CN118304171A - Liquid preparation method based on image recognition - Google Patents
Liquid preparation method based on image recognition Download PDFInfo
- Publication number
- CN118304171A CN118304171A CN202310559807.8A CN202310559807A CN118304171A CN 118304171 A CN118304171 A CN 118304171A CN 202310559807 A CN202310559807 A CN 202310559807A CN 118304171 A CN118304171 A CN 118304171A
- Authority
- CN
- China
- Prior art keywords
- suction
- injection device
- image
- medicine bottle
- dimensional coordinate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000007788 liquid Substances 0.000 title claims abstract description 136
- 238000002360 preparation method Methods 0.000 title claims abstract description 41
- 238000002347 injection Methods 0.000 claims abstract description 172
- 239000007924 injection Substances 0.000 claims abstract description 172
- 239000003814 drug Substances 0.000 claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 78
- 230000003287 optical effect Effects 0.000 claims description 49
- 230000036544 posture Effects 0.000 claims description 33
- 238000005286 illumination Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 18
- 238000001514 detection method Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 11
- 230000008859 change Effects 0.000 description 9
- 229940079593 drug Drugs 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
Landscapes
- Medical Preparation Storing Or Oral Administration Devices (AREA)
- Automatic Analysis And Handling Materials Therefor (AREA)
Abstract
The disclosure describes a liquid dispensing method based on image recognition, comprising: forming a calibration area by the first camera and the second camera; moving the suction and injection device to a calibration area, acquiring a first image of the suction and injection device through a first camera, and acquiring a second image of the suction and injection device through a second camera; acquiring three-dimensional coordinate parameters of the suction injector; performing compensation operation on three-dimensional coordinate parameters of the suction and injection device, and controlling the suction and injection device to match with a medicine bottle for liquid preparation; wherein the compensating operation comprises: and comparing the three-dimensional coordinate parameter with the reference coordinate parameter to obtain a deviation value, and judging whether the deviation value is larger than a tolerance range. Therefore, the three-dimensional coordinate position and the three-dimensional coordinate gesture of the suction and injection device can be detected through machine vision, and compensation calibration is carried out to solve the problem of alignment of the suction and injection device and the medicine bottle in the liquid preparation process.
Description
Technical Field
The present disclosure relates generally to the field of automated production, and in particular, to a liquid dispensing method based on image recognition.
Background
In an automated dispensing system, the pipettor and the drug (or drug solution) are not fixed, but are only transferred to the dispensing station when being pipetted, in which case, the problem . that the drug is displaced or the pipettor is not accurately clamped due to shaking during the transfer process is easily occurred, and in addition, in order to reduce the waste of the drug solution, the carrier (such as a drug bottle) is often tilted by a certain angle so that the pipettor can fully aspirate the drug solution. However, the caliber of the medicine bottle used in the process of preparing the liquid is generally limited, the caliber is not suitable to be too large, the medicine bottle in an inclined state and the medicine bottle with the limited caliber may influence the accurate entering of the suction and injection device into the medicine bottle to suck and inject the liquid medicine, that is, the problem of alignment between the suction and injection device and the medicine bottle exists, for example, the needle tube (the suction and injection device is also called an injector, and generally comprises the needle tube, the piston and the like) of the suction and injection device may touch the medicine bottle mouth when moving downwards, and the medicine bottle is difficult to enter the medicine bottle. Therefore, the medicine bottle position or the suction and injection device position needs to be detected and adjusted in a targeted manner in the dispensing process so as to improve the dispensing accuracy.
In the prior art, in order to solve the above problems, a liquid dispensing machine with a fixed point position is generally used for dispensing liquid, and because the mechanism for clamping the suction and injection device and the medicine bottle is carried out on the fixed point position, the problem of alignment between the suction and injection device and the medicine bottle is easily solved. However, the liquid dispensing machine with the fixed point position has less freedom and poor flexibility, and has less realized functions, while the multifunctional machine needs to be additionally provided with a functional mechanism or device to realize, so that the machine equipment has complex and heavy structure. In the prior art, a bionic manipulator (an automatic operation device capable of simulating certain action functions of a human hand and an arm and used for grabbing and carrying objects or operating tools according to a fixed program) and visual detection are adopted to carry out liquid preparation, the needle point position of an injection sucker is detected through machine vision, then the needle point is calibrated, liquid preparation is completed at the calibrated needle point position, the liquid preparation mode is high in automation degree, the liquid preparation process is more accurate, the equipment structure is simplified, and multifunctional liquid preparation operation can be realized.
However, in the prior art based on visual detection, a single visual device is generally used to detect the suction and injection device, only two-dimensional coordinates of the suction and injection device can be obtained, and a complex calculation method is needed if three-dimensional coordinates of the suction and injection device are needed to be obtained. In addition, there is also a scheme of detecting the suction and injection device by using a plurality of vision devices (such as binocular cameras), but in the scheme, optical axes of the plurality of vision devices are almost parallel, three-dimensional coordinates of the suction and injection device are obtained by acquiring images of the measured object under two visual angles and combining an algorithm for calculating depth, and if the measured object (such as a needle point of the suction and injection device) has fewer grippable features, it is difficult to accurately judge the posture of the suction and injection device. In the automatic dispensing process, the judgment of the three-dimensional coordinate position and the posture of the suction injector is particularly important for the accurate matching of the medicine bottle to complete the liquid dispensing process, and the prior art is difficult to meet.
Disclosure of Invention
The present disclosure has been made in view of the above-mentioned conventional art, and an object thereof is to provide a liquid dispensing method based on image recognition, which can detect the three-dimensional coordinate position and posture of a suction and injection device through machine vision and perform compensation calibration to solve the alignment problem of the suction and injection device and a medicine bottle in the liquid dispensing process.
Therefore, the present disclosure provides a liquid dispensing method based on image recognition, which is a method for completing liquid dispensing by controlling a suction and injection device to suck and inject liquid by a mechanical arm in combination with a medicine bottle, comprising: forming a calibration area by a first camera having a first optical axis and a second camera having a second optical axis, the first optical axis being non-parallel to the second optical axis; moving the suction and injection device to the calibration area, acquiring a first image of the suction and injection device through the first camera, and acquiring a second image of the suction and injection device through the second camera; acquiring three-dimensional coordinate parameters of the suction and injection device based on the first image and the second image, wherein the three-dimensional coordinate parameters of the suction and injection device comprise three-dimensional coordinates of a plurality of specific points of the suction and injection device and the gesture of the suction and injection device; performing compensation operation on the three-dimensional coordinate parameters of the suction and injection device, and controlling the suction and injection device to match with a medicine bottle to perform liquid preparation according to the compensated three-dimensional coordinate parameters; wherein the compensating operation includes: and comparing the three-dimensional coordinate parameter with a reference coordinate parameter to obtain a deviation value, judging whether the deviation value is larger than a tolerance range, if the deviation value is not larger than the tolerance range, compensating the three-dimensional coordinate parameter based on the deviation value so that the three-dimensional coordinate parameter is consistent with the reference coordinate parameter, and if the deviation value is larger than the tolerance range, replacing the suction injector and carrying out the compensation operation again.
