Shelling apparatus based on visual recognition and laser treatment

Abstract

The disclosure provides a shelling device based on visual recognition and laser processing, which is applied to the technical field of intelligent agriculture and specifically applied to the technical field of a shelling device based on visual recognition and laser processing, and comprises the following steps: firstly, determining the laser processing path of each to-be-processed nut based on an image recognition and path planning module; then, performing laser pretreatment on the to-be-processed nut through a laser pretreatment module based on the determined laser processing path of each to-be-processed nut, so as to form a pre-cracking or weakening path; and then, performing shelling and separation processing on the to-be-processed nut through a shelling and separation module, so as to obtain the kernel of the to-be-processed nut; thereby, high-integrity shelling processing of the kernel of the to-be-processed nut is realized, and the physiological activity of the kernel is ensured.

Description

Technical Field

[0001] This disclosure relates to the field of smart agriculture technology, and more particularly to the field of shelling equipment based on visual recognition and laser processing. Background Technology

[0002] In the processing of typical shelled agricultural products such as peanuts, walnuts, almonds, and chestnuts, shelling is a key process, and its operation directly affects product quality, utilization rate, and subsequent use value.

[0003] Traditional fruit shell processing methods mainly rely on mechanical force to break the shell, heat treatment to soften it, or chemical treatment. While these methods have been applied to some extent in industrial processing, they still have many technical limitations. For example, the most common mechanical shelling technology uses devices such as crushing, rolling, impact, or friction to break the shell and separate the kernel. This type of equipment has advantages such as simple structure and high processing efficiency, but it easily causes crushing, breakage, or peeling of the kernel during processing, and in severe cases, even kernel splitting. This damage not only affects the commercial quality but also makes it difficult to meet the requirements for integrity and activity when the kernel is used as seed, reducing germination rate and breeding value. Heat treatment or chemical shelling methods soften the shell through steam, high-temperature baking, alkali solutions, or other reagents to reduce the difficulty of shelling. However, these methods usually have problems such as high energy consumption, long processing time, and high risk of chemical residues. Furthermore, high temperatures and chemical stimulation can easily damage the hypocotyl tissue of the kernel, thus seriously affecting seed activity and germination ability.

[0004] As mentioned above, existing shelling technologies for fruit-bearing agricultural products generally suffer from problems such as high kernel damage rate and inability to guarantee activity. Especially in applications where kernels are used as seeds, there is an urgent need for a shelling method or equipment that can achieve high integrity of kernel removal while ensuring its physiological activity and germination ability. Summary of the Invention

[0005] In view of this, the present disclosure provides a peeling device based on visual recognition and laser processing, which at least partially solves the problems existing in the prior art.

[0006] This disclosure provides a peeling device based on visual recognition and laser processing, including:

[0007] Image recognition and path planning module, laser preprocessing module, peeling and separation module;

[0008] The image recognition and path planning module is used to recognize the images of the nuts to be processed and determine the laser processing path for each nut.

[0009] The laser preprocessing module is used to perform laser preprocessing on the nuts to be processed based on the laser processing paths of each nut to be processed determined by the image recognition and path planning module, so as to form pre-cracked or weakened paths.

[0010] The shelling and separation module is used to shell and separate the nuts based on the pre-cracked or weakened path formed by the nuts to be processed, so as to obtain the kernels of the nuts to be processed.

[0011] Optionally, the image recognition and path planning module is specifically used to determine the minimum bounding rectangle of the nut to be processed based on the image of the nut to be processed, and use the major axis of the minimum bounding rectangle as the laser processing path; or, it is used to determine the longest center line connecting the outer edges of the nut to be processed based on the image of the nut to be processed, and use the longest center line as the laser processing path.

[0012] Optionally, the laser preprocessing module is specifically used to adjust the laser power, focal depth, scanning speed and pulse mode according to the determined laser processing path, the thickness distribution information of the nut to be processed and / or the germ position information of the kernel of the nut to be processed, to perform laser preprocessing on the nut to be processed.

