A method and device for detecting the growth of edible fungi mycelium

Abstract

The present invention relates to the technical field of edible fungus hyphae detection, and more specifically, to a method and device for detecting the growth of edible fungi hyphae. The method, when detecting the growth of edible fungi hyphae cultured in a rectangular cultivation box, uses the cultivation box as a detection target; specifically, the method comprises the following steps: S1, acquiring a grayscale image of the detection target at different growth nodes during the growth of the edible fungi; S2, based on the grayscale image G of the current growth node i+1 and the grayscale image G of the previous growth node i , the mycelium growth potential of the edible fungus at the current growth node is detected. The device is used to implement the above method. The present invention can preferably realize automatic detection of mycelium growth potential.

Description

Technical Field

[0001] The invention relates to the technical field of edible fungus mycelium detection, and in particular to a method and a device for detecting the growth potential of edible fungus mycelium. Background Art

[0002] In the process of breeding and planting edible fungi, it is necessary to measure the growth of mycelium of edible fungi in order to screen out excellent strains or monitor the growth status of edible fungi. The measurement of mycelium growth mainly involves the measurement of mycelium growth rate, density, and robustness. Conventional measurement methods mostly rely on manual measurement of colony size, observation of colony density and color morphology, etc. This method is difficult to be objective and scientific due to the subjective factors of the observer, and the efficiency is relatively low. Summary of the invention

[0003] The invention provides a method for detecting the growth potential of edible fungi mycelium, which can overcome certain defects of the prior art.

[0004] According to a method for detecting the growth of edible fungi hyphae of the present invention, when detecting the growth of edible fungi hyphae cultured in a rectangular cultivation box, the cultivation box is used as a detection target; the method specifically comprises the following steps:

[0005] S1. At different growth nodes during the growth of edible fungi, grayscale images of the detection target are obtained;

[0006] S2, grayscale image G based on the current growth node i+1 and the grayscale image G of the previous growth node i , to detect the growth of mycelium of edible fungi at the current growth node.

[0007] Through the above means, the growth of hyphae can be better detected by image detection, thereby overcoming the shortcomings of conventional manual observation, such as insufficient objectivity of the detection results and relatively low detection efficiency.

[0008] Preferably, in step S2,

[0009] Set the first grayscale threshold G x and the second grayscale threshold G y , G x <G y ;

[0010] Get the grayscale value in the corresponding grayscale image that is higher than the first grayscale threshold G x A set of pixels is taken as the edible fungus growth area; any pixel point Px in the edible fungus growth area j The corresponding gray value is G j ;

[0011] Get the grayscale value in the corresponding grayscale image that is higher than the second grayscale threshold G y The pixel point set is taken as the dominant edible fungus growth area; any pixel point Px in the dominant edible fungus growth area k The corresponding gray value is G k ;

[0012] The detection of the mycelium growth potential of the edible fungus at the current growth node includes obtaining the mycelium growth rate Gr1, the mycelium density Gr2 and the mycelium solidity Gr3;

[0013]

[0014]

[0015]

[0016] Where M is the grayscale image G i+1 The total number of pixels in the edible fungus growth area in the grayscale image G i The total number of pixels in the edible fungus growth area;

[0017] in, is the grayscale image G i+1 The averaged grayscale of the edible fungus growth area in is the grayscale image G i The averaged grayscale of the edible fungus growth area in the figure;

[0018]

[0019]

[0020] in, is the grayscale image G i+1 The proportion of dominant edible fungi in is the grayscale image G i The proportion of dominant edible fungi in

[0021]

[0022]

[0023] Among them, M 0 is the grayscale image G i+1 The total number of pixels in the dominant edible fungus growth area, N 0 is the grayscale image G i The total number of pixels in the dominant edible fungus growth area.

[0024] Based on the above method, it is possible to quickly find and locate the edible fungus growth area and the dominant edible fungus growth area based on threshold judgment; then, based on the characteristics such as the pixel distribution in the grayscale image, the mycelium growth detection of the edible fungus at the current growth node can be realized, so it is simple and easy.