In the present disclosure, images of the suction and injection device under different viewing angles are acquired through two cameras with non-parallel optical axes, three-dimensional coordinate positions and postures of the suction and injection device can be obtained based on the images of the suction and injection device under different viewing angles, and deviation values of the three-dimensional coordinates and postures of the suction and injection device are obtained through comparison with reference coordinate parameters. In addition, whether the deviation value is in the tolerance range or not is judged in advance in the compensation process, so that the efficiency of detecting the position and the gesture of the suction and injection device through machine vision can be improved, and the liquid preparation efficiency can be improved.
In addition, according to the liquid dispensing method related to the present disclosure, optionally, the first optical axis and the second optical axis are both perpendicular to the vertical direction, and the first optical axis and the second optical axis are perpendicular to each other. In this case, the first image of the suction and injection device acquired through the first camera can determine whether the posture of the suction and injection device is deviated on a plane formed by the first optical axis and the vertical direction through the first image, namely, whether the suction and injection device is deviated in the vertical direction by taking the first optical axis as a viewing angle, and the first image of the suction and injection device acquired through the first camera can determine whether the posture of the suction and injection device is deviated on a plane formed by the second optical axis and the vertical direction through the second image, namely, whether the suction and injection device is deviated in the vertical direction by taking the second optical axis as a viewing angle; in addition, as the first optical axis and the second optical axis are mutually perpendicular, whether the posture of the suction and injection device deviates in the three-dimensional coordinate can be judged through two perpendicular planes; in addition, the three-dimensional coordinates of the suction and injection device can be directly obtained through two perpendicular planes, so that the complex problem of obtaining the three-dimensional coordinates by the general binocular vision based on a depth calculation method is solved, namely, the calculated amount of coordinate conversion can be reduced, and the operation process is simplified.
In addition, according to the liquid preparation method related to the disclosure, optionally, the method further includes: before the suction and injection device moves to the calibration area, the reference suction and injection device parallel to the vertical direction is moved to the calibration area; and acquiring three-dimensional coordinates and postures of a plurality of specific points of the reference suction and injection device, and generating the reference coordinate parameters based on the three-dimensional coordinates and postures of the plurality of specific points of the reference suction and injection device. In this case, the reference coordinate parameter can be obtained by the reference suction and injection device, whereby the deviation value can be obtained by comparing the three-dimensional coordinate parameter of the suction and injection device with the reference coordinate parameter at the time of the compensation operation.
In addition, according to the liquid dispensing method related to the present disclosure, optionally, after moving the reference suction and injection device parallel to the vertical direction to the calibration area, the method further includes: and adjusting the focal lengths of the first camera and the second camera, and adjusting the illumination intensities of the first camera and the second camera. In this case, the image quality of the first image and the second image can be improved by adjusting the camera focal length and the illumination, whereby the accuracy of the subsequent acquisition of the coordinate parameters and the like based on the images can be improved.
In addition, according to the liquid preparation method related to the disclosure, before generating the reference coordinate parameter, optionally further includes: and placing the reference suction and injection device at a plurality of target positions in the calibration area, acquiring three-dimensional coordinates and postures of a plurality of specific points of the reference suction and injection device corresponding to the plurality of target positions, and generating the reference coordinate parameters based on the three-dimensional coordinates and postures of the plurality of specific points of the reference suction and injection device. In this case, by generating a plurality of reference coordinate parameters with the reference pipette at a plurality of target positions in the calibration area, thereby enabling to select at least one of the plurality of reference coordinate parameters as a reference coordinate parameter during actual dispensing, in addition, the plurality of reference coordinate parameters can generate a tolerance range, enabling to allow the pipette to shift and compensate within the tolerance range, thereby improving efficiency of alignment of the pipette and the vial during dispensing to improve efficiency of dispensing.
In addition, according to the liquid dispensing method related to the disclosure, optionally, a first characteristic parameter is acquired based on the first image, a second characteristic parameter is acquired based on the second image, and a three-dimensional coordinate parameter of the suction and injection device is acquired based on the first characteristic parameter and the second characteristic parameter, wherein the first characteristic parameter is represented as a position of a characteristic point where the suction and injection device is located in the first image, and the second characteristic parameter is represented as a position of a characteristic point where the suction and injection device is located in the second image. In this case, coordinates of the corresponding feature points, that is, feature parameters can be obtained by extracting the feature points in the image of the suction and injection device, whereby the three-dimensional coordinates of the suction and injection device can be determined by the feature parameters, and the posture of the suction and injection device can be determined by comparison with the reference coordinate parameters.
In addition, according to the liquid dispensing method related to the disclosure, optionally, the first image and the second image are read, and preprocessed, and the first characteristic parameter and the second characteristic parameter are respectively acquired based on the processed first image and the processed second image. In this case, preprocessing the image of the inhaler can facilitate recognition of the characteristic points of the inhaler, whereby the characteristic parameters of the inhaler can be readily obtained.
In addition, according to the liquid dispensing method related to the present disclosure, optionally, contours of the suction and injection devices are extracted from the first image and the second image, an circumscribed rectangle is drawn based on the contours of the suction and injection devices, an ROI area is extracted within the circumscribed rectangle, and the first characteristic parameter and the second characteristic parameter are acquired based on the ROI area. ROI (Region of Interest) denotes a region of interest, which means that the region to be processed is outlined from the processed image in the form of a square, a circle, an ellipse, an irregular polygon, etc. In this case, by extracting the outline of the suction and injection device in the image, it is possible to facilitate recognition of the suction and injection device and drawing of the circumscribed rectangle and the ROI area, whereby the feature points of the suction and injection device can be accurately recognized by using the circumscribed rectangle and the ROI area, and interference of image noise can be reduced.
In addition, according to the liquid preparation method related to the disclosure, optionally, the method further includes: and tilting the medicine bottle by a preset angle, acquiring a two-dimensional coordinate parameter of the medicine bottle through a third camera, comparing the two-dimensional coordinate parameter of the medicine bottle with a reference coordinate parameter of the medicine bottle to acquire the position deviation of the medicine bottle, and performing the compensation operation on the three-dimensional coordinate parameter of the suction injector based on the deviation value and the position deviation of the medicine bottle. In this case, the accuracy of the liquid preparation can be improved by simultaneously acquiring the coordinate positions of the medicine bottle and the liquid suction and injection device and compensating the three-dimensional coordinate parameters of the liquid suction and injection device based on the deviation of the two relative to the respective reference coordinate parameters, thereby calibrating the liquid suction and injection device.
In addition, according to the liquid dispensing method related to the present disclosure, optionally, the two-dimensional coordinate parameters of the medicine bottle include two-dimensional coordinates of a plurality of specific points of the medicine bottle and a posture of the medicine bottle. In this case, whether the medicine bottle is inclined in place or the position is deviated can be judged by the two-dimensional coordinates and the postures of a plurality of specific points of the medicine bottle, so that the accuracy of the alignment of the suction and injection device and the medicine bottle in the liquid preparation process can be improved by performing the compensation operation on the medicine bottle, or the suction and injection device can be compensated so that the suction and injection device can accurately enter the medicine bottle even if the medicine bottle is not calibrated for sucking and injecting liquid.
