forming an acute angle with a plane in which the device for conveying said flow of objects extends. This improves the appearance of distinctive light contours on the edges of objects.

In particular, the second lighting source forms an angle of 30° to 45° with the plane in which the device for conveying said flow of objects extends, which ensures relatively grazing lighting capable of illuminating a wide area. of objects to detect.

The system further comprises an object sampling unit connected to the characterization member, the sampling unit being configured to sample objects according to predetermined characteristics, obtained via the characterization member.

In particular the picking unit is a robotic gripping unit.

1. a) fournir un flux d'objets à trier ;
2. b) illuminer au moins une partie dudit flux avec au moins une première source lumineuse et une deuxième source lumineuse de manière concomitante, la première et la deuxième source lumineuse étant de natures différentes, et au moins une des deux sources comprenant des longueurs d'onde du spectre visible,
3. c) acquérir au moins une image dans le spectre visible de ladite partie de flux illuminée, ladite deuxième source lumineuse permettant l'apparition d'informations visuelles supplémentaires dans le spectre visible sur ladite au moins une image acquise;
4. d) détecter au moins un objet dans ladite image acquise ;
5. e) caractériser ledit objet détecté en fonction des informations visuelles acquises dans ladite au moins une image, telles que sa couleur et/ou sa transparence et/ou sa matière et en fonction desdites informations visuelles supplémentaires.

Another object of the invention relates to a method for characterizing objects to be sorted, comprising the following successive steps:

1. a) provide a stream of objects to sort;
2. b) illuminating at least part of said flow with at least a first light source and a second light source concomitantly, the first and second light sources being of different natures, and at least one of the two sources comprising wavelengths of the visible spectrum,
3. c) acquiring at least one image in the visible spectrum of said illuminated flow portion, said second light source allowing the appearance of additional visual information in the visible spectrum on said at least one acquired image;
4. d) detect at least one object in said acquired image;
5. e) characterize said detected object as a function of the visual information acquired in said at least one image, such as its color and/or its transparency and/or its material and as a function of said additional visual information.

Advantageously and in a non-limiting manner, the first light source is a white light source, and
the second light source is chosen from an ultraviolet light source, a monochrome light source of the visible spectrum, or a mixture thereof.

• la lumière UV génère un phénomène de fluorescence pour certaines matières, qui va apporter des caractères discriminants pour la détection de celles-ci, notamment la composition (matière) du déchet, sa masse, sa forme, sa surface ou l'épaisseur de certaines parties de celui-ci (i.e. forme ou aspect) et
• les sources de lumière monochrome (de couleur) apportent, notamment en fonction de la matière et/ou de l'opacité des déchets, certaines réflexions colorées (au niveau des angles et de certaines surfaces planes) et des zones d'ombre, qui permettent d'améliorer la discrimination dans un flux de déchets. En effet, les zones de réflexion ainsi que les zones d'ombre sont différentes en fonction de la forme, la surface, l'orientation de certaines surfaces et angles, la composition du déchet.

Object detection is improved in the visible spectrum because:

• UV light generates a fluorescence phenomenon for certain materials, which will provide discriminating characteristics for their detection, in particular the composition (material) of the waste, its mass, its shape, its surface or the thickness of certain parts of it (ie form or appearance) and
• monochrome (colored) light sources provide, particularly depending on the material and/or opacity of the waste, certain colored reflections (at angles and certain flat surfaces) and shadow areas, which allow to improve discrimination in a waste stream. Indeed, the reflection zones as well as the shadow zones are different depending on the shape, the surface, the orientation of certain surfaces and angles, and the composition of the waste.

• f) une étape d'irradiation d'une partie au moins du flux de déchet par une source de lumière infrarouge, notamment une source de lumière dans le proche infrarouge (NIR),
• g) une étape de détection du spectre infrarouge réfléchi du flux irradié de l'étape f), à l'aide d'un capteur d'infrarouge,
• h) une étape d'analyse du spectre infrarouge de l'étape g) pour caractériser les déchets dudit flux, en particulier en fonction de leur matière.

Advantageously and in a non-limiting manner, the method further comprises an infrared characterization step, comprising:

• f) a step of irradiating at least part of the waste stream with an infrared light source, in particular a near-infrared (NIR) light source,
• g) a step of detecting the reflected infrared spectrum of the irradiated flow of step f), using an infrared sensor,
• h) a step of analyzing the infrared spectrum of step g) to characterize the waste in said flow, in particular according to their material.