[0025] Preferably, weight coefficients α1, α2 and α3 are constructed, α1+α2+α3=1; the mycelium growth index Q is obtained, Q=α1*Gr1+α2*Gr2+α3*Gr3, "*" is a product operation. Therefore, a unique index value can be preferably obtained to characterize the mycelium growth, which is convenient for a more intuitive description of the growth changes of edible fungi.

[0026] Preferably, in step S1, a camera device is used to capture images of the detection target; for the same detection target, the relative posture between the detection target and the camera device when the detection target is first imaged is used as the reference posture, and the relative posture between the detection target and the camera device is controlled to be consistent with the reference posture in subsequent image capture. This ensures that the images captured at each growth node in the growth process of the edible fungus can have basically consistent image features, thereby better counteracting the reduction in detection accuracy caused by factors such as image distortion caused by inconsistent shooting angles.

[0027] As a preference,

[0028] For the original image I0 obtained when the image of the detection target is first collected, four feature points in the original image I0 are obtained; the four feature points are P1(x p1 ,y p1 )、P2(x p2 ,y p2 )、P3(x p3 ,y p3 ) and P4(x p4 ,y p4 ); wherein the feature points P1 and P2 are a pair of diagonal points, and the feature points P3 and P4 are another pair of diagonal points;

[0029] For any subsequent image acquisition of the detection target, the original image obtained Get the original image The four corresponding feature points in are T1(x T1 ,y T1 )、T2(x T2 ,y T2 )、T3(x T3 ,y T3 ) and T4(x T4 ,y T4 );

[0030] Construct the original image I0 feature matrix P and the original image The characteristic matrix T of

[0031]

[0032] Constructing the original image The scaling matrix Z between the original image I0,

[0033]

[0034] in,

[0035]

[0036]

[0037] Get the original image Compared with the rotation matrix R between the original image I0,

[0038]

[0039] Where K is the intrinsic parameter matrix of the camera device,

[0040] The spatial attitude of the camera device is adjusted by using u in the rotation matrix R as the heading angle and v as the pitch angle. After the spatial attitude adjustment of the camera device is completed, the image of the detection target is captured again, and the original image I obtained at this time is used as the i+1 As the original image of the corresponding growth node.

[0041] That is, in each subsequent image acquisition of the detection target, the image of the detection target can be acquired twice, wherein the image acquired for the first time can be used to correct the relative posture between the detection target and the camera device, and the image acquired for the second time is used as the basis for the final judgment of the mycelium growth; therefore, it can be better achieved that the original image of each grayscale image involved in the mycelium growth detection can have basically consistent image features.

[0042] As a preference,

[0043] Based on the same feature point extraction algorithm, the original image I0 and the original image are obtained. The four feature points and the four corresponding feature points in ;

[0044] The feature point extraction algorithm specifically includes the following steps:

[0045] Step S11: Detect the original image I0 or the original image The edge of the image;

[0046] Step S12: Detect each pixel within the edge of the image and obtain the first feature point P1 (x p1 ,y p1 ) or T1(x T1 ,y T1 );

[0047] Step S13: Detect each pixel located within the edge of the image and obtain the second feature point P2 (x p2 ,y p2 ) or T2(x T2 ,y T2 );

[0048] Step S14, obtain the third feature point P3 (x p3 ,y p3 ) or T3(x T3 ,y T3 ), and the fourth feature point P4(x p4 ,y p4 ) or T4(x T4 ,y T4 ).

[0049] Through the above, the first pair of diagonal points can be obtained first, and then the second pair of diagonal points can be better obtained based on the first pair of diagonal points, so that two pairs of orthogonally distributed diagonal points can be better obtained. The features of the two pairs of diagonal points on the captured image are obvious and can all be located within the field of view, so that image processing can be better facilitated and the scaling of the image in the row and column directions can be better characterized.

[0050] Preferably, in step S12, a loop traversal algorithm is used to traverse each pixel point located within the edge of the image by traversing row by row from top to bottom and column by column from left to right, thereby obtaining the first feature point P1 (x p1 ,y p1 ) or T1(x T1 ,y T1 ). Therefore, the acquisition of the first feature point can be achieved better, and due to the introduction of the loop traversal algorithm, the interference of discrete edges on feature point recognition can be better avoided.

