A method and system for intelligently identifying the life state of a silkworm

Abstract

The application discloses a kind of silkworm life state intelligent identification method and identification system, the method comprises: obtaining the growth video of silkworm, the silkworm is in real breeding environment and intensive breeding condition;From growth video, the activity track of each silkworm in the preset time period is obtained;According to activity track, the behavior data of each silkworm is determined, and the behavior data includes the relative crawling distance of silkworm in the preset time period, head shaking frequency, body shaking frequency and body activity degree;The behavior data of each silkworm is assigned to behavior vector and compared with the standard value of healthy silkworm obtained in advance, so as to identify the life state of silkworm.The application mainly according to the abnormal behavior characteristics shown when silkworm is ill or poorly developed, for example: frenzied crawling, refuse mulberry leaf and not in time hibernate etc., using deep learning obtains and quantifies silkworm behavior, and then by contrast with standard value, the life state of silkworm is intelligently identified.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of behavior recognition, and particularly relates to a silkworm life state intelligent recognition method and a recognition system. BACKGROUND

[0002] Silkworms are insects that are densely bred, and are very susceptible to pathogen invasion. Silkworm diseases usually have strong infectivity, and the life cycle of silkworms is short, so it is difficult to cure sick silkworms with drugs, and the silkworms are usually directly bred or not cocooned, resulting in a large amount of cocoon loss every year. At the same time, improper breeding methods can easily lead to poor development of silkworms, causing diseases to breed and affecting the quality of cocoon.

[0003] Some existing documents use deep learning to carry out silkworm disease recognition, which is mainly based on the morphological characteristics of silkworms after they are diseased, and needs to carry out data labeling on the basis of manual recognition, so it cannot achieve early recognition of diseases and cannot work under intensive breeding conditions. SUMMARY

[0004] In view of the problem that silkworm diseases cannot be effectively recognized in the existing silkworm breeding process, the application extracts corresponding behavior data according to the abnormal behavior characteristics of silkworms in the state of disease or other abnormalities, and recognizes the life state of silkworms by analyzing the behavior data, thereby realizing a silkworm life state intelligent recognition method and a recognition system.

[0005] To achieve the above technical purposes, the technical solutions adopted by the application are as follows:

[0006] In a first aspect, the application provides a silkworm life state intelligent recognition method, comprising:

[0007] obtaining a growth video of silkworms, wherein the silkworms are in a real breeding environment and intensive breeding conditions;

[0008] obtaining the activity trajectory of each silkworm in a preset time period from the growth video;

[0009] determining the behavior data of each silkworm according to the activity trajectory, wherein the behavior data includes the relative crawling distance, the head shaking frequency, the body shaking frequency and the body activity level of the silkworm in the preset time period;

[0010] assigning the behavior data of each silkworm to a behavior vector and comparing it with the pre-obtained standard value of healthy silkworms, so as to recognize the life state of the silkworms.

[0011] Preferably, the activity trajectory of each silkworm in the preset time period is obtained from the growth video, specifically comprising:

[0012] converting the growth video into frame images according to the time sequence and preprocessing the frame images;

[0013] From the first frame image, key point detection is performed on each silkworm in time sequence, so as to obtain the key point coordinates of each silkworm, wherein the key points include five key points of the head, tail and three back stripes of the silkworm;

[0014] According to the key point coordinates of each silkworm obtained in time sequence, the activity trajectory of each key point of each silkworm is obtained.

[0015] Preferably, the key point detection on each silkworm in time sequence from the first frame image to obtain the key point coordinates of each silkworm specifically comprises:

[0016] Each silkworm is numbered from the first frame image;

[0017] Feature extraction is performed on the numbered silkworm in each frame image to obtain the key point coordinates.

[0018] Preferably, the feature extraction on the numbered silkworm in each frame image to obtain the key point coordinates specifically comprises:

[0019] A convolutional neural network is used to perform feature operation on each frame image of the silkworm to obtain the probability of each pixel point belonging to each key point of each silkworm;

[0020] The pixel point with the maximum probability value is selected as the key point coordinate of the silkworm.

[0021] Preferably, the feature extraction on the numbered silkworm in each frame image to obtain the key point coordinates specifically comprises: feature extraction is performed on each frame image of the silkworm by a sequence model, so as to obtain the key point coordinates of each type of key point.