Thus, we can combine characterization in the visible spectrum, in the ultraviolet with an infrared, or near infrared, characterization technique, according to a method known as Near Infra-Red (NIR) in English.

1. a) une étape de mise en oeuvre de la méthode de caractérisation de déchets tel que décrite précédemment ; et
2. b) une étape de tri automatisé de déchets sur la base de la caractérisation de l'étape a), en fonction de paramètres prédéterminés, tels que la matière, la couleur et/ou la transparence du déchet.

The invention also relates to a method of sorting waste, said method comprising the following successive steps:

1. a) a step of implementing the waste characterization method as described above; And
2. b) a step of automated sorting of waste based on the characterization of step a), according to predetermined parameters, such as the material, color and/or transparency of the waste.

In particular, step b) is carried out using a robotic sampling unit.

As it implements the characterization method of the invention, the sorting method makes it possible to obtain sorted waste streams with a purity and/or quality superior to that obtained with conventional characterization methods and systems using a unique light source.

Furthermore, the method of the invention is easy to implement, in particular on commercial sorting units or detection arches: the modifications to be made are minimal (simple addition of complementary light sources, and possibly adjustment of the bank of images).

• un convoyeur, ledit convoyeur comprenant une zone de caractérisation d'objets et une zone de prélèvement d'objets,
• un système de caractérisation d'objets tel que décrit précédemment, comprenant un organe de caractérisation positionné autour ou au-dessus de ladite zone de caractérisation d'objets.

Another object of the invention relates to a sorting assembly comprising:

• a conveyor, said conveyor comprising an object characterization zone and an object sampling zone,
• an object characterization system as described above, comprising a characterization member positioned around or above said object characterization zone.

The sorting assembly is in particular adapted to implement the method described above.

Detailed presentation

For the purposes of the present invention, “two light sources of different nature” mean two light sources whose emitted wavelength spectrum is not completely identical. For example, two light sources of different nature are a white light source and a UV light source, or a white light source and a monochrome light source.

For the purposes of the present invention, an “ultraviolet (UV) light source” is a light source emitting light in wavelengths between 10 and 400 nm. A UV source can emit in all or part of the ultraviolet spectrum.

For the purposes of the present invention, a “white light source” is a light source emitting light in wavelengths between 400 and 700 nm, possibly between 400 nm and 670 nm. A white light source emits in the entire visible spectrum, unlike monochrome light.

For the purposes of the present invention, a “monochrome light source” is a light source emitting in only part of the visible light spectrum (i.e. only part of the white light spectrum). For example, a blue monochrome source can emit in wavelengths between 470 and 485 nm, while a red monochrome source can emit in wavelengths between 610 and 650 nm, and a green monochrome source can emit in wavelengths between 500 and 555 nm.

For the purposes of the present invention, an “infrared (IR) light source” is a light source emitting light in wavelengths between 700 nm and 350 µm. An IR source can emit in all or part of the IR spectrum. Advantageously, the IR light source is a near-infrared source, that is to say emitting light in wavelengths between 700 nm and 2.5 µm, preferably between 1 and 2.5 µm.

For the purposes of the present invention, illumination “concomitantly” by at least 2 light sources means common illumination and at the same time of at least part of the waste stream, so as to obtain a superposition of the light spectra of the two light sources on this waste stream.

For the purposes of the present invention, a “waste stream” means a set of pre-sorted waste. It may for example be waste from a selective sorting of household waste sector, that is to say essentially comprising packaging made of paper, cardboard, plastic and/or metal (for example, it may be a mixture of PET bottles, HDPE bottles, aluminum or steel cans or boxes, plastic films, or mixtures of paper-cardboards, such as newspapers, magazines, office papers, boxes in cartons or cardboard boxes, etc.). According to a particular embodiment, it is a set of “monomaterial” waste, that is to say waste comprising a majority (that is to say more than 60% in number, preferably more than 70% by volume, more preferably more than 85% by volume or even more than 95% by volume) elements of the same material. In particular, it is plastic waste, or a mixture of paper and cardboard waste.

