Intelligent device for accurately identifying, measuring and sorting cubilose strips based on machine vision

Abstract

The utility model relates to an intelligent device for accurately identifying and measuring cubilose strips based on machine vision and an intelligent sorting device. The device comprises a photographing module, a processing circuit and a control assembly, the camera module is connected with the processing circuit through the server, and the control assembly is connected with the server and the camera module. When detecting a first control signal from the server, the control assembly outputs a second control signal to the camera module so as to control the camera module to collect images containing different swallow strips; the camera module transmits an image to the processing circuit through the server; the processing circuit performs edge identification, length measurement and proportion analysis on the received image in sequence to obtain quantity proportion information of all swallow strips in the image in different length intervals and evaluation feature information of corresponding batches; and on the basis of the sorting module, generating a corresponding sorting signal so as to sort the swallow strips. Therefore, the swallow strips can be accurately and efficiently measured and sorted.

Description

Technical Field

[0001] The present application relates to the field of food processing technology, and in particular to an intelligent device for accurately identifying and measuring the shape of bird's nest strips based on machine vision and an intelligent sorting device. Background Art

[0002] During the bird's nest processing, it is necessary to monitor the proportion of bird's nest strips in real time, and ensure that the proportion of long bird's nest strips is high to ensure the quality of the bird's nest product.

[0003] In traditional technology, it is usually necessary to manually measure the length of the bird's nest strips to obtain the proportion of long bird's nest strips in the bird's nest product, and manually pick the long bird's nest strips that meet the production standards.

[0004] However, in the current process of manually measuring the length of bird's nest strips and manually sorting them, the bird's nest strips need to be measured one by one manually, and then manually sorted one by one. In addition, the measurement and sorting process is easily affected by the subjective factors of the operator, resulting in inconsistency in the measurement and sorting results, thereby reducing the accuracy and efficiency of measuring and sorting the bird's nest strips. Utility Model Content

[0005] Based on this, it is necessary to provide an intelligent device based on machine vision to accurately identify and determine the shape of bird's nest strips, and a sorting intelligent device to accurately and efficiently measure and sort the bird's nest strips in order to solve the above-mentioned technical problems. Based on this, the bird's nest strips can be accurately detected and measured and grasped, and the strips that meet the high-quality bird's nest standards can be used in production to ensure the quality of the bird's nest.

[0006] The present application provides an intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision, the device comprising a camera module, a processing circuit and a control component; the camera module is connected to the processing circuit via a server, and the control component is connected to the server and the camera module respectively; when the control component detects a first control signal from the server, it outputs a second control signal to the camera module to control the camera module to capture images containing different bird's nest strips; the camera module transmits the image to the processing circuit via the server; the processing circuit sequentially performs edge recognition, length measurement, and proportion analysis on the received image to obtain the quantity proportion information of all bird's nest strips in the image in different length ranges and the evaluation feature information of the corresponding batches.

[0007] In one embodiment, the processing circuit includes an edge detection circuit, a length detection circuit and a proportion analysis circuit; the server, the edge detection circuit, the length detection circuit and the proportion analysis circuit are connected in sequence respectively; when the edge detection circuit receives an image from the server, it generates contour information of each strip of bird in the image; when the length measurement circuit receives the contour information from the edge detection circuit, it generates the length information of each strip of bird according to the number of pixels occupied by each strip of bird in the image and the pixel density of the image; when the proportion analysis circuit receives the length information from the length measurement circuit, it classifies each strip of bird into groups corresponding to different length intervals according to the corresponding length information, and generates the proportion information of the number of strips of bird corresponding to each group and the evaluation feature information of the corresponding batch.

[0008] In one embodiment, the camera module includes an acquisition controller, an acquisition card and an image sensor; the acquisition card is connected to the acquisition controller and the image sensor respectively, and the acquisition controller is connected to the control component; when the acquisition controller detects the second control signal, the acquisition controller controls the acquisition card to output a trigger signal to the image sensor, so that the image sensor acquires the image and outputs the image to the acquisition card; the acquisition card transmits the image to the processing circuit through the server.