According to the liquid dispensing method based on image recognition, the three-dimensional coordinate position and the three-dimensional coordinate gesture of the suction and injection device can be detected through machine vision, and compensation calibration is performed to solve the problem of alignment of the suction and injection device and a medicine bottle in the liquid dispensing process.
Drawings
The present disclosure will now be explained in further detail by way of example only with reference to the accompanying drawings, in which:
fig. 1 is a schematic diagram illustrating an application scenario of a liquid dispensing method according to an example of the present disclosure.
Fig. 2 is a flow chart illustrating a liquid dispensing method according to an example of the present disclosure.
Fig. 3 is a schematic diagram illustrating a calibration area formed by a first camera and a second camera in a liquid dispensing method according to an example of the present disclosure.
Fig. 4 is a flowchart showing a second example of the liquid dispensing method according to the example of the present disclosure.
Fig. 5 is a flowchart showing a third example of the liquid preparation method according to the example of the present disclosure.
Fig. 6 is a flowchart showing step S300 in the liquid preparation method according to the example of the present disclosure.
Fig. 7 is a flowchart showing a fourth example of the liquid preparation method according to the example of the present disclosure.
Fig. 8 is a flowchart showing step S500 in the liquid preparation method according to the example of the present disclosure.
Fig. 9 is a flowchart showing step S501 in the liquid preparation method according to the example of the present disclosure.
Fig. 10 is a flowchart showing step S051 in the liquid preparation method according to the example of the present disclosure.
Fig. 11 is a schematic diagram showing a first positional relationship between the inhaler and the vial in step S051 of the liquid dispensing method according to the example of the present disclosure.
Fig. 12 is a schematic diagram showing a second positional relationship between the inhaler and the vial in step S051 of the liquid dispensing method according to the example of the present disclosure.
Fig. 13 is a schematic diagram showing a third positional relationship between the inhaler and the vial in step S051 of the liquid dispensing method according to the example of the present disclosure.
Fig. 14 is a schematic view showing a change in the position of the suction syringe when the liquid dispensing method according to the example of the present disclosure performs step S052.
Fig. 15 is a schematic view showing a scene of a change in the position of the suction and injection device when the liquid dispensing method according to the example of fig. 14 of the present disclosure performs step S052.
Reference numerals illustrate:
1 … manipulator, 2 … suction and injection device, 3 … medicine bottle, H … calibration area, A1 … first optical axis, A2 … second optical axis, a … basic point, b … first point, c … second point, f … contact point.
Detailed Description
The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, not all embodiments. All other embodiments, which are filled by those of ordinary skill in the art without undue burden based on the embodiments in this disclosure, are within the scope of the present disclosure.
It should be noted that the terms "first," "second," "third," and "fourth," etc. in the description and claims of the present disclosure and in the above figures are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "include," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed or inherent to such process, method, article, or apparatus but may optionally include other steps or elements not listed. In the following description, the same members are denoted by the same reference numerals, and overlapping description thereof is omitted. In addition, the drawings are schematic, and the ratio of the sizes of the components to each other, the shapes of the components, and the like may be different from actual ones.
Fig. 1 is a schematic diagram illustrating an application scenario of a liquid dispensing method according to an example of the present disclosure. The present disclosure provides a liquid dispensing method based on image recognition, which can detect the three-dimensional coordinate position and posture of a suction and injection device 2 through machine vision and perform compensation calibration to solve the alignment problem of the suction and injection device 2 and a medicine bottle 3 in the liquid dispensing process. In the disclosure, as shown in fig. 1, a liquid dispensing method based on image recognition is a method for controlling a suction and injection device 2 to perform suction and injection on liquid by matching with a medicine bottle 3 through a mechanical arm 1 to complete liquid dispensing. In addition, the liquid dispensing method based on image recognition according to the present disclosure may also be referred to as a "machine vision-based liquid dispensing method", a "vision-detection-based liquid dispensing method", or a "multi-vision-assisted liquid dispensing method", or may be simply referred to as a "liquid dispensing method" or a "method" hereinafter for convenience of description.
Fig. 2 is a flow chart illustrating a liquid dispensing method according to an example of the present disclosure. Fig. 3 is a schematic diagram illustrating formation of a calibration area H by a first camera and a second camera in a liquid dispensing method according to an example of the present disclosure.
The liquid preparation method based on image recognition according to the present disclosure, as shown in fig. 2, may include: forming a calibration area H by the first camera and the second camera (step S100); moving the suction and injection device 2 to a calibration area H, and acquiring a first image and a second image of the suction and injection device 2 (step S200); acquiring three-dimensional coordinate parameters of the suction and injection device 2 based on the first image and the second image (step S300); performing a compensation operation on the three-dimensional coordinate parameters of the suction injector 2 (step S400); the suction and injection device 2 is controlled to match the medicine bottle 3 to dispense liquid according to the compensated three-dimensional coordinate parameters (step S500).
In some examples, in step S100, a first image of the suction and injection device 2 may be acquired by a first camera and a second image of the suction and injection device 2 may be acquired by a second camera.
In some examples, in step S100, as shown in fig. 3, the first camera may have a first optical axis A1, the second camera may have a second optical axis A2, and the first optical axis A1 may be non-parallel to the second optical axis A2. Preferably, in the present disclosure, the first optical axis A1 and the second optical axis A2 may be perpendicular to the vertical direction, and the first optical axis A1 and the second optical axis A2 may be perpendicular to each other, that is, the first optical axis A1, the second optical axis A2, and the vertical direction may form a shape such as a three-dimensional coordinate system, for example, the vertical direction corresponds to a Z-axis of the three-dimensional coordinate system, the first optical axis A1 corresponds to a Y-axis of the three-dimensional coordinate system, and the second optical axis A2 corresponds to an X-axis of the three-dimensional coordinate system. In this case, the first image of the suction and injection device 2 acquired by the first camera can determine whether the posture of the suction and injection device 2 is deviated on the plane formed by the first optical axis A1 and the vertical direction by the first image, that is, whether the suction and injection device 2 is deviated in the vertical direction by taking the first optical axis A1 as the viewing angle; the second image of the suction and injection device 2 acquired by the second camera can be used for judging whether the posture of the suction and injection device 2 deviates on a plane formed by the second optical axis A2 and the vertical direction or not through the second image, namely, whether the suction and injection device 2 deviates in the vertical direction or not by taking the second optical axis A2 as a visual angle.
In addition, since the first optical axis A1 and the second optical axis A2 are perpendicular to each other, in this case, whether the posture of the suction and injection device 2 is offset in the three-dimensional coordinates can be determined by two perpendicular planes, and meanwhile, the three-dimensional coordinates of the suction and injection device 2 can be directly obtained by two perpendicular planes, so that the complex problem of obtaining the three-dimensional coordinates based on the depth calculation method two in general binocular vision is reduced.
In some examples, the first optical axis A1 of the first camera may refer to an output optical axis of the first camera, i.e., an axis on which a lens center is located when the first camera images an article. In some examples, the second optical axis A2 of the second camera may refer to the output optical axis of the second camera, i.e. the axis on which the lens center is located when the second camera images an object.
