Temperature monitoring management method based on manual green tea fixation process

Abstract

The invention discloses a temperature monitoring and management method based on a manual green tea fixation process. The method comprises the following steps: acquiring a thermal imaging temperature map shot by a thermal imager mounted right above a wok in real time; judging whether the highest temperature in the thermal imaging temperature map is within the preset temperature range of the temperature required by fixation, if not, acquiring the thermal imaging temperature map within the preset time length before the current time from the image set to identify the hand position of the tea frying worker, obtaining a hand imaging map, detecting the change of the hand state according to the hand imaging map, and performing fixation. When changing, adding 1 to the stir-frying action times; the total number of stir-frying action times in the analysis queue is counted, and the stir-frying speed is solved according to the total number of stir-frying action times; and reminding a tea frying worker to adjust the frying speed according to a comparison result of the highest temperature in the current thermal imaging temperature diagram and a preset temperature range. The temperature of the frying pan is monitored and analyzed in real time by monitoring the thermal imaging temperature diagram of the frying pan, and a tea frying worker is reminded to adjust the manual frying technique in time to adapt to the current temperature.

Description

Technical Field

[0001] The invention relates to the technical field of temperature control for frying and fixing green tea, and in particular to a temperature monitoring and management method based on a manual green tea fixing process. Background Art

[0002] In the preparation of green tea, withering is a key process in green tea processing. This withering process plays a crucial role in the appearance and quality of green tea. After treatment, the withering leaves should maintain a lush green color, and the dried tea leaves should have a green and moist color. Existing withering methods include manual frying and mechanical frying. Of these two methods, manual frying allows manual adjustment to the different qualities and shapes of the tea leaves, providing greater flexibility. Machine frying requires pre-set settings and can only adapt to the relatively single characteristics of the tea leaves, making it less flexible than manual frying.

[0003] Hand-roasted tea, due to the meticulous manual labor involved, boasts a fresher flavor and richer aroma. While mechanical roasting is highly efficient, it can lose some of the original tea flavor, resulting in a more subdued taste. Therefore, hand-roasted tea is more popular among tea lovers. However, this method requires experienced tea-makers to adjust the temperature and speed based on years of experience, feeling the heat from the wok and their hands. For those learning to roast tea, it can be difficult to sense and adjust temperature changes during the roasting process. Therefore, a method is needed to help tea roasters detect and adjust temperature changes. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for monitoring the temperature of manual green tea withering, which monitors and analyzes the temperature of the wok in real time by monitoring the thermal imaging temperature map of the wok, and promptly reminds the tea roaster to change the frying speed when the temperature is not suitable for the withering speed, so that the withering temperature of the tea can be maintained within the temperature range required for withering, and can also promptly remind the tea roaster to adjust the manual frying technique to adapt to the current temperature.

[0005] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a temperature monitoring and management method based on a manual green tea withering process, specifically comprising the following steps: S1, real-time acquisition of thermal imaging temperature images captured by a thermal imager installed directly above the wok and storing the images in an image collection; S2. Perform real-time temperature analysis on the thermal imaging temperature map to determine whether the highest temperature in the thermal imaging temperature map is within a preset temperature range required for fixing. If not, obtain a thermal imaging temperature map within a preset time period before the current time from the image collection and store it in the analysis data set; S3. Perform edge detection on the thermal imaging temperature map in the analysis data set, identify and mark the position of the tea roaster's hand from the thermal imaging temperature map, obtain the hand image xn, and store it in the analysis queue X(x1, ..., xn) in sequence; S4, comparing two adjacent hand images in the analysis queue in sequence to detect whether the hand state has changed. If so, the number of stir-frying actions is increased by one; S5. Statistically analyzing the total number of stir-frying actions in the queue, and calculating the stir-frying speed based on the ratio of the total number of stir-frying actions to a preset time length; S6. Remind the tea roaster to adjust the roasting speed based on the comparison result between the highest temperature in the current thermal imaging temperature map and the preset temperature range.

