Planning method and system for hair follicle extraction path, and storage medium

Abstract

Provided in the present invention are a planning method and system for a hair follicle extraction path, and a computer-readable storage medium. The planning method for a hair follicle extraction path comprises the following steps: acquiring a hair map comprising a plurality of hair follicle units; on the basis of a preset local planning area radius, performing a first neighborhood search on a preset initial hair follicle unit on the hair map, so as to determine a plurality of candidate hair follicle units; respectively determining a linear distance, an upward-direction projection distance and a forward-direction projection distance from each candidate hair follicle unit to the initial hair follicle unit, wherein an upward direction is opposite to a gravity direction, and a forward direction is perpendicular to the upward direction; sequentially checking the candidate hair follicle units in ascending order of upward-direction projection distances; and in response to the linear distance from any candidate hair follicle unit to the initial hair follicle unit being less than a preset adjacent distance upper limit and the forward-direction projection distance from the candidate hair follicle unit to the initial hair follicle unit being positive, determining the candidate hair follicle unit to be a target hair follicle unit to be extracted.

Description

A hair follicle extraction path planning method, system and storage medium Technical Field

[0001] The present invention relates to the technical field of hair follicle extraction, and in particular to a hair follicle extraction path planning method, a hair follicle extraction path planning system, and a computer-readable storage medium. Background Art

[0002] During hair transplant surgery, doctors need to rationally plan the number of hair follicles to be extracted and develop a plan for re-implanting the follicles, so that no traces of hair removal can be seen in the donor area and the recipient area (i.e., the area of ​​hair loss) is significantly improved. In addition, the planning of the hair follicle extraction path needs to be based on a certain density and spacing so that some hair in the donor area can be retained to maintain beauty, and both efficiency and coverage must be achieved at the same time. Here, efficiency refers to the optimal extraction efficiency within an area to be extracted, and coverage refers to the maximum number of hair follicles that can be extracted in an area to be extracted. In addition, there is the problem of blood overflow during the extraction process, and blood will flow downward according to the direction of gravity. Therefore, the planning of the hair follicle extraction path must also avoid extraction in the blood.

[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides a hair follicle extraction path planning technology, which can effectively improve the efficiency and coverage of hair follicle extraction while maintaining the interval of hair follicle extraction and avoid extracting hair follicles in the blood.

[0004] Summary of the Invention

[0005] The following is a brief summary of one or more aspects to provide a basic understanding of these aspects. This summary is not an exhaustive overview of all conceivable aspects and is neither intended to identify key or critical elements of all aspects nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that will be provided later.

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a hair follicle extraction path planning technology, which can effectively improve the efficiency and coverage of hair follicle extraction while maintaining the interval of hair follicle extraction and avoid extracting hair follicles in the blood.

[0007] Specifically, the hair follicle extraction path planning method provided in accordance with the first aspect of the present invention includes the following steps: obtaining a hair map including a plurality of follicular units; performing a first neighborhood search on a preset initial follicular unit on the hair map based on a preset local planning area radius to determine a plurality of candidate follicular units; determining a straight-line distance, an upward projection distance, and a front projection distance from each candidate follicular unit to the initial follicular unit, respectively, wherein the upward direction is opposite to the direction of gravity and the front direction is perpendicular to the upward direction; sequentially examining each candidate follicular unit in ascending order of the upward projection distance; and in response to any candidate follicular unit having a straight-line distance from the initial follicular unit less than a preset upper limit of the adjacent distance and a positive front projection distance from the candidate follicular unit to the initial follicular unit, determining the candidate follicular unit as a target follicular unit to be extracted.

[0008] Preferably, in one embodiment of the present invention, the following steps are further included: in response to the absence of a candidate follicle unit having a positive front projection distance to the initial follicle unit within the range of the upper limit of the adjacent distance, the candidate follicle unit having the smallest straight-line distance to the initial follicle unit is determined as the target follicle unit to be extracted, and the front direction is reversed.

[0009] Preferably, in an embodiment of the present invention, after determining the target follicular unit, the planning method further comprises the following steps: setting the target follicular unit as a new initial follicular unit, and re-implementing the planning method to determine the next target follicular unit to be extracted.

