Systems for sorting and sorting pig carcass cuts

Abstract

The present invention provides a system for classifying, identifying and diverting pig carcass cuts, the system comprising: an image acquisition device, which is arranged above the assembly line platform and is used to perform image acquisition on the pig carcass cuts that enter the image acquisition area of ​​the assembly line platform to obtain image information for classifying and identifying the pig carcass cuts; and an industrial computer, which is used to: receive the image information from the image acquisition device; and input the image information into a deep learning algorithm model for category reasoning to obtain category information of the pig carcass cuts. A diversion device, which is used to divert the pig carcass cuts to the corresponding product line according to the received category information. Utilizing the solution of the present invention, the classification and diversion operations of pig carcass cuts can be completed instead of manual work.

Description

Technical Field

[0001] The present invention generally relates to the field of classification and identification, and more particularly to a system, method and computer-readable storage medium for classifying and sorting pig carcass cuts. Background Art

[0002] As one of the main meat consumer products, the quality of pork has received extensive attention from quality supervisors, meat processing companies and consumers. Most of the current pig slaughtering companies sort and number the pig carcasses in a fixed manner, and then use manual or automatic counting to identify and locate each pig carcass. However, the inability to automatically track and control the flow of pig carcass cuts is still a risk point. At present, the classification and identification method of pig carcass cuts in the cutting workshop of the slaughterhouse mainly relies on human subjective vision to determine the category information of the cuts, and then records the category information of the cuts by manual clicking. As the labor time increases, it is very easy to cause human eye fatigue to rely on human subjective vision to determine the category information of the cuts, which not only leads to low production efficiency, but also increases labor costs. In addition, there is no relevant information tracking operation for pig carcass cuts in the prior art, which will cause the problem of food safety information asymmetry. In view of this, the prior art needs a technical solution that can quickly, efficiently and automatically classify, divert and trace the information of pig carcass cuts. Summary of the invention

[0003] In order to at least solve one or more technical problems in the above-mentioned background technology, the present invention proposes a system, method and computer-readable storage medium for classifying, identifying and sorting pig carcass cuts. By using a deep learning algorithm model to perform category reasoning on pig carcass cuts, the classification efficiency and accuracy of pig carcass cuts can be improved. Based on this, the present invention provides the following multiple solutions in multiple aspects.

[0004] In one aspect, the present invention discloses a system for classifying, identifying and diverting pig carcass cuts, wherein the pig carcass cuts are placed on an assembly line platform, and characterized in that the system comprises: an image acquisition device, which is arranged above the assembly line platform and is used to perform image acquisition on the pig carcass cuts that enter the image acquisition area of ​​the assembly line platform to obtain image information for classifying and identifying the pig carcass cuts; an industrial computer, which is communicatively connected to the image acquisition device and is used to: receive the image information from the image acquisition device; input the image information into a deep learning algorithm model for category reasoning to obtain category information of the pig carcass cuts; and a diversion device, which is used to divert the pig carcass cuts to the corresponding product line according to the received category information.

[0005] In one embodiment, it also includes a cut product holder for holding the pig carcass cut products; and a plurality of blocking devices, which are arranged upstream of the assembly line platform relative to the image acquisition area; and a plurality of sensors, which are arranged between adjacent blocking devices and are communicatively connected to the corresponding blocking devices, wherein in response to the sensor detecting that the cut product holder enters the corresponding area upstream of the assembly line platform, the blocking device is used to block the cut product holder so as to allow a plurality of the cut product holders to enter the image acquisition area in an orderly manner.

[0006] In another embodiment, the blocking device comprises a blocking cylinder and the sensor comprises a photoelectric sensor, wherein a plurality of the blocking cylinders are sequentially arranged along one side of the assembly line platform.

[0007] In yet another embodiment, a radio frequency identification chip is further included, which is arranged on the cut product holder to record the category information of the pig carcass cut products.

[0008] In another embodiment, it also includes a radio frequency identification reader / writer, which is arranged in the image acquisition area of ​​the assembly line platform and corresponds to the position of the radio frequency identification chip, and is communicatively connected to the industrial computer, so as to be used for: reading the electronic number information of the radio frequency identification chip; binding the category information with the electronic number information of the radio frequency identification chip; and writing the category information into the radio frequency identification chip, so that the radio frequency identification chip records the category information of the pig carcass cuts.