[0006] In some specific implementations, the specific process of step S3 is: S31, performing edge detection of a hand contour on the thermal imaging temperature image, and identifying a hand contour from the thermal imaging temperature image based on a temperature difference between the hand and the wok, where the hand contour includes the arm and the palm; S32. Mark the arm position and the palm position in the thermal imaging temperature map, and record the temperature of the arm position and the temperature of the palm position respectively.

[0007] In some specific implementations, the specific process of step S4 is: S411, traverse each hand image in the analysis queue, obtain two adjacent hand images xn and xn-1 in the analysis queue, compare the temperature change values ​​at the palm position of hand image xn and hand image xn-1, if the temperature change value is within the difference range and the temperature change changes from high to low, it is determined that the hand state has changed, and the number of stir-frying actions is increased by one; S412: Continue to obtain the next two adjacent hand imaging images xn-1 and xn-2, and repeat step S411 until all hand imaging images in the analysis queue are traversed.

[0008] In some specific embodiments, the process of step S4 includes: S421, traversing each hand image in the analysis queue, obtaining two adjacent hand image images xn-1 and xn in the analysis queue, comparing the hand motion changes between the hand image xn and the hand image xn-1, and if the hand motion changes from the first motion to the second motion, determining that the hand state has changed, and increasing the number of stir-frying motions by one; S422: Continue to obtain the next two adjacent hand imaging images xn-2 and xn-1, and repeat step S421 until all hand imaging images in the analysis queue are traversed.

[0009] In some specific implementations, the process of identifying changes in hand movements is as follows: When marking the palm position, mark the relative position relationship between the thumbs and the palms of both hands. When the relative position of the thumbs of both hands to the palms is the first distance, and the palms are facing down, the current action is recorded as the first action; When the thumbs of both hands are located at a second distance relative to the palms with the palms facing upward, the current hand movement is recorded as the second movement, and the first distance is smaller than the second distance.

[0010] In some specific embodiments, when the hand movement changes from the first movement to the second movement, timing is started from the hand image corresponding to the second movement, and the time duration when the hand movement changes from the second movement to the first movement is calculated to obtain the hand movement time; The hand movement time of each frying action is counted to obtain the total duration and average duration of the tea fryer's hand movement time within the preset time length.

[0011] In some specific implementations, the method of reminding the tea roaster to adjust the roasting speed is: S61. If the highest temperature in the current thermal imaging temperature map is lower than the preset temperature range, it is determined that the wok temperature has dropped, the wok power is increased to heat the wok, and the tea stirrer is reminded that the current temperature is low and the stir-frying speed is reduced; S62. If the highest temperature in the current thermal imaging temperature map exceeds the preset temperature range, it is determined that the wok temperature is overheated, the wok temperature is controlled to be lowered, and the tea stirrer is reminded that the current temperature is high and to speed up the stir-frying.

[0012] In some specific implementations, the ratio of the total duration of the hand movement to the preset time length is calculated to obtain the jitter ratio; When the wok temperature drops, remind the tea stirrer to reduce the shaking ratio; When the wok is too hot, remind the tea roaster to increase the shaking ratio.

[0013] In some specific embodiments, in step S3, it is determined whether the current frying is one-handed or two-handed based on the number of hand contours identified. If it is one-handed, the process of step S4 is as follows: Each hand image in the analysis queue is traversed by window moving traversal, with the window length set to three and the step value of each movement to two; In the analysis queue, the hand images xn, xn-1, and xn-2 obtained in the window are compared as a data group to compare the changes in the hand movements in the hand images in the current window. If the hand movement changes from the first position to the second position and then returns to the first position, it is determined that the hand state has changed, and the number of stir-frying actions is increased by one; The window is moved to obtain the next set of hand images xn-1, xn-2, and xn-3 for comparison, until all hand images in the analysis queue are traversed.