[0022] Preferably, the key point coordinates of each silkworm obtained in time sequence are used to obtain the activity trajectory of each key point of each silkworm, specifically comprising:

[0023] Each key point of a single silkworm is connected into a line on the first frame image;

[0024] In the next frame image, the nearest silkworm is selected, and each key point thereof is matched with each key point of the previous frame, until the last frame image;

[0025] The key point coordinates of each silkworm from the first frame to the last frame are sequentially connected to obtain the activity trajectory of each key point of the silkworm.

[0026] Preferably, the behavior data of each silkworm determined according to the activity trajectory specifically comprises:

[0027] According to the behavior vector of two key points of the head and tail of the silkworm, the relative crawling distance of the silkworm in a preset time period is obtained;

[0028] According to the behavior vector of three key points of the head, tail and one stripe of the back of the silkworm, the body shaking frequency of the silkworm in a preset time period is obtained;

[0029] According to the behavior vector of three key points of the head, tail and one stripe of the back of the silkworm, the body shaking frequency of the silkworm in a preset time period is obtained;

[0030] According to the behavior vector of three key points of the head, tail, back and two stripes of the silkworm, the body activity degree of the silkworm in a preset time period is obtained.

[0031] Preferably, the pre-obtained behavior data of healthy silkworms includes behavior data of healthy silkworms at each daily age in a preset period.

[0032] In a second aspect, the present application further provides a silkworm life state intelligent recognition system, comprising:

[0033] An image acquisition module is configured to acquire growth videos of silkworms, wherein the silkworms are in a real breeding environment and intensive breeding conditions;

[0034] An activity trajectory acquisition module is configured to acquire an activity trajectory of each silkworm in a preset time period from the growth videos;

[0035] A behavior data acquisition module is configured to determine behavior data of each silkworm according to the activity trajectory, wherein the behavior data includes a relative crawling distance, a head shaking frequency, a body shaking frequency and a body activity degree of the silkworm in the preset time period;

[0036] A recognition module is configured to compare the behavior data of each silkworm with pre-obtained standard values of healthy silkworms in a behavior vector, so as to recognize the life state of the silkworm.

[0037] In a third aspect, the present application further provides a silkworm life state intelligent recognition system, comprising a camera device, a processor and a memory, wherein the processor is connected with the camera device and the memory, respectively, the camera device is configured to acquire growth videos of silkworms, the memory is configured to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 8.

[0038] Compared with the prior art, the present application has the following beneficial effects:

[0039] According to the different behavior characteristics of the silkworm in the diseased or abnormal state, the life state intelligent recognition is carried out through deep learning quantification of the behavior of the silkworm, manual data labeling is not needed, the recognition is more objective and accurate, and early identification of diseases can be realized. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A silkworm life state intelligent recognition method flow chart is provided for the embodiment of the present application.

[0041] Figure 2 A process chart for obtaining the activity track of each silkworm in a preset time period from the growth video is provided.

[0042] Figure 3 A key point coordinate acquisition method flow chart of the silkworm is provided.

[0043] Figure 4 A process chart for obtaining the activity track of each key point of each silkworm according to the key point coordinates is provided.

[0044] Figure 5 An embodiment structure schematic diagram of a silkworm life state intelligent recognition system is provided.

[0045] Figure 6 Another embodiment structure schematic diagram of a silkworm life state intelligent recognition system is provided. DETAILED DESCRIPTION

[0046] In order to facilitate the understanding of those skilled in the art, the present application will be further described below in conjunction with the embodiments and drawings. The content mentioned in the embodiments is not a limitation of the present application.

[0047] The present application provides a silkworm life state intelligent recognition method for silkworm life state recognition in a real breeding environment, including disease and developmental disorders. The recognition principle is that when the silkworm is diseased or has developmental disorders, it will exhibit abnormal behavior characteristics, such as frantic crawling, refusal to eat mulberry leaves, and not sleeping in time, etc. According to the phenomenon that the silkworm is not always blocked by mulberry leaves and is not always overlapped with each other in the actual breeding environment, the corresponding algorithm is used to obtain the quantified behavior characteristics of the silkworm, and then compared with the standard value established in advance. The standard value is the behavior data of healthy silkworms obtained in advance. The life state of the silkworm is recognized according to the comparison result.