[0013] Optionally, the thickness distribution information of the nuts to be processed includes the spatial coordinates of the thickest position of the shell, the thickness value, and the thickness variation trend information along the thickest position of the shell.

[0014] Optionally, the device also includes:

[0015] Feeding and conveying module;

[0016] The feeding and conveying module is used to realize automated feeding, and to spread the nuts to be processed on the conveyor belt and send them into the recognition area of ​​the image recognition and path planning module.

[0017] Optionally, the conveyor belt adopts a type B mesh belt structure, so that the longest direction of the nuts to be processed is as perpendicular as possible to the conveying direction.

[0018] Optionally, the device also includes

[0019] A kneading and peeling module, comprising a pair of differential rotating rollers and an adjustable friction belt or flexible kneading plate;

[0020] The kneading and shelling module is used to apply dynamic kneading and squeezing forces along the axial and tangential directions to the laser-pretreated nuts, causing the shells of the nuts to naturally break down along the weakened cracks.

[0021] Optionally, the device also includes

[0022] The separation module is used to separate the shells and kernels after the shelling module has been used to rub and peel the fruit.

[0023] Optionally, the device also includes

[0024] The control and linkage system module is used to control the image recognition and path planning module, laser preprocessing module, feeding and conveying module, kneading and peeling module, and separation module in a coordinated manner.

[0025] Optionally, the nuts to be processed are any one of the following: peanuts, walnuts, macadamia nuts, chestnuts, and almonds.

[0026] This disclosure provides a shelling device based on visual recognition and laser processing, comprising: an image recognition and path planning module, a laser preprocessing module, and a shelling and separation module. The image recognition and path planning module is used to recognize images of the nuts to be processed and determine the laser processing path for each nut. The laser preprocessing module is used to perform laser preprocessing on the nuts based on the laser processing paths determined by the image recognition and path planning module, forming pre-cracked or weakened paths. The shelling and separation module is used to shell and separate the nuts based on the pre-cracked or weakened paths formed on the nuts, obtaining the kernels. In other words, firstly, the laser processing path for each nut is determined based on visual recognition; then, the laser preprocessing module performs laser preprocessing on the nuts based on the determined laser processing paths, forming pre-cracked or weakened paths; finally, the nuts are shelled and separated to obtain the kernels, thereby achieving high-integrity shelling of the kernels and ensuring their physiological activity.

[0027] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0029] Figure 1This is a side view of the peeling device based on visual recognition and laser processing shown in an embodiment of this disclosure;

[0030] Figure 2 This is a side view of the feeding and conveying module structure shown in the embodiments of this disclosure;

[0031] Figure 3 This is a top view of the laser preprocessing module structure shown in the embodiment of this disclosure;

[0032] Figure 4 This is a side view of the laser preprocessing module structure shown in an embodiment of this disclosure;

[0033] Figure 5 This is a side sectional view of the laser preprocessing module structure shown in the embodiment of this disclosure;

[0034] Figure 6 This is a side view of the kneading and peeling module structure shown in an embodiment of this disclosure;

[0035] Figure 7 This is a side sectional view of the kneading and peeling module structure shown in the embodiment of this disclosure;

[0036] Figure 8 This is a schematic diagram of the separate module structure shown in an embodiment of this disclosure;

[0037] Figure 9 This is a flowchart illustrating the peeling method based on visual recognition and laser processing as shown in an embodiment of this disclosure;

[0038] Figure 10 This is a schematic diagram illustrating the determination of the minimum fitting matrix using peanut as an example in an embodiment of this disclosure.

[0039] Figure 11 This is a schematic diagram illustrating the determination of the longest center line of the outer edge, using a peanut as an example, in an embodiment of this disclosure.

[0040] Figure 12 This is an example diagram of a type B mesh belt structure shown in an embodiment of this disclosure.