[0010] Preferably, in one embodiment of the present invention, the step of performing a first neighborhood search on a preset initial follicular unit on the hair map based on a preset local planning area radius to determine a plurality of candidate follicular units includes: performing the first neighborhood search on the initial follicular unit on the hair map to screen out a plurality of first candidate follicular units whose straight-line distances to the initial follicular unit are less than the local planning area radius; and excluding, from the plurality of first candidate follicular units, follicular units whose straight-line distances to the initial follicular unit are less than a preset expansion circle radius to determine a plurality of second candidate follicular units.

[0011] Preferably, in one embodiment of the present invention, the step of obtaining a hair map including a plurality of follicular units includes: obtaining a hair map including point cloud data of a plurality of hairs; clustering the point cloud data based on a preset minimum number of points m to obtain a first temporary cluster having at least m points within a preset first neighborhood radius; checking whether each point in the first temporary cluster is a core point of another second temporary cluster; in response to a check result that any point in the first temporary cluster is a core point of another second temporary cluster, merging the first temporary cluster and the second temporary cluster to generate a new first temporary cluster; and in response to a check result that none of the points in the first temporary cluster is a core point of another second temporary cluster, upgrading each of the remaining temporary clusters to a cluster to indicate the follicular units included in the hair map.

[0012] Preferably, in one embodiment of the present invention, the step of obtaining a hair map including point cloud data of a plurality of hairs includes: obtaining and parsing a plurality of hair images from a plurality of camera perspectives to respectively determine a root point and a tip point of each hair in each of the hair images; constructing a point cloud structure based on the root point and the tip point of each hair to determine point cloud data of each hair image; and fusing the point cloud data of each hair image into the same perspective to obtain the hair map including point cloud data of the plurality of hairs.

[0013] Preferably, in one embodiment of the present invention, the step of constructing a point cloud structure based on the root point and the tip point of each hair to determine the point cloud data of each hair image includes: predefining the hair direction based on prior information from camera scanning to preliminarily determine the root point and the tip point of each hair; performing a second neighborhood search using the root point as a search point, and calculating the hair direction gradient of each root point in the point cloud data within the second neighborhood radius based on the characteristic that the hair growth direction within the neighborhood continuously changes; in response to the hair direction gradient of any root point within the second neighborhood radius deviating from the average hair direction gradient of each root point within the second neighborhood radius, swapping the root point and the tip point of the point cloud structure, and recalculating the hair direction gradient of each root point in the point cloud data within the second neighborhood radius; and in response to the absence of gradient outliers that deviate from the average hair direction gradient within the second neighborhood radius for each root point in the point cloud data, determining the point cloud data of the hair image.

[0014] Preferably, in one embodiment of the present invention, the step of fusing the point cloud data of each hair image into the same perspective to obtain the hair map comprising the point cloud data of the plurality of hairs comprises: uniformly transforming the point cloud data of each hair image into a reference coordinate system; using a frame of point cloud data as a reference frame and creating a corresponding point list of reference frame points for each hair root point in the reference frame; selecting a matching frame from the unmatched point cloud data and calculating a corresponding point set between the matching frame and the reference frame in the reference coordinate system, adding the matching frame points in the corresponding point set to the corresponding point list of the corresponding reference frame points, adding each hair root point for which no corresponding reference frame point is found in the matching frame to the reference frame, and creating a new corresponding point list for the hair root point; in response to completing the matching of the point cloud data of each frame, treating each reference frame point in the reference frame as a hair entity and using the reference frame point and all points in its corresponding point list as a measurement sequence of the hair entity; and determining the spatial position of the hair root point of each hair entity from the perspective of the reference coordinate system based on the measurement sequence of each hair entity.

[0015] Furthermore, the hair follicle extraction path planning system provided in accordance with the second aspect of the present invention includes a memory and a processor. The memory stores computer instructions. The processor is connected to the memory and configured to execute the computer instructions stored in the memory to implement the hair follicle extraction path planning method provided in any of the above embodiments.

[0016] Furthermore, the computer-readable storage medium provided according to the third aspect of the present invention stores computer instructions, which, when executed by a processor, implement the hair follicle extraction path planning method provided in any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above features and advantages of the present invention will be better understood after reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily drawn to scale, and components with similar related properties or characteristics may have the same or similar reference numerals.