Plastic waste includes different types of plastic: we generally have a mixture of transparent and opaque plastics, colored or not, in particular waste in PET, in PP (polypropylene), in PE (polyethylene), in particular in HDPE, in PS ( Polystyrene) or any resins generally used in packaging.

For the purposes of the present invention, “waste characterization” means the determination of a certain number of parameters associated with the waste, in particular its material, color and/or transparency. This step is a prerequisite for sorting, which makes it possible to obtain batches of waste that are homogeneous in material, color and/or transparency, which is necessary for recycling. For example, transparent PET obtained by recycling transparent PET will be of better quality if the “purity” and homogeneity of the waste used for recycling is greater.

For the purposes of the invention, the term “characterization” of waste is understood in the broad sense including both the characterization of the materials composing the waste, as explained previously, and the identification of the waste, for example by recognizing their shape.

In the present invention, the percentages in number are calculated in relation to the total number of objects considered, in particular in relation to the total number of waste to be characterized respectively to be sorted.

1. Waste characterization method

According to a particular embodiment, the waste stream comprises plastic waste, in particular transparent or opaque plastic.

According to another particular embodiment, the waste stream comprises paper and/or cardboard waste.

According to one variant, the waste stream consists of paper and/or cardboard waste, in particular of a different color.

The waste stream is supplied on a carrier, which may be light colored or dark colored. Note that the color of the support may not be homogeneous in time and space. In fact, the support is generally a conveyor belt. The color of the support can be chosen so as to optimize the contrast effects during the illumination of step b).

Advantageously, the first light source being a white light source, and the second light source being chosen from an ultraviolet light source, a monochrome light source, or a mixture of these.

The illumination of step b) is preferably continuous for the two light sources, so that the waste stream is illuminated by light with a homogeneous spectrum over time.

Typically, the second light source comprises an ultraviolet light source, optionally in combination with at least one monochrome light source. In particular, the second light source may consist of an ultraviolet light source. The UV light source may emit all or part of the UV spectrum, depending on the parameters to be determined, particularly in terms of the shape, material, opacity, thickness and/or color of the objects to be characterized.

According to a particular embodiment, the second light source comprises a monochrome light source, such as a blue, green, yellow or red monochrome source, or a mixture of these, provided that their combination does not form light white. For example, the second light source includes a blue or red monochrome source.

According to a particular embodiment, the second light source comprises an ultraviolet light source in combination with at least one monochrome light, in particular red, green, blue or yellow monochrome light. In particular, the second light source may consist of an ultraviolet light source in combination with monochrome light, such as blue or red monochrome light.

According to a particular embodiment, the second light source comprises an ultraviolet light source in combination with at least two monochrome light sources, in particular a red, green, blue or yellow monochrome light source, preferably a red monochrome light source. and a green monochrome light source.

• Les objets en matière synthétique (de type bouteilles et flacons en plastique, films plastiques, autres objets en plastique, tissus synthétique, ...),
• Les objets composés de matières organiques (de type bois, papier, cartons, coton, ...) ou
• Les matières métalliques (de type canettes, barquette en aluminium, boîtes à conserve, film alu, ...) ou
• Les matières minérales (verre, céramique, pierre, sable, ...).
• L'étape c) est usuelle pour un homme du métier.

The combination of light sources provides a notable increase in identification performance by improving discrimination in the recognition process for any object, whether:

• Objects made of synthetic material (such as plastic bottles and flasks, plastic films, other plastic objects, synthetic fabrics, etc.),
• Objects made of organic materials (such as wood, paper, cardboard, cotton, etc.) or
• Metallic materials (such as cans, aluminum trays, cans, aluminum film, etc.) or
• Mineral materials (glass, ceramic, stone, sand, etc.).
• Step c) is usual for a person skilled in the art.

The image in step c) means an image at a time T. It may change over time (in particular because the waste stream is moving).

Step d) is carried out in particular by computer. It may include a sub-step of comparing a part of an image to an image bank, associating images with characterization parameters such as color, opacity, thickness, material, etc. Step d) may also include an automated learning sub-step (“deep learning”), in particular using so-called artificial intelligence algorithms.

According to a variant of the invention, step d) also includes an analysis of the coverage rate of the support (in particular thanks to the reinforcement of contrasts and contours, in particular for transparent objects).