[0048] As shown in Figure 1 The silkworm life state intelligent recognition method specifically includes the following steps:

[0049] S100: Obtain the growth video of the silkworm, and the silkworm is in a real breeding environment and intensive breeding condition.

[0050] Since the density of silkworms is high, the growth video of silkworms is captured by using a high-definition camera, the shooting position is vertically downward above the silkworm foil, the height is fixed, which is set when establishing the identification standard, and the collection time is about 1 hour to avoid collecting when there are a large number of mulberry leaves blocking after feeding.

[0051] S200: Obtain the activity trajectory of each silkworm in the preset time period from the growth video.

[0052] The preset time period can be the length of the growth video collection, such as 1 hour, or a selected video in the growth video.

[0053] The activity trajectory is the path of the silkworm in the growth video or the selected time period, which is used to judge the activity state of the silkworm.

[0054] This step is specifically shown in Figure 2

[0055] S210: Convert the growth video into frame images in time sequence and pre-process them.

[0056] After the growth video of silkworms is collected, image processing methods can be used to convert the video into frame images. When the video length is short, all images can be saved; when the video length is long, a frame image can be obtained every 1 second, and then the frame images are saved in time sequence.

[0057] The pre-processing of the converted frame images includes necessary size segmentation and bright transformation of the images.

[0058] S220: Starting from the first frame image, key point detection is performed on each silkworm in time sequence, so as to obtain the key point coordinates of each silkworm, the key points including the head, tail and three spots of the back of the silkworm.

[0059] This step mainly detects the key points of silkworms in the frame images, so as to obtain the coordinates of each key point of silkworms in each frame image. These key point coordinates can be used to judge the movement process of silkworms, so as to obtain the corresponding behavior data of silkworms.

[0060] The specific selection of key points is related to the analysis of behavior data. For example, to analyze the relative crawling distance of silkworms, the key point information of the head and tail of silkworms is needed. In this embodiment, five key points of silkworms are selected, i.e. the head key point, the tail key point and the three spot key points of the back.

[0061] The method for obtaining the key point coordinates of silkworms is shown in ​

[0062] S221: Number each silkworm from the first frame image

[0063] The numbering rule is not unique, and the basic requirement is to ensure that each silkworm corresponds to a unique number. At the same time, multiple silkworms will be included in a single frame image, and the density and actual breeding environment are consistent.

[0064] S222: Feature extraction is performed on the numbered silkworms in each frame image to obtain key point coordinates.

[0065] Feature extraction is performed on each silkworm in each frame image. The feature extraction method can use convolutional neural networks or sequence models, etc. Feature extraction process also includes feature operation, feature fusion, attention mechanism, residual connection, deconvolution and other common methods in deep learning.

[0066] When the feature extraction network uses a convolutional neural network, the output of the network for the extracted features is a heat map in the original image, i.e. the probability of each pixel in the original image belonging to each key point of each silkworm. The pixel with the maximum probability value is the key point of the silkworm individual.

[0067] When the feature extraction network is a sequence model, the output of the network is an array of coordinate points for each type of key point, i.e. directly outputting the key point coordinates.

[0068] During the training process of the key point detection network, the conventional process for training deep learning models should also be included, including calculating the loss value between the network prediction value and the true value, parameter updating, and iteration operations.

[0069] In this step, whether the algorithm uses a convolutional neural network or a sequence model, it needs to be trained with sample images. In the corresponding algorithm, the input is the frame image, and the output is the key point coordinates. In addition to the above-mentioned algorithms, existing classic algorithms such as Hourglass, Cascaded, and HRNet human pose estimation algorithms can be used as a basis for structural fine-tuning and structural modification based on silkworm datasets for silkworm key point detection model training.

[0070] During the model training process for silkworm key point detection in frame images, the corresponding parameters need to be continuously verified and adjusted to achieve the desired detection accuracy. The key point detection model is tested on different datasets, and the method is optimized and improved based on the test results to achieve an average detection accuracy of silkworm key points of more than 95%.