[0018] FIG1 shows a flow chart of a method for planning a hair follicle extraction path according to some embodiments of the present invention.

[0019] FIG2 shows a flowchart of determining point cloud data of each hair image according to some embodiments of the present invention.

[0020] FIG3 shows a flowchart of fusing point cloud data of multi-view hair images according to some embodiments of the present invention.

[0021] FIG4 shows a flowchart of obtaining a hair map including a plurality of follicular units according to some embodiments of the present invention. DETAILED DESCRIPTION

[0022] The following specific embodiments illustrate the embodiments of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Although the description of the present invention will be introduced in conjunction with the preferred embodiment, this does not mean that the features of this invention are limited to this embodiment. On the contrary, the purpose of introducing the invention in conjunction with the embodiment is to cover other options or modifications that may be extended based on the claims of the present invention. In order to provide a deep understanding of the present invention, the following description will include many specific details. The present invention can also be implemented without using these details. In addition, in order to avoid confusion or blurring the focus of the present invention, some specific details will be omitted in the description.

[0023] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0024] Furthermore, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," and "vertical" used in the following description should be understood to refer to the orientations depicted in that section and the accompanying drawings. These relative terms are used solely for convenience of description and do not necessarily imply that the devices described herein must be manufactured or operated in a specific orientation. Therefore, they should not be construed as limiting the present invention.

[0025] It will be understood that although the terms "first," "second," "third," etc. may be used herein to describe various components, regions, layers, and / or portions, these components, regions, layers, and / or portions should not be limited by these terms, and these terms are merely used to distinguish different components, regions, layers, and / or portions. Thus, a first component, region, layer, and / or portion discussed below may be referred to as a second component, region, layer, and / or portion without departing from some embodiments of the present invention.

[0026] As mentioned above, during hair transplant surgery, the follicle extraction path planning must be based on a certain density and spacing to preserve some hair in the donor area for aesthetic reasons, while also achieving both efficiency and coverage. Furthermore, the extraction process poses the risk of blood spillage, as blood flows downward due to gravity. Therefore, the follicle extraction path planning also needs to avoid extraction within the bloodstream.

[0027] In order to overcome the above-mentioned defects of the prior art, the present invention provides a hair follicle extraction path planning technology, which can effectively improve the efficiency and coverage of hair follicle extraction while maintaining the interval of hair follicle extraction and avoid extracting hair follicles in the blood.

[0028] In some non-limiting embodiments, the hair follicle extraction path planning method provided in the first aspect of the present invention can be implemented via the hair follicle extraction path planning system provided in the second aspect of the present invention. Specifically, the hair follicle extraction path planning system can be configured with a memory and a processor. The memory includes, but is not limited to, the computer-readable storage medium provided in the third aspect of the present invention, which stores computer instructions. The processor is connected to the memory and configured to execute the computer instructions stored in the memory to implement the hair follicle extraction path planning method provided in the first aspect of the present invention.

[0029] Please refer to FIG1 , which shows a flow chart of a method for planning a hair follicle extraction path according to some embodiments of the present invention.

[0030] As shown in FIG1 , in the process of planning a hair follicle extraction path, the planning system may first obtain a hair map including a plurality of hair follicle units.

[0031] In some embodiments, the hair map can be constructed by a planning system based on hair images. To construct the hair map, the planning system can first capture multiple hair images from multiple camera perspectives using multiple cameras (e.g., binocular cameras), then perform preprocessing and image analysis to determine the three-dimensional coordinates of the root and tip of each hair in each hair image based on a reference point (e.g., a tensioner tag). The planning system can then construct a point cloud structure based on the root and tip coordinates of each hair, and combine the point cloud structures of each hair to determine the point cloud data for each hair image.

[0032] Please refer to FIG. 2 for details, which shows a flowchart of determining point cloud data of each hair image according to some embodiments of the present invention.

[0033] As shown in Figure 2, when determining the point cloud data for each hair image, the planning system can first predefine the hair direction based on prior information from the camera scan to preliminarily determine the root and tip points of each hair. For example, the planning system can default the camera scan direction to the normal hand-eye direction (i.e., the eye's viewing direction is consistent with the extracted direction). The direction with an angle of no more than 90 degrees with the +y direction of the camera during scanning is defined as the direction from the hair root to the hair tip, and the root and tip points of each hair are determined.