• e) une étape d'irradiation du flux de déchet par une source de lumière infrarouge, notamment une source de lumière dans le proche infrarouge (NIR),
• f) détecter le spectre infrarouge réfléchi du flux irradié de l'étape e), à l'aide d'un capteur d'infrarouge,
• g) analyser le spectre infrarouge de l'étape f) pour caractériser les déchets dudit flux, en particulier en fonction de leur matière.

The characterization method may also include an infrared characterization step. Such a step typically includes:

• e) a step of irradiating the waste stream with an infrared light source, in particular a near-infrared (NIR) light source,
• f) detect the reflected infrared spectrum of the irradiated flow of step e), using an infrared sensor,
• g) analyze the infrared spectrum of step f) to characterize the waste in said flow, in particular according to their material.

2. Waste characterization device

Advantageously, the first light source being a white light source, and the second light source being chosen from an ultraviolet light source, a monochrome light source, or a mixture of these.

Advantageously, the light sources are continuous sources.

According to a particular embodiment, the second light source is an ultraviolet light source (5) optionally in combination with a monochrome light source (6, 7). According to a variant, the second light source consists of an ultraviolet light source. The UV light source may emit in all or part of the UV spectrum, in depending on the parameters to be determined, particularly in terms of material, opacity, thickness and/or color.

According to a particular embodiment, the second light source comprises a monochrome light source (6,7), such as a blue, green, young or red monochrome source, or a mixture of these, provided that their combination does not does not form white light. For example, the second light source includes a blue or red monochrome light source.

According to a particular embodiment, the second light source comprises an ultraviolet light source in combination with at least two monochrome light sources, in particular a red, green, blue or yellow monochrome light source, preferably a red monochrome light source. and a green monochrome light source.

According to a particular embodiment, the first light source is parallel to the waste flow (i.e. the light rays are orthogonal to the waste flow), and the second light source is parallel to the waste flow.

In other words, when the first light source is parallel to the waste stream, the axis of the light beam of the first light source is orthogonal to the waste stream.

According to a particular embodiment, the first light source is parallel to the waste flow, and the second light source forms an incident angle with the waste flow (i.e. the light rays form an incident angle with the waste flow). The incident angle makes it possible to optimize contrasts and characterization. For example, the incident angle of the light rays with the waste stream will then be approximately 30 or 60 degrees.

The visible light sensor could be any sensor adapted for such use, and in particular a camera active in the visible.

The image captured by the sensor means an image at a time T. It may change over time (in particular because the waste stream is moving).

3. Waste sorting method

Step a) can be carried out according to any particular or advantageous variant or embodiment presented above in connection with the waste sorting method.

Advantageously, step b) is carried out using a robotic sampling unit.

The method according to the invention makes it possible to achieve sorting performance superior to the methods currently used. In particular, on a single-material waste stream of the plastic type, the method of the invention advantageously makes it possible to achieve sorting performances greater than 90% by number, and preferably greater than 95% by number.

Advantageously, the use of detection methods implementing machine learning techniques makes it possible to obtain sorting performances of up to 99% in number.

For the purposes of the invention, the term sorting performance means the ability of the method to correctly detect the objects to be sorted, independently of the actual carrying out of the sorting.

4. Device for sorting a waste stream

Advantageously, the waste characterization device is positioned around said waste characterization zone (2).

In particular, the waste is supplied on the conveyor belt. This serves as a support for the waste during the waste sorting stage. The color of the support can be chosen so as to optimize the contrast effects when implementing the methods of the invention. The color of the conveyor belt may not be consistent over time and space.

According to a particular embodiment, the sorting device further comprises a waste sampling unit connected to the characterization device, the sampling unit being configured to sample waste according to predetermined characteristics, obtained via the sorting device. waste characterization.

For example, the picking unit is a robotic gripping unit. It may be any sorting robot known to those skilled in the art adapted for such use.

According to a particular embodiment, the device further comprises an infrared waste characterization device, such as an infrared characterization arch. An infrared waste characterization device typically comprises:

- a zone for identifying waste in a flow, said zone comprising at least one infrared light source to illuminate the waste,

- an infrared sensor, said sensor being positioned so as to capture at least in part the image of the illuminated waste in the identification zone, and said sensor being connected to an infrared spectrum analysis unit adapted to characterize the waste, in particular according to its material, based on the spectrum captured by the infrared sensor.