[0051] Preferably, in step S13, a loop traversal algorithm is used to traverse each pixel point located within the edge of the image by traversing row by row from bottom to top and column by column from right to left, thereby obtaining the second feature point P2 (x p2 ,y p2 ) or T2(x T2 ,y T2). Similarly, the acquisition of the second feature point can be better realized, and due to the introduction of the loop traversal algorithm, the interference of discrete edges on the feature point recognition can be better avoided.

[0052] Preferably, in step S14, a characteristic formula f(d) is constructed:

[0053] f(d)=(y2-y1)x i -(x2-x1)y i +x2y1-x1y2;

[0054] With x1=x p1 , y1=y p1 , x2=x p2 , y2=y p2 Substitute the condition into the characteristic formula f(d) and take the coordinate point (x i ,y i ) as the feature point P3(x p3 ,y p3 ), the coordinate point (x i ,y i ) as the feature point P4(x p4 ,y p4 );

[0055] With x1=x T1 , y1=y T1 , x2=x T2 , y2=y T2 Substitute the condition into the characteristic formula f(d) and take the coordinate point (x i ,y i ) as the feature point T3(x T3 ,y T3 ), the coordinate point (x i ,y i ) as the feature point T4(x T4 ,y T4 ).

[0056] Through the above, the third and fourth feature points can be preferably obtained based on the distance formula.

[0057] In addition, the present invention also provides a device for detecting the growth of edible fungi hyphae, which includes a camera device and a processing device, wherein the camera device is used to realize image acquisition of the detection target, and the processing device is used to detect the growth of edible fungi hyphae at the current growth node based on the image acquired by the camera device. Therefore, automatic detection of the growth of hyphae can be preferably realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Schematic diagram of the detection method in Example 1. DETAILED DESCRIPTION

[0059] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0060] Example 1

[0061] Taking into account the growth detection of mycelium, the growth rate of mycelium can be detected based on the growth size of the colony; and considering that the mycelium of most edible fungi is white in the early stage of growth, the density and strength of the mycelium can be detected based on the depth of color, that is, the denser the mycelium, the whiter it is, and the stronger the mycelium, the whiter it is.

[0062] Therefore, this embodiment provides a method for detecting the growth of edible fungi hyphae based on image detection. Figure 1 When the method of this embodiment is used to detect the growth of mycelium of edible fungi cultured in a rectangular cultivation box, the cultivation box is used as the detection target (here, the entire cultivation box in which the edible fungi are cultivated is used as the detection target, and the rectangular shape of the cultivation box and the clear edge contour in the image can be used to better achieve the correction of the shooting angle described below); specifically, the following steps are included:

[0063] S1. At different growth nodes during the growth of edible fungi, grayscale images of the detection target are obtained;

[0064] S2, grayscale image G based on the current growth node i+1 and the grayscale image G of the previous growth node i , to detect the growth of mycelium of edible fungi at the current growth node.

[0065] Through the above means, the growth of hyphae can be better detected by image detection, thereby overcoming the shortcomings of conventional manual observation, such as insufficient objectivity of the detection results and relatively low detection efficiency.

[0066] As shown below, the acquisition of the grayscale image of the detection target can be achieved by first using a camera device to capture an RGB image as an original image, and then converting the R, G, and B values ​​of each pixel point into a grayscale value through a processing device. As for the conversion method or formula for converting the R, G, and B values ​​into grayscale values, the existing conventional conversion formula can be used, and it will not be described in detail in this embodiment.