[0041] The explanations of the symbols in the attached figures are as follows:

[0042] Feeding and conveying module 1, laser pretreatment module 2, kneading and peeling module 3, separation module 4, feed inlet 1-1, conveyor belt 1-2, support leg 1-3, caster wheel 1-4, laser pretreatment module feed inlet 2-1, metal conveyor belt 2-2, metal conveyor belt servo motor 2-3, metal conveyor belt drive wheel 2-4, metal conveyor belt driven wheel 2-5, metal conveyor belt tension wheel 2-6, leveling brush 2-7, camera 2-8, laser 2-9, laser galvanometer 2-10, exhaust fan 2-11, industrial computer 2-12 2-13 Water chiller, 2-14 Support frame, 2-15 Casters, 3-1 Rubber rolling belt, 3-2 Rubber rolling belt servo motor, 3-3 Rubber conveyor belt drive wheel, 3-4 Rubber conveyor belt driven wheel, 3-5 Rubber rolling wheel displacement servo motor, 3-6 Rubber rolling wheel limit rod, 3-7 Rubber rolling wheel, 3-8 Rubber rolling wheel servo motor, 3-9 Rolling and shelling mechanism support frame, 4-1 Shell and kernel separation vibrating screen, 4-2 Vibrating screen motor, 4-3 Fruit shell discharge port, 4-4 Kernel discharge port, 4-5 Separation module support frame. Detailed Implementation

[0043] The following specific examples illustrate the implementation of embodiments of this disclosure. Those skilled in the art can easily understand other advantages and effects of the embodiments of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Embodiments of this disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the embodiments of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of the embodiments of this disclosure.

[0044] In the processing of typical shelled agricultural products such as peanuts, walnuts, almonds, and chestnuts, shelling is a key step, and its operation directly affects product quality, utilization rate, and subsequent use value. Addressing the common problems of high kernel breakage rates and inability to guarantee viability in existing shelling technologies for shelled agricultural products, this disclosure provides a shelling device and method based on visual recognition and laser processing. Particularly in applications where kernels are used as seeds, it enables high-integrity kernel removal while ensuring their physiological activity and germination ability.

[0045] This disclosure provides a peeling device based on visual recognition and laser processing, such as... Figure 1-8 As shown, it includes:

[0046] Image recognition and path planning module, laser preprocessing module, peeling and separation module;

[0047] The image recognition and path planning module is used to recognize the acquired images of the nuts to be processed and determine the laser processing path for each nut. Specifically, the image recognition and path planning module may include a camera 2-8 and an industrial control computer 2-12. The image recognition and path planning module can be a separate module unit, or it can be composed of different module units or corresponding functions of different module units, as long as it can realize image acquisition, recognition, and corresponding algorithm processing functions. Specifically, the image recognition and path planning module is used to determine the minimum bounding rectangle of the nut to be processed based on the acquired images of the nuts to be processed, and use the major axis of the minimum bounding rectangle as the laser processing path; or, it is used to determine the longest center line connecting the outer edges of the nut to be processed based on the images of the nut to be processed, and use the longest center line as the laser processing path. Taking peanuts as an example, ... Figure 10 As shown, the minimum bounding rectangle of the nut to be processed is determined, and the major axis of the minimum bounding rectangle is used as the laser processing path; as shown... Figure 11 As shown, the longest center line connecting the outer edges of the nut to be processed is determined, and the longest center line is used as the laser processing path.

[0048] The nuts to be processed are any of the following: peanuts, walnuts, macadamia nuts, chestnuts, almonds, or other nuts that can be shelled using the shelling device disclosed herein.

[0049] The laser preprocessing module is used to perform laser preprocessing on the nuts to be processed based on the laser processing paths determined by the image recognition and path planning module, forming pre-cracked or weakened paths. Specifically, the laser preprocessing module is used to adjust the laser power, focal depth, scanning speed, and pulse mode according to the determined laser processing paths, the thickness distribution information of the nuts to be processed, and / or the germ position information of the kernels, to perform laser preprocessing on the nuts to be processed. The laser preprocessing module may include a laser 2-9 and a laser galvanometer 2-10. The laser outputs a laser beam, which is rapidly scanned by the laser galvanometer 2-10 to perform non-contact micro-cutting on the surface of the nuts to be processed, thereby weakening the shell structure without damaging the internal kernels. The thickness distribution information of the nuts to be processed includes the spatial coordinates of the thickest position of the shell, the thickness value, and the thickness change trend information along the thickest position of the shell.