[0014] In some embodiments, the process of comparing changes in hand movements is: When marking the palm position, mark the relative position relationship between the thumb and the palm, and record the positions of the thumb on both sides of the palm as the first position and the second position respectively.

[0015] The inventive concept of this application is: Hand-fried tea is more popular because of its unique flavor, but hand-fried tea relies on the skill of the tea roaster. For tea roasters who have just learned, it is difficult to perceive the temperature changes of the wok and the speed of frying the tea with their hands, so it is difficult to control the temperature of the tea.

[0016] In light of this, the present application considers the process of frying tea in an electric wok. While electric woks can precisely control the wok's temperature, adjusting the wok's temperature also takes time. Therefore, during this temperature adjustment process, the tea roaster can adjust the frying speed to adapt to temperature changes. When frying tea leaves in a wok, a common technique used by tea roasters is to press down on the tea leaves with their palms, then pick up the tea leaves, shake them in the air, and return them to the wok. It can be seen that, on the one hand, due to the high temperature in the wok, the tea roaster's hand temperature rises significantly when pressing and grabbing the tea leaves, while the hand temperature decreases when picking up and shaking the tea leaves in the air. Therefore, the number of frying actions can be counted by determining the number of hand temperature changes. Furthermore, the tea roaster's hand movements significantly change during the pressing, grabbing, and shaking processes. Therefore, the number of frying actions can be counted by determining the number of these hand movement changes over a period of time, thereby determining the tea roaster's frying speed. Moreover, when the wok is too hot, the tea roaster will usually speed up the turning process to avoid prolonged contact between the tea leaves and the inner wall of the wok, which would cause the tea leaves to be burnt.

[0017] Therefore, the present application installs a thermal imager just above the wok, so that the detection range is the entire area of ​​the wok. In this way, the temperature change of the wok can be monitored by collecting the thermal imaging temperature map of the wok captured by the thermal imager and analyzing the thermal imaging temperature map in real time. When the temperature change of the wok is not within the preset temperature range for frying and killing tea, the wok temperature can be adjusted while reminding the tea roaster of the direction of adjusting the current frying speed based on the manual frying speed of the tea roaster at the previous moment, so that the frying temperature of the tea can be maintained within the temperature range required for killing tea, and the tea roaster can be reminded in time to adjust the manual frying technique to adapt to the current temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of a temperature monitoring and management method based on a manual green tea withering process provided by an embodiment of the present invention; Figure 2 A schematic diagram of the installation position of a thermal imager provided in an embodiment of the present invention; Figure 3 A schematic diagram of a thermal imaging temperature map provided by an embodiment of the present invention; Figure 4 A schematic diagram of the change of hand state in a hand imaging diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is in no way intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Unless otherwise specifically stated, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention.

[0021] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0022] Additionally, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness. Those skilled in the art will recognize that various changes and modifications can be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0023] Technologies, methods and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods and equipment should be considered part of the authorization specification.

[0024] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0025] Example 1 like Figure 1 As shown, this embodiment provides a temperature monitoring and management method based on the manual green tea withering process, which specifically includes the following steps: S1, real-time acquisition of thermal imaging temperature images captured by a thermal imager installed directly above the wok, and sequential storage of the acquired thermal imaging temperature images into an image set in the order of sampling time; Specifically, the frying pan in this application can be an electric frying pan, and the temperature of the electric frying pan can be changed by controlling the heating power of the electric frying pan. The installation method of the thermal imager is as follows: Figure 2 As shown, the thermal imager is installed above the wok so that the shooting range can cover all areas of the wok, including the arm and palm that are inserted into the wok. For the thermal imaging temperature map captured by the thermal imager, the edge of the wok needs to be cut out to obtain the following Figure 3 Thermographic temperature map shown. Figure 3 As can be seen, the temperature inside the wok is not evenly distributed, but rather decreases from the inside out. However, as long as the temperature inside the wok is within the temperature range for the hot pot, it is sufficient. The current hot pot process uses three hot pots, each with a lower temperature. Therefore, the temperature range required for each hot pot can be set. When capturing thermal imaging temperature images, the sampling time of each image is marked. The sampling frequency can be set based on the acquisition frame rate of the thermal imager, making it easier to calculate the duration based on the image sampling time.