In some examples, in step S300, the three-dimensional coordinate parameters of the aspirator 2 may include the three-dimensional coordinates of a plurality of specific points of the aspirator 2 and the pose of the aspirator 2. In some examples, the manipulator 1 can be facilitated to control the pipettor 2 to perform the dispensing operation by knowing the three-dimensional coordinates of a plurality of specific points of the pipettor 2. In some examples, the pose of the suction and injection device 2 may refer to the form of the suction and injection device 2 represented by the three-dimensional coordinates of the partial channel points of the suction and injection device 2, and may include a form completely aligned with the reference three-dimensional coordinates and a form incompletely aligned with the reference three-dimensional coordinates, namely, a correct pose and an incorrect (required calibration) pose. In some examples, it may be determined whether the suction and injection device 2 is in the correct posture by three-dimensional coordinates of a plurality of specific points of the suction and injection device 2.
In some examples, in step S400, the compensating operation may include: and comparing the three-dimensional coordinate parameter with the reference coordinate parameter to obtain a deviation value, judging whether the deviation value is larger than a tolerance range, if the deviation value is not larger than the tolerance range, compensating the three-dimensional coordinate parameter based on the deviation value to enable the three-dimensional coordinate parameter to be consistent with the reference coordinate parameter, and if the deviation value is larger than the tolerance range, replacing the suction injector 2 to carry out position compensation operation again.
In some examples, the tolerance range may refer to a maximum deviation value of the suction device 2 allowed by at least one reference coordinate parameter, for example, assuming that the tolerance range is 0 to 1cm, when the suction device 2 is tilted or offset, the deviation value of the three-dimensional coordinate parameter of the suction device 2 acquired in the calibration area H is 1.1 cm, and the suction device 2 is considered not to be within the tolerance range.
In the present disclosure, images of the suction and injection device 2 under different viewing angles are acquired through two cameras with non-parallel optical axes, three-dimensional coordinate positions and postures of the suction and injection device 2 can be obtained based on the images of the suction and injection device 2 under different viewing angles, deviation of the three-dimensional coordinates and postures of the suction and injection device 2 is obtained through comparison with reference coordinate parameters, in this case, the positions of the suction and injection device 2 can be detected and compensated in a targeted manner to continue to complete the liquid preparation process, that is, the three-dimensional coordinate positions and postures of the suction and injection device 2 can be detected through machine vision and compensated and calibrated to solve the alignment problem of the suction and injection device 2 and the medicine bottle 3 in the liquid preparation process. In addition, whether the deviation value is within the tolerance range is judged in advance in the compensation process, the efficiency of detecting the position of the suction and injection device 2 through machine vision can be improved, and therefore the liquid preparation efficiency can be improved.
Fig. 4 is a flowchart showing a second example of the liquid dispensing method according to the example of the present disclosure.
In addition, in some examples, as shown in fig. 4, the liquid preparation method according to the present disclosure may further include: moving the reference suction and injection device 2 parallel to the vertical direction to the calibration area H (step S110); reference coordinate parameters are generated (step S120). Specifically, in step S120, the reference coordinate parameters may be generated by acquiring the three-dimensional coordinates and the attitudes of the plurality of specific points of the reference suction and injection machine 2, and based on the three-dimensional coordinates and the attitudes of the plurality of specific points of the reference suction and injection machine 2. In some examples, step S110 and step S120 may be performed after step S100 and before step S200, that is, before the inhaler 2 is moved to the calibration area H, in which case the reference coordinate parameter can be obtained by the reference inhaler 2, whereby the deviation value can be obtained by comparing the three-dimensional coordinate parameter of the inhaler 2 with the reference coordinate parameter when the compensation operation is performed.
In some examples, the reference inhaler 2 may refer to the inhaler 2 being located in the calibration area H, which inhaler 2 may ideally be parallel to the vertical (axis of the inhaler 2) and be able to properly enter the vial 3 from a specified location to complete the inhalation as desired. In other examples, the reference stopper 2 may not be parallel to the vertical, for example in some production examples the stopper 2 may not enter vertically but at a predetermined angle, where the reference stopper 2 may be a stopper 2 that ideally enters the vial 3 at the predetermined angle and is able to properly enter the vial 3 from the desired location to complete the stopper.
Fig. 5 is a flowchart showing a third example of the liquid preparation method according to the example of the present disclosure. Wherein, for the sake of attractive drawing, some steps or contents have been omitted in fig. 5, that is, those skilled in the art can easily understand the omitted steps or contents after comparing fig. 5 with the flow chart of any liquid preparation method described above.
In addition, in some examples, as shown in fig. 5, the liquid preparation method according to the present disclosure may further include: the focal lengths of the first camera and the second camera are adjusted, and the illumination intensities of the first camera and the second camera are adjusted (step S111). In some examples, step S111 may be performed after moving the reference pipettor 2 parallel to the vertical direction to the calibration area H, i.e., step S111 may follow step S110 and precede step S120. In this case, the first camera or the second camera can obtain clear image quality by adjusting the focal length and illumination of the cameras, and thus the accuracy of obtaining coordinate parameters and the like based on the images can be improved.
In some examples, step S111 may also be included before the first and second images of the suction and injection device 2 are acquired by the first and second cameras. In this case, the reference coordinate parameter can be made to coincide with the three-dimensional coordinate parameter acquired from the first image, the second image, whereby the accuracy of the compensation operation can be improved.
In addition, in some examples, as shown in fig. 5, the liquid preparation method according to the present disclosure may further include: the reference pipettes 2 are placed at a plurality of target positions in the calibration area H (step S112). Specifically, step S112 may include: and placing the reference suction and injection device 2 at a plurality of target positions in the calibration area H, and acquiring three-dimensional coordinates and postures of a plurality of specific points of the reference suction and injection device 2 corresponding to the plurality of target positions.
In some examples, it is also necessary to generate a plurality of corresponding reference coordinate parameters based on the three-dimensional coordinates and the attitudes of a plurality of specific points of the reference suction and injection device 2 of a plurality of target positions of the calibration area H after step S112, that is, step S112 may be performed after step S111 and before step S120. In this case, by generating a plurality of reference coordinate parameters with the reference pipettor 2 at a plurality of target positions in the calibration area H, thereby enabling at least one of the plurality of reference coordinate parameters to be selected as a reference coordinate parameter in the actual liquid dispensing process, in addition, a tolerance range can be generated by the plurality of reference coordinate parameters, enabling the pipettor 2 to be shifted and compensated within the tolerance range, thereby improving the liquid dispensing efficiency.
Fig. 6 is a flowchart showing step S300 in the liquid preparation method according to the example of the present disclosure.
In some examples, step S300 may specifically include: acquiring a first characteristic parameter based on the first image, and acquiring a second characteristic parameter based on the second image (step S301); three-dimensional coordinate parameters of the suction and injection device 2 are acquired based on the first characteristic parameters and the second characteristic parameters (step S302).