[0034] The planning system then constructs a point cloud for each hair based on the coordinates of its root and tip points. It then performs a second neighborhood search using the root as the search point. Based on the continuous variation in hair growth direction within this neighborhood, the system calculates the hair direction gradient within the second neighborhood radius for each root point in the point cloud data. Here, the "neighborhood" refers to the area within a certain radius of the root point, and the radius can be customized based on actual needs.

[0035] Afterwards, the planning system can calculate the average hair direction gradient of each hair root point within its second neighborhood radius based on the hair direction gradient of each hair root point in the point cloud data, and perform statistical filtering based on the average hair direction gradient.

[0036] Specifically, during the statistical filtering process, the planning system can traverse each hair in the hair point cloud and set the hair direction of its root point as v i , the direction of other hairs within the second neighborhood radius is v j , to calculate v i With v j The angle α ij As the directional gradient, and the angle α ij Find the root point p i The average directional gradient of:

[0037] The planning system can then calculate the average hair orientation gradient for the entire hair point cloud:

[0038] Calculate the statistical value (i.e., mean value and standard deviation) of the directional gradient of the point cloud data of the entire hair image:

[0039] And determine the filtering threshold according to the custom coefficient λ:

[0040] α th =α avg +λ·α std

[0041] Afterwards, in response to any root point p i The hair direction gradient α within its second neighborhood radius i Less than the filtering threshold α th , the planning system can determine the root point p iIf the hair root point and hair tip point deviate too far from the gradient average, the hair root point and hair tip point of the point cloud structure are exchanged, and the hair direction gradient of each hair root point in the point cloud data within its second neighborhood radius is recalculated until each hair root point in the point cloud data has no gradient anomalies that deviate from the hair direction gradient average within its second neighborhood radius, so as to determine the point cloud data of the hair image.

[0042] By adopting the above method, the present invention can determine the three-dimensional coordinates of each end point of the hair using the tensioner tag as a reference point, and then accurately determine the root and tip of each hair line based on three-dimensional spatial information such as the hair direction gradient, thereby overcoming the defect that traditional visual recognition algorithms cannot accurately distinguish between hair roots and tips.

[0043] Furthermore, for multiple hair images acquired by multiple cameras from multiple camera perspectives, the planning system may preferably fuse the point cloud data of each hair image under the same perspective to obtain a hair map including point cloud data of multiple hairs.

[0044] Please refer to FIG3 for details, which shows a flowchart of fusing point cloud data of multi-view hair images according to some embodiments of the present invention.

[0045] As shown in Figure 3, when fusing point cloud data from various viewpoints, the planning system first transforms the point cloud data of each hair image into a unified reference coordinate system. It then uses a frame of point cloud data as a reference frame and creates a corresponding point list for each hair root point in the reference frame. This reference coordinate system includes, but is not limited to, the reference system of the label on the tensioner, the base reference system of the hair follicle extraction robot, and the reference system of a specific camera viewpoint.

[0046] The planning system can then select a matching frame from the unmatched point cloud data and calculate the corresponding point set between the matching frame and the reference frame using an iterative nearest neighbor (ICP) algorithm in the reference coordinate system. The matching frame points in the corresponding point set are added to the corresponding point list of the corresponding reference frame points. Each root point in the matching frame for which no corresponding reference frame point is found is added to the reference frame, and a new corresponding point list is created for each root point. In a non-limiting embodiment, corresponding point estimation can employ a mutual correspondence estimation method to ensure a one-to-one correspondence between the matching frame points and the reference frame points.

[0047] Afterwards, in response to completing the matching of the point cloud data of each frame, the planning system can regard each reference frame point in the reference frame as a hair entity, and use the reference frame point and all points in the corresponding point list as the measurement sequence of the hair entity, and then determine the spatial position of the root point of each hair entity from the perspective of the reference coordinate system based on the measurement sequence of each hair entity to obtain a hair map including point cloud data of multiple hairs.