FIGURES

• [ Fig. 1 ] There figure 1 represents an example of an embodiment of the invention. This is a conveyor 1 equipped with a robot and an analysis system with an object identification zone 2 and a robot gripping zone 3.
• [ Fig. 2 ] There figure 2 represents in more detail the analysis system of the figure 1 . It comprises zones 4 for emitting white light, zones 5 for emitting UV light (for example a spot or a ramp) and/or zones 6, 7 for emitting monochrome lights, identical or different, and a visible light detection zone 8 (for example a camera).
• [ Fig. 3 ] Transparent plastic packaging on a dark surface: a. visible light only - b. visible light + UV - c. UV only.
• [ Fig. 4 ] Transparent plastic packaging on a pink surface: a. visible light only - b. visible light + UV - c. UV only.
• [ Fig. 5 ] Opaque plastic/aluminum packaging on a dark surface: a. visible light only - b. visible light + UV - c. UV only.
• [ Fig. 6 ] Opaque plastic/aluminum packaging on a pink surface: a. visible light only - b. visible light + UV - c. UV only.
• [ Fig. 7 ] Paper/cardboard on a dark surface: a. visible light only - b. visible light + UV - c. UV only.

DETAILED DESCRIPTION OF AN MODE OF CARRYING OUT THE INVENTION

The embodiment described and the following examples associated with it are given for purely illustrative purposes and should not be considered as limiting the invention in any way.

According to a first embodiment of the invention, an object sorting assembly, for example waste sorting, comprises a conveyor, such as a belt conveyor 1, driving in movement a flow of objects to be sorted, a system for characterizing the flow of objects and a sorting device for sorting the objects in a sorting zone 3 according to their characterization.

The characterization system comprises an image acquisition member 8, a characterization member for characterizing the objects to be sorted according to at least one acquired image and at least two light sources 4, 5, 6, 7 as described below.

The flow of objects to be sorted is composed of a plurality of objects of various types, such as objects to be recycled.

The objects to be recycled may in particular include aluminum objects, such as cans, transparent and/or opaque polyethylene terephthalate (PET) objects, such as plastic bottles, containers for household or hygiene products, but these Examples are non-limiting and any object known in the field of recycling of objects and treatment of waste could be an object to be sorted within the meaning of the present invention.

The image acquisition member 8 is adapted to capture one or more images of a predefined zone 2 on the conveyor belt 1. Thus the image acquisition member 8 acquires, for a given instant, a image of the portion of the flow of objects passing in the field of vision of the image acquisition member 8, here called object identification zone.

In this embodiment the image acquisition member 8 is a camera capturing images in the visible spectrum, but the invention is however not limited to a single type of camera, and can also use a camera or any other device suitable for capturing images.

It is generally accepted that the visible spectrum corresponds to a wavelength range in a vacuum ranging from 380nm to 780nm, however the camera implemented by the invention is not limited to this defined range, and the camera can in particular capturing images going beyond this wavelength range, for example by additionally capturing ultraviolet light between 200nm and 380nm, we then speak of a hyper-spectral camera; or conversely going below this wavelength range as long as the camera is adapted to capture usable images of the objects to be treated according to the lighting conditions described below.

Indeed, the objective of the camera is to acquire an image of the portion of the flow of objects making it possible to characterize the objects visible in the image.

By characterization we mean the act of defining the shape, the material or even the type of the object visible in the image.

Thus, the image acquisition unit 8 transmits the acquired images to the characterization unit which detects, characterizes the objects and determines, object by object, the sorting to be carried out. Then the characterization unit commands the sorting unit to carry out the sorting based on the detection carried out.

To obtain a reliable image analysis, it is relatively important to define lighting adapted to the good visibility of the objects in the identification zone 2 corresponding substantially to the field of vision of the camera.

In practice, it is common for the characterization member to include a characterization arch passing above the object conveyor. The camera can then be installed under the arch or at a distance from the arch, so that identification zone 2 is defined as the area extending under the characterization arch.

The identification zone 2 is illuminated with a main light 4, also called the first light source 4.

This first light source 4 is not necessarily made from a single emission point. In particular, the first light source 4 is generally adapted to provide uniform lighting on the identification zone 2. Also, it is possible to arrange a plurality of identical lights forming a first light source 4.

This first light source 4 is, in the first embodiment of the invention, a set of white lights 4 distributed overlooking the acquisition zone.