In some examples, in step S301, the first characteristic parameter may be represented as a position of a characteristic point where the suction and injection device 2 is located in the first image, and the second characteristic parameter may be represented as a position of a characteristic point where the suction and injection device 2 is located in the second image. In this case, coordinates of the corresponding feature points, that is, feature parameters can be obtained by extracting the feature points in the image of the suction and injection device 2, whereby the three-dimensional coordinates of the suction and injection device 2 can be determined by the feature parameters, and the posture of the suction and injection device 2 can be determined by comparison with the reference coordinate parameters.
In some examples, the feature points may refer to locations where the pixel area of the article in the image appears to be distinct from the remaining pixel area, such as a contoured edge of the syringe 2, a bulge of a connection site of a needle tip or needle cannula of the syringe 2 to a syringe, a color depth of different sites of the syringe 2, and so on. In the present disclosure, since the syringe of the suction injector 2 is smaller in width than the syringe and is made of a stainless steel material, a clear image is not easily obtained under irradiation of a light source, and a portion of the syringe of the suction injector 2 connected with the syringe has a larger width, a clear color difference, and more obvious contour characteristics, it is preferable that the feature point of the suction injector 2 may refer to a connection portion of the syringe of the suction injector 2 with the syringe.
In some examples, in step S301, the first image and the second image may be read and preprocessed. In some examples, the preprocessing may include gray scale, binarization, gaussian blur processing, or the like. In some examples, the first and second characteristic parameters may be acquired based on the processed first and second images, respectively. In this case, performing gradation, binarization, or gaussian blur processing on the image of the suction and injection device 2 can facilitate recognition of the characteristic points of the suction and injection device 2, and thus can facilitate acquisition of the characteristic parameters of the suction and injection device 2.
In some examples, in step S301, the outline of the suction and injection device 2 may also be extracted in the first image and the second image, an circumscribed rectangle is drawn based on the outline of the suction and injection device 2, and the ROI region is extracted within the circumscribed rectangle. In some examples, the first and second characteristic parameters may be acquired based on the ROI area. ROI (Region of Interest) denotes a region of interest, which means that the region to be processed is outlined from the processed image in the form of a square, a circle, an ellipse, an irregular polygon, etc. In this case, by extracting the outline of the suction and injection device 2 in the image, it is possible to facilitate recognition of the suction and injection device 2 and drawing of the circumscribed rectangle and extraction of the ROI area, whereby the feature points of the suction and injection device 2 can be accurately recognized by using the circumscribed rectangle and the ROI area, reducing noise interference.
Fig. 7 is a flowchart showing a fourth example of the liquid preparation method according to the example of the present disclosure. Wherein, for the sake of attractive drawing, some steps or contents have been omitted in fig. 7, i.e. those skilled in the art can easily understand the omitted steps or contents after comparing fig. 7 with the flow chart of any liquid preparation method described above.
In addition, in some examples, as shown in fig. 7, the liquid preparation method according to the present disclosure may further include: acquiring two-dimensional coordinate parameters of the medicine bottle 3 inclined by a preset angle through a third camera (step S310); the positional deviation of the vial 3 is acquired (step S320). In some examples, step S310, step S320 may be performed before step S400.
In some examples, after performing step S310 and step S320, performing step S400 may specifically include: the three-dimensional coordinate parameters of the inhaler 2 are compensated based on the deviation value and the positional deviation of the medicine bottle 3 (step S401), that is, step S401 may be the content of step S400 (see fig. 7, step S401 may be optionally substituted for step S400). In other words, after the positional deviation of the medicine bottle 3 is acquired, the three-dimensional coordinate parameters of the inhaler 2 may be compensated based on the value of the positional deviation of the inhaler 2 and the positional deviation of the medicine bottle 3. In this case, by simultaneously acquiring the coordinate positions of the medicine bottle 3 and the suction and injection device 2 and compensating the suction and injection device 2 based on the deviation of both relative to the respective reference coordinate parameters, the suction and injection device 2 can be calibrated, and the accuracy of dispensing liquid can be improved.
In some examples, steps S310 to S320 specifically include: and tilting the medicine bottle 3 by a preset angle, acquiring a two-dimensional coordinate parameter of the medicine bottle 3 by a third camera, and comparing the two-dimensional coordinate parameter of the medicine bottle 3 with a reference coordinate parameter of the medicine bottle 3 to acquire the position deviation of the medicine bottle 3. In some examples, the reference coordinate parameters of the vial 3 may be obtained in a similar or identical manner to the reference coordinate parameters of the inhaler 2, i.e., the reference coordinate parameters of the vial 3 may be obtained with reference to the reference coordinate parameters of the inhaler 2.
In some examples, in step S310, the two-dimensional coordinate parameters of the medicine bottle 3 may include the two-dimensional coordinates of a plurality of specific points of the medicine bottle 3 and the posture of the medicine bottle 3. In this case, whether the medicine bottle 3 is inclined in place or the position is shifted can be judged by the two-dimensional coordinates and the postures of the plurality of specific points of the medicine bottle 3, whereby the liquid dispensing accuracy can be improved by performing the compensation operation thereof, or the liquid suction and injection device 2 can be compensated so that the liquid suction and injection device 2 can accurately enter the medicine bottle 3 even if not calibrated.
Fig. 8 is a flowchart showing step S500 in the liquid preparation method according to the example of the present disclosure. Fig. 9 is a flowchart showing step S501 in the liquid preparation method according to the example of the present disclosure.
In addition, in some examples, as shown in fig. 8, step S500 may include: moving the inhaler 2 to a predetermined position in the vial 3 (step S501); the suction and injection device 2 is driven to perform suction and injection (step S502).
In some examples, as shown in fig. 9, step S501 may include a detection step (step S051) and a movement step (step S052). Specifically, it may include: by driving the inhaler 2 by the manipulator 1 to move from a first position located outside the medicine bottle 3 to a second position located inside the medicine bottle 3, it is detected whether the inhaler 2 is located inside the medicine bottle 3. In this case, the accuracy of the inhalation of the liquid by the inhaler 2 into the medicine bottle 3 can be improved, and thus, the occurrence of undesirable damage to the inhaler 2 can be reduced.
Because the change of the current of the driving mechanism (for example, the manipulator 1) has a corresponding relation with the change of the load, the actual situation of the load can be judged by detecting the working current of the driving mechanism, for example, the change of the moment can influence the current of a motor in the manipulator 1 when the manipulator 1 or an object clamped by the manipulator 1 (namely, the load) collides with the object, and the detection of the change of the current can judge whether the manipulator 1 or the object clamped by the manipulator 1 collides with the object or not. In this case, the position of the suction and injection device 2 can be detected by detecting the operating current of the robot arm 1 in a simple manner, whereby the problem of high cost or complicated data processing caused by the detection using the sensor can be reduced.
In some examples, the operating current at which the manipulator 1 drives the pipettor 2 to move without obstruction may be referred to as a first current value. In some examples, the manipulator 1 drives the inhaler 2 to move under the unobstructed condition may refer to a situation that the manipulator 1 drives the inhaler 2 to move according to a pre-calibrated route and the inhaler 2 does not contact a container such as a medicine bottle 3, but it should be noted that during the dispensing process, since the sensitivity is limited when the motion joint of the manipulator 1 touches the liquid, the current change when the inhaler 2 is driven to move as a whole may not be an unobstructed condition.