[0009] In yet another embodiment, the method further includes a radio frequency identification reader arranged downstream of the assembly line platform relative to the image acquisition area, which is communicatively connected to the diversion device and is used to: read the category information recorded in the radio frequency identification chip; and transmit the category information to the diversion device so that the diversion device diverts the pig carcass cuts according to the category information.

[0010] In yet another embodiment, the diverting device comprises a plurality of diverting cylinders, each of which is used to divert the classified pig carcass cuts to a corresponding product line.

[0011] In yet another embodiment, a plurality of diverter ports are arranged downstream of the assembly line platform, and the plurality of diverter cylinders are respectively arranged on the other side relative to the diverter ports so as to divert the classified pig carcass cuts to corresponding product lines through the diverter ports.

[0012] In yet another embodiment, a touch display screen is further included to receive control instructions input by a user and display working status information of the system to the user.

[0013] In yet another embodiment, the control instructions include instructions for placing the system in manual or automatic diversion operation, so as to make the system operate in automatic mode or manual mode.

[0014] In another aspect, the present invention also provides a method for classifying, identifying and diverting pig carcass cuts, wherein the pig carcass cuts are placed on an assembly line platform, and characterized in that the method comprises: using an image acquisition device arranged above the assembly line platform to perform image acquisition on the pig carcass cuts that enter the image acquisition area of ​​the assembly line platform to obtain image information for classifying and identifying the pig carcass cuts; inputting the image information into a deep learning algorithm model for category reasoning to obtain category information of the pig carcass cuts; and diverting the pig carcass cuts to the corresponding product line according to the received category information.

[0015] In another aspect, the present invention provides a computer-readable storage medium, which includes program instructions for classifying, identifying and diverting pig carcass cuts. When the program instructions are executed by a processor, the above method is implemented. By utilizing the device, method, system and computer program product discussed in the above and multiple embodiments of the present invention, unmanned automatic classification and diversion of pig carcass cuts can be implemented. Specifically, the present invention uses a deep learning algorithm model to perform category inference on the input pig carcass cut image information, thereby realizing unmanned automatic classification of pig carcass cuts, and improving the work efficiency of the cutting workshop and the recognition accuracy of the cut product category. Further, according to the category information inferred by the deep learning algorithm model, the category information is written into the radio frequency identification chip using a radio frequency identification reader, so that information tracking of the cuts in each cut product container can be realized. In addition, the diversion device can realize the diversion operation of pig carcass cuts according to the category information, laying the foundation for the future realization of unmanned factories in slaughterhouses. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present disclosure will become readily understood. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0017] Figure 1 is an exemplary simplified diagram showing a system for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention;

[0018] Figure 2is another exemplary simplified block diagram of a system for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention;

[0019] Figure 3 is an exemplary detailed schematic diagram showing a system for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram from a rear side perspective showing an exemplary schematic diagram of a system for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention; and

[0021] Figure 5 is an exemplary flow chart showing a system for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0023] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 1 is an exemplary simplified diagram showing a system 100 for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention. Figure 1 As shown in , the system 100 may include an image acquisition device 101, an industrial computer 102 and a diversion device 103. Through the coordinated use of the aforementioned image acquisition device, industrial computer and diversion device, the system of the present invention can realize automatic classification and diversion operations of pig carcass cut products. The aforementioned image acquisition device, industrial computer and diversion device will be described in detail below.

[0025] In one embodiment, the image acquisition device 101 is arranged above the above-mentioned assembly line platform, and is used to perform image acquisition on the pig carcass cuts entering the image acquisition area of ​​the assembly line platform to obtain image information for classifying and identifying the pig carcass cuts. In some embodiments, the image acquisition device can be, for example, an industrial camera. It can be understood that the essential function of the industrial camera is to convert the optical signal into an ordered electrical signal so as to realize the image acquisition of the inspected object. Specifically, the industrial camera can illuminate the pig carcass cuts using a light source arranged above the industrial camera so as to obtain reflected light about the pig carcass cuts. Further, the reflected light is refracted on the photosensitive sensor (CCD or CMOS) through the industrial lens so as to generate an analog electrical signal about the pig carcass cuts. In order to realize the detection of the aforementioned analog current signal, the analog current signal can be converted into a digital signal using the analog-to-digital converter of the industrial camera so as to transmit the digital signal to the image processor of the industrial camera, and then the image information about the pig carcass cuts can be obtained. In addition, industrial cameras can use the communication interface to transmit the obtained image information to the industrial computer in order to perform category reasoning on the image information.