[0050] The shelling and separation module is used to shell and separate the nuts based on the pre-cracked or weakened paths formed by the nuts to be processed, thereby obtaining the kernels of the nuts. Specifically, the shelling and separation module may include two separate modules: a kneading and shelling module 3 and a separation module 4.

[0051] This disclosure provides a shelling device based on visual recognition and laser processing, including: an image recognition and path planning module, a laser preprocessing module, and a shelling and separation module. The image recognition and path planning module is used to recognize images of nuts to be processed and determine the laser processing path for each nut. The laser preprocessing module is used to perform laser preprocessing on the nuts based on the laser processing paths determined by the image recognition and path planning module, forming pre-cracked or weakened paths. The shelling and separation module is used to shell and separate the nuts based on the pre-cracked or weakened paths formed on the nuts, obtaining the kernels. In other words, first, the laser processing path for each nut is determined based on visual recognition; then, the laser preprocessing module performs laser preprocessing on the nuts based on the determined laser processing paths, forming pre-cracked or weakened paths; and then the nuts are shelled and separated to obtain the kernels, thereby achieving high-integrity shelling of the nuts and ensuring their physiological activity.

[0052] This disclosure provides a possible implementation, and the device further includes:

[0053] Feeding and conveying module 1; The feeding and conveying module 1 is used to realize automated feeding, and to spread the nuts to be processed on the conveyor belt 1-2 and send them into the recognition area of ​​the image recognition and path planning module.

[0054] Specifically, the conveyor belts 1-2 adopt a type B mesh belt structure (e.g., Figure 12 As shown in the figure, the longest direction of the nut to be processed is as perpendicular as possible to the conveying direction.

[0055] This disclosure provides a possible implementation method, in which the shelling and separation module further includes a kneading and shelling module 3 and a separation module 4; wherein, the kneading and shelling module 3 includes a pair of differential rotating rollers and an adjustable friction belt or flexible kneading plate; the kneading and shelling module 4 is used to apply axial and tangential dynamic kneading and squeezing forces to the laser-pretreated nuts, causing the shells of the nuts to naturally crack along weakened fissures. Specifically, the kneading and shelling module 3 may include a rubber rolling belt (3-1), a rubber rolling belt servo motor (3-2), a rubber rolling belt drive wheel (3-3), a rubber rolling belt driven wheel (3-4), a rubber rolling wheel displacement servo motor (3-5), a ball screw (3-6), a rubber rolling wheel (3-7), a rubber rolling wheel servo motor (3-8), and a rolling and shelling mechanism support (3-9). The laser-pretreated nuts are transferred from the metal conveyor belt (2-2) to the rolling belt (3-1). The compaction belt is driven by a servo motor (3-2), and a pair of opposing rubber compaction rollers (3-7) are mounted above it. An adjustable gap is formed between the rubber compaction rollers and the compaction belt. The compaction rollers (3-7) are moved up and down along the ball screw (3-6) by a displacement servo motor (3-5), thereby adjusting the compaction pressure. A rubber compaction roller servo motor (3-8) drives the rollers to rotate and enables differential speed control between the rollers and the compaction belt.

[0056] As the nuts pass through the crushing zone, the shells are uniformly cracked based on the previously laser-cut slits, achieving shell-kernel separation. The crushing and shelling mechanism support (3-9) ensures the rigidity and stability of the mechanism.