[0071] Then, the key point detection model is used to detect the key points of each frame image to obtain the key point coordinates of each silkworm and match these key points.

[0072] S230: Obtain the key point coordinates of each silkworm according to the time sequence, thereby obtaining the activity trajectory of each key point of each silkworm.

[0073] This step mainly estimates the activity trajectory of the five key points of the silkworm through the five key point coordinates of the same numbered silkworm in each frame of image, and the specific steps are shown in 4:

[0074] S231: Connect each key point of a single silkworm into a line on the first frame of image.

[0075] The key points of the silkworm collected in the first frame of image are used as the starting point of the activity trajectory, and the five key points of the corresponding silkworm are connected into a line, which is conducive to determining the silkworm corresponding to the whole line.

[0076] S232: Select the nearest silkworm on the next frame of image, and match each key point with each key point of the previous frame until the last frame of image.

[0077] Since the silkworm does not suddenly change position in adjacent frame images, the key point position changes of the same silkworm can be matched through consecutive frame images.

[0078] S233: Connect the key point coordinates of each silkworm from the first frame to the last frame in turn to obtain the activity trajectory of each key point of the silkworm.

[0079] Finally, according to the frame images in time sequence, each silkworm can obtain the activity trajectory of five key points, and these activity trajectories are important data for judging the behavior data of the silkworm.

[0080] S300: Determine the behavior data of each silkworm according to the activity trajectory, and the behavior data includes the relative crawling distance, head shaking frequency, body shaking frequency and body activity level of the silkworm in the preset time period.

[0081] According to the key point activity trajectory of the silkworm obtained before, the corresponding behavior data can be obtained according to the following method, and the specific process is as follows:

[0082] According to the foregoing, the behavior data of the silkworm in this embodiment mainly considers the relative crawling distance, head shaking frequency, body shaking frequency and body activity level of the silkworm in the growth video. These parameters can reflect the behavior data of the silkworm to a certain extent after years of research.

[0083] Specifically, when evaluating the relative crawling distance of the silkworm in the preset time period, the activity trajectories of the head and tail key points of the silkworm are mainly considered.

[0084] In evaluating the head shaking frequency of the silkworm in a predetermined time period, the shaking of the head and back is mainly considered, and therefore the activity trajectories of the two key points (a total of three) of the head and back are selected as the consideration.

[0085] In evaluating the body shaking frequency of the silkworm in a predetermined time period, the shaking of the head, tail and back is mainly considered, and therefore the activity trajectories of the three key points of the head, tail and back are selected as the consideration.

[0086] In evaluating the body activity degree of the silkworm in a predetermined time period, the activity trajectories of the five key points are all considered.

[0087] S400: The behavior data of each silkworm is allocated to the behavior vector and compared with the standard value of the healthy silkworm obtained in advance, so as to identify the life state of the silkworm.

[0088] Since the behavior data includes multiple parameter values, it can be composed into a set of behavior vectors and compared with the standard value of the healthy silkworm (including the standard value of multiple behavior data parameters) to identify the silkworms that are outside a certain range of the standard value as sick or poorly developed silkworms, and output the identification result.

[0089] Specifically, the judgment standard value of the behavior data of the healthy silkworm is obtained similarly to steps S100-S300, and the difference is that the standard value needs to be calculated for the healthy silkworm in advance. The specific process can be as follows:

[0090] (1) Collect the growth video of the silkworm. The silkworm here must be fed by a professional in a standard feeding environment, and the silkworm grows healthily without disease or developmental disorders, so as to ensure that the final behavior data can be used as a standard value for judgment.

[0091] (2) After the collection is completed, the video is converted into frame images according to the time sequence, preprocessed, and then the silkworm features are extracted through the key point detection model, so as to analyze the activity trajectory from the time sequence frame images, and finally obtain the corresponding behavior data from the activity trajectory. The parameters of the behavior data are also calculated by step S300 to obtain the standard value.