However, this first light source 4 is not necessarily white and can emit any other color suitable for image analysis after acquisition by an image acquisition member such as a camera in the visible spectrum.

The purpose of this first light source 4 is in particular to define relatively uniform lighting capable of allowing clear and contrasting acquisition of objects from the portion of the flow of objects in the field of view of the camera while reducing the appearance of visual artifacts that may affect the analysis of acquired images, such as shadows or reflections induced by lighting.

In order to improve the characterization of the objects present in the acquired image, a second light source 5, 6, 7 is added.

This second light source 5, 6, 7 is selected according to the materials that we wish to identify in particular in the portion of the flow of objects analyzed.

This second light source 5, 6, 7 can be obtained by a light having a color distinct from the main light.

The examples described below illustrate in particular the results obtained by combining a first light source with a second light source 5 diffusing ultraviolet, as well as the visual improvement obtained depending on the materials of the objects present in the portion of the flow of objects analyzed .

EXAMPLES EXAMPLE 1 : Irradiation with a combination of visible and UV light on waste such as transparent plastic packaging 1. Material

• Dark-colored support: 2cm graphite expanded polystyrene panel;
• Light-colored support: 2cm extruded polyurethane panel;
• White light : set of 4 LED lamps placed at the 4 corners of the panels, GU10 type, 5W, 400lumens, warm white 2700-3000K on 110°;
• UV light :
  • 1 black light tube 20W, 60cm long (located just below the lower part of the photo),
  • 1 15W T3 mini-spiral compact fluorescent bulb (located along the right side of the photo);
• Image sensor : Panasonic Lumix type camera, DMC-PZ 100, automatic mode in MP4.

2. Results

Waste such as transparent plastic packaging is arranged randomly on a dark support ( Figure 3 ) or on a light support (pink, figure 4 ). The waste is illuminated with white light only ( figures 3a And 4a ), a combination of UV light and white light ( figures 3b And 4b ), or with UV light alone ( figures 3c And 4c ).

• Les papiers blancs et étiquettes ressortent plus ;
• Le PET transparent présente un voile blanc par fluorescence, d'autant plus marqué qu'il est épais ; et
• La fluorescence des plastiques transparents est plus visible sur un fond foncé, non réfléchissant.

We observe that:

• White papers and labels stand out more;
• Transparent PET presents a white haze by fluorescence, the more marked the thicker it is; And
• The fluorescence of transparent plastics is more visible against a dark, non-reflective background.

EXAMPLE 2 : Irradiation with a combination of visible and UV light on waste such as opaque plastic packaging

The same equipment as in Example 1 is used for the implementation of Example 2.

Waste such as opaque plastic packaging is arranged randomly on a dark support ( Figure 5 ) or on a light support (pink, Figure 6 ). The waste is illuminated with white light only ( figures 5a And 6a ), a combination of UV light and white light ( figures 5b And 6b ), or with UV light alone ( figures 5c And 6c ).

• Les papiers blancs et étiquettes ressortent plus, et
• Le PE et le PP ne changent pas vraiment de couleur alors que d'autres plastiques s'illuminent par fluorescence, présentant un caractère discriminant plus poussé que simplement la lumière blanche.

We observe that:

• White papers and labels stand out more, and
• PE and PP do not really change color while other plastics glow by fluorescence, presenting a more discriminating character than simply white light.

EXAMPLE 3 : Irradiation with a combination of visible and UV light on waste such as paper and cardboard

The same equipment as in Example 1 is used for the implementation of Example 3.

Waste such as paper and cardboard packaging is placed randomly on a dark support ( Figure 7 ). The waste is illuminated with white light only ( figure 7a ), a combination of UV light and white light ( figure 7b ), or with UV light alone ( figure 7c ).

• Les papiers blancs apparaissent beaucoup plus blancs (par fluorescence),
• Le contraste entre le carton brun, blanc et gris est beaucoup plus fort.

We observe that:

• White papers appear much whiter (by fluorescence),
• The contrast between brown, white and gray cardboard is much stronger.

Conclusions:

Thus, we note that the addition of a light source 5 by ultraviolet UV, in addition to visible light 4 for image recognition, makes it possible to provide additional discriminating characteristics for visual recognition and induces an increase in recognition performance in certain sorting scenarios.