In some examples, the operating current at which the manipulator 1 drives the suction injector 2 to move in the presence of a blockage may be referred to as a second current value. In some examples, the manipulator 1 drives the inhaler 2 to move in the case of obstruction may refer to a situation in which the inhaler 2 touches or abuts the medicine bottle 3 due to a relative positional deviation between the inhaler 2 and the container such as the medicine bottle 3 during the process of driving the inhaler 2 by the manipulator 1, but does not include a situation in which the liquid in the medicine bottle 3 is touched.
In some examples, the manipulator 1 may have a third current value when driving the inhaler 2 to draw air from the vial 3. In some examples, the manipulator 1 may have a fourth current value when driving the pipettor 2 to aspirate liquid from the vial 3. In this case, the subsequent detection of the operation state of the manipulator 1 based on the two current values can be facilitated by acquiring the current values of the manipulator 1 in both cases.
In some examples, the manipulator 1 is operated to drive the suction syringe 2 to reciprocate in a direction toward the vial with an operating current and to have a first operating current value. In some examples, the manipulator 1 is operated to drive the inhaler 2 to have an operating current when performing an aspiration action in the vial 3, and to have a second operating current value. In this case, the first operation state of the manipulator 1 can be obtained from the first operation current value, and the second operation state of the manipulator 1 can be obtained from the second operation current value, so that the relative positions of the pipette 2 and the vial 3 can be determined based on the first operation state of the manipulator 1 and the second operation state of the manipulator 1.
In some examples, the sensitivity of the current of the motor that the manipulator 1 drives the inhaler 2 into the vial 3 to perform the aspirating action is greater than the sensitivity of the current of the motor that the manipulator 1 drives the inhaler 2 to reciprocate in the direction toward the vial.
Fig. 10 is a flowchart showing step S051 in the liquid preparation method according to the example of the present disclosure. Fig. 11 is a schematic diagram showing a first positional relationship between the inhaler 2 and the vial 3 in step S051 of the liquid dispensing method according to the example of the present disclosure. Fig. 12 is a schematic diagram showing a second positional relationship between the inhaler 2 and the vial 3 in step S051 of the liquid dispensing method according to the example of the present disclosure. Fig. 13 is a schematic diagram showing a third positional relationship between the inhaler 2 and the vial 3 in step S051 of the liquid dispensing method according to the example of the present disclosure.
In some examples, as shown in fig. 10, step S051 may include: a first comparison threshold is obtained based on the first current value and the second current value (step S001), a second comparison threshold is obtained based on the third current value and the fourth current value (step S002), a first detection result is obtained based on the first comparison threshold and the first operation current value (step S003), a second detection result is obtained based on the second comparison threshold and the second operation current value (step S004), and the relative position of the inhaler 2 and the vial 3 is determined based on the first detection result and the second detection result (step S005).
In step S051, whether the manipulator 1 is in a state of normal operation (i.e., whether the operation is in a hindrance) or not, that is, a first detection result, may be obtained by comparing the first operation current value with the first comparison threshold, so that it can be determined whether the suction and injection device 2 clamped on the manipulator 1 touches the medicine bottle 3.
In step S051, the operation condition of the manipulator 1 (i.e. whether the manipulator 1 drives the back suction syringe 2 to suck the liquid) may be obtained by comparing the second operation current value with the second comparison threshold, i.e. the second detection result, so as to determine whether the suction syringe 2 touches the liquid and can suck the liquid, i.e. the suction syringe 2 is partially located in the medicine bottle 3 and can suck the liquid.
In the liquid dispensing method according to the present disclosure, by the detection step (i.e., step S051), the specific position of the inhaler 2 (particularly, the portion of the inhaler 2 that enters the medicine bottle 3, such as the needle tube or the needle tip) with respect to the medicine bottle 3 can be automatically detected, for example, see fig. 11, the inhaler 2 is located at the mouth of the medicine bottle 3 (when the operation of the manipulator 1 is blocked), see fig. 12, the inhaler 2 is located outside the medicine bottle 3 (when the operation of the manipulator 1 is unobstructed but the manipulator 1 sucks air), or see fig. 13, the inhaler 2 is correctly located inside the medicine bottle 3 (when the operation of the manipulator 1 is unobstructed and the manipulator 1 sucks liquid), and so on, thereby improving the safety of the overall liquid dispensing flow without the need of an external sensor.
In some examples, step S052 may specifically include: the inhaler 2 is moved from the second position to the third position in the vial 3 so as to abut against the inner wall of the vial 3. Specifically, the suction and injection device 2 may be driven by the manipulator 1 to move from the second position to the third position in the medicine bottle 3 so that the suction and injection device 2 abuts against the inner wall of the medicine bottle 3.
In some examples, the second position may refer to a position where the vial 3 abuts the inhaler 2 or any position inside the vial 3 and above the abutting position prior to abutment. In some examples, the second position and the third position are different.
In some examples, the third position may refer to the lowest position of the inner wall of the inclined vial 3. In this case, the medicine bottle 3 is inclined by a preset angle, so that the suction injector 2 can conveniently suck the liquid at the lowest position of the inclined medicine bottle 3, thereby reducing the waste of the liquid and improving the utilization rate of the liquid; by moving the inhaler 2 to the third position so as to abut against the inner wall of the vial 3, it is possible to reduce occurrence of undesirable situations such as damage to the inhaler 2 or damage to the vial 3 by the inhaler 2. In some examples, step S052 may also be referred to as a "soft floating pipetting step", i.e. the soft floating function of the manipulator 1 may be turned on to move the pipette 2 to the third position in such a way that it abuts against the inner wall of the tilted vial 3. In some examples, the soft floating function may be that the manipulator 1 exhibits better flexibility when physically interacting with the external environment or the user, to reduce the occurrence of excessive collision forces damaging the workpiece (vial 3 or pipette 2) and even the manipulator 1 itself.
In some examples, the needle tube of the inhaler 2 may have a certain rigidity, i.e. when step S052 is performed, the force or reaction force to which the needle tube of the inhaler 2 is in contact with the inner wall of the vial 3 may be greater than the output torque of the manipulator 1 without undesired damage such as deformation. In this case, the soft floating function can be turned on to move the inhaler 2 from the second position to the third position in the medicine bottle 3 so as to abut against the inner wall of the medicine bottle 3, thereby facilitating the inhaler 2 to suck the liquid at the lowest position of the inclined medicine bottle 3, reducing the waste of the liquid, and improving the utilization ratio of the liquid.
Fig. 14 is a schematic diagram showing a change in the position of the suction syringe 2 when the liquid dispensing method according to the example of the present disclosure performs step S052. Fig. 15 is a schematic view showing a scene of a change in the position of the suction and injection device 2 when the liquid dispensing method according to the example of fig. 14 of the present disclosure performs step S052.