[0026] In one embodiment, the industrial computer 102 is connected to the image acquisition device in communication, and can be used to receive image information from the image acquisition device, and input the image information into the deep learning algorithm model for category reasoning, so as to obtain the category information of the pig carcass cuts. In an exemplary scenario, the industrial computer can be connected to the image acquisition device in communication via TCP / IP network communication to receive the image information transmitted by the image acquisition device. In addition, the industrial computer can also be connected to the radio frequency identification reader / writer arranged in the image acquisition area of ​​the assembly line platform in communication, so as to read the electronic number information of the radio frequency identification chip. Further, the radio frequency identification reader / writer is used to bind the category information with the electronic number information of the radio frequency identification chip, and the category information is written into the radio frequency identification chip, so that the radio frequency identification chip records the category information of the pig carcass cuts.

[0027] As described above, the solution of the present invention utilizes a deep learning algorithm model based on a neural network to efficiently and accurately classify pig carcass cuts. For ease of understanding, a brief introduction to the neural network is provided below.

[0028] As known to those skilled in the art, neural networks usually need to be trained to obtain a neural network model that can actually perform inference operations after training (such as the deep learning algorithm model of the present invention). The aforementioned training process can generally be divided into forward propagation and back propagation. Here, forward propagation can involve forward processing of signals (such as known training data, specifically pig carcass segment image data in the present invention), including data processing from the input layer of the neural network through the hidden layer, and finally to the output layer of the neural network. Back propagation mainly involves back propagation gradients, including data processing from the output layer of the neural network to the hidden layer, and finally to the input layer, which can specifically be adjusting the weights and biases of each layer in the neural network in turn according to the gradient.

[0029] In the forward process described above, the input value is input to the input layer of the neural network, and the output of the predicted value is obtained from the output layer of the neural network. In the hidden layer, the second hidden layer obtains the predicted intermediate result value from the first hidden layer and performs calculation operations and activation operations, and then passes the obtained predicted intermediate result value to the next hidden layer. The same operations are performed in the subsequent hidden layers until the output value called the predicted value is finally obtained in the output layer of the neural network. In order to calculate the error, the predicted value is compared with the actual output value to obtain the corresponding error value.

[0030] Backpropagation usually uses the chain rule of differential calculus. In the chain rule, the derivatives of the error values ​​corresponding to the weights of the last layer of the neural network are first calculated (these derivatives are called gradients). Next, these gradients are used to calculate the gradients of the second-to-last layer in the neural network. This process is repeated until the gradients corresponding to each weight in the neural network are obtained. Finally, the corresponding gradients are subtracted from each weight in the neural network, thereby updating the weights to achieve the purpose of reducing the error value. For some neural networks, it is also possible to perform fine-tuning operations on the trained neural network to obtain a neural network model that can finally execute actual data.

[0031] Specifically to the scheme of the present invention, the training data about the image data of the pig carcass cuts of the present invention can be input in advance by the industrial computer into the deep learning algorithm model based on the above-mentioned neural network. Then, in the forward propagation, the training output result can be obtained through the calculation of the convolution layer, the pooling layer and the fully connected layer in the model. Thereafter, the training output result and the loss function can be used to adjust the parameters of each layer in the deep learning algorithm model in the back propagation direction. Repeat the aforementioned forward propagation and back propagation operations until a deep learning algorithm model that meets the classification expectations is obtained, that is, a deep learning algorithm model that can classify the pig carcass cuts of the present invention.

[0032] In one embodiment, the diverter device 103 is used to divert the pig carcass cuts to the corresponding product line according to the received category information. In an application scenario, the RFID reader arranged downstream of the assembly line platform relative to the image acquisition area is communicatively connected to the diverter device, and is used to read the category information recorded in the RFID chip. According to the aforementioned read category information, the RFID reader can transmit the category information to the diverter device, so that the diverter device diverts the pig carcass cuts according to the category information. In addition, the diverter device of the present invention may include a plurality of diverter cylinders, each of which is used to divert the classified pig carcass cuts to the corresponding product line. Further, the diverter device is arranged with a plurality of diverter ports downstream of the assembly line platform, and each of the diverter ports is arranged on the other side relative to the diverter cylinder, so as to divert the classified pig carcass cuts to the corresponding product line through the diverter port.