[0026] S2. Perform real-time temperature analysis on the thermal imaging temperature map to determine whether the highest temperature in the thermal imaging temperature map is within a preset temperature range required for fixing. If not, obtain a thermal imaging temperature map within a preset time period before the current time from the image collection and store it in the analysis data set; By analyzing the collected thermal imaging temperature map in real time, we can determine the temperature changes within the wok. If the highest temperature in the thermal imaging temperature map exceeds the preset temperature range, indicating that the wok temperature is too high, we can reduce the wok's heating power to lower the wok temperature. However, lowering the wok temperature takes time, so we can also remind the tea roaster to change the current roasting speed and speed up the roasting process based on the current roasting speed to avoid excessive contact between the tea leaves and the wok bottom, which can lead to burning of the tea leaves due to excessive temperature. To determine the roaster's current roasting speed, we can analyze the roasting actions within a period of time (10 seconds) before the temperature change to determine the roaster's current roasting speed.

[0027] S3. Perform edge detection on the thermal imaging temperature map in the analysis data set, identify and mark the position of the tea roaster's hand from the thermal imaging temperature map, obtain the hand image xn, and store it in the analysis queue X(x1, ..., xn) in sequence; Specifically, the specific process of step S3 is: S31. Performing edge detection on the thermal imaging temperature image to identify the hand contour from the thermal imaging temperature image based on the temperature difference between the hand and the wok. Determining whether the current stir-frying is one-handed or two-handed based on the number of palms in the identified hand contour, where the hand contour includes both the arm and the palm. S32. Mark the arm and palm positions in the thermal image and record the arm and palm temperatures. To identify whether the palm is facing up or down, the relative position of the thumb and the palm is marked when marking the palm position. This relative position includes the left and right sides. The image with the hand outline is grayscaled and stored in an analysis queue for subsequent processing.

[0028] S4, comparing two adjacent hand images in the analysis queue in sequence to detect whether the hand state has changed. If so, the number of stir-frying actions is increased by one; When detecting whether the hand state has changed, the number of frying actions can be counted by detecting the hand temperature change state or the hand movement change, or it can be judged based on the hand temperature change and the hand movement change. For example, when the hand temperature change and the hand movement change are detected, the number of frying actions is increased by 1. Since the palm of the hand will reach into the higher temperature area in the wok to grab the tea leaves at the bottom and turn them upwards, the grabbed tea leaves will be shaken in the air. Since the temperature in the wok is high, the temperature of the hand will rise when the hand is put into the wok to grab and turn the tea leaves, and the temperature of the hand will drop when the hand grabs the tea leaves in the air. Therefore, the number of frying actions can be counted by detecting the hand temperature change. The specific method is: S411, traverse each hand image in the analysis queue, obtain two adjacent hand images x1 and x2 in the analysis queue, compare the temperature change values ​​at the palm position of hand image x1 and hand image x2, if the temperature change value is within the difference range and the temperature change changes from high to low, it is determined that the hand state has changed, and the number of stir-frying actions is increased by one; S412: Continue to obtain the next two adjacent hand imaging images x2 and x3, and repeat step S412 until all hand imaging images in the analysis queue are traversed.