[0009] In one embodiment, the device further comprises a storage circuit; the storage circuit is connected to the processing circuit and stores data from the processing circuit.

[0010] In one embodiment, the device further includes a display module; the display module is connected to the processing circuit and displays data from the processing circuit.

[0011] In one embodiment, the camera module also includes a lens and a light source module, the lens is used to guide light to the image sensor, and the light source module is used to provide lighting for the area to be collected of the camera module; wherein, a carrier loaded with swallowtail strips is arranged in the area to be collected, and the lens and the light source module are respectively arranged above and below the area to be collected, and the light emitted by the light source module passes through the area to be collected and enters the lens.

[0012] In one embodiment, the light source module includes a planar light source, and the planar light source is used to uniformly irradiate light on the area to be collected.

[0013] In one of the embodiments, an elastic member is provided at the edge of the area to be collected, and the elastic member is used to fix the carrier in the area to be collected.

[0014] In one embodiment, the camera module also includes a lens and a bracket, wherein the lens is used to guide light to the image sensor, and the bracket is used to provide structural support for the camera module; the lens is movably mounted on the bracket to adjust the distance between the lens and the area to be captured.

[0015] In one embodiment, the apparatus further includes an external interface, which includes at least one of an input interface, an output interface, a display interface, a storage interface, and a network interface, and is used to connect to an external device or system for data transmission or communication.

[0016] The present application also provides an intelligent sorting device, which includes the intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision, and also includes a sorting module, which is connected to the processing circuit and includes a manipulator and a clamp; the manipulator is movably arranged above the area to be collected where the bird's nest strips are located, and is used to locate the position of the bird's nest strips to be sorted in the area to be collected according to the sorting signal from the processing circuit, and control the clamp to move from the position of the bird's nest strips to be sorted in the area to be collected to the corresponding group area; wherein the group area refers to the area where the bird's nest strips are classified and placed after the length group of the bird's nest strips is determined; the clamp is arranged at one end of the manipulator close to the bird's nest strips, and is used to clamp the bird's nest strips.

[0017] The above-mentioned intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision and the intelligent sorting device, on the one hand, when the control component detects the first control signal from the server, outputs a second control signal to the camera module to control the camera module to collect images containing different bird's nest strips, and the camera module transmits the image to the processing circuit through the server, and the processing circuit performs edge recognition, length measurement, and proportion analysis on the received image in sequence to obtain the quantity proportion information of all bird's nest strips in the image in different length ranges and the evaluation feature information of the corresponding batch; on the other hand, based on the sorting module, a corresponding sorting signal is generated to pick the bird's nest strips; based on this, the image features of the bird's nest strips are accurately and efficiently extracted and analyzed, so as to reliably obtain the length measurement results and evaluation results of the bird's nest strip products, and further based on the length measurement results, the bird's nest strip products are accurately and efficiently sorted. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a structural block diagram of an intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision in one embodiment;

[0020] Figure 2 It is a structural block diagram of an intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision in another embodiment;

[0021] Figure 3 It is a structural block diagram of an intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision in another embodiment;

[0022] Figure 4 It is a structural block diagram of an intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision in another embodiment;

[0023] Figure 5 It is a structural block diagram of a sorting intelligent device in yet another embodiment. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0025] In an exemplary embodiment, Figure 1 As shown, an intelligent device for accurately identifying and measuring the shape of bird's nest strips based on machine vision is provided, including a camera module 101, a processing circuit 102 and a control component 103. The camera module 101 is connected to the processing circuit 102 through a server 104, and the control component 103 is connected to the server 104 and the camera module 101 respectively.

[0026] When the control component 103 detects the first control signal from the server 104, it outputs a second control signal to the camera module 101 to control the camera module 101 to capture images containing different swallow strips; the camera module 101 transmits the image to the processing circuit 102 through the server 104; the processing circuit 102 performs edge recognition, length measurement, and proportion analysis on the received image in sequence to obtain the quantity proportion information of all the swallow strips in the image in different length ranges and the evaluation feature information of the corresponding batches.