[0092] The activity trajectory of the silkworm can be analyzed from the time series frame images by referring to the steps S231-S233. After key point detection is performed on the continuous image frames, each silkworm is numbered on the first frame image, and the key points of each silkworm are connected to form a line. Then, in the next frame image, the silkworms are matched to the same silkworm according to the phenomenon that the position of the silkworm does not change suddenly and does not appear or disappear suddenly in the video, and the key points of each silkworm are matched to each other. The silkworms are numbered and the key points are matched in sequence on the next frame image until the last frame of the video data. The key point coordinates of each silkworm are printed in sequence to obtain the activity trajectory of the silkworm.

[0093] It should be noted that the discrimination standard value established in the embodiment includes the behavior data of each day of the first day of the first instar to the seventh day of the fifth instar of the silkworm (a total of 20 groups of values). The standard value is based on each day of the silkworm, and the behavior data of the silkworm during the day and at night is different. When the silkworm individual is small, a physical magnification method is used, that is, an electron microscope is used to magnify the silkworm individual to collect images when the silkworm is 1-2 years old, and the growth video data of the silkworm is also magnified data. The discrimination standard is established in different silkworm varieties and various feeding environments, and the larger the data set used when training the key point detection model, the wider the application range of the method.

[0094] Considering the physiological differences between different silkworm varieties, the above training takes into account multiple silkworm varieties to improve the application range. If a specific silkworm variety is targeted, a behavior quantification method suitable for the silkworm variety should be used.

[0095] It should also be noted that in the actual breeding process, there may be silkworms blocked by mulberry leaves, and there may be silkworms overlapping each other. For this reality, the solution of the method is that in the process of establishing the discrimination standard, the approximate position of the invisible key point is manually marked, and it is set as invisible for key point detection, which is further used for key point detection model training to enhance the predictive ability of the model under partial blocking conditions. In extreme cases, if a silkworm is completely blocked, no data labeling is performed, which is also not helpful for training.

[0096] After key point detection, key point matching is continued, and the activity trajectory of the silkworm is obtained by the position change of the key points of the silkworm on the continuous video frame images.

[0097] For the method provided by the embodiment, the silkworms are blocked by mulberry leaves or other silkworms during use, according to the physiological characteristics of the silkworms, which are insects with self-activity and upward climbing, and thus are not always blocked, and the method is based on a video data set, so a single silkworm is not always blocked in a video and can be identified in continuous detection, and thus the silkworm blocking problem in the actual breeding environment can be overcome.

[0098] As shown in Figure 5 The embodiment further provides a silkworm life state intelligent identification system, which comprises an image acquisition module 51, an activity track acquisition module 52, a behavior data acquisition module 53 and an identification module 54.

[0099] The image acquisition module 51 is used to acquire the growth video of the silkworms, and the silkworms are in a real breeding environment and intensive breeding conditions; the activity track acquisition module 52 is used to acquire the activity track of each silkworm in a preset time period from the growth video; the behavior data acquisition module 53 is used to determine the behavior data of each silkworm according to the activity track, and the behavior data comprises the relative climbing distance of the silkworm in the preset time period, the head shaking frequency, the body shaking frequency and the body activity level; and the identification module 54 is used to assign the behavior data of each silkworm to a behavior vector and compare the behavior data with a standard value of a healthy silkworm obtained in advance, so that the silkworms can be identified as diseased or poorly developed when the behavior data of the silkworms is greatly different from the standard value.

[0100] As shown in Figure 6 The embodiment further provides a silkworm life state intelligent identification system, which comprises a camera 61, a processor 62 and a memory 63, the processor 62 is connected with the camera 61 and the memory 63, the camera 61 is used to acquire the growth video of the silkworms, the memory 63 is used to store a computer program, the computer program comprises program instructions, and the processor 62 is configured to call the program instructions and execute the silkworm life state intelligent identification method.