[0057] Specifically, the separation module 4 is used to separate the shells and kernels after they have been crushed and peeled by the crushing and peeling module 3. Specifically, the separation module 4 includes a shell-kernel separation vibrating screen 4-1, a vibrating screen motor 4-2, a shell outlet 4-3, a kernel outlet 4-4, and a separation module support 4-5. The shell-kernel mixture, after being crushed and peeled, enters the vibrating screen 4-1, where the vibrating screen motor 4-2 generates high-frequency vibration to achieve shell-kernel separation. The screen classifies the kernels according to their particle size; larger and lighter shells are discharged through the shell outlet (4-3), while smaller and heavier kernels pass through the screen and are discharged through the kernel outlet (4-4). A large-area rubber pad is provided at the end of the separation module support (4-5) to reduce overall machine vibration.

[0058] This disclosure provides a possible implementation, and the device further includes...

[0059] The control and linkage system module may include an industrial computer 2-18, which can be used to control the image recognition and path planning module, laser preprocessing module, feeding and conveying module, kneading and peeling module, and separation module.

[0060] For example, combined Figure 1-8 The diagram shows an example of a peeling device based on visual recognition and laser processing according to an embodiment of this disclosure:

[0061] The system includes a feeding and conveying module 1, an image recognition and path planning module (including cameras 2-8 and an industrial control computer 2-12), a laser preprocessing module 2, a shelling and separation module 4, and a control and linkage system module (the control and linkage function of the industrial control computer 2-12), all connected in sequence. Material is continuously conveyed between these mechanisms via conveyor belts. The entire machine is controlled by the industrial control computer 2-12 within the control and linkage system module, enabling automatic feeding of nuts, image recognition and path planning, laser preprocessing, mechanical shelling, and kernel separation. Specifically:

[0062] 1. The feeding and conveying module (1) includes: a feeding port (1-1), a conveyor belt (1-2), support legs (1-3), and casters (1-4). The feeding port (1-1) is located at one end of the machine and is used for mechanical feeding. Under the control of the industrial computer (2-12), the conveyor belt (1-2) transports the nuts to be processed along the conveying direction to the feeding port (2-1) of the laser pretreatment module (2). The support legs (1-3) support the entire machine structure and can be adjusted in height to maintain horizontality; the casters (1-4) are located at the bottom for easy movement and positioning of the equipment. This mechanism achieves uniform feeding and stable conveying of the nuts to be processed.

[0063] 2. Image recognition and path planning module, including: a camera (2-8) fixed above the conveyor belt and connected to an industrial computer (2-12) for acquiring image information of the nuts to be processed. The industrial computer 2-12 analyzes the shape, position, and posture of each nut to be processed through its built-in image recognition algorithm, calculates the optimal cutting path for the nut, and generates the corresponding laser cutting path signal.

[0064] 3. Laser pretreatment module 2 includes:

[0065] Laser pretreatment module feed inlet (2-1), metal conveyor belt (2-2), metal conveyor belt servo motor (2-3), metal conveyor belt drive wheel (2-4), metal conveyor belt driven wheel (2-5), metal conveyor belt tension wheel (2-6), nut-to-be-processed flattening brush (2-7), laser (2-9), laser galvanometer (2-10), exhaust fan (2-11), industrial computer (2-12), water chiller (2-13), bracket (2-14), and casters (2-15).

[0066] The nuts to be processed enter the metal conveyor belt (2-2) through the feed inlet (2-1). This conveyor belt is driven by a servo motor (2-3) and forms a closed transmission structure via a drive wheel (2-4), a driven wheel (2-5), and a tension wheel (2-6). A nut-flattening brush (2-7) is positioned above the feed end to flatten the stacked nuts, ensuring they are arranged in a single layer on the conveyor belt and guaranteeing the stability of laser processing. The metal conveyor belt (2-2) uses a type-II mesh belt structure, which allows the longest direction of the nuts to be processed to be as perpendicular as possible to the conveying direction, optimizing the subsequent cutting path and also improving heat dissipation.

[0067] The fumes generated by laser cutting are promptly extracted by the exhaust fan (2-11). The water chiller (2-13) is used for laser heat dissipation. The bracket (2-14) and casters (2-15) form an independent movable module for easy movement and maintenance.