Indeed, ultraviolet 5 lighting of objects makes it possible to add, by fluorescence, discriminating pixels in the acquired images, which improves the efficiency of the image analysis and object characterization processes.

The invention is however not limited to a second light source diffusing ultraviolet.

According to a particular embodiment of the invention, the second light source 6, 7 comprises monochrome light of the visible spectrum, of a color different from white, for example green or red.

As with the main light, the second light source is not limited to a single point of emission. Here the second light source consists of two light sources 6, 7, of identical optical characteristics, but opposite each other with respect to the flow of objects, or in other words each on one side of the zone of identification 2.

This second light source 6, 7 is then diffused at an angle different from the main angle of emission of the first light source 4.

In particular, each point of emission of the second light source 6, 7 is installed so that its main axis of emission forms an angle comprised substantially between 30° to 45° with the normal of the support on which the objects are installed. of the portion of objects analyzed.

By main axis of emission is meant the axis forming the center of the light beam emitted by the light source 6, 7.

The objective of the particular arrangement of this second light source 6, 7 is to allow the appearance of reflections on the objects, and in particular to color the edges of the objects, so as to bring out the edges of the objects on the acquired images. in the color of the second light source 6, 7.

Thus, if the second light source is red, the borders of the objects in the identification zone will reflect the color red, this color being able to vary with the color of the material concerned, which relatively facilitates the characterization of the objects of the image acquired.

According to a particular mode of implementation of the invention, the second light source 6, 7 could be of a color similar to the first light source but of a distinct emission intensity, for example with a lighting intensity noticeably higher, so that the edges of objects will be overlit.

Furthermore, it is possible to combine the previous embodiments, and in particular define a characterization system comprising a source main light source 4, a second light source 6, 7 in the visible spectrum, for example of a color distinct from the main light source 4 and a third light source 5 emitting ultraviolet light as described above, this making it possible to combine the advantages described previously.

Furthermore, it is possible to combine a second light source 5, 6, 7 and possibly an additional light source, for example an ultraviolet source and a visible spectrum light source, for example red or green, with infrared lighting. , or near infrared.

In the field of object sorting, the infrared or near infrared characterization technique (better known as NIR for Near Infra-Red) is well known to those skilled in the art, and this material characterization technique can be combined with the detection means described in the present invention.

The invention also relates to a method for characterizing the objects of a flow of objects, comprising in particular a step of providing a flow of objects to be sorted, such as a waste flow.

We carry out a step of illuminating an identification zone 2 through which at least a portion of the object flow passes at a given instant.

Illumination is implemented by arranging a first light source 4 and a second light source 5, 6, 7 having a nature distinct from the first light source 4.

We then acquire, by an image acquisition member 8, at least one image of said portion of the object flow at the given instant.

• lorsque la deuxième source lumineuse est une source ultraviolet, de caractériser les matériaux par la fluorescence pouvant être produite sur les objets du flux d'objets, tel que décrit dans les exemples précédents ; et/ou
• lorsque la deuxième source lumineuse est une source monochrome du spectre du visible, par exemple rouge ou verte ou toute autre couleur visible, de caractériser les objets notamment par l'amélioration des contours de ces objets.

This image is transmitted to the characterization unit, which detects and characterizes the objects present in the image. The double lighting described previously allows in particular:

• when the second light source is an ultraviolet source, to characterize the materials by the fluorescence that can be produced on the objects of the flow of objects, as described in the previous examples; and or
• when the second light source is a monochrome source of the visible spectrum, for example red or green or any other visible color, to characterize the objects in particular by improving the contours of these objects.

Thus, the illumination step makes it possible to improve the result obtained in the characterization step.

Then, depending on the characterization of the objects present in the acquired image, the sorting unit is ordered to sort the detected objects, in accordance with the usual practice in the field of sorting.

• caractériser les matériaux constitutifs des objets de l'image acquise, par exemple en évaluant la fluorescence lors d'un éclairage par UV ; et/ou
• reconnaître des objets par la mise en oeuvre de procédé de reconnaissance d'image, notamment par l'identification de contours et de formes remarquables.

The characterization of objects can thus be freely adapted to:

• characterize the constituent materials of the objects in the acquired image, for example by evaluating fluorescence during UV illumination; and or
• recognize objects by implementing image recognition processes, in particular by identifying remarkable contours and shapes.