[0067] In step S2,

[0068] Able to set the first gray threshold G xand the second grayscale threshold G y , G x <G y ;

[0069] Get the grayscale value in the corresponding grayscale image that is higher than the first grayscale threshold G x A set of pixels is taken as the edible fungus growth area; any pixel point Px in the edible fungus growth area j The corresponding gray value is G j ;

[0070] Get the grayscale value in the corresponding grayscale image that is higher than the second grayscale threshold G y The pixel point set is taken as the dominant edible fungus growth area; any pixel point Px in the dominant edible fungus growth area k The corresponding gray value is G k ;

[0071] The detection of the mycelium growth potential of the edible fungus at the current growth node includes obtaining the mycelium growth rate Gr1, the mycelium density Gr2 and the mycelium solidity Gr3;

[0072]

[0073]

[0074]

[0075] Where M is the grayscale image G i+1 The total number of pixels in the edible fungus growth area in the grayscale image G i The total number of pixels in the edible fungus growth area;

[0076] in, is the grayscale image G i+1 The averaged grayscale of the edible fungus growth area in is the grayscale image G i The averaged grayscale of the edible fungus growth area in the figure;

[0077]

[0078]

[0079] in, is the grayscale image G i+1 The proportion of dominant edible fungi in is the grayscale image G i The proportion of dominant edible fungi in

[0080]

[0081]

[0082] Among them, M 0 is the grayscale image G i+1 The total number of pixels in the dominant edible fungus growth area, N 0 is the grayscale image G i The total number of pixels in the dominant edible fungus growth area.

[0083] Based on the above method, it is possible to quickly find and locate the edible fungus growth area and the dominant edible fungus growth area based on threshold judgment; then, based on the characteristics such as the pixel distribution in the grayscale image, the mycelium growth detection of the edible fungus at the current growth node can be realized, so it is simple and easy.

[0084] It is understandable that the culture medium or culture soil of edible fungi is dark (smaller gray value), while the mycelium of edible fungi is white (larger gray value), so the threshold determination method can be used to better detect the pixel points corresponding to the mycelium. x By filtering out the pixel points whose grayscale value is higher than the second grayscale threshold G y The pixel point set can better screen out the pixel points belonging to the mycelium of the dominant edible fungus; it can be understood that the mycelium of the dominant edible fungus has a whiter chromaticity.

[0085] And, it can be understood that the first gray threshold G x and the second grayscale threshold G y Can be set according to empirical data.

[0086] At the same time, in this embodiment, weight coefficients α1, α2 and α3 can be constructed, α1+α2+α3=1; the mycelium growth index Q is obtained, Q=α1*Gr1+α2*Gr2+α3*Gr3, "*" is a product operation. Therefore, a unique index value can be preferably obtained to characterize the mycelium growth, which is convenient for a more intuitive description of the growth changes of edible fungi.

[0087] Among them, the weight coefficients α1, α2 and α3 can be obtained based on experience.

[0088] In addition, in step S1, a camera device can be used to capture images of the detection target; for the same detection target, the relative posture between the detection target and the camera device when the detection target is first imaged is used as the reference posture, and the relative posture between the detection target and the camera device is controlled to be consistent with the reference posture in subsequent image acquisitions. This ensures that the images captured at each growth node in the growth process of the edible fungus can have basically consistent image features, thereby better counteracting the reduction in detection accuracy caused by factors such as image distortion caused by inconsistent shooting angles.

[0089] in:

[0090] For the original image I0 obtained when the image of the detection target is first collected, four feature points in the original image I0 are obtained; the four feature points are P1(x p1 ,y p1 )、P2(x p2 ,y p2 )、P3(x p3 ,y p3 ) and P4(x p4 ,y p4 ); wherein the feature points P1 and P2 are a pair of diagonal points, and the feature points P3 and P4 are another pair of diagonal points;

[0091] For any subsequent image acquisition of the detection target, the original image obtained Get the original image The four corresponding feature points in are T1(x T1 ,y T1 )、T2(x T2 ,y T2 )、T3(x T3 ,y T3 ) and T4(x T4 ,y T4 );

[0092] Construct the original image I0 feature matrix P and the original image The characteristic matrix T of

[0093]

[0094] Constructing the original image The scaling matrix Z between the original image I0,

[0095]

[0096] in,

[0097]

[0098]

[0099] Get the original image Compared with the rotation matrix R between the original image I0,

[0100]

[0101] Where K is the intrinsic parameter matrix of the camera device,

[0102] The spatial attitude of the camera device is adjusted by using u in the rotation matrix R as the heading angle and v as the pitch angle. After the spatial attitude adjustment of the camera device is completed, the image of the detection target is captured again, and the original image I obtained at this time is used as the i+1 As the original image of the corresponding growth node.