[0048] Furthermore, when determining the spatial position of each hair entity's root point from the perspective of the reference coordinate system based on the measurement sequence of each hair entity, the planning system can first perform statistical filtering, straight-through filtering, or other filtering on the measurement sequence of the hair entity, and then average the measurement sequence to obtain the optimal measurement value for the hair entity. The planning system can then use this optimal measurement value to replace the original coordinate value of the hair root point in the reference frame, thereby more accurately determining the spatial position of the corresponding hair entity's root point from the perspective of the reference coordinate system.

[0049] Since the positioning accuracy of the reference system is very high, by averaging the measurement values ​​of each hair entity under multiple perspectives in a unified reference system to obtain the best measurement value, the present invention can effectively reduce the error of single, single-perspective measurement, thereby further improving the accuracy and precision of the hair map.

[0050] Please further refer to FIG. 4 , which shows a flowchart of obtaining a hair map including a plurality of follicular units according to some embodiments of the present invention.

[0051] As shown in FIG4 , after obtaining a hair map including point cloud data of multiple hairs, the planning system can use a density-based clustering method to divide the point cloud data of each hair in the hair map into follicle units, treating each dense area of ​​the hair as a cluster, and representing a follicle unit with a cluster.

[0052] Specifically, during the follicular unit segmentation process, the planning system can first cluster the point cloud data of multiple hairs in the hair map based on a preset minimum number of points m (e.g., m = 1) to obtain a first temporary cluster with at least m points within a preset first neighborhood radius. Here, the first neighborhood radius can be determined based on the maximum distance between adjacent hairs within a follicular unit in clinical anatomy.

[0053] After determining the first temporary cluster, the planning system can continue to check whether each point in the first temporary cluster is a core point of another second temporary cluster. Here, a core point refers to a point with at least m points within a neighborhood radius, and other points within the neighborhood of the core point are called boundary points. In response to the result of checking that any point in the first temporary cluster is a core point of another second temporary cluster, the planning system can determine that the density between the core points of the two temporary clusters is directly connected, thereby merging the first temporary cluster and the second temporary cluster to generate a new first temporary cluster.

[0054] This cycle continues until no point in any first temporary cluster is a core point in another second temporary cluster. The planning system then determines that all temporary clusters of densely connected core points in the hair map have been merged, and upgrades the remaining temporary clusters to clusters to indicate the follicular units included in the hair map. A cluster containing only one point indicates a single follicular unit, while a cluster containing multiple points indicates multiple follicular units. The number of points in the cluster indicates the number of hairs in the follicular unit.

[0055] By implementing the above method, the present invention can adapt to the actual demand of hair follicle extraction using the hair follicle unit as the minimum extraction unit, accurately divide the hair follicle units included in the hair map, and thus provide an accurate data basis for hair follicle extraction path planning.

[0056] Those skilled in the art will appreciate that the above-mentioned methods for constructing a hair map comprising multiple follicle units are merely some non-limiting embodiments provided by the present invention, intended to clearly illustrate the main concepts of the present invention and to provide some preferred solutions for improving the accuracy of hair follicle distribution in hair maps, and are not intended to limit the scope of protection of the present invention.

[0057] Optionally, in other embodiments, those skilled in the art may also construct a hair map describing the distribution of hair follicle units by other methods, or obtain a hair map including multiple hair follicle units by downloading or purchasing an existing hair map describing the distribution of hair follicle units. The specific acquisition method is not limited here.

[0058] Continuing with Figure 1, after obtaining a hair map comprising multiple follicular units, the planning system can select a preset initial follicular unit on the hair map and perform a first neighborhood search on the initial follicular unit based on a preset local planning area radius (denoted as R1) to identify multiple candidate follicular units. Here, the local planning area refers to the local search range centered on the initial follicular unit on the hair map. The local planning area radius R1 refers to the radius of the local search range centered on the initial follicular unit. The first neighborhood search can be implemented using a neighborhood search algorithm, including but not limited to a K-dimensional binary tree (KD-tree).