This recognition step can be implemented by conventional image recognition methods or automatic learning methods, such as neural networks. In particular, convolutional neural networks are particularly effective for performing object recognition in an acquired image.

Claims (14)

1. System for classifying objects in a flow of objects to be sorted, the flow of objects to be sorted being installed on a conveying device (1), said system comprising:

   - a device (8) for acquiring an image in the visible spectrum installed so as to be able to acquire at least one image of a portion of the flow of objects to be sorted;

   - a first light source (4), emitting in the visible spectrum, installed overhanging and illuminating said portion of flow of objects to be sorted, said at least one image of which is acquired by the image acquisition device (8);

   - a classification device able to classify the objects in said portion of the flow of objects to be sorted according to said at least one image acquired;

   characterized in that the system further comprises at least one second light source (5, 6, 7), with a nature distinct from the first light source (4), allowing the appearance of additional visual information in the visible spectrum on said at least one image acquired;

   the classification device further being adapted to classify said objects in said portion of the flow of objects according to said additional visual information.
2. System according to claim 1, characterized in that said at least one second light source (5) emits an ultraviolet light allowing the appearance of fluorescence in the visible spectrum when an object in the portion of flow of objects reacts to the ultraviolet.
3. System according to claim 1 or 2, characterized in that said at least one second light source (6, 7) emits a light in the visible spectrum, with a color and/or intensity distinct from the first light source (4), and oriented so as to illuminate, at an illumination angle distinct from the first light source (4), the objects in the portion of flow of objects illuminated by the first light source (4).
4. System according to claim 3, characterized in that said at least one second light source (6, 7) is installed so as to define a main illumination axis forming an acute angle with a plane wherein the device conveying said flow of objects extends.
5. System according to claim 4, characterized in that the second light source (6, 7) forms an angle of 30° to 45° with the plane in which the device conveying said flow of objects extends.
6. System according to any one of claims 1 to 5, characterized in that it further comprises a unit for taking off objects connected to the classification device, the take-off unit being configured to take off objects in accordance with predetermined characteristics, obtained by means of the classification device.
7. System according to claim 6, characterized in that the take-off unit is a robotic gripping unit.
8. Method for classifying objects to be sorted, comprising the following successive steps:

   a) providing a flow of objects to be sorted;

   b) illuminating at least part of said flow with at least one first light source and one second light source concomitantly, the first (4) and second light sources (5, 6, 7) being of different natures, and at least one of the two sources comprising wavelengths in the visible spectrum,

   c) acquiring at least one image in the visible spectrum of said illuminated flow part, said second light source (5, 6, 7) allowing the appearance of additional visual information in the visible spectrum on said at least one acquired image;

   d) detecting at least one object in said acquired image;

   e) classifying said detected object according to the visual information acquired in said at least one image, such as the color and/or transparency and/or material thereof and according to said additional visual information.
9. Method according to claim 8, characterized in that:

   the first light source (4) is a source of white light, and

   the second light source (5, 6, 7) is selected from a source of ultraviolet light, a source of monochrome light in the visible spectrum, or a mixture thereof.
10. Method according to either one of claims 8 to 9, characterized in that it further comprises a step of classification by infrared, comprising:

    f) a step of irradiating at least part of the flow of waste by an infrared light source, in particular a source of light in the near infrared (NIR),

    g) a step of detecting the infrared spectrum reflected from the irradiated flow of step f), by means of an infrared sensor,

    h) a step of analyzing the infrared spectrum of step g) to classify the waste of said flow, in particular according to the material thereof.
11. Waste sorting method, said method comprising the following successive steps:

    a) a step of implementing the waste classification method according to any one of claims 8 to 10; and

    b) a step of automated waste sorting on the basis of the classification of step a), according to predetermined parameters, such as the material, the color and/or the transparency of the waste.
12. Method according to claim 11, characterized in that step b) is implemented by means of a robotic take-off unit.
13. Sorting assembly comprising:

    - a conveyor (1), said conveyor comprising an object classification zone and an object take-off zone,

    - an object classification system according to any one of claims 1 to 7, comprising a classification device positioned around or above said object classification zone.
14. Sorting assembly according to claim 13, characterized in that it is adapted to implement the method according to any one of claims 8 to 12.

Images