[0103] That is, in each subsequent image acquisition of the detection target, the image of the detection target can be acquired twice, wherein the image acquired for the first time can be used to correct the relative posture between the detection target and the camera device, and the image acquired for the second time is used as the basis for the final judgment of the mycelium growth; therefore, it can be better achieved that the original image of each grayscale image involved in the mycelium growth detection can have basically consistent image features.

[0104] It can be understood that the feature point P1(x p1 ,y p1 ) and the corresponding feature point T1(x T1 ,y T1 ) are the leftmost and topmost pixels in the corresponding image, and the feature point P2(x p2 ,y p2 ) and the corresponding feature point T2(x T2 ,y T2 ) are the rightmost and bottommost pixels in the corresponding image. This structure is related to the rectangular characteristics of the cultivation box, that is, the relative posture between the detection target and the camera device can be corrected based on the positions of the four vertex corners of the cultivation box.

[0105] It can be understood that the camera device in this embodiment can be set at a fixed height through a gimbal, and the shooting angle of the camera device can be automatically adjusted by using u in the rotation matrix R as the heading angle and v as the pitch angle as the control instruction of the gimbal.

[0106] The heading angle u in this embodiment refers to the offset between the shooting axis of the monitoring camera and the horizontal direction, and the pitch angle v in this embodiment refers to the offset between the shooting axis of the monitoring camera and the vertical direction.

[0107] In this embodiment, the original image I0 and the original image I1 can be obtained based on the same feature point extraction algorithm. The four feature points and the four corresponding feature points in ;

[0108] The feature point extraction algorithm specifically includes the following steps:

[0109] Step S11: Detect the original image I0 or the original image The edge of the image;

[0110] Step S12: Detect each pixel within the edge of the image and obtain the first feature point P1 (x p1 ,y p1 ) or T1(x T1 ,y T1 );

[0111] Step S13: Detect each pixel located within the edge of the image and obtain the second feature point P2 (x p2 ,y p2 ) or T2(x T2 ,y T2 );

[0112] Step S14, obtain the third feature point P3 (x p3 ,y p3 ) or T3(x T3 ,y T3 ), and the fourth feature point P4(x p4 ,y p4 ) or T4(x T4 ,y T4 ).

[0113] Through the above, the first pair of diagonal points can be obtained first, and then the second pair of diagonal points can be better obtained based on the first pair of diagonal points, so that two pairs of orthogonally distributed diagonal points can be better obtained. The features of the two pairs of diagonal points on the captured image are obvious and can all be located within the field of view, so that image processing can be better facilitated and the scaling of the image in the row and column directions can be better characterized.

[0114] In step S11 of this embodiment, the detection of the image edge can be realized based on conventional operators such as the Canny operator, so the edge recognition of the cultivation box can be realized preferably.

[0115] In step S12 of this embodiment, a loop traversal algorithm can be used, for example, to traverse each pixel point located within the edge of the image row by row from top to bottom and column by column from left to right, thereby obtaining the first feature point P1 (x p1 ,yp1 ) or T1(x T1 ,y T1 ). Therefore, the acquisition of the first feature point can be achieved better, and due to the introduction of the loop traversal algorithm, the interference of discrete edges on feature point recognition can be better avoided.

[0116] In step S13 of this embodiment, a loop traversal algorithm can be used to traverse each pixel point located within the edge of the image by traversing row by row from bottom to top and column by column from right to left, thereby obtaining the second feature point P2 (x p2 ,y p2 ) or T2(x T2 ,y T2 ). Similarly, the acquisition of the second feature point can be better realized, and due to the introduction of the loop traversal algorithm, the interference of discrete edges on the feature point recognition can be better avoided.