[0033] Based on the above description, it can be known that the present invention can realize the collection of image information of pig carcass cuts through an image acquisition device, and use a deep learning algorithm model to perform category reasoning on the input image information through an industrial computer, so as to realize efficient and accurate classification operations of pig carcass cuts. Furthermore, the classified pig carcass cuts can be diverted to the corresponding product line by using a diversion device to meet the business needs of the pig carcass cuts production line. By utilizing the system of the present invention, the problem of relying on human subjective vision to determine the category information of the cuts can be solved, and the operation of writing the category information of the pig carcass cuts into the radio frequency identification electronic tag chip by manually clicking can be replaced, thereby improving the working efficiency of the assembly line platform and the accuracy of classifying pig carcass cuts, while also saving labor costs and improving corporate profits.

[0034] The system of the present invention may also include a sensor and a blocking device, which can ensure that only a single segmented product exists within the field of view of the image acquisition device each time, thereby avoiding interference with the acquisition work of the image acquisition device. Figure 2 The system of the present invention is described in detail.

[0035] Figure 2 FIG. 2 is another exemplary simplified block diagram of a system for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention. Figure 2 As shown in FIG. , the system may include the above Figure 1 The image acquisition device 101, the industrial computer 102 and the diversion device 103 (i.e., the system for classifying, identifying and diverting pig carcass cuts of the present invention) may also include a blocking device 201 and a sensor 202. It is understood that the above reference has been made to Figure 1The image acquisition device 101, the industrial computer 102 and the diversion device 103 have been described in detail, so the same contents will not be repeated below.

[0036] In one embodiment, the blocking device 201 is arranged upstream of the assembly line platform relative to the image acquisition area. In some application scenarios, the blocking device can be, for example, a plurality of blocking cylinders, and the plurality of blocking cylinders are arranged in sequence along one side of the assembly line platform. It can be understood that the blocking cylinder is mainly used to stop the split product holder on the assembly line, so it is also called a stop cylinder. The blocking cylinder is mainly composed of a cylinder part and a spring part, wherein the cylinder part can include a piston and a stop rod, for example. Specifically, when the blocking cylinder is in an unventilated state, the piston of the blocking cylinder is in a reset state under the action of a spring, and the blocking operation is performed on the split product holder on the assembly line platform by using a stop rod, so that only a single split product holder is in the image acquisition area. When the blocking cylinder is in a ventilated state, the piston of the blocking cylinder can drive the stop rod to be retracted under the action of a spring, so as to release the blocked split product holder.

[0037] In one embodiment, the sensor 202 is arranged between adjacent blocking devices and is communicatively connected with the corresponding blocking devices. In some application scenarios, the sensor may be, for example, a photoelectric sensor. It is understandable that the photoelectric sensor uses a photoelectric element as a detection element and detects the object to be detected according to the change of light. Specifically, when the cut product holder containing the pig carcass cut products enters the sensing range of the photoelectric sensor, it will cause the light sent by the transmitter to the receiver to change, and then the receiver will transmit the changed light signal to the detection circuit. In order to realize the detection of the above-mentioned light signal, the detection circuit can use the photoelectric element to convert the light signal into an electrical signal based on the photoelectric effect, so as to realize the sensing of the cut product holder. Furthermore, the image acquisition device can be triggered via the communication module according to the signal sensed by the photoelectric sensor, thereby realizing the image acquisition operation of the pig carcass cut products. In addition, the present invention can ensure that only a single cut product exists in the field of view of each photo by using the cooperation of the photoelectric sensor and the blocking cylinder. Regarding the cooperation method of the photoelectric sensor and the blocking cylinder, it will be combined with the attached later. Figure 3 Describe in detail.