[0068] To achieve intelligent control of laser parameters, a fruit shell feature database can be established, containing multiple batches of sample images and their corresponding fruit shell thickness, moisture content, hardness, and optimal laser parameters (power, scanning speed, focal length). An industrial control computer uses a deep learning model to perform feature comparison and thickness prediction on the images captured by the camera, analyzing the fruit shell thickness distribution in real time. Combined with the parameters labeled in the database, it achieves adaptive adjustment of power and speed: when the fruit shell is thin, the power is reduced and the scanning speed is increased to prevent heat loss; when the fruit shell is thick or has low reflectivity, the power is increased and the scanning speed is decreased to ensure complete cutting.

[0069] 4. The kneading and peeling module 3 includes:

[0070] Rubber rolling belt (3-1), rubber rolling belt servo motor (3-2), rubber rolling belt drive wheel (3-3), rubber rolling belt driven wheel (3-4), rubber rolling wheel displacement servo motor (3-5), ball screw (3-6), rubber rolling wheel (3-7), rubber rolling wheel servo motor (3-8), and rolling and peeling mechanism bracket (3-9).

[0071] After laser pretreatment, the nuts to be processed are transferred from a metal conveyor belt (2-2) to a rolling belt (3-1). The rolling belt is driven by a servo motor (3-2), and a pair of opposing rubber rolling rollers (3-7) are mounted on top of it. An adjustable gap is formed between the rubber rolling rollers and the rolling belt. The rolling pressure is adjusted by controlling the up-and-down movement of the rubber rolling rollers (3-7) along the ball screw (3-6) via a displacement servo motor (3-5). A servo motor (3-8) for the rubber rolling rollers drives the rotation of the rolling rollers and enables differential speed control between them and the rolling belt.

[0072] As the nuts pass through the crushing zone, the shells are uniformly cracked based on the previously laser-cut slits, achieving shell-kernel separation. The crushing and shelling mechanism support (3-9) ensures the rigidity and stability of the mechanism.

[0073] 5. Separation module 4 includes:

[0074] The shell and kernel separation vibrating screen (4-1), the vibrating screen motor (4-2), the shell discharge port (4-3), the kernel discharge port (4-4), and the separation module support (4-5) are all included.

[0075] After being crushed and shelled, the mixture of shells and kernels enters a vibrating screen (4-1), where a high-frequency vibration is generated by a vibrating screen motor (4-2) to separate the shells and kernels. The screen classifies the kernels according to their particle size; larger and lighter shells are discharged through the shell outlet (4-3), while smaller and heavier kernels pass through the screen and are discharged through the kernel outlet (4-4). A large-area rubber pad is provided at the end of the separation module support (4-5) to reduce the vibration of the entire machine.

[0076] The intelligent laser nut shelling machine of the present invention is uniformly controlled by an industrial control computer (2-12). The industrial control computer is electrically connected to the camera (2-8), laser (2-9), laser galvanometer (2-10), feeding and conveying module, each servo motor (2-3, 3-2, 3-5, 3-8) and vibrating screen motor (4-2), and realizes synchronous control and status feedback through a bus system.

[0077] When the equipment is working, the nuts to be processed enter the laser pretreatment module (2) through the feeding and conveying module (1). The camera collects images and identifies the position of each nut. The industrial control computer controls the laser and galvanometer to precisely cut or punch holes on the surface of the nuts to be processed according to the identification results. Then the nuts to be processed enter the crushing and shelling mechanism (3). The shells are broken and the kernels are separated by the action of the crushing belt and crushing wheel. The separated mixture enters the separation module (4). The shells and kernels are separated by multi-layer screening. Finally, the kernels are output from the kernel outlet (4-4).

[0078] The entire process is automated. Operators only need to input the nut variety, moisture content, and working mode into the industrial control computer interface, and the system can automatically match the corresponding laser power, conveying speed, and crushing pressure parameters to achieve intelligent shelling of different batches of nuts.