[0027] The quantity ratio information refers to the ratio or percentage of the number of objects in a group to the total number. The evaluation feature information refers to the data used to evaluate, judge or describe the object; the evaluation feature information evaluates the object based on objective evaluation indicators.

[0028] Among them, a preset number of bird's nest strips are selected from a batch of bird's nest strips products as samples, and images containing the sample bird's nest strips are captured by the camera module 101.

[0029] Optionally, the camera module 101 may convert the pixel value of each pixel of the color image into a grayscale value to obtain a grayscale image, thereby simplifying the image processing and contour extraction process, reducing the amount of calculation, and improving the efficiency and accuracy of the calculation.

[0030] Optionally, the bird's nest strips are dyed with edible dyes for 30 seconds; after the dyeing process is completed, the bird's nest strips are dispersed and separated so that the bird's nest strips are not connected to each other, and then the camera module 101 obtains images of these bird's nest strips, thereby improving the accuracy of identifying the edges of the bird's nest strips. Optionally, the camera module 101 can use a computer device including edge connection analysis, curve fitting and other algorithms to improve the accuracy of identifying the edges of the bird's nest strips that are connected to each other.

[0031] In this embodiment, through the information transmission and information interaction process between the camera module, processing circuit, control component, and server, the acquisition and processing of the bird's nest image is realized, and the quantity ratio information of the bird's nest and the evaluation feature information of the corresponding batch are obtained efficiently and accurately.

[0032] In an exemplary embodiment, Figure 2 As shown, the processing circuit 102 includes an edge detection circuit 102a, a length measurement circuit 102b and a ratio analysis circuit 103c, wherein the server 104, the edge detection circuit 102a, the length measurement circuit 102b and the ratio analysis circuit 102c are connected in sequence.

[0033] When the edge detection circuit 102a receives the image from the server 104, it generates the contour information of each stripe in the image; when the length measurement circuit 102b receives the contour information from the edge detection circuit 102a, it generates the length information of each stripe according to the number of pixels occupied by each stripe in the image and the pixel density of the image; when the proportion analysis circuit 102c receives the length information from the length measurement circuit 102b, it classifies each stripe into groups corresponding to different length intervals according to the corresponding length information, and generates the proportion information of the number of stripes corresponding to each group and the evaluation feature information of the corresponding batch.

[0034] Among them, contour information refers to a way of describing the boundary of an object, which can be used to identify the shape, size, position and relative relationship of the object with other objects; contour information can be represented as a series of continuous points, line segments or curves that define the boundary of the object.

[0035] Among them, pixel density refers to the number of pixels per inch, and its unit is PPI (Pixels Per Inch). The higher the PPI value, the richer the details of the picture. Length information refers to the size or distance of an object in a certain dimension; length information can represent information describing the length of the strip.

[0036] Exemplarily, the length measurement circuit 102b obtains the number of pixels occupied by the strip in the image based on the contour information of the current strip, and the physical length corresponding to the strip can be calculated through the numerical relationship between the number of pixels occupied by the strip and the pixel density of the image. Optionally, the numerical relationship between the number of pixels occupied by the strip and the pixel density of the image can be expressed as the number of pixels occupied by the strip divided by the pixel density of the image, and the resulting value is the physical length corresponding to the strip.

[0037] Exemplarily, the length measurement circuit 102b can also obtain the number of pixels occupied by the distance between the two ends of the strip in the image based on the boundary of the strip, and then calculate the physical length corresponding to the strip. Further, when the strip is in a bent state, the distance between the two ends of the strip can be divided into a plurality of straight lines connected in sequence, and the overall layout of the plurality of straight lines is consistent with the bending direction of the strip, and the number of pixels occupied by each straight line is obtained in sequence and then summed up, so as to calculate the physical length corresponding to the strip. Optionally, the length measurement circuit 102b can extract the feature points of the strip through feature point extraction technology, and extract a curve through several feature points of a strip, the direction of the curve is consistent with the overall shape of the strip, traverse each point on the curve, connect every two adjacent points into a line segment, and then add up the lengths of all line segments to obtain the length of the curve, and the length of the curve can be expressed as the length of the strip.