[0029] In other embodiments, since the hand will press the tea leaves when reaching into the wok to grab them, the palm of the hand will face downwards during the hand movement. However, when the tea leaves are grabbed and shaken in the air, the palm of the hand will face upwards. The number of frying actions can be counted by the change in hand movement. In addition, since the tea leaves are relatively fluffy in the early stage of frying, they are generally frying and turning with both hands. In the later stage of withering, when the tea leaves are inside the wok, they may be frying with one hand. When frying with both hands, the specific process of step S4 is as follows: S421, traverse each hand image in the analysis queue, obtain two adjacent hand images xn-1 and xn in the analysis queue, compare the hand motion changes of hand image xn and hand image xn-1, if the hand motion changes from the first motion to the second motion, Figure 4As shown, it is determined that the hand state has changed, and the number of stir-frying actions is increased by one; Since the stir-fry is done with both hands, the process of identifying changes in hand movements is as follows: When marking the palm positions, mark the relative position relationship between the thumbs and the palms of both hands. Based on the relative position relationship between the thumbs and the palms, when the thumb of one hand is on the left side of the palm and the thumb of the other hand is on the right side of the palm, determine the straight-line distance between the two thumbs; When the relative positions of the thumbs of both hands are at the first distance, that is, the straight-line distance between the two thumbs is short, that is, the palms are facing downward, the current action is recorded as the first action. At this time, the state of the hands is that the thumbs of the two hands are close to each other, which is a grasping state; When the thumbs of both hands are at the second distance relative to the palms, that is, the straight-line distance between the two thumbs is greater and the palms are facing upward, the current hand movement is recorded as the second movement, and the first distance is less than the second distance. At this time, the state of the hands is that the thumbs of the two hands are away from each other, indicating a shaking state.

[0030] S422: Continue to obtain the next two adjacent hand imaging images xn-2 and xn-1, and repeat step S421 until all hand imaging images in the analysis queue are traversed.

[0031] In some embodiments, when the number of recognized hand contours is an odd number of palms, it is determined that the frying is performed with one hand. When the frying process is performed with one hand, the specific process of step S4 is as follows: S431, using a window moving traversal method to traverse each hand image in the analysis queue, setting the window length to three and the step value of each movement to two; that is, every three hand images are regarded as a group for recognition, and when moving, the last image of the group is used as the first image of the next group; S432: In the analysis queue, the hand images xn, xn-1, and xn-2 acquired within the window are compared as a data group to compare changes in the hand motion in the hand image within the current window. If the hand motion changes from the first position to the second position and then returns to the first position, it is determined that the hand state has changed, and the number of stir-frying actions is increased by one. Since it is impossible to directly determine which hand the tea roaster uses when roasting tea leaves with one hand, it is impossible to simply determine by the relative position relationship between the thumb and the palm that when the thumb changes from the left side of the palm to the right side, it is considered a hand movement. However, in the process of pressing, taking and shaking tea leaves, the hand movement will change from palm down to palm up and then to downward, or from palm up to palm down and then to upward. It can be seen that a complete roasting action will have a flipping action. Therefore, by identifying this flipping action, when it returns to the initial state after flipping once, it is recorded as a roasting action. According to the relative position relationship between the marked thumb and the palm when marking the palm position, the position of the thumb on both sides of the palm is recorded as the first position and the second position respectively. Therefore, the first position can be defined as the thumb on the left or right side of the palm, and the second position is correspondingly defined as the thumb on the right or left side of the palm. The first position and the second position are two relative directions.

[0032] S433: Move the window to obtain the next set of hand imaging images xn-1, xn-2, and xn-3 for comparison, and repeat step S432 until all hand imaging images in the analysis queue are traversed.

[0033] S5. Statistically analyze the total number of stir-frying actions in the queue, and calculate the stir-frying speed based on the ratio of the total number of stir-frying actions to the preset time length. For example, if 12 stir-frying actions are detected within 10 seconds, the stir-frying speed is 1.2 times / s. If the temperature is too high, the number of stir-frying actions per second is increased, and if the temperature is too low, the number of stir-frying actions per second is reduced.