[0059] Furthermore, in some embodiments, the planning system may also be preferably configured with an expansion circle radius (denoted as R2). The expansion circle radius R2 indicates the minimum extraction interval between follicle units, and its value can be specifically determined based on factors such as maintaining aesthetics and reducing damage to the skin, and is generally 1 / 6 to 1 / 4 of the local planning area radius R1. During the first neighborhood search of the initial follicle unit on the hair map, the planning system can first screen out a plurality of first candidate follicle units whose straight-line distance to the initial follicle unit is less than the local planning area radius R1, and then screen out the follicle units whose straight-line distance to the initial follicle unit is less than the preset expansion circle radius R2 from the plurality of first candidate follicle units to determine a plurality of second candidate follicle units, thereby reducing damage to the hair supply area and weakening the traces of hair removal in the hair supply area.

[0060] Afterwards, the planning system can determine the straight-line distance d, the upward projection distance dy and the front projection distance dx of each candidate follicle unit to the initial follicle unit, and calculate the distance according to the minimum straight-line distance d. min Determine the upper limit of the adjacent distance. Here, the upward direction is opposite to the direction of gravity and indicates the direction opposite to the blood flow direction. The forward direction is perpendicular to the upward direction and indicates the main direction of search when planning the next follicle unit from the initial follicle unit. Technicians can determine the amplification factor c (usually 1.5 to 2) based on actual efficiency requirements and determine the upper limit of the adjacent distance R3 based on this amplification factor c = c *d min .

[0061] The planning system then sorts the candidate follicle units in ascending order of their upward projection distance dy and examines each candidate follicle unit in turn. If the straight-line distance d between any candidate follicle unit and the initial follicle unit is less than a preset upper limit R3 of the adjacent distance, and the forward projection distance between the candidate follicle unit and the initial follicle unit is positive (i.e., dx > 0), the planning system determines the candidate follicle unit as the next target follicle unit P to be extracted.

[0062] On the contrary, in response to the fact that there is no candidate follicle unit with a positive front projection distance to the initial follicle unit within the range of the adjacent distance upper limit R3, the planning system can determine the candidate follicle unit with the smallest straight-line distance d to the initial follicle unit as the next target follicle unit P to be extracted, and reverse the front direction.

[0063] Afterwards, the planning system can also set the target follicle unit P as a new initial follicle unit and re-implement the planning method to continue to determine the next target follicle unit to be extracted until the screening and planning of all follicle units in the hair map are completed.

[0064] In this way, by checking each candidate follicle unit in order from small to large in the upward projection distance, and then judging whether the front projection distance from the candidate follicle unit to the initial follicle unit is positive, the hair follicle extraction path planning method provided by the present invention can improve efficiency and coverage while avoiding extracting hair follicles in the blood, thereby meeting the path planning requirements of hair transplant surgery.

[0065] Although the above methods are illustrated and described as a series of acts for simplicity of explanation, it is to be understood and appreciated that these methods are not limited by the order of the acts, as some acts may occur in a different order and / or concurrently with other acts from those illustrated and described herein or not illustrated and described herein but understandable to those skilled in the art according to one or more embodiments.

[0066] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for planning a hair follicle extraction path, characterized in that: The following steps are involved: obtaining a hair map including a plurality of follicular units; Based on a preset local planning area radius, performing a first neighborhood search on a preset initial hair follicle unit on the hair map to determine a plurality of candidate hair follicle units; Respectively determine the straight-line distance, the upward projection distance and the front projection distance from each candidate follicle unit to the initial follicle unit, wherein the upward direction is opposite to the gravity direction, and the front direction is perpendicular to the upward direction; In order of the upward projection distance from small to large, the candidate hair follicle units are tested in sequence; as well as In response to the straight-line distance from any of the candidate follicle units to the initial follicle unit being less than a preset upper limit of the adjacent distance, and the front-direction projection distance from the candidate follicle unit to the initial follicle unit being positive, the candidate follicle unit is determined as a target follicle unit to be extracted; In response to the fact that there is no candidate follicle unit with a positive front direction projection distance to the initial follicle unit within the range of the adjacent distance upper limit, the candidate follicle unit with the smallest straight-line distance to the initial follicle unit is determined as the target follicle unit to be extracted, and the front direction is reversed.

2. The planning method according to claim 1, characterized in that: After determining the target follicle unit, the planning method further comprises the following steps: The target follicle unit is set as a new initial follicle unit, and the planning method is re-implemented to determine the next target follicle unit to be extracted.