[0038] Optionally, the edge detection circuit 102a, the length measurement circuit 102b and the proportion analysis circuit 103c can respectively adopt hardware circuits with relevant functions, and the relevant hardware circuits cooperate with each other to form a processing circuit of this embodiment, so that the processing circuit supports the corresponding processing functions. Computer equipment or storage media that include existing image processing algorithms such as edge detection algorithms, length measurement algorithms, and proportion algorithms can also be used to respectively realize corresponding edge detection functions, length measurement functions, or proportion analysis functions.

[0039] In this embodiment, data is processed and transmitted through an edge detection circuit, a length measurement circuit, and a proportion analysis circuit, respectively, so that the image features of the bird's nest strips are accurately and efficiently extracted and analyzed, thereby improving the accuracy and efficiency of the evaluation of bird's nest strip products.

[0040] In an exemplary embodiment, Figure 3As shown, the camera module 101 includes an acquisition controller 101a, an acquisition card 101b and an image sensor 101c. The acquisition card 101b is connected to the acquisition controller 101a and the image sensor 101c respectively, and the acquisition controller 101a is connected to the control component 103.

[0041] When the acquisition controller 101a detects the second control signal, it controls the acquisition card 101b to output a trigger signal to the image sensor 101c, so that the image sensor 101c acquires an image and outputs the image to the acquisition card 101b; the acquisition card 101b transmits the image to the processing circuit 102 through the server 104.

[0042] Optionally, the camera module 101 may include an industrial camera, which includes the acquisition controller 101a, acquisition card 101b and image sensor 101c mentioned above. The image of the swallow bar is obtained through the industrial camera, and the high resolution of the camera must be guaranteed, for example, more than 20 million pixels; in addition, the camera can adjust imaging parameters such as image exposure time, contrast, saturation, etc. to adapt to different lighting conditions and the characteristics of different swallow bars.

[0043] The camera module 101 further includes a lens and a light source module. The lens is used to guide light to the image sensor 101c, and the light source module is used to provide lighting for the area to be collected by the camera module 101. The carrier loaded with swallow strips is set in the area to be collected, and the lens and the light source module are respectively set above and below the area to be collected. The light emitted by the light source module passes through the area to be collected and enters the lens.

[0044] Optionally, the light source module includes a planar light source, which can be an LED light source, for providing a uniform lighting environment for the area to be collected, and reducing or eliminating reflections and shadows caused by moisture, thereby improving image clarity; the color temperature of the light source should match the processing circuit 102 to ensure color accuracy and consistency.

[0045] Optionally, the carrier for loading the swallow strips can be made of glass material to have good light transmittance; and the size of the carrier needs to be adapted to the field of view of the camera; during use, care should be taken to keep the transparent carrier and the light source dry and tidy to prevent water stains or foreign objects from affecting photo taking and recognition; the carrier is located in a square area to be collected, and the edge of the area to be collected is provided with elastic limit strips to protect and fix the carrier.

[0046] Among them, the camera module 101 also includes a bracket, which is used to provide structural support for the camera module 101; the lens is movably installed on the bracket, and the motor is controlled to rise and fall by operating the button to adjust the height of the lens, thereby adjusting the distance between the lens and the area to be collected, so as to accurately control the imaging field of view according to actual imaging requirements.

[0047] In this embodiment, an optical path is constructed between the camera module and the area to be collected so as to quickly and clearly obtain the image of the swallowtail in the area to be collected.

[0048] In an exemplary embodiment, Figure 4 As shown, the device further includes a storage circuit 105 and a display module 106. The storage circuit 105 is connected to the processing circuit 102 and stores data from the processing circuit 102; the display module 106 is connected to the processing circuit 102 and displays data from the processing circuit 102.