In fig. 14, a represents the point coordinates of a portion (e.g., a needle tip) of the syringe 2 located at the first position, which is also referred to as a base point a, b represents the point coordinates (e.g., a needle tip) of a portion of the syringe 2 located at the third position in an ideal case (when neither the syringe 2 nor the vial 3 is offset), which is also referred to as a first point b, c represents the point coordinates (e.g., a needle tip) of a portion of the syringe 2 located at the third position in an actual case (when the syringe 2 or the vial 3 may be offset), which is also referred to as a second point c, f represents the contact position (e.g., a contact point between the needle tip and the vial 3) of a portion of the syringe 2 and the inner wall of the vial 3, and f may be located at the second position, which is also referred to as a contact point f.
As shown in fig. 14, the suction and injection device 2 may be moved from the base point a to the first point b by the manipulator 1 (holding the suction and injection device 2). In some examples, the first point b may be the lowest point of the interior of the vial 3 that is ideally tilted by a preset angle.
As shown in fig. 14, when the inhaler 2 moves toward the first point b, the inhaler 2 reaches the second point c by abutting against and moving along the inner wall of the medicine bottle 3 having an inclined preset angle, that is, the inhaler 2 can move along with the inner wall of the medicine bottle 3. In other words, the suction and injection device 2 can move from the original first point b to the second point c and reach the second point c through the flexible connection with the manipulator 1. In some examples, the second point location c may refer to the lowest point of the inner wall of the actual vial 3 (i.e., the vial 3 is now tilted at the tilt preset angle but is positionally offset, or is not positionally offset but is not tilted at the tilt preset angle, in an ideal case, the first point location b may be identical to the second point location c) (see fig. 15). In this case, it can be convenient to match or align the pipettes 2 with the vials 3, and it can be convenient to complete an accurate dispensing process in each vial 3 by driving the pipettes 2.
In some examples, driving the inhaler 2 to aspirate (step S502) may be by the manipulator 1 driving the inhaler 2 to aspirate or inject liquid into the vial 3. In other examples, the driving of the suction and injection device 2 to perform suction and injection (step S502) may be that the manipulator 1 drives the suction and injection device 2 to suck or inject the liquid in the liquid containing carrier such as the liquid bag.
According to the present disclosure, a liquid dispensing method based on image recognition can be provided, in which the three-dimensional coordinate position and posture of the suction and injection device 2 can be detected by machine vision and compensation calibration is performed to solve the alignment problem of the suction and injection device 2 and the medicine bottle 3 in the liquid dispensing process. In addition, the liquid dispensing method according to the present disclosure can detect the relative position of the inhaler 2 and the vial 3 by detecting the current of the motor of the manipulator 1, thereby reducing the cost and data calculation problems caused by the detection using the sensor. In addition, the liquid dispensing method according to the present disclosure can move the inhaler 2 along with the inside of the vial 3 by turning on the soft floating function, and thus, it is possible to reduce undesirable situations such as damage to the inhaler 2 or the vial 3 due to rigid movement of the manipulator 1.
While the disclosure has been described in detail in connection with the drawings and examples, it is to be understood that the foregoing description is not intended to limit the disclosure in any way. Those skilled in the art can make modifications and variations to the present disclosure as required without departing from the true spirit and scope of the disclosure, and such modifications and variations are within the scope of the disclosure.
Claims (10)
1. A liquid preparation method based on image recognition is a method for completing liquid preparation by controlling a suction and injection device to be matched with a medicine bottle to suck and inject liquid through a mechanical arm, and is characterized in that,
Comprising the following steps: forming a calibration area by a first camera having a first optical axis and a second camera having a second optical axis, the first optical axis being non-parallel to the second optical axis; moving the suction and injection device to the calibration area, acquiring a first image of the suction and injection device through the first camera, and acquiring a second image of the suction and injection device through the second camera;
Acquiring three-dimensional coordinate parameters of the suction and injection device based on the first image and the second image, wherein the three-dimensional coordinate parameters of the suction and injection device comprise three-dimensional coordinates of a plurality of specific points of the suction and injection device and the gesture of the suction and injection device;
Performing compensation operation on the three-dimensional coordinate parameters of the suction and injection device, and controlling the suction and injection device to match with a medicine bottle to perform liquid preparation according to the compensated three-dimensional coordinate parameters;
Wherein the compensating operation includes: and comparing the three-dimensional coordinate parameter with a reference coordinate parameter to obtain a deviation value, judging whether the deviation value is larger than a tolerance range, if the deviation value is not larger than the tolerance range, compensating the three-dimensional coordinate parameter based on the deviation value so that the three-dimensional coordinate parameter is consistent with the reference coordinate parameter, and if the deviation value is larger than the tolerance range, replacing the suction injector and carrying out the compensation operation again.
2. The method for preparing liquid according to claim 1, wherein,
The first optical axis and the second optical axis are perpendicular to the vertical direction, and the first optical axis and the second optical axis are perpendicular to each other.
3. The method for preparing liquid according to claim 1, wherein,
Further comprises: before the suction and injection device moves to the calibration area, the reference suction and injection device parallel to the vertical direction is moved to the calibration area; and acquiring three-dimensional coordinates and postures of a plurality of specific points of the reference suction and injection device, and generating the reference coordinate parameters based on the three-dimensional coordinates and postures of the plurality of specific points of the reference suction and injection device.
4. The method for preparing liquid according to claim 3, wherein,
After moving the reference pipette parallel to the vertical direction to the calibration area, the method further comprises: and adjusting the focal lengths of the first camera and the second camera, and adjusting the illumination intensities of the first camera and the second camera.
5. The method for preparing liquid according to claim 3, wherein,
The method further comprises the following steps before generating the reference coordinate parameters: and placing the reference suction and injection device at a plurality of target positions in the calibration area, acquiring three-dimensional coordinates and postures of a plurality of specific points of the reference suction and injection device corresponding to the plurality of target positions, and generating the reference coordinate parameters based on the three-dimensional coordinates and postures of the plurality of specific points of the reference suction and injection device.
6. The method for preparing liquid according to claim 1, wherein,
Acquiring a first characteristic parameter based on the first image, acquiring a second characteristic parameter based on the second image, and acquiring a three-dimensional coordinate parameter of the suction and injection device based on the first characteristic parameter and the second characteristic parameter, wherein the first characteristic parameter is expressed as the position of a characteristic point of the suction and injection device in the first image, and the second characteristic parameter is expressed as the position of a characteristic point of the suction and injection device in the second image.
7. The method for preparing liquid according to claim 6, wherein,
And reading the first image and the second image, preprocessing the first image and the second image, and respectively acquiring the first characteristic parameter and the second characteristic parameter based on the processed first image and the processed second image.
8. The method for preparing liquid according to claim 7, wherein,
Extracting the outline of the suction and injection device from the first image and the second image, drawing a circumscribed rectangle based on the outline of the suction and injection device, extracting an ROI (region of interest) area in the circumscribed rectangle, and acquiring the first characteristic parameter and the second characteristic parameter based on the ROI area.
9. The method for preparing liquid according to claim 1, wherein,
Further comprises: and tilting the medicine bottle by a preset angle, acquiring a two-dimensional coordinate parameter of the medicine bottle through a third camera, comparing the two-dimensional coordinate parameter of the medicine bottle with a reference coordinate parameter of the medicine bottle to acquire the position deviation of the medicine bottle, and performing the compensation operation on the three-dimensional coordinate parameter of the suction injector based on the deviation value and the position deviation of the medicine bottle.