[0038] Figure 3 is an exemplary detailed schematic diagram of a system for classifying, identifying and diverting pig carcass cuts according to an embodiment of the present invention. It should be understood that Figure 3 The system in is the above Figure 1 A specific embodiment of the system 100 is described, so the above Figure 1 The description of system 100 also applies to Figure 3 The situations shown and the same contents will not be described again in detail.

[0039] like Figure 3 As shown in , multiple sensors and multiple blocking devices are arranged upstream of the assembly line platform. In operation, the cooperation of multiple sensors and multiple blocking devices can ensure that only a single split product exists within the field of view of each image acquisition. In an application scenario, photoelectric sensors and blocking cylinders can be used to ensure that only a single split product exists within the field of view of image acquisition. Specifically, when the photoelectric sensor 301 is in a triggered state (i.e., it senses the split product holder 302), if the photoelectric sensor 303 is triggered by a signal, the blocking cylinder 304 is controlled by the industrial computer 311 via the communication module to perform a blocking operation, so as to prevent the split product holder 305 from interfering with the industrial camera 310 in collecting image information of pig carcass split products. In addition, the photoelectric sensor 306 is also triggered by a signal to control the blocking cylinder 307 to perform a blocking operation, thereby achieving a blocking operation on the split product holder 308.

[0040] Further, when the photoelectric sensor 301 is in a no-signal trigger state, that is, the cut product holder 302 containing the pig carcass cut products in the image acquisition area has completed image acquisition, the first signal trigger of the photoelectric sensor 303 controls the blocking cylinder 304 to disable the blocking operation. According to the action of the blocking cylinder disabling the blocking operation, the cut product holder 305 can enter the field of view of the industrial camera 310, so that the industrial camera 310 can perform an image acquisition operation on the pig carcass cut products held in the cut product holder 305. Similarly, the first signal trigger of the photoelectric sensor 306 also controls the blocking cylinder 307 to disable the blocking operation, so as to transfer the cut product holder 308 to the position of the cut product holder 305, and then the cut product holder 308 can perform the operation performed by the cut product holder 305 again. In addition, when the photoelectric sensors 301, 303 and 306 do not sense the cut product holder, they will be in a no-signal trigger state, that is, the blocking cylinder 309 cannot be triggered to perform the blocking action. On the contrary, when the photoelectric sensor detects the cut product holder, it can activate the blocking cylinder 309 to perform the blocking action, for example, via the industrial computer. Thus, the system can ensure that when collecting images of pig carcass cut products, only one cut product holder is allowed to be within the image collection range.

[0041] According to the above, when there is only one pig carcass cut product within the field of view of the industrial camera 310, the industrial camera 310 arranged above the assembly line platform uses the light source 311 for illumination, and performs image acquisition of the pig carcass cut product contained in the cut product holder 302. Further, the image information of the pig carcass cut product is transmitted to the industrial computer 102 via the communication module 312, and the category inference of the pig carcass cut product is performed through the deep learning algorithm model (as described above) to obtain the category information of the pig carcass cut product. After obtaining the category information, the RFID reader / writer 313 arranged in the image acquisition area of ​​the assembly line platform can read the number information of the RFID electronic chip 314 arranged on the side of the cut product holder, and then write the category information into the RFID electronic chip 314 on the side of the cut product holder.

[0042] By writing the aforementioned category information, it is possible to trace the information of pig carcass cuts, and provide data source information for the downstream cuts to enter the stereoscopic warehouse (which is, for example, a "upper and lower" warehouse for storing cuts). In addition, a radio frequency identification reader 315 is arranged downstream of the assembly line platform for reading the category information recorded in the radio frequency identification chip 314 on the side of the cut product holder. At the same time, a plurality of diversion cylinders 316 are arranged downstream of the assembly line platform, and the diversion cylinders 316 are used to divert the corresponding pig carcass cuts into different assembly lines through the diversion port 317 according to the pig carcass cut category information read by the radio frequency identification reader 315 and business needs, thereby realizing the diversion operation of the system for pig carcass cuts.

[0043] To ensure efficient operation of the system, the system can be switched between automatic mode and manual mode during operation, so that when a failure occurs in the automatic mode, the normal operation of the pipeline platform can be ensured by switching from the automatic mode to the manual mode. Figure 4 As shown, for example, the control instructions input by the user are received through the touch display screen 318 and the working status information of the system is displayed to the user, wherein the control instructions include instructions for putting the system into manual or automatic diversion operation so as to make the system work in automatic mode or manual mode.