[0049] Among them, the data information from the processing circuit 102 may include image information, numerical information and evaluation feature information; the image information includes image number, resolution, brightness, depth and other information; the numerical information includes the number of each swallow strip, the contour information and length information corresponding to each swallow strip, the quantity proportion information of each group, the total number of swallow strips and other information; the evaluation feature information includes the batch number of swallow strips, evaluation level and other information.

[0050] In this embodiment, the data information from the processing circuit is displayed visually to facilitate operators to observe and record measurement results and monitor the data in real time; the data information from the processing circuit is associated and stored in a database to provide comprehensive data recording and traceability functions, which is convenient for subsequent data analysis, quality control and traceability of the production process.

[0051] In an exemplary embodiment, the camera module 101 acquires an image of a standard object, and transmits the image to the processing circuit 102 via the server 104. The processing circuit 102 obtains the number of pixels occupied by the standard object in the standard image, as well as the numerical relationship between the known physical length of the standard object and the corresponding number of pixels occupied.

[0052] The processing circuit 102 inputs the information about the number of pixels occupied by a stripe into the numerical relationship to obtain the theoretical length information of the stripe under the numerical relationship.

[0053] The processing circuit 102 then determines the error range corresponding to each swallow strip based on the theoretical length information of each swallow strip. If the length information corresponding to the swallow strips with a preset proportion is within the corresponding error range, the data verification result is qualified; if the length information corresponding to the swallow strips with a preset proportion is not within the corresponding error range, the data verification result is unqualified. According to the deviation value between the length information corresponding to each swallow strip and the corresponding theoretical length information, the numerical relationship between the number of pixels occupied by each swallow strip in the corresponding image pixel and the pixel density of the image is corrected.

[0054] Among them, standard objects refer to objects with specified size, shape, quality or performance, which are usually used as reference objects for comparing, testing, calibrating or calibrating other objects. Standard images refer to images with known characteristics, size, content or quality, which are usually used for testing, calibrating, comparing or evaluating image processing algorithms.

[0055] Optionally, the processing circuit 102 obtains the lengths of different standard objects and the number of pixels occupied in the standard image to form multiple sets of data; based on the multiple sets of data, a fitting function of the numerical relationship between the length of the standard object and the number of pixels occupied in the standard image is obtained; the number of pixels occupied in the image pixels corresponding to each stripe is input into the fitting function to obtain theoretical length information corresponding to each stripe. The fitting function can be expressed as a relationship between the number of pixels occupied by objects of different lengths.

[0056] Optionally, the maximum allowable error between the theoretical length information and the length information may be set to 15%, that is, when the theoretical length information is greater than 0.85 times the length information and less than 1.15 times the length information, the data verification result is determined to be qualified.

[0057] Optionally, the preset number ratio can be set to 10%, that is, when the number of swallow strips whose length information is within the corresponding error range accounts for less than or equal to 10%, the data verification result is judged to be qualified; when the number of swallow strips whose length information is not within the corresponding error range accounts for more than 10%, the data verification result is judged to be unqualified.

[0058] Optionally, if the evaluation data verification result is unqualified, the numerical relationship between the number of pixels occupied by the swallow strips and the pixel density of the image can be corrected by setting a corresponding correction circuit. For example, a correction curve can be drawn to visualize the relationship between the actual measured value and the theoretical value, and the correction factor can be determined according to the shape of the curve; the correction factor can also be determined by using regression analysis to analyze relevant variables existing in the processes of image acquisition, pixel number analysis, and conversion of length values; the correction factor can also be calculated according to the nature of the error source by identifying and quantifying the possible error sources in the measurement.

[0059] Optionally, if the data verification result is unqualified, the lens height and built-in parameters of the camera module 101, the layout and built-in parameters of the light source module, etc. may be checked, or related components may be repaired.