[0079] like Figure 9 As shown, this disclosure provides a flowchart of a peeling method based on visual recognition and laser processing, applicable to a peeling device based on visual recognition and laser processing according to embodiments of this disclosure, including:

[0080] Step S901: Based on the image of the target nut, identify and determine the laser processing path of the target nut.

[0081] The target nut can be one of the nuts to be processed; the target nut is any one of the following: peanut, walnut, macadamia nut, chestnut, or almond. Identifying and determining the laser processing path for the target nut includes at least one of the following: based on the image of the target nut, determining the minimum bounding rectangle of the target nut, and using the major axis of the minimum bounding rectangle as the laser processing path; based on the image of the target nut, determining the longest center line connecting the outer edges of the target nut, and using the longest center line as the laser processing path. Specifically, each target nut can be identified from the nuts to be processed using a corresponding Multi-Object Tracking (MOT) method, and then the laser processing path for each target nut can be determined using a corresponding algorithm.

[0082] Specifically, the step of identifying and determining the laser processing path of the target nut based on its image includes: step S9011 (not shown in the figure), determining the shape type of the target nut based on its image, wherein the shape type includes regular type and irregular type; step S9012 (not shown in the figure), if the shape type is regular type, determining the minimum bounding rectangle of the target nut based on its image, and using the major axis of the minimum bounding rectangle as the laser processing path; if the shape type is regular type, determining the longest center line connecting the outer edges of the target nut based on its image, and using the longest center line as the laser processing path. The regular type refers to pods (nuts to be treated) whose target nut shape is approximately elliptical or has a continuous, smooth, and symmetrical shape, with a clear long axis, uniform contour curvature, and no obvious concavity or abrupt change points (e.g., most common peanut varieties, such as Silihong and Yuhua 20, are regular elliptical, with basically symmetrical sides and continuous, smooth shell ridges, which can be considered as regular types). The irregular type refers to pods whose target nut shape has significant bending, twisting, or multi-segment deformities, with uneven contour curvature and obvious concavity or abrupt change points, which cannot be effectively fitted by the standard elliptical model (e.g., characteristics of varieties such as Huayu 60 and Qicai peanuts, or excessively bent pods, deformed multi-chambered pods, and Longsheng-type peanuts formed due to the influence of the growth environment, whose shell structure is complex and whose long axis direction is discontinuous, which can be considered as irregular types).

[0083] Step S902: Perform laser processing on the target nut based on the determined laser processing path to obtain the laser-processed target nut;

[0084] Specifically, step S902 may include step S9021: determining the shell thickness distribution information of the target nut and / or the germ position information of the kernel of the target nut; step S9022: determining the laser processing power of the target nut based on the shell thickness distribution information and / or the germ position information of the kernel of the target nut; and step S9023: performing laser processing based on the determined laser processing power and the determined laser processing path of the target nut. The shell thickness distribution information includes the spatial coordinates of the thickest point of the shell, the thickness value, and the thickness change trend along the thickest point of the shell. Specifically, when laser processing the target nut, the laser processing power can be relatively reduced based on the germ position information of the kernel of the target nut, thereby avoiding damage to the germ of the kernel of the target nut, and thus improving the seed survival rate in seed selection.

[0085] Specifically, determining the shell thickness distribution information of the target nut may include: identifying and determining the type of the target nut; determining the shell thickness distribution information of that type of nut based on the determined type of the target nut and a pre-built database; and correcting the shell thickness distribution of that type of nut based on the spectral absorption / reflection information of the target nut to obtain the thickness distribution information of the target nut. The pre-built database includes nut types and shell thickness distribution information for that type of nut. In this embodiment, by first determining the shell thickness distribution information of that type of nut based on its type, and then correcting the shell thickness distribution of that type of nut based on its spectral absorption / reflection information to obtain the shell thickness distribution information of the target nut, the efficiency and accuracy of determining the thickness distribution information of the target nut can be improved.

[0086] Step S903: Peel the target nut after laser treatment to obtain the kernel of the target nut.