[0101] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the foregoing described technical solutions, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for intelligent identification of the life state of silkworms, characterized in that, include: Obtain videos of silkworm growth, where the silkworms are in a real breeding environment and under intensive breeding conditions; The process of obtaining the activity trajectory of each silkworm within a preset time period from the growth video includes: converting the growth video into frame images according to the time sequence and preprocessing them; starting from the first frame image, performing key point detection on each silkworm according to the time sequence to obtain the key point coordinates of each silkworm, wherein the key points include five key points: the head, tail, and three markings on the back of the silkworm; and obtaining the activity trajectory of each key point of each silkworm based on the key point coordinates of each silkworm obtained from the time sequence. The behavioral data of each silkworm is determined based on its activity trajectory. The behavioral data includes the relative crawling distance, head shaking frequency, body shaking frequency, and body activity level of the silkworm within the preset time period. The behavioral data of each silkworm is assigned to a behavioral vector and compared with the pre-obtained standard values ​​of healthy silkworms to identify the life status of the silkworms. Starting from the first frame image, keypoint detection is performed on each silkworm according to the time sequence to obtain the keypoint coordinates of each silkworm. Specifically, this includes: numbering each silkworm from the first frame image; and extracting features from the numbered silkworms in each frame image to obtain the keypoint coordinates. Specifically, this includes: extracting features from each frame image of the silkworms using a sequence model to obtain the keypoint coordinates of each type of keypoint. Alternatively, a convolutional neural network can be used to perform feature calculations on each frame of the silkworm image to obtain the probability of each pixel belonging to each key point of each silkworm; the pixel with the highest probability value is selected as the key point coordinate of the silkworm.

2. The intelligent identification method for the life state of silkworms according to claim 1, characterized in that, The process of obtaining the key point coordinates of each silkworm based on the time series, thereby acquiring the activity trajectory of each silkworm at each key point, specifically includes: Connect each key point of a single silkworm in the first frame image with a line. Select the nearest adjacent silkworm in the next frame and match each of its key points with each key point of the previous frame, until the last frame. By connecting the key point coordinates of each silkworm from the first frame to the last frame, the activity trajectory of each key point of the silkworm can be obtained.

3. The intelligent identification method for the life state of silkworms according to claim 1, characterized in that, The behavioral data for each silkworm, determined based on its activity trajectory, specifically includes: The relative crawling distance of the silkworm within a preset time period is obtained based on the behavioral vectors of two key points: the head and the tail. The frequency of head shaking of silkworms within a preset time period is obtained by using the behavioral vectors of three key points, namely two spots on the head and back of the silkworm. The frequency of the silkworm's body swaying within a preset time period was obtained based on the behavioral vectors of three key points: one of the markings on the silkworm's head, tail, and back; and The level of physical activity of silkworms within a preset time period is obtained by analyzing the behavioral vectors of the silkworm's head, tail, back, and two key points of its markings.

4. The intelligent identification method for the life state of silkworms according to claim 1, characterized in that, The pre-obtained healthy silkworm behavior data includes: the behavior data of healthy silkworms at each age within a preset period.

5. A smart identification system for the life status of silkworms, characterized in that, include: The image acquisition module is used to acquire videos of the growth of silkworms, which are in a real breeding environment and under intensive breeding conditions; The activity trajectory acquisition module is used to acquire the activity trajectory of each silkworm within a preset time period from the growth video. Specifically, it includes: converting the growth video into frame images according to the time sequence and preprocessing them; starting from the first frame image, performing key point detection on each silkworm according to the time sequence to obtain the key point coordinates of each silkworm. The key points include five key points: the head, tail, and three markings on the back of the silkworm; and obtaining the activity trajectory of each key point of each silkworm based on the key point coordinates of each silkworm obtained from the time sequence. Starting from the first frame image, keypoint detection is performed on each silkworm according to the time sequence to obtain the keypoint coordinates of each silkworm. Specifically, this includes: numbering each silkworm from the first frame image; and extracting features from the numbered silkworms in each frame image to obtain the keypoint coordinates. Specifically, this includes: extracting features from each frame image of the silkworms using a sequence model to obtain the keypoint coordinates of each type of keypoint. The behavior data acquisition module determines the behavior data of each silkworm based on its activity trajectory. The behavior data includes the relative crawling distance, head shaking frequency, body shaking frequency, and body activity level of the silkworm within the preset time period. The identification module assigns the behavioral data of each silkworm to a behavioral vector and compares it with the pre-obtained standard values ​​for healthy silkworms to identify the life status of the silkworms.

6. A smart identification system for the life status of silkworms, characterized in that, The device includes a camera, a processor, and a memory, wherein the processor is interconnected with the camera and the memory, respectively. The camera is used to capture videos of the growth of silkworms, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method as described in any one of claims 1 to 4.

Images