[0060] In this embodiment, the actual measured value of the length of the swallow strip is verified by setting the data verification standard to check the reliability of the process and results of extracting the characteristic information of the swallow strip; furthermore, by fitting the data, a fitting function of the object length and the number of pixels occupied is obtained to more reliably deduce the theoretical length value corresponding to the swallow strip, thereby realizing the calibration and accuracy control of the measurement results.

[0061] In an exemplary embodiment, the proportion analysis circuit 102c regards the swallow strips with a length greater than or equal to a preset threshold as long swallow strips and classifies them into the same group; according to the number of long swallow strips and the number of all swallow strips, the quantity proportion information of the long swallow strips corresponding to the group is obtained; according to the numerical range in which the quantity proportion information of the long swallow strips is located, the evaluation level of the batch is determined; wherein different numerical ranges correspond to different evaluation levels, respectively, and the evaluation level increases as the quantity proportion of the long swallow strips increases.

[0062] Among them, the evaluation grade refers to the evaluation of the characteristic information of the bird's nest strips or the rating of the quality of the bird's nest strips based on objective standards.

[0063] Exemplarily, the preset threshold can be set to 4 cm, and the rating unit will regard the swallow strips with a length greater than or equal to 4 cm as long swallow strips, and classify all long swallow strips into the same group; based on the number of long swallow strips and all swallow strips, the number ratio of long swallow strips is obtained, and based on the number ratio value of long swallow strips, the evaluation grade of the batch of swallow strips is determined.

[0064] Optionally, the rating unit sets different evaluation levels according to different numerical intervals, and the evaluation level increases as the proportion of the number of long swallow strips increases. For example, when the proportion of the number of long swallow strips is equal to or greater than 70%, the evaluation level is A; when the proportion of the number of long swallow strips is between 65% and 70% (excluding 70%), the evaluation level is B; when the proportion of the number of long swallow strips is between 60% and 65% (excluding 65%), the evaluation level is C; when the proportion of the number of long swallow strips is less than 60%, the evaluation level is D.

[0065] In this embodiment, by setting the evaluation grade standard, the evaluation results of the characteristic information of the corresponding batch of bird's nest strips can be obtained efficiently.

[0066] In an exemplary embodiment, the apparatus further includes an external interface, which includes at least one of an input interface, an output interface, a display interface, a storage interface, and a network interface, and is used to connect to an external device or system for data transmission or communication.

[0067] In an exemplary embodiment, Figure 5 As shown, a sorting intelligent device is provided, which includes the above-mentioned intelligent device for accurately identifying and measuring the shape of bird's nest strips based on machine vision, and also includes a sorting module 107, the sorting module 107 is connected to the processing circuit 102, and includes a manipulator 107a and a clamp 107b.

[0068] The manipulator 107a is movably arranged above the area to be collected where the bird's nest strips are located, and is used to locate the position of the bird's nest strips to be sorted in the area to be collected according to the sorting signal from the processing circuit 102, and control the clamping claw 107b to move from the position of the bird's nest strips to be sorted in the area to be collected to the corresponding grouping area; wherein the grouping area refers to the area where the bird's nest strips are grouped and placed after the length group of the bird's nest strips is determined. The clamping claw 107b is arranged at one end of the manipulator close to the bird's nest strips, and is used to clamp the bird's nest strips.

[0069] Exemplarily, the processing circuit 102 obtains the corresponding position information of each swallow strip in the area to be collected based on the contour information of each swallow strip in the image, that is, there is a mapping relationship between the position of the same swallow strip in the image and the position in the area to be collected; based on the position information of the current swallow strip in the area to be collected and the corresponding group, the processing circuit 102 generates a corresponding sorting signal and sends it to the sorting module 107.

[0070] After the sorting module 107 receives the sorting signal, based on the bird's nest position information corresponding to the sorting signal, the robot 107a is positioned to the corresponding position in the area to be collected, that is, the position of the corresponding bird's nest, and the clamp 107b performs a closing action to clamp the bird's nest; then, based on the bird's nest group corresponding to the sorting signal, the robot 107a moves the clamp 107b clamping the bird's nest to the group area corresponding to the bird's nest group, and then the clamp 107 performs an opening action to place the bird's nest in the corresponding group area, thereby realizing the sorting function for the bird's nest.