[0087] In this embodiment, the laser processing path of the target nut is first determined based on visual recognition. Then, based on the determined laser processing path of each nut to be processed, the target nut is laser-processed to form a pre-cracked or weakened path. Then, the target nut is shelled and separated to obtain the kernel of the target nut, thereby achieving a high integrity peeling process of the kernel of the nut to be processed and ensuring its physiological activity.

[0088] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the embodiments of this disclosure. The drawings only show the components related to the embodiments of this disclosure and are not drawn according to the actual number, shape and size of the components. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0089] The following embodiments of this disclosure illustrate the implementation of this disclosure through specific examples. Those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0090] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0091] The embodiments described above are some, but not all, of the embodiments disclosed herein. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0092] In the description of the embodiments of this disclosure, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this disclosure. In addition, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0093] In the description of the embodiments of this disclosure, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this disclosure based on the specific circumstances.

[0094] The above are merely specific embodiments of this disclosure, but the protection scope of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this disclosure should be included within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the scope of the claims.

Claims

1. A peeling device based on visual recognition and laser processing, characterized in that, include: Image recognition and path planning module, laser preprocessing module, peeling and separation module; The image recognition and path planning module is used to recognize the images of the nuts to be processed and determine the laser processing path for each nut. The laser preprocessing module is used to perform laser preprocessing on the nuts to be processed based on the laser processing paths of each nut to be processed determined by the image recognition and path planning module, so as to form pre-cracked or weakened paths. The shelling and separation module is used to shell and separate the nuts based on the pre-cracked or weakened path formed by the nuts to be processed, so as to obtain the kernels of the nuts to be processed.

2. The shelling device according to claim 1, characterized in that, The image recognition and path planning module is specifically used to determine the minimum bounding rectangle of the nut to be processed based on the image of the nut to be processed, and use the major axis of the minimum bounding rectangle as the laser processing path; or, it is used to determine the longest center line connecting the outer edges of the nut to be processed based on the image of the nut to be processed, and use the longest center line as the laser processing path.

3. The shelling device according to claim 1, characterized in that, The laser preprocessing module is specifically used to adjust the laser power, focal depth, scanning speed and pulse mode according to the determined laser processing path, the thickness distribution information of the nuts to be processed and / or the germ position information of the kernels of the nuts to be processed, so as to perform laser preprocessing on the nuts to be processed.

4. The shelling device according to claim 3, characterized in that, The thickness distribution information of the nuts to be processed includes the spatial coordinates of the thickest part of the shell, the thickness value, and the thickness change trend along the thickest part of the shell.

5. The shelling device according to any one of claims 1-4, characterized in that, The device also includes: Feeding and conveying module; the feeding and conveying module is used to realize automated feeding, and to spread the nuts to be processed on the conveyor belt and send them into the recognition area of ​​the image recognition and path planning module.

6. The shelling device according to claim 5, characterized in that, The conveyor belt adopts a type B mesh belt structure, which makes the longest direction of the nuts to be processed as perpendicular as possible to the conveying direction.

7. The shelling device according to any one of claims 1-4, characterized in that, The shelling and separation module includes: a kneading shelling module, which includes a pair of differential rotating rollers and an adjustable friction belt or flexible kneading plate; The kneading and shelling module is used to apply dynamic kneading and squeezing forces along the axial and tangential directions to the laser-pretreated nuts, causing the shells of the nuts to naturally break down along the weakened cracks.

8. The shelling device according to any one of claims 1-4, characterized in that, The peeling and separation module includes: The separation module is used to separate the shells and kernels after the shelling module has been used to rub and peel the fruit.

9. The shelling device according to any one of claims 1-4, characterized in that, The device also includes: The control and linkage system module is used to control the image recognition and path planning module, laser preprocessing module, feeding and conveying module, kneading and peeling module, and separation module in a coordinated manner.

10. The shelling device according to any one of claims 1-4, characterized in that, The nuts to be processed are any one of the following: peanuts, walnuts, macadamia nuts, chestnuts, and almonds.

Images