[0117] In step S14 of this embodiment, the characteristic formula f(d) can be constructed:

[0118] f(d)=(y2-y1)x i -(x2-x1)y i +x2y1-x1y2;

[0119] With x1=x p1 , y1=y p1 , x2=x p2 , y2=y p2 Substitute the condition into the characteristic formula f(d) and take the coordinate point (x i ,y i ) as the feature point P3(x p3 ,y p3 ), the coordinate point (x i ,y i ) as the feature point P4(x p4 ,y p4 );

[0120] With x1=x T1 , y1=y T1 , x2=x T2 , y2=y T2 Substitute the condition into the characteristic formula f(d) and take the coordinate point (x i ,y i ) as the feature point T3(x T3 ,y T3 ), the coordinate point (x i ,y i) as the feature point T4(x T4 ,y T4 ).

[0121] Through the above, the third and fourth feature points can be preferably obtained based on the distance formula.

[0122] It is further explained here that after the first and second feature points are determined, the equation of the straight line L connecting the two points can be expressed as:

[0123] (y2-y1)x-(x2-x1)y+x2y1-x1y2=0.

[0124] Any pixel (x i ,y i ) to the straight line L can be expressed as:

[0125]

[0126] The denominator in the above distance formula is a constant, so the characteristic formula f(d) can be simplified in this embodiment, thereby reducing the amount of calculation. By obtaining the maximum and minimum values ​​of the characteristic formula f(d), the third and fourth characteristic points can be obtained preferably.

[0127] In addition, in order to implement the method of this embodiment, this embodiment also provides an edible fungus hyphae growth detection device, which includes a camera device and a processing device, the camera device is used to realize image acquisition of the detection target, and the processing device is used to detect the hyphae growth of the edible fungus at the current growth node based on the image acquired by the camera device. Therefore, the automatic detection of hyphae growth can be better achieved.

[0128] The present invention and its embodiments are described schematically above, and the description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. Therefore, if a person skilled in the art is inspired by it and designs a structural method and an embodiment similar to the technical solution without creativity without departing from the purpose of the invention, they shall all fall within the protection scope of the present invention.

Claims

1. A method for detecting the growth of edible fungi hyphae, wherein the method detects the growth of edible fungi hyphae cultured in a rectangular cultivation box, with the cultivation box as the detection target; the method specifically comprises the following steps: S1. At different growth nodes during the growth of edible fungi, grayscale images of the detection target are obtained; S2, grayscale image G based on the current growth node i+1 and the grayscale image G of the previous growth node i , detect the mycelium growth of edible fungi at the current growth node; In step S2, Set the first grayscale threshold G x and the second grayscale threshold G y , G x <G y ; Get the grayscale value in the corresponding grayscale image that is higher than the first grayscale threshold G x A set of pixels is taken as the edible fungus growth area; any pixel point Px in the edible fungus growth area j The corresponding gray value is G j ; Get the grayscale value in the corresponding grayscale image that is higher than the second grayscale threshold G y The pixel point set is taken as the dominant edible fungus growth area; any pixel point Px in the dominant edible fungus growth area k The corresponding gray value is G k ; The detection of the mycelium growth potential of the edible fungus at the current growth node includes obtaining the mycelium growth rate Gr1, the mycelium density Gr2 and the mycelium solidity Gr3; in, M is the grayscale image G i+1 The total number of pixels in the edible fungus growth area in the grayscale image G i The total number of pixels in the edible fungus growth area; in, is the grayscale image G i+1 The averaged grayscale of the edible fungus growth area in is the grayscale image G i The averaged grayscale of the edible fungus growth area in the figure; in, is the grayscale image G i+1 The proportion of dominant edible fungi in is the grayscale image G i The proportion of dominant edible fungi in Among them, M 0 is the grayscale image G i+1 The total number of pixels in the dominant edible fungus growth area, N 0 is the grayscale image G i The total number of pixels in the dominant edible fungus growth area.

2. The method for detecting the growth potential of edible fungi mycelium according to claim 1, characterized in that: Construct weight coefficients α1, α2 and α3, α1+α2+α3=1; obtain the mycelium growth index Q, Q=α1*Gr1+α2*Gr2+α3*Gr3, "*" represents the product operation.