[0034] S6. Remind the tea roaster to adjust the roasting speed based on the comparison result between the highest temperature in the current thermal imaging temperature map and the preset temperature range.

[0035] The way to remind tea roasters to adjust the roasting speed is: S61. If the highest temperature in the current thermal imaging temperature map is lower than the preset temperature range, it is determined that the wok temperature has dropped, the wok power is increased to heat the wok, and the tea stirrer is reminded that the current temperature is low and the stir-frying speed is reduced; S62. If the highest temperature in the current thermal imaging temperature map exceeds the preset temperature range, it is determined that the wok temperature is overheated, the wok temperature is controlled to be lowered, and the tea stirrer is reminded that the current temperature is high and to speed up the stir-frying.

[0036] Here, the stir-frying speed can be adjusted by speeding up / slowing down the speed of turning the tea leaves, or increasing the time or speed of shaking the tea leaves in the air. Taking the case of stir-frying with two hands as an example, the time of shaking the tea leaves in the air can be adjusted to adapt to temperature changes. Specifically, when the hand action changes from the first action to the second action, that is, when the hand grabs the tea leaves from the wok and shakes them in the air, the time is started from the hand image corresponding to the second action, and the time length when the hand action changes from the second action to the first action is calculated to obtain the hand action time; The hand movement time of each frying action is counted to obtain the total duration and average duration of the tea fryer's hand movement time within the preset time length.

[0037] Calculate the ratio of the total hand movement time to the preset time length to obtain the jitter ratio; When the wok temperature drops, remind the tea stirrer to reduce the shaking ratio; that is, do not shake the tea leaves quickly to dissipate heat; When the wok is too hot, remind the tea roaster to increase the shaking ratio, that is, increase the shaking frequency, reduce the contact time between the tea leaves and the wok, and stir-fry the tea leaves quickly.

[0038] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0039] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0040] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0041] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide the functions for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0042] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Based on the technical essence of the present invention and within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement of the above embodiment shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A temperature monitoring and management method based on the manual green tea withering process, characterized in that: The specific steps include: S1, real-time acquisition of thermal imaging temperature images taken by a thermal imager installed directly above the wok and storing them in an image set; S2, performing real-time temperature analysis on the thermal imaging temperature map to determine whether the highest temperature in the thermal imaging temperature map is within the preset temperature range required for the temperature of the hot greening. If not, obtaining the thermal imaging temperature map within the preset time length before the current time from the image set and storing it in the analysis data set; S3, performing edge detection on the thermal imaging temperature map in the analysis data set, identifying and marking the hand position of the tea roaster from the thermal imaging temperature map, obtaining the hand imaging map xn, and sequentially storing it in the analysis queue X(x1,…,xn); S4, comparing two adjacent hand images in the analysis queue in sequence to detect whether the hand state has changed, and if so, increasing the number of stir-frying actions by one; S5, statistically analyzing the total number of stir-frying actions in the queue, and solving the stir-frying speed according to the ratio of the total number of stir-frying actions to the preset time length; S6. Remind the tea roaster to adjust the roasting speed according to the comparison result between the highest temperature in the current thermal imaging temperature map and the preset temperature range.

2. The temperature monitoring and management method based on the manual green tea withering process according to claim 1 is characterized in that: The specific process of step S3 is: S31, performing edge detection of a hand contour on the thermal imaging temperature map, and identifying a hand contour from the thermal imaging temperature map according to a temperature difference between the hand and the wok, wherein the hand contour includes an arm and a palm; S32. Mark the arm position and the palm position in the thermal imaging temperature map, and record the temperature of the arm position and the temperature of the palm position, respectively.

3. The temperature monitoring and management method based on the manual green tea withering process according to claim 2 is characterized in that: The specific process of step S4 is: S411, traversing each hand image in the analysis queue, obtaining two adjacent hand images xn and xn-1 in the analysis queue, comparing the temperature change values ​​at the palm position of the hand image xn and the hand image xn-1, if the temperature change value is within the difference range and the temperature change changes from high to low, it is determined that the hand state has changed, and the number of stir-frying actions is increased by one; S412, continue to obtain the next two adjacent hand imaging images xn-1 and xn-2, and repeat step S411 until all hand imaging images in the analysis queue are traversed.