3. The planning method according to claim 1, characterized in that: The step of performing a first neighborhood search on a preset initial hair follicle unit on the hair map based on a preset local planning area radius to determine a plurality of candidate hair follicle units comprises: Performing the first neighborhood search on the initial follicle unit on the hair map to screen a plurality of first candidate follicle units whose straight-line distance to the initial follicle unit is less than the radius of the local planning area; and The hair follicle units whose straight-line distance to the initial hair follicle unit is less than a preset expansion circle radius are screened out from the plurality of first candidate hair follicle units to determine a plurality of second candidate hair follicle units.

4. The planning method according to claim 1, characterized in that: The step of obtaining a hair map including a plurality of hair follicle units comprises: Obtaining a hair map including point cloud data of a plurality of hairs; Based on the preset minimum number of points m, the point cloud data is clustered to obtain a preset The first temporary cluster with at least m points within a neighborhood radius; Check whether each point in the first temporary cluster is a core point of another second temporary cluster; In response to a check result that any point in the first temporary cluster is a core point of another second temporary cluster, merging the first temporary cluster and the second temporary cluster to generate a new first temporary cluster; and In response to a check result that each point in the first temporary cluster is not a core point of another second temporary cluster, each of the remaining temporary clusters is upgraded to a cluster to indicate a follicle unit included in the hair map.

5. The planning method according to claim 4, characterized in that: The step of obtaining a hair map including point cloud data of a plurality of hairs comprises: Acquire and analyze multiple hair images under multiple camera viewing angles to respectively determine the root point and the tip point of each hair in each hair image; Constructing a point cloud structure according to the root point and the tip point of each hair to determine the point cloud data of each hair image; and The point cloud data of each of the hair images are fused under the same viewing angle to obtain the hair map including the point cloud data of the plurality of hairs.

6. The planning method according to claim 5, characterized in that: The step of constructing a point cloud structure according to the root points and the tip points of each hair to determine the point cloud data of each hair image comprises: Predefine the hair direction according to the prior information scanned by the camera to preliminarily determine the root point and the tip point of each hair; Performing a second neighborhood search with the hair root point as the search point, and calculating the hair direction gradient of each hair root point in the point cloud data within the second neighborhood radius based on the characteristic that the hair growth direction in the neighborhood changes continuously; In response to the hair direction gradient of any of the hair root points within its second neighborhood radius deviating from the average hair direction gradient of each of the hair root points within its second neighborhood radius, exchanging the hair root point and the hair tip point of the point cloud structure, and recalculating the hair direction gradient of each of the hair root points in the point cloud data within its second neighborhood radius; and In response to the fact that each of the hair root points in the point cloud data does not have a gradient abnormal value deviating from the hair direction gradient average value within its second neighborhood radius, the point cloud data of the hair image is determined.

7. The planning method according to claim 5, characterized in that: The step of fusing the point cloud data of each hair image into the same viewing angle to obtain the hair map including the point cloud data of the plurality of hairs comprises: uniformly transforming the point cloud data of each of the hair images into a reference coordinate system; A frame of point cloud data is used as a reference frame, and a corresponding point list of reference frame points is created for each of the rooting points in the reference frame; A matching frame is selected from the unmatched point cloud data, and a corresponding point set between the matching frame and the reference frame is calculated in the reference coordinate system, so as to add the matching frame points in the corresponding point set to a corresponding point list of the reference frame points, and each of the root points for which no corresponding reference frame points are found in the matching frame is added to the reference frame, and a new corresponding point list is created for it; In response to completing the matching of the point cloud data of each frame, each of the reference frame points in the reference frame is regarded as a hair entity, and the reference frame point and all points in the corresponding point list are used as a measurement sequence of the hair entity; and According to the measurement sequence of each hair entity, the spatial position of the hair root point of each hair entity in the perspective of the reference coordinate system is determined.

8. A hair follicle extraction path planning system, characterized in that: include: a memory having computer instructions stored thereon; as well as A processor is connected to the memory and is configured to execute computer instructions stored in the memory to implement the hair follicle extraction path planning method according to any one of claims 1 to 7.

9. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by the processor, the method for planning a hair follicle extraction path according to any one of claims 1 to 7 is implemented.

Images