[0071] Furthermore, after the sorting module 107 completes the sorting task for one bird's nest strip, the sorting module 107 sends a feedback signal to the processing circuit 102 to drive the processing circuit 102 to generate a sorting signal corresponding to another bird's nest strip.

[0072] Optionally, the clamps may be flexible clamps obtained through 3D printing technology, which can reduce the clamping force on the bird's nest strips while firmly maintaining the clamping force, thereby avoiding damage to the soaked and weaker bird's nest strips.

[0073] Optionally, the area to be collected can be divided into multiple detection partitions according to a preset unit area. For example, the area to be collected can be divided into multiple rectangular detection partitions of the same area; for the swallow strips in one detection partition, a corresponding sorting signal is generated according to the corresponding position information and group, and at the same time, for the swallow strips in another detection partition, the corresponding length information is obtained according to the numerical relationship between the number of pixels occupied in the corresponding image pixels and the pixel density of the image. Based on this, the two detection partitions concurrently execute the sorting signal generation task and the length information acquisition task, thereby simultaneously improving the efficiency of swallow strip length recognition and sorting while reducing the data processing burden.

[0074] Optionally, based on the position information of each bird's nest strip in the area to be collected, the distance value between the bird's nest strip and the corresponding group area is identified, and the distance value is selected from multiple distance values ​​in order from small to large, and the sorting signal of the corresponding bird's nest strip is generated in sequence according to the selected distance value, that is, according to the distance between the bird's nest strip and the corresponding group area, the sorting order of the bird's nest strip is adjusted accordingly, so as to plan the optimal and shortest movement trajectory for the sorting task of the sorting module 107, so as to improve the sorting efficiency and reduce energy consumption.

[0075] In the present embodiment, on the premise of accurately measuring the length of the bird's nest strips, the corresponding sorting signal is further generated through the position information and group corresponding to each bird's nest strip, so that the bird's nest strips are sorted from the to-be-collected area to the corresponding group area according to the corresponding group, thereby efficiently and accurately realizing the sorting function for the bird's nest strips, so as to efficiently pick up the bird's nest strips that meet the high-quality bird's nest standards and use them in production, thereby ensuring the quality of the bird's nest.

[0076] In addition, the intelligent device and sorting intelligent device for accurately identifying and measuring the shape of bird's nest strips based on machine vision have good integration and can be seamlessly connected with other production equipment or production lines; they also have certain scalability and can cope with the measurement and sorting needs of bird's nest strips of different sizes, shapes and types. For example, it supports standard interfaces and communication protocols to connect and exchange data with other equipment or production lines. Commonly used interfaces and protocols include Ethernet, serial ports, Modbus, OPC UA, etc., and data transmission and sharing functions can also be achieved through network communication, database storage, message queues and other technologies; it can also receive and parse instructions from external devices or production lines, and start, stop or adjust the measurement process as needed to achieve collaborative work, automated control and automated scheduling with other equipment or production lines; it also provides software platforms and APIs (application programming interfaces) so that other equipment or production lines can access corresponding functions and data by calling interfaces, so as to customize integration and expansion according to their own needs.

[0077] Furthermore, in an exemplary embodiment, the intelligent device for accurately identifying and measuring the shape of bird's nest strips based on machine vision can be applied to the following scenarios:

[0078] During the bird's nest production process, manufacturers can use this method to measure the length of the bird's nest strips in real time and compare it with the set standards to ensure that the produced bird's nest strips meet the quality requirements; during the processing and grading of bird's nests, this method can be used to automatically determine the length of the bird's nest strips, and the bird's nests can be grouped or graded according to length to meet the needs of different markets and customers; in the trade and import and export of bird's nests, this method can be used to obtain reliable length measurement results as a basis for bird's nest quality inspection to ensure compliance with relevant trade standards and regulations; in scientific research and data analysis of bird's nests, this method can be used to obtain a large amount of bird's nest strip length data, and use these data for statistical analysis, trend analysis and correlation research.