[0044] In order to facilitate understanding of the solutions of the above embodiments of this article, Figure 5 is an exemplary flow chart showing a system for classifying, identifying and sorting pig carcass cuts according to an embodiment of the present invention.

[0045] like Figure 5 As shown, first, in step S501, the entire system is started (eg Figure 3 and 4The system shown). Then, in step S502, it is determined whether a cut product holder for holding pig carcass cut products is sensed in the image acquisition area. If no cut product holder is sensed, that is, there are no pig carcass cut products to be imaged in the image acquisition area at this time, then the industrial computer control can be used to temporarily disable the blocking cylinder so that the pig carcass cut products can move forward in sequence along the assembly line and the front pig carcass cut product in the direction of the assembly line platform can enter the image acquisition area. On the contrary, if a cut product holder is sensed in the image acquisition area, the process proceeds to step S504. In step S504, an industrial camera is used to perform an image acquisition operation on the cut product holder in the image acquisition area. Similar to the above, when a cut product holder is sensed in the image acquisition area, the industrial computer can control the temporary activation of the blocking cylinder to block the subsequent cut product holder from moving along the direction of the assembly line platform to ensure the orderliness of image acquisition. Next, in step S505, the image information is uploaded to the industrial computer via the communication module. After the operation of the above step S505 is performed, the process proceeds to step S506. In step S506, the deep learning algorithm model is used to perform a category reasoning operation on the collected image information to obtain the category information of the pig carcass cut products, and then proceeds to step S507.

[0046] In step S507, the category information of the obtained pig carcass cuts is output. Then, in step S508, the RFID reader is used to write the category information into the RFID chip, and the RFID reader is used to bind the electronic number of the RFID chip with the category information, so as to realize the signal tracking of the pig carcass cuts. After completing the operation of step S508, the process proceeds to step S509. In step S509, the RFID reader is used to read the category information in the RFID chip. Further, in step S510, the industrial computer is used to start the diversion cylinder according to the category information read by the RFID reader to push different types of pig carcass cuts into the corresponding diversion ports, thereby realizing the diversion operation of the system. After completing step S510, the process proceeds to step S511 to execute the end operation.

[0047] Through the above combination Figure 5 According to the description, those skilled in the art can understand that the system of the present invention can automatically realize the classification, identification and diversion of pig carcass cuts, so as to replace the manual use of subjective vision to realize the classification of pig carcass cuts, thereby improving the efficiency of the classification operation of pig carcass cuts. At the same time, the present invention can improve the accuracy of the classification operation of pig carcass cuts by using a deep learning algorithm model.

[0048] Based on the previous Figure 1-Figure 5, those skilled in the art can also understand that the present invention actually also discloses a method for classifying, identifying and diverting pig carcass cuts, wherein the pig carcass cuts are placed on an assembly line platform, and the method may include first using an image acquisition device arranged above the assembly line platform to perform image acquisition on the pig carcass cuts that enter the image acquisition area of ​​the assembly line platform to obtain image information for classifying and identifying the pig carcass cuts. Then, the image information can be input into a deep learning algorithm model for category reasoning to obtain category information of the pig carcass cuts. Finally, the pig carcass cuts can be diverted to the corresponding product line according to the received category information.

[0049] In some implementation scenarios, the device of the present invention can be implemented in the form of a software program module. If implemented in the form of a software program module and sold or used as an independent product, the software program module can be stored in a computer-readable memory. Based on this, when the solution of the present invention is embodied in the form of a software product (such as a computer-readable storage medium), the software product can be stored in a memory, which may include several instructions to enable a computer device (such as a personal computer, a server or a network device, etc.) to perform some or all of the steps of the method described in the embodiment of the present invention. The aforementioned memory may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a flash drive, a read-only memory ("Read Only Memory", abbreviated as ROM), a random access memory ("Random Access Memory", abbreviated as RAM), a mobile hard disk, a magnetic disk or an optical disk. It should be understood that the terms "first", "second", "third" and "fourth" in the claims, specifications and drawings of the present disclosure are used to distinguish different objects, rather than to describe a specific order. The terms “include” and “comprising” used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0050] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0051] As used in this specification and claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0052] Although the embodiments of the present invention are as described above, the contents are only examples used to facilitate understanding of the present invention, and are not intended to limit the scope and application scenarios of the present invention. Any technician in the technical field of the present invention can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed by the present invention, but the scope of patent protection of the present invention shall still be based on the scope defined by the attached claims.