3. The method for detecting the growth potential of edible fungi mycelium according to claim 1, characterized in that: In step S1, a camera device is used to capture images of the detection target; for the same detection target, the relative posture between the detection target and the camera device when the image of the detection target is captured for the first time is used as the reference posture, and in subsequent image captures, the relative posture between the detection target and the camera device is controlled to be consistent with the reference posture.

4. The method for detecting the growth potential of edible fungi mycelium according to claim 3, characterized in that: For the original image I0 obtained when the image of the detection target is first collected, four feature points in the original image I0 are obtained; the four feature points are P1(x p1 ,y p1 )、P2(x p2 ,y p2 )、P3(x p3 ,y p3 ) and P4(x p4 ,y p4 ); wherein the feature points P1 and P2 are a pair of diagonal points, and the feature points P3 and P4 are another pair of diagonal points; For any subsequent image acquisition of the detection target, the original image obtained Get the original image The four corresponding feature points in are T1(x T1 ,y T1 )、T2(x T2 ,y T2 )、T3(x T3 ,y T3 ) and T4(x T4 ,y T4 ); Construct the original image I0 feature matrix P and the original image The characteristic matrix T of Constructing the original image The scaling matrix Z between the original image I0, in, Get the original image Compared with the rotation matrix R between the original image I0, Where K is the intrinsic parameter matrix of the camera device, The spatial attitude of the camera device is adjusted by using u in the rotation matrix R as the heading angle and v as the pitch angle. After the spatial attitude adjustment of the camera device is completed, the image of the detection target is captured again, and the original image I obtained at this time is used as the i+1 As the original image of the corresponding growth node.

5. The method for detecting the growth potential of edible fungi mycelium according to claim 4, characterized in that: Based on the same feature point extraction algorithm, the original image I0 and the original image are obtained. The four feature points and the four corresponding feature points in ; The feature point extraction algorithm specifically includes the following steps: Step S11: Detect the original image I0 or the original image The edge of the image; Step S12: Detect each pixel within the edge of the image and obtain the first feature point P1 (x p1 ,y p1 ) or T1(x T1 ,y T1 ); Step S13: Detect each pixel located within the edge of the image and obtain the second feature point P2 (x p2 ,y p2 ) or T2(x T2 ,y T2 ); Step S14, obtain the third feature point P3 (x p3 ,y p3 ) or T3(x T3 ,y T3 ), and the fourth feature point P4(x p4 ,y p4 ) or T4(x T4 ,y T4 ).

6. A method for detecting the growth potential of edible fungi mycelium according to claim 5, characterized in that: In step S12, a loop traversal algorithm is used to traverse each pixel point located within the edge of the image by traversing row by row from top to bottom and column by column from left to right, thereby obtaining the first feature point P1 (x p1 ,y p1 ) or T1(x T1 ,y T1 ).

7. The method for detecting the growth potential of edible fungi mycelium according to claim 5, characterized in that: In step S13, a loop traversal algorithm is used to traverse each pixel point within the edge of the image by traversing row by row from bottom to top and column by column from right to left, thereby obtaining the second feature point P2 (x p2 ,y p2 ) or T2(x T2 ,y T2 ).

8. The method for detecting the growth potential of edible fungi mycelium according to claim 5, characterized in that: In step S14, construct the characteristic formula f(d), f(d)=(y2-y1)x i -(x2−x1)y i +x2y1-x1y2: With x1=x p1 , y1=y p1 , x2=x p2 , y2=y p2 Substitute the condition into the characteristic formula f(d) and take the coordinate point (x i ,y i ) as the feature point P3(x p3 ,y p3 ), the coordinate point (x i ,y i ) as the feature point P4(x p4 ,y p4 ); With x1=x T1 , y1=y T1 , x2=x T2 , y2=y T2 Substitute the condition into the characteristic formula f(d) and take the coordinate point (x i ,y i ) as the feature point T3(x T3 ,y T3 ), the coordinate point (x i ,y i ) as the feature point T4(x T4 ,y T4 ).

Images