[0079] Each module in the intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision and the intelligent device for sorting can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0080] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An intelligent device for accurately identifying and measuring the shape of bird's nest strips based on machine vision, characterized in that: The device includes a camera module, a processing circuit and a control component; The camera module is connected to the processing circuit via a server, and the control component is connected to the server and the camera module respectively; When the control component detects the first control signal from the server, it outputs a second control signal to the camera module to control the camera module to capture images containing different bird strips; the camera module transmits the image to the processing circuit through the server; the processing circuit sequentially performs edge recognition, length measurement, and proportion analysis on the received image to obtain the quantity proportion information of all bird strips in the image in different length intervals and the evaluation feature information of the corresponding batch; Wherein, the processing circuit includes an edge detection circuit, a length measurement circuit and a proportion analysis circuit; the server, the edge detection circuit, the length measurement circuit and the proportion analysis circuit are connected in sequence respectively; When the edge detection circuit receives the image from the server, it outputs the contour information of each strip of bird in the image; when the length measurement circuit receives the contour information from the edge detection circuit, it outputs the length information of each strip of bird according to the number of pixels occupied by each strip of bird in the image and the pixel density of the image; when the proportion analysis circuit receives the length information from the length measurement circuit, it classifies each strip of bird into groups corresponding to different length intervals according to the corresponding length information, and outputs the proportion information of the number of strips of bird corresponding to each group and the evaluation feature information of the corresponding batch.

2. The device according to claim 1, characterized in that The camera module includes an acquisition controller, an acquisition card and an image sensor; The acquisition card is connected to the acquisition controller and the image sensor respectively, and the acquisition controller is connected to the control component; When detecting the second control signal, the acquisition controller controls the acquisition card to output a trigger signal to the image sensor, so that the image sensor acquires the image and outputs the image to the acquisition card; the acquisition card transmits the image to the processing circuit through the server.

3. The device according to claim 1, characterized in that The device also includes a storage circuit; The storage circuit is connected to the processing circuit and stores data from the processing circuit.

4. The device according to claim 1, characterized in that The device also includes a display module; The display module is connected to the processing circuit and displays data from the processing circuit.

5. The device according to claim 4, characterized in that The camera module also includes a lens and a light source module, wherein the lens is used to guide light to the image sensor, and the light source module is used to provide illumination for the area to be captured by the camera module; Among them, the carrier loaded with swallow strips is set in the area to be collected, and the lens and the light source module are respectively arranged above and below the area to be collected, and the light emitted by the light source module passes through the area to be collected and enters the lens.

6. The device according to claim 5, characterized in that The light source module includes a planar light source, and the planar light source is used to irradiate light uniformly on the area to be collected.

7. The device according to claim 5, characterized in that An elastic member is provided at the edge of the area to be collected, and the elastic member is used to fix the carrier in the area to be collected.

8. The device according to claim 1, characterized in that The camera module further includes a lens and a bracket, wherein the lens is used to guide light to the image sensor, and the bracket is used to provide structural support for the camera module; The lens is movably mounted on the bracket to adjust the distance between the lens and the area to be collected.

9. An intelligent sorting device, characterized in that: The intelligent sorting device comprises the intelligent device for accurately identifying and determining the shape of bird's nest strips based on machine vision according to any one of claims 1 to 8, and further comprises a sorting module, the sorting module is connected to the processing circuit and comprises a manipulator and a gripper; The manipulator is movably arranged above the area to be collected where the bird's nest strips are located, and is used to locate the position of the bird's nest strips to be sorted in the area to be collected according to the sorting signal from the processing circuit, and control the gripper to move from the position of the bird's nest strips to be sorted in the area to be collected to the corresponding grouping area; wherein the grouping area refers to the area where the bird's nest strips are grouped and placed after the length group of the bird's nest strips is determined; The clamping claw is arranged at one end of the manipulator close to the swallow bar and is used for clamping the swallow bar.

Images