Claims

1. A system for classifying, identifying and sorting pig carcass cuts, wherein the pig carcass cuts are placed on an assembly line platform, characterized in that: The system comprises: An image acquisition device is arranged above the assembly line platform and is used to perform image acquisition on the pig carcass cuts placed in the cut product holder that enters the image acquisition area of ​​the assembly line platform to obtain image information for classifying and identifying the pig carcass cuts placed in the cut product holder; An industrial computer is connected to the image acquisition device for communication and is used for: receiving the image information from the image acquisition device; Inputting the image information into a deep learning algorithm model for category inference, so as to obtain category information of the pig carcass cuts placed in the cuts container; A diverting device, which is used to divert the pig carcass cut products contained in the cut product container to a corresponding product line according to the received category information; A cut product container for holding the pig carcass cut products, wherein a radio frequency identification chip is arranged on the cut product container for recording category information of the pig carcass cut products held in the cut product container; a plurality of blocking devices arranged upstream of the pipeline platform relative to the image acquisition area; and A plurality of sensors are arranged between adjacent blocking devices and are in communication connection with the corresponding blocking devices, In response to the sensor detecting that the divided product holder enters the corresponding area upstream of the assembly line platform, the blocking device is used to block the divided product holder so that a plurality of the divided product holders can enter the image acquisition area in an orderly manner; The blocking device blocks the cut product holder to prevent the pig carcass cut products placed in the cut product holder from moving along the direction of the assembly line platform; The sensor and the blocking device ensure that only the pig carcass cuts placed in a single cut container exist within the field of view of the image acquisition device each time.

2. The system according to claim 1, characterized in that The blocking device comprises a blocking cylinder and the sensor comprises a photoelectric sensor, wherein a plurality of the blocking cylinders are arranged in sequence along one side of the assembly line platform.

3. The system according to claim 1, characterized in that It also includes a radio frequency identification reader / writer, which is arranged in the image acquisition area of ​​the assembly line platform and corresponds to the position of the radio frequency identification chip, and is connected to the industrial computer for communication, so as to be used for: Reading the electronic number information of the radio frequency identification chip; Binding the category information with the electronic number information of the radio frequency identification chip; as well as The category information is written into the radio frequency identification chip so that the radio frequency identification chip records the category information of the pig carcass cut product.

4. The system according to claim 1, characterized in that Also includes: A radio frequency identification reader is arranged downstream of the pipeline platform relative to the image acquisition area, is communicatively connected with the diversion device, and is used to: Reading the category information recorded in the RFID chip; as well as The category information is transmitted to the diverting device so that the diverting device diverts the pig carcass cuts according to the category information.

5. The system according to claim 4, characterized in that The diverting device includes a plurality of diverting cylinders, each of which is used to divert the classified pig carcass cuts to a corresponding product line.

6. The system according to claim 5, characterized in that A plurality of diversion ports are arranged downstream of the assembly line platform, and the plurality of diversion cylinders are respectively arranged on the other side relative to the diversion ports so as to divert the classified pig carcass cuts to the corresponding product lines through the diversion ports.

7. A method for classifying, identifying and sorting pig carcass cuts, wherein the pig carcass cuts are placed on an assembly line platform, characterized in that: The method is performed by the system according to any one of claims 1 to 6, and the method further comprises: Using an image acquisition device disposed above the assembly line platform, performing image acquisition on the pig carcass cuts placed in the cuts container that enter the image acquisition area of ​​the assembly line platform, so as to obtain image information for classifying and identifying the pig carcass cuts; Inputting the image information into a deep learning algorithm model for category inference, so as to obtain category information of the pig carcass cuts placed in the cuts container; and The pig carcass cuts placed in the cuts container are diverted to corresponding product lines according to the received category information.

8. A computer-readable storage medium, characterized in that: The invention comprises program instructions for classifying, identifying and sorting pig carcass cuts, and when the program instructions are executed by a processor, the method according to claim 7 is implemented.

Images