4. The temperature monitoring and management method based on the manual green tea withering process according to claim 2 is characterized in that: The process of step S4 includes: S421, traversing each hand image in the analysis queue, obtaining two adjacent hand image images xn-1 and xn in the analysis queue, comparing the hand motion changes of the hand image xn and the hand image xn-1, if the hand motion changes from the first motion to the second motion, it is determined that the hand state has changed, and the number of stir-frying motions is increased by one; S422, continue to obtain the next two adjacent hand imaging images xn-2 and xn-1, and repeat step S421 until all hand imaging images in the analysis queue are traversed.

5. The temperature monitoring and management method based on the manual green tea withering process according to claim 4 is characterized in that: The process of identifying changes in hand movements is: When marking the palm position, the relative position relationship between the thumbs of both hands and the palms is marked respectively. When the relative position of the thumbs of both hands to the palms is the first distance, the current action is recorded as the first action; When the relative positions of the thumbs of both hands to the palms are at the second distance, the current hand movement is recorded as the second movement, and the first distance is smaller than the second distance.

6. The temperature monitoring and management method based on the manual green tea withering process according to claim 5 is characterized in that: When the hand movement changes from the first movement to the second movement, the timing starts from the hand image corresponding to the second movement, and the time length when the hand movement changes from the second movement to the first movement is calculated to obtain the hand movement time; The hand movement time of each frying action is counted to obtain the total duration of the tea fryer's hand movement time within the preset time length.

7. The temperature monitoring and management method based on the manual green tea withering process according to claim 6 is characterized in that: The way to remind the tea roaster to adjust the roasting speed is: S61, if the highest temperature in the current thermal imaging temperature map is lower than the preset temperature range, it is determined that the wok temperature has dropped, the wok power is controlled to increase to heat the wok, and the stir-fryer is reminded that the current temperature is low and the stir-frying speed is reduced; S62. If the highest temperature in the current thermal imaging temperature map exceeds the preset temperature range, it is determined that the wok temperature is overheated, the wok temperature is controlled to be lowered, and the tea stirrer is reminded that the current temperature is high and to speed up the stir-frying.

8. The temperature monitoring and management method based on the manual green tea withering process according to claim 7 is characterized in that: Calculate the ratio of the total duration of the hand movement to the preset time length to obtain the jitter ratio; When the wok temperature drops, remind the tea stir-fryer to reduce the shaking ratio; When the wok temperature is too hot, remind the tea roaster to increase the shaking ratio.

9. The temperature monitoring and management method based on the manual green tea withering process according to claim 2 is characterized in that: In step S3, according to the number of hand contours identified, it is determined whether the current frying is one-handed frying or two-handed frying. If it is one-handed frying, the process of step S4 is: Each hand image in the analysis queue is traversed by window moving traversal, the window length is set to three, and the step value of each movement is two; In the analysis queue, the hand imaging images xn, xn-1, and xn-2 obtained in the window are compared as a group of data groups, and the changes of the hand movements in the hand imaging images in the current window are compared. If the hand movement changes from the first position to the second position and then returns to the first position, it is determined that the hand state has changed, and the number of stir-frying actions is increased by one; The window is moved to obtain the next set of hand images xn-1, xn-2, and xn-3 for comparison until all hand images in the analysis queue are traversed.

10. The temperature monitoring and management method based on the manual green tea withering process according to claim 9, characterized in that: The process of comparing hand movement changes is: When marking the palm position, the relative position relationship between the thumb and the palm is marked respectively, and the positions of the thumb on both sides of the palm are recorded as the first position and the second position respectively.

Images