10. The method for preparing liquid according to claim 9, wherein,
The two-dimensional coordinate parameters of the medicine bottle include two-dimensional coordinates of a plurality of specific points of the medicine bottle and a posture of the medicine bottle.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310020144 | 2023-01-06 | ||
| CN2023100201442 | 2023-01-06 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118304171A true CN118304171A (en) | 2024-07-09 |
Family
ID=88247394
Family Applications (10)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310401214.9A Pending CN118304811A (en) | 2023-01-06 | 2023-04-13 | Liquid preparation method based on soft floating function |
| CN202320965563.9U Active CN219814711U (en) | 2023-01-06 | 2023-04-21 | Dispensing machine |
| CN202320954775.7U Active CN219814590U (en) | 2023-01-06 | 2023-04-21 | Dispensing machine |
| CN202310467636.6A Pending CN118304168A (en) | 2023-01-06 | 2023-04-24 | Liquid preparation system |
| CN202310449200.4A Pending CN118304167A (en) | 2023-01-06 | 2023-04-24 | Liquid preparation system |
| CN202310482679.1A Pending CN118304169A (en) | 2023-01-06 | 2023-04-26 | Liquid dispensing device and liquid dispensing method |
| CN202310495421.5A Pending CN118304170A (en) | 2023-01-06 | 2023-04-26 | Liquid dispensing device |
| CN202310559807.8A Pending CN118304171A (en) | 2023-01-06 | 2023-05-15 | Liquid preparation method based on image recognition |
| CN202310581687.1A Pending CN118304172A (en) | 2023-01-06 | 2023-05-19 | Method and system for preparing liquid based on cooperation of multiple industrial robots |
| CN202311012526.7A Pending CN118304173A (en) | 2023-01-06 | 2023-08-11 | Liquid preparation method and liquid preparation system |
Family Applications Before (7)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310401214.9A Pending CN118304811A (en) | 2023-01-06 | 2023-04-13 | Liquid preparation method based on soft floating function |
| CN202320965563.9U Active CN219814711U (en) | 2023-01-06 | 2023-04-21 | Dispensing machine |
| CN202320954775.7U Active CN219814590U (en) | 2023-01-06 | 2023-04-21 | Dispensing machine |
| CN202310467636.6A Pending CN118304168A (en) | 2023-01-06 | 2023-04-24 | Liquid preparation system |
| CN202310449200.4A Pending CN118304167A (en) | 2023-01-06 | 2023-04-24 | Liquid preparation system |
| CN202310482679.1A Pending CN118304169A (en) | 2023-01-06 | 2023-04-26 | Liquid dispensing device and liquid dispensing method |
| CN202310495421.5A Pending CN118304170A (en) | 2023-01-06 | 2023-04-26 | Liquid dispensing device |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310581687.1A Pending CN118304172A (en) | 2023-01-06 | 2023-05-19 | Method and system for preparing liquid based on cooperation of multiple industrial robots |
| CN202311012526.7A Pending CN118304173A (en) | 2023-01-06 | 2023-08-11 | Liquid preparation method and liquid preparation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (10) | CN118304811A (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103417375B (en) * | 2012-05-18 | 2016-08-03 | 辽宁九洲龙跃医用科技股份有限公司 | A kind of machine automatization venous medicine dispensing device |
| CN110979889B (en) * | 2019-12-31 | 2024-03-15 | 宁波银信智康科技有限公司 | Dispensing machine for granular preparation formula |
| CN217971542U (en) * | 2022-09-06 | 2022-12-06 | 美蓝(杭州)医药科技有限公司 | Pick-up device of suction injector |
-
2023
- 2023-04-13 CN CN202310401214.9A patent/CN118304811A/en active Pending
- 2023-04-21 CN CN202320965563.9U patent/CN219814711U/en active Active
- 2023-04-21 CN CN202320954775.7U patent/CN219814590U/en active Active
- 2023-04-24 CN CN202310467636.6A patent/CN118304168A/en active Pending
- 2023-04-24 CN CN202310449200.4A patent/CN118304167A/en active Pending
- 2023-04-26 CN CN202310482679.1A patent/CN118304169A/en active Pending
- 2023-04-26 CN CN202310495421.5A patent/CN118304170A/en active Pending
- 2023-05-15 CN CN202310559807.8A patent/CN118304171A/en active Pending
- 2023-05-19 CN CN202310581687.1A patent/CN118304172A/en active Pending
- 2023-08-11 CN CN202311012526.7A patent/CN118304173A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN118304173A (en) | 2024-07-09 |
| CN118304167A (en) | 2024-07-09 |
| CN118304172A (en) | 2024-07-09 |
| CN118304168A (en) | 2024-07-09 |
| CN118304811A (en) | 2024-07-09 |
| CN219814711U (en) | 2023-10-13 |
| CN118304169A (en) | 2024-07-09 |
| CN219814590U (en) | 2023-10-13 |
| CN118304170A (en) | 2024-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9409291B2 (en) | Robot system, method for inspection, and method for producing inspection object | |
| JP2710850B2 (en) | Work holding device, work and its storage case | |
| JP6180087B2 (en) | Information processing apparatus and information processing method | |
| CN107073719B (en) | Robot and robot system | |
| US10697991B2 (en) | Dispensing system, and dispensing method | |
| CN108544531B (en) | Automatic chemical examination mechanical arm device based on visual calibration, control system and control method thereof | |
| US20120296469A1 (en) | Sucking-conveying device having vision sensor and suction unit | |
| US20120004774A1 (en) | Robot apparatus and gripping method for use in robot apparatus | |
| US11554501B2 (en) | Robot system and control method | |
| US10837977B2 (en) | Rack for dispensing and dispensing system | |
| JP2012076216A (en) | Method for combining camera coordinate system and robot coordinate system in robot control system, image processing device, program, and storage medium | |
| CN112549052B (en) | Control device for robot device for adjusting position of robot-supported component | |
| US20190126473A1 (en) | Information processing apparatus and robot arm control system | |
| US11570422B2 (en) | Method for calibrating a sensor unit of an industrial truck | |
| JP2019150904A (en) | Information processing device and sorting system | |
| WO2014158936A1 (en) | Laser triangulation for pipette tip position | |
| JP2004243215A (en) | Robot teaching method for sealer applicator and sealer applicator | |
| CN118304171A (en) | Liquid preparation method based on image recognition | |
| CN113165188B (en) | Alignment device | |
| US11173603B2 (en) | Robot system and robot | |
| CN109799632A (en) | A kind of accurate laminating apparatus and method of liquid crystal display and touch tablet based on laser sensor | |
| US20210069912A1 (en) | Method for determining a position of a rack on a rack placement unit of a laboratory handling system and laboratory handling system | |
| JP6507792B2 (en) | Robot and robot system | |
| JP2003145004A (en) | Apparatus for detecting deviation of nozzle position and apparatus for applying material using the same | |
| KR20000002415U (en) | Silicone coating device of liquid crystal panel |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |