Intelligent Path Planning System for Medical Handling Robots

Abstract

The present invention relates to the technical field of path planning, and specifically relates to an intelligent path planning system for a medical handling robot, including: an environmental image module for collecting consecutive frames of environmental images; a region extraction module for segmenting the environmental images and screening out suspected obstacle regions, and extracting a number of high-light regions from the suspected obstacle regions; a blur processing module for screening out the obstacle regions in the suspected obstacle regions, and further performing de-blurring processing on the obstacle regions by using the gradient and gray-scale distribution characteristics corresponding to the edge information in the obstacle regions to obtain an enhanced environmental image; and a path planning module for performing path planning on the medical handling robot by using the enhanced environmental image. The present invention greatly improves the resolution of the obstacle edges through adaptive de-blurring, reduces the collision risk of the medical handling robot, and further ensures the transportation safety of medical equipment in the complex environment of the hospital.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and particularly to an intelligent path planning system for medical handling robots. Background Art

[0002] Medical handling robots are of great significance in modern hospitals. By automatically transporting items such as drugs, medical devices, and sheets, they greatly improve the work efficiency of hospitals and reduce the burden on medical staff. At the same time, they reduce contact between people, lower the risk of cross-infection, and ensure the safety of the medical environment. The robots also effectively avoid labor injuries caused by manual handling, improve the accuracy and safety of item handling, promote the intelligent development of hospitals, and improve the overall quality of medical services and patient experience.

[0003] Under normal circumstances, medical handling robots sense the surrounding environment through visual sensors to provide necessary information for path planning. However, if the visual sensors of medical handling robots experience violent movement or vibration during the shooting process, especially in a fast-moving environment, the images may become blurred due to relative movement. Since the influence degree of motion blur is different in different regions, using a unified deblurring method may not achieve the ideal effect, further resulting in an unsatisfactory path planning effect for medical handling robots. Summary of the Invention

[0004] The present invention provides an intelligent path planning system for medical handling robots to solve the existing problems.

[0005] The intelligent path planning system for medical handling robots of the present invention adopts the following technical solutions:

[0006] An embodiment of the present invention provides an intelligent path planning system for medical handling robots, which includes the following modules:

[0007] An environmental image module for collecting consecutive frames of environmental images through a visual sensor during the movement of the medical handling robot;

[0008] A region extraction module for performing region segmentation on any frame of environmental image and screening out suspected obstacle regions based on the colors and areas of different regions, and extracting a number of high-light regions from the suspected obstacle regions through the relative brightness of different regions;

[0009] A deblurring processing module for using the comprehensive result of the spatial distribution characteristics of the high-light regions in the corresponding suspected obstacle regions and the regularity degree of the edge information in the suspected obstacle regions to screen out the obstacle regions in the suspected obstacle regions, further using the gradient and gray-scale distribution characteristics corresponding to the edge information in the obstacle regions, and combining the comprehensive result to perform deblurring processing on the obstacle regions to obtain an enhanced environmental image;

[0010] A path planning module for path planning of a medical handling robot using an enhanced environment image.

[0011] Preferably, the method for performing region segmentation on any frame of environment image and screening out suspected obstacle regions based on the colors and areas of different regions includes the following specific steps:

[0012] Perform clustering processing on the pixel points in each frame of environment image using the DBSCAN clustering algorithm according to the distances and gray values between pixel points to obtain a number of initial connected regions;

[0013] For the number of initial connected regions in any environment image, perform clustering on all connected regions using the K-means clustering algorithm according to the areas of the connected regions to obtain a number of clusters;

[0014] For any frame of environment image, calculate the average area of all initial connected regions included in each cluster in the environment image, and mark all the initial connected regions corresponding to the cluster with the largest average area as irrelevant regions; mark all the connected regions in the environment image except the irrelevant regions as suspected obstacle regions.

[0015] Preferably, the method for extracting a number of highlight regions from the suspected obstacle regions based on the relative brightness of different regions includes the following specific steps:

[0016] Convert each frame of RGB-format environment image into an HSV environment image, denoted as the HSV environment image, and use A window of size to divide each suspected obstacle region in each frame of HSV environment image into a number of regions, denoted as equal division regions, where is a preset window parameter;

[0017] According to the difference between the overall V-channel level of each equal division region in any HSV environment image and the overall V-channel level of the environment image, as the possibility that the equal division region is a highlight region;

[0018] Use the magnitude of the possibility that the equal division region is a highlight region to screen out a number of highlight regions.

[0019] Preferably, the method for screening out obstacle regions in the suspected obstacle regions by using the comprehensive result of the spatial distribution characteristics of the highlight regions in the suspected obstacle regions and the regularity degree of the edge information in the suspected obstacle regions includes the following specific steps:

[0020] The distribution that comprehensively reflects the area ratio feature of the high-light region in the suspected obstacle region and the positional relationship between the high-light region and other high-light regions within the suspected obstacle region is regarded as the distribution discreteness of the high-light region in the suspected obstacle region;

[0021] Obtain the edge information in any suspected obstacle region and fit the straight-line information through the edge information, and regard the ratio of the straight-line information in the edge information as the regularity degree of the suspected obstacle region;

[0022] Based on the regularity degree of each suspected obstacle region and the distribution discreteness of the high-light region in each frame of HSV environmental image, screen out the obstacle regions in the HSV environmental image.

[0023] Preferably, the specific method for obtaining the distribution discreteness of the high-light region in the suspected obstacle region is as follows:

[0024] Taking the vertex at the lower left corner of each frame of HSV environmental image as the origin, with the horizontal right direction as the positive direction of the horizontal axis and the vertical upward direction as the positive direction of the vertical axis, construct a rectangular coordinate system to obtain the rectangular coordinate system of each frame of HSV environmental image, and obtain the minimum circumscribed circle of each suspected obstacle region in each frame of HSV environmental image;

[0025] For any frame of HSV environmental image, mark any high-light region as the target high-light region, and obtain the high-light region that is the closest to the target high-light region among the high-light regions other than the target high-light region, and mark it as the high-light reference region of the target high-light region;

[0026] Using the area ratio of the high-light region on the corresponding minimum circumscribed circle of the suspected obstacle region and the distance between the high-light region and the corresponding high-light reference region, calculate the distribution discreteness of the high-light region in the suspected obstacle region, where the distribution discreteness is negatively correlated with the area ratio and positively correlated with the distance.

[0027] Preferably, the specific method for obtaining the regularity degree of the suspected obstacle region is as follows:

[0028] Obtain several edge lines in each suspected obstacle region of each frame of HSV environmental image through the Canny edge detection algorithm, and use the Hough line detection algorithm to perform straight-line detection on each edge line to obtain several straight-line segments of each suspected obstacle region in each frame of HSV environmental image;

[0029] Obtain the differences in quantity and length between the edge lines and the corresponding straight-line segments in the suspected obstacle region as the regularity degree of the suspected obstacle region.

[0030] Preferably, the specific method for obtaining the obstacle region is as follows:

[0031] Combining the regularity degree of the suspected obstacle area and the distribution discreteness of the highlight areas in the suspected obstacle area to obtain the possibility of the suspected obstacle area, where the possibility is positively correlated with both the regularity degree and the distribution discreteness;

[0032] If the obstacle possibility of the suspected obstacle area is greater than or equal to a preset obstacle area threshold, then mark the suspected obstacle area as an obstacle area.

[0033] Preferably, the method of using the gradient and gray-scale distribution characteristics corresponding to the edge information in the obstacle area and combining the comprehensive result to perform de-blurring processing on the obstacle area to obtain an enhanced environment image includes the following specific method:

[0034] For any obstacle area in the HSV environment image, obtain the blurring degree of the obstacle area according to the gradient distribution of the edge pixel points in the obstacle area and the average difference between the gray scale of each edge pixel point and the overall gray scale level of all edge pixel points;

[0035] Take the sum value between the blurring degree and the obstacle possibility of each obstacle area in each frame of the HSV environment image as the sharpening factor, and combine the sharpening factor with the image sharpening algorithm to perform de-blurring operations on each obstacle area in each frame of the HSV environment image, obtaining several frames of enhanced environment images.

[0036] Preferably, the method of combining the sharpening factor with the image sharpening algorithm to perform de-blurring operations on each obstacle area in each frame of the HSV environment image includes the following specific method:

[0037] Use the USM sharpening algorithm to perform sharpening processing on each obstacle area, and during the sharpening processing, multiply and adjust the scaling factor in the USM sharpening algorithm using the sharpening factor corresponding to each obstacle area.

[0038] Preferably, the method of using the enhanced environment image to perform path planning for the medical handling robot includes the following specific method:

[0039] Use the SLAM technology to analyze consecutive frames of the enhanced environment image, construct an environmental model of the hospital, and use the Dijkstra algorithm to calculate the travel path of the medical handling robot in the environmental model.

[0040] The beneficial effects of the technical solution of the present invention are as follows: Through multi-modal environmental perception and intelligent optimization algorithms, the navigation accuracy and safety in complex medical scenarios are significantly improved. The system adopts dynamic environmental image acquisition and hierarchical processing technology. First, it screens suspected obstacle areas through color, area, and brightness features, and then based on a dual verification mechanism of spatial distribution and edge regularity, effectively solves the misjudgment problem caused by high-light reflection in traditional visual navigation. In a hospital environment, the system can accurately distinguish real obstacles from optical interference, and greatly improves the edge resolution of obstacles through adaptive de-blurring. This system effectively improves the obstacle avoidance success rate of medical handling robots during the peak period of the emergency passage, reduces the collision risk of medical handling robots, and further ensures the transportation safety of medical equipment in the complex environment of the hospital. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0042] Figure 1 It is a structural block diagram of the intelligent path planning system for a medical handling robot of the present invention;

[0043] Figure 2 It is a step flow chart of the region extraction module;

[0044] Figure 3 It is a step flow chart of the de-blurring processing module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manner, structure, features, and effects of the intelligent path planning system for a medical handling robot proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0047] The following specifically describes the specific solution of the intelligent path planning system for a medical handling robot provided by the present invention with reference to the accompanying drawings.

[0048] Please refer to Figure 1, which shows the step flowchart of the intelligent path planning system for a medical handling robot provided by an embodiment of the present invention. The system includes the following modules:

[0049] Environmental image module 001: It is used to collect consecutive frames of environmental images through a vision sensor during the movement of the medical handling robot.

[0050] It should be noted that the medical handling robot usually uses machine vision technology to analyze the environment. However, due to the influence of relative motion and the motion interference of the environment on the movement of the medical handling robot, there is a problem of motion blur in the environmental images collected by the medical handling robot. As a result, when the medical handling robot uses the environmental images for image analysis to achieve path planning, the path planning result has problems. Therefore, the embodiment of the present invention selects to perform deblurring processing on the consecutive frames of environmental images collected by the medical handling robot to reduce the impact of motion blur on path planning.

[0051] Specifically, in order to implement the intelligent path planning system for the medical handling robot proposed in this embodiment, first, it is necessary to collect the environmental images of the medical handling robot during the movement. The specific process is as follows:

[0052] First, use the vision sensor installed on the medical handling robot to collect images of the environment, and obtain consecutive frames of images during the movement, which are recorded as environmental images. The preset image acquisition frequency during the image acquisition process is 0.1 s.

[0053] Then, use mean filtering to perform filtering processing on each frame of the environmental image.

[0054] It should be noted that mean filtering is a well-known technology, so the specific filtering process will not be elaborated in the embodiment of the present invention.

[0055] So far, the consecutive frames of environmental images of the medical handling robot during the movement are obtained through the above method.

[0056] Region extraction module 002: It is used to perform region segmentation on any frame of the environmental image and screen out suspected obstacle regions based on the colors and areas of different regions, and extract several high-light regions from the suspected obstacle regions through the relative brightness of different regions.

[0057] It should be noted that the medical handling robot relies on a vision sensor to recognize the environment, such as obstacles, etc., to assist in path planning. However, when moving quickly, the vision sensor may vibrate, causing the captured image to become blurred, affecting the image quality, and further affecting the path planning. Since the blur degrees of different regions are different, the effect of a unified deblurring method is limited. Therefore, the embodiment of the present invention analyzes the characteristics of the obstacle region and performs targeted deblurring processing to focus on solving the blur problem of the obstacle region, such as Figure 2The figure shows the step flow chart of the region extraction module.

[0058] There may be obstacles on the road surface where the medical handling robot travels, and protruding parts such as fire-fighting equipment and handrails on the wall may also hinder the progress of the robot. Moreover, the colors of the road surface and the wall are usually relatively single. The K-means clustering image segmentation algorithm is used to operate on each environmental image, and the region with a larger connected domain area (wall or road surface) obtained is recorded as the irrelevant region. And the connected domains other than the irrelevant region are recorded as suspected obstacle regions. However, there may be stickers on the wall or road surface, which interfere with the screening of the obstacle regions; therefore, according to the characteristics of the obstacle regions, the obstacle possibility of each suspected obstacle region is calculated, several obstacle regions are screened out, and then the fuzziness of each obstacle region is calculated.

[0059] Specifically, in step S201, the scene image is segmented by means of clustering segmentation, and the suspected obstacle regions are screened out based on the color and area of the connected domains after the segmentation process.

[0060] As an optional embodiment, the method for obtaining the suspected obstacle regions includes:

[0061] First, the pixel points in each frame of the environmental image are clustered by using the DBSCAN clustering algorithm according to the distance and gray value between the pixel points, and several initial connected domains are obtained.

[0062] Then, for the several initial connected domains in any environmental image, all the connected domains are clustered by using the K-means clustering algorithm according to the area of the connected domains, and several clusters are obtained.

[0063] It should be noted that since the K-means clustering algorithm is a well-known technology, the specific clustering process of the K-means clustering algorithm in the embodiments of the present invention will not be elaborated. The clustering number parameter of the preset K-means clustering algorithm is 2, and this is used as an example for description. The specific preset value is an empirical value, and it can be adjusted adaptively according to the actual situation.

[0064] Finally, for any frame of the environmental image, the area average value of all the initial connected domains included in each cluster in the environmental image is calculated, and all the initial connected domains corresponding to the cluster with the largest area average value are recorded as the irrelevant region; all the connected domains in the environmental image other than the irrelevant region are recorded as the suspected obstacle regions, and several suspected obstacle regions in each frame of the environmental image are obtained.

[0065] It should be noted that: Since the colors of the road surface and the wall are usually relatively single, and the road surface and the wall area, as a background area, have a much larger corresponding area than the obstacles, in the embodiments of the present invention, clustering is performed according to the area of each connected component, and several irrelevant areas (road surface or wall area) are screened out, and the areas outside the irrelevant areas may be obstacle areas.

[0066] Step S202, in the environmental image in HSV format, according to the horizontal difference in the V-channel value between different ranges, extract the highlight areas from the suspected obstacle areas.

[0067] It should be noted that through the above process, several suspected obstacle areas of each frame of environmental image are obtained. However, there may be stickers on the wall or the road surface, which will interfere with the screening of the obstacle areas; therefore, the differences in features between the obstacle areas and the stickers are used for screening. Among them, since the obstacle has a three-dimensional structure, multiple highlight areas will be generated on its surface under the action of light. These highlight areas usually appear in different parts of the obstacle, and due to factors such as the light angle, the material and shape of the object surface, their distribution is often relatively scattered and irregular. Therefore, within the obstacle area, there may be multiple scattered and discontinuous highlight areas; according to the above characteristics, several highlight areas of each suspected obstacle area are screened out.

[0068] As a preferred embodiment, the specific method for obtaining the highlight areas includes:

[0069] First, convert each frame of environmental image in RGB format to an HSV environmental image, denoted as the HSV environmental image, and use windows of size to divide each suspected obstacle area in each frame of HSV environmental image into several areas, denoted as equal division areas, where is a preset window parameter.

[0070] Among them, the technology of mutual transformation between RGB and HSV is a well-known technology, so it will not be specifically described in the embodiments of the present invention; in addition, in the embodiments of the present invention, the window parameter is preset as 10 according to experience, which can be adjusted according to the actual situation, and the embodiments of the present invention do not specifically limit it.

[0071] Then, according to the difference between the overall V-channel level of each equal division area in any HSV environmental image and the overall V-channel level of the environmental image, as the possibility that the equal division area is a highlight area, so as to screen out the highlight areas.

[0072] As an alternative embodiment, taking the th frame of HSV environmental image as an example, obtain the The first frame of the HSV environment image The first suspected obstacle area The probability that each equally divided area is a highlight area is calculated as follows:

[0073]

[0074] in, Indicates The first frame of the HSV environment image The first suspected obstacle area The probability that each equally divided area is a highlight area; represents the linear normalization function; Indicates The first frame of the HSV environment image The first suspected obstacle area The number of pixels contained in each equally divided area; Indicates The first frame of the HSV environment image The first suspected obstacle area The first The value of the pixel in the V channel; Indicates The average value of the V channel for all pixels in the frame HSV environment image.

[0075] It should be noted that: in the HSV image, the value corresponding to the pixel point in the V channel reflects the brightness characteristics of the pixel point, so in the embodiment of the present invention, It reflects the brightness level of the equally divided area relative to the ambient image. Therefore, the greater the difference between the V channel value of the pixel points in the equally divided area and the average value of the V channel value of all pixels in the entire ambient image, the greater the brightness of the equally divided area compared to the overall brightness of the ambient image, and the greater the possibility that the equally divided area is a highlight area.

[0076] By performing calculations on each equally divided area of each suspected obstacle area of each frame of the HSV environment image according to the above process, the possibility that each equally divided area of each suspected obstacle area of each frame of the HSV environment image is a highlight area is obtained.

[0077] As an optional embodiment, a plurality of highlight regions are selected based on the probability that the equally divided regions are highlight regions. The specific process is as follows: a highlight probability threshold is preset. , if the probability that the equally divided area is a highlight area is greater than or equal to , then the equally divided area is recorded as the highlight area.

[0078] So far, several highlight areas in any frame environment image are obtained through the above method.

[0079] Blur processing module 003: It is used to utilize the comprehensive result of the spatial distribution characteristics of the highlight area in the suspected obstacle area and the regularity degree of the edge information in the suspected obstacle area, so as to screen out the obstacle area in the suspected obstacle area, further utilize the gradient and gray-scale distribution characteristics corresponding to the edge information in the obstacle area, and combine the comprehensive result to perform de-blurring processing on the obstacle area to obtain an enhanced environment image.

[0080] It should be noted that in order to accurately extract the obstacle characteristics that usually appear in the complex environment of a hospital, the embodiments of the present invention take into account that the spatial distribution of different areas of obstacles in the environmental image and the gradient and gray-scale information on the corresponding edges are different from those of other non-obstacles. Therefore, in order to ensure that an appropriate environmental model can be accurately established based on the position of the obstacles in the image during subsequent path planning and improve the success rate of obstacle avoidance, the embodiments of the present invention perform de-blurring processing on the obstacle area in the environmental image through the analysis results of the above characteristics, as Figure 3 shown in the step flow chart of the blur processing module.

[0081] Specifically, in step S301, the distribution situation comprehensively reflected by the area ratio characteristic of the highlight area in the suspected obstacle area to which it belongs and the positional relationship between the highlight area and other highlight areas within the suspected obstacle area to which it belongs is used as the distribution discreteness of the highlight area in the suspected obstacle area.

[0082] It should be noted that: Since obstacles usually have complex three-dimensional structures, their surfaces present different inclination angles and shapes, which causes light to be reflected and refracted when it hits their surfaces, and the distribution of multiple highlight areas formed is usually uneven and scattered. Therefore, the embodiments of the present invention calculate the distribution discreteness of the highlight areas in each suspected obstacle area of each frame of HSV environmental image according to the above characteristics.

[0083] As a preferred embodiment, the process of obtaining the distribution discreteness of the highlight areas in each suspected obstacle area includes:

[0084] First, taking the vertex at the lower left corner of each frame of HSV environmental image as the origin, the horizontal right direction as the positive direction of the horizontal axis, and the vertical upward direction as the positive direction of the vertical axis to construct a rectangular coordinate system, obtaining the rectangular coordinate system of each frame of HSV environmental image, and obtaining the minimum circumscribed circle of each suspected obstacle area in each frame of HSV environmental image.

[0085] Then, for any frame of HSV environmental image, any highlight area is denoted as the target highlight area, and the highlight area closest to the target highlight area among the highlight areas other than the target highlight area is obtained and denoted as the highlight reference area of the target highlight area.

[0086] Finally, the distribution discreteness of the highlight regions in the suspected obstacle regions is calculated by using the proportion of the area of the highlight regions on the minimum circumscribed circle corresponding to the suspected obstacle regions to which they belong, and the distance between the highlight regions and the corresponding highlight reference regions, where the distribution discreteness is negatively correlated with the proportion of the area, and the distribution discreteness is positively correlated with the distance magnitude.

[0087] As an alternative embodiment, for the th suspected obstacle region in the th frame of the HSV environmental image, the distribution discreteness of the highlight regions in the th suspected obstacle region in the th frame of the HSV environmental image is obtained, and the specific calculation formula is:

[0088]

[0089] where, represents the distribution discreteness of the highlight regions in the th suspected obstacle region in the th frame of the HSV environmental image; represents the linear normalization function; represents the area of the minimum circumscribed circle of the th suspected obstacle region in the th frame of the HSV environmental image; represents the number of highlight regions in the th suspected obstacle region in the th frame of the HSV environmental image; represents the area of the th highlight region in the th suspected obstacle region in the th frame of the HSV environmental image; represents the distance between the th highlight region and the corresponding highlight reference region in the th suspected obstacle region in the th frame of the HSV environmental image.

[0090] It should be noted that: is the proportion of the area of the highlight regions on the minimum circumscribed circle corresponding to the suspected obstacle regions to which they belong, and since and They are reciprocal to each other. Therefore, in the embodiments of the present invention, the distribution discreteness is negatively correlated with the area ratio. The smaller the area of the high-brightness region in the suspected obstacle region, and the larger the area of the minimum circumscribed circle of the suspected obstacle region, it indicates that the distribution of the high-brightness regions in the suspected obstacle region is more discrete, and the distribution discreteness of the high-brightness regions in the suspected obstacle region is greater. The greater the distance between the center of the high-brightness region in the suspected obstacle region and the center of its corresponding high-brightness reference region, the greater the distribution discreteness of the high-brightness regions in the suspected obstacle region.

[0091] So far, by performing operations on each suspected obstacle region of each frame of HSV environmental image according to the above process, the distribution discreteness of the high-brightness regions of each suspected obstacle region of each frame of HSV environmental image is obtained.

[0092] Step S302: Obtain the edge information in any suspected obstacle region and fit the straight-line information through the edge information, and use the ratio of the straight-line information in the edge information as the regularity degree of the suspected obstacle region.

[0093] It should be noted that: in order to further improve the accuracy of screening the obstacle region, other features are used for further screening. Among them, stickers or signs usually contain various characters, and the shapes of these characters often show a certain degree of irregularity, which may be curves, sharp corners or complex structures intertwined together. In contrast, the structures of obstacles are usually relatively regular, and they often present clear geometric shapes, such as straight lines or rectangles, such as medical cabinets and trolleys. According to the above features, the regularity degree of each suspected obstacle region is calculated.

[0094] First, obtain several edge lines in each suspected obstacle region of each frame of HSV environmental image through the Canny edge detection algorithm, and use the Hough line detection algorithm to perform line detection on each edge line to obtain several line segments of each suspected obstacle region of each frame of HSV environmental image.

[0095] It should be noted that the Hough line detection algorithm is a well-known algorithm, so the specific process of the algorithm is not specifically described in the embodiments of the present invention.

[0096] Then, obtain the differences in quantity and length between the edge lines and the corresponding line segments in the suspected obstacle region as the regularity degree of the suspected obstacle region.

[0097] As an optional embodiment, for the th suspected obstacle region of the th frame of HSV environmental image, obtain the regularity degree of the th suspected obstacle region of the th frame of HSV environmental image. The specific calculation formula is:

[0098]

[0099] Among them, represents the regularity degree of the th suspected obstacle area in the th frame of HSV environmental image; represents the number of edge lines of the th suspected obstacle area in the th frame of HSV environmental image; represents the length of the th edge line of the th suspected obstacle area in the th frame of HSV environmental image; represents the number of straight line segments of the th suspected obstacle area in the th frame of HSV environmental image; represents the length of the th straight line segment of the th suspected obstacle area in the th frame of HSV environmental image.

[0100] It should be noted that: the longer the lengths of all the straight line segments of the suspected obstacle area, the more regular the suspected obstacle area is, and the greater the regularity degree of the suspected obstacle area is.

[0101] Thus, by performing operations on each suspected obstacle area of each frame of HSV environmental image according to the above process, the regularity degree of each suspected obstacle area of each frame of HSV environmental image is obtained.

[0102] Step S303, based on the regularity degree of each suspected obstacle area of each frame of HSV environmental image and the distribution discreteness of the highlight area, screen out the obstacle areas in the HSV environmental image.

[0103] First, by combining the regularity degree of the suspected obstacle area and the distribution discreteness of the highlight area in the suspected obstacle area, the possibility of the suspected obstacle area is obtained, where the possibility is positively correlated with both the regularity degree and the distribution discreteness.

[0104] As an optional embodiment, for the th suspected obstacle area of the th frame of HSV environmental image, obtain the obstacle possibility of the th suspected obstacle area of the th frame of HSV environmental image. The specific calculation formula is:

[0105]

[0106] Among them, represents the obstacle possibility of the th suspected obstacle area in the th frame of HSV environment image; represents the distribution discreteness of the highlight area of the th suspected obstacle area in the th frame of HSV environment image; represents the regularity degree of the th suspected obstacle area in the th frame of HSV environment image; represents the linear normalization function.

[0107] It should be noted that: the greater the distribution discreteness of the highlight area of the suspected obstacle area, and the greater the regularity degree of the suspected obstacle area, the greater the obstacle possibility of the suspected obstacle area.

[0108] Then, if the obstacle possibility of the suspected obstacle area is greater than or equal to the preset obstacle area threshold, the suspected obstacle area is recorded as an obstacle area.

[0109] Thus, several obstacle areas in any HSV environment image are obtained.

[0110] Step S304, using the gradient and gray-scale distribution characteristics corresponding to the edge information in the obstacle area, and combining the obstacle possibility corresponding to the obstacle area as a sharpening factor, so as to perform de-blurring processing on the obstacle area to obtain an enhanced environment image.

[0111] It should be noted that in the embodiment of the present invention, through the above process, several obstacle areas of each frame of HSV environment image are obtained. Since vibration will cause different degrees of blurring of different obstacle areas, it is necessary to calculate the blurring degrees of different obstacles. Image blurring will cause the standard deviation of the gradient amplitude of edge pixel points to decrease and the difference between the gray values of all pixel points to also decrease. According to the above characteristics, the blurring degree of each obstacle area in each frame of HSV environment image is calculated.

[0112] As a preferred embodiment, the specific method for obtaining the enhanced environment image includes:

[0113] First, for the obstacle area in any HSV environment image, according to the gradient distribution of the edge pixel points in the obstacle area and the average difference between the gray value of each edge pixel point and the overall gray level of all edge pixel points, the blurring degree of the obstacle area is obtained.

[0114] Then, the sum value between the blur degree and the obstacle possibility of each obstacle area in each frame of the HSV environmental image is used as the sharpening factor, and the sharpening factor is combined with the image sharpening algorithm to perform de-blurring operations on each obstacle area of each frame of the HSV environmental image, obtaining several frames of enhanced environmental images.

[0115] As an optional embodiment, for the th obstacle area of the th frame of the HSV environmental image, obtain the th obstacle area of the th frame of the HSV environmental image, and the specific calculation formula is:

[0116]

[0117] where, represents the blur degree of the th obstacle area of the th frame of the HSV environmental image; represents the exponential function with the natural constant as the base; represents the th obstacle area of the th frame of the HSV environmental image, which is the variance of the gradient magnitudes of all edge pixel points; represents the th obstacle area of the th frame of the HSV environmental image, which is the number of pixel points; represents the absolute value function; represents the th obstacle area of the th frame of the HSV environmental image, which is the th gray value of the th edge pixel point; represents the th obstacle area of the

[0118] It should be noted that: the smaller the variance of the gradient magnitudes of all edge pixel points in the obstacle area, the greater the blur degree of the obstacle area; the smaller the difference between the gray values of all edge pixel points in the obstacle area, the greater the blur degree of the obstacle area.

[0119] As an optional embodiment, the specific method for performing de-blurring operations on each obstacle area of each frame of the HSV environmental image is: using the USM sharpening algorithm to perform sharpening processing on each obstacle area, and during the sharpening process, using the sharpening factor corresponding to each obstacle area to multiply and adjust the scaling factor in the USM sharpening algorithm.

[0120] It should be noted that the USM (Unsharp Masking) sharpening algorithm is a well-known technology. Therefore, the specific process of sharpening the obstacle area by the USM sharpening algorithm will not be elaborated in the embodiments of the present invention. Through the above process, the embodiments of the present invention obtain the blurring degree of each obstacle area in each frame of HSV environmental image and the possibility of being an obstacle area. Different degrees of de-blurring operations are performed on each obstacle area according to the sharpening factor obtained from these two characteristic values, realizing the adaptive enhancement of different areas in the environmental image.

[0121] Thus, through the above method, each frame of de-blurred HSV environmental image, that is, the enhanced environmental image, is obtained.

[0122] Path planning module 004: used to perform path planning for the medical handling robot using the enhanced environmental image.

[0123] Specifically, the SLAM technology is used to analyze consecutive frames of the enhanced environmental image to construct an environmental model of the hospital, and the Dijkstra algorithm is used to calculate the travel path of the medical handling robot in the environmental model.

[0124] It should be noted that: SLAM (Simultaneous Localization and Mapping) is simultaneous localization and mapping. It is a technology that enables a robot to perform self-localization and construct an environmental map in real time through sensor data without a prior map in an unknown environment. It combines the two tasks of localization and mapping, usually using a camera or other sensors to perceive the surrounding environment. SLAM is widely used in fields such as autonomous driving, service robots, and drones to help robots navigate autonomously, avoid obstacles, and make decisions. The Dijkstra algorithm is a classic algorithm for calculating the shortest path between two nodes in a graph, applicable to graphs with non-negative edge weights, and thus realizes the calculation of the shortest path by gradually expanding the shortest path tree.

[0125] Thus, this embodiment is completed.

[0126] It should be noted that the model used in this embodiment is only used to represent the negative correlation relationship and constrain the result of the model output to be within the interval. Specifically in implementation, it can be replaced with other models with the same purpose. This embodiment only takes the model as an example for description and does not make specific limitations on it, where refers to the input of the model.

[0127] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent path planning system for a medical handling robot, characterized in that, The system includes the following modules: An environmental image module, configured to collect consecutive frames of environmental images through a vision sensor during the movement of a medical handling robot; A region extraction module, configured to perform region segmentation on any frame of environmental image, screen out suspected obstacle regions based on the colors and areas of different regions, and extract several high-light regions from the suspected obstacle regions based on the relative brightness of different regions; A blurring processing module, configured to use the comprehensive result of the spatial distribution characteristics of the high-light regions in the corresponding suspected obstacle regions and the regularity degree of the edge information in the suspected obstacle regions, so as to screen out the obstacle regions in the suspected obstacle regions, further use the gradient and gray-scale distribution characteristics corresponding to the edge information in the obstacle regions, and combine the comprehensive result to perform de-blurring processing on the obstacle regions to obtain an enhanced environmental image; Among them, the specific method for obtaining the obstacle regions includes: Regarding the distribution situation comprehensively reflected by the area proportion characteristics of the high-light regions in the corresponding suspected obstacle regions and the positional relationship between the high-light regions and other high-light regions within the corresponding suspected obstacle regions as the distribution discreteness of the high-light regions in the suspected obstacle regions; Obtaining the edge information in any suspected obstacle region and fitting the straight-line information through the edge information, and regarding the proportion of the straight-line information in the edge information as the regularity degree of the corresponding suspected obstacle region; Comprehensively considering the regularity degree of each suspected obstacle region and the distribution discreteness of the high-light regions in each frame of HSV environmental image, and screening out the obstacle regions in the HSV environmental image; A path planning module, configured to perform path planning on the medical handling robot by using the enhanced environmental image.

2. The intelligent path planning system for a medical handling robot according to claim 1, wherein The specific method for performing region segmentation on any frame of environmental image and screening out suspected obstacle regions based on the colors and areas of different regions includes: Performing clustering processing on the pixel points in each frame of environmental image by using the DBSCAN clustering algorithm according to the distances and gray-scale values between the pixel points to obtain several initial connected regions; For the several initial connected regions in any environmental image, performing clustering on all the connected regions by using the K-means clustering algorithm according to the areas of the connected regions to obtain several clusters; For any frame of environmental image, calculating the average area of all the initial connected regions included in each cluster in the environmental image, and regarding all the initial connected regions corresponding to the cluster with the largest average area as the irrelevant regions; and regarding all the connected regions in the environmental image except the irrelevant regions as the suspected obstacle regions.

3. The intelligent path planning system for a medical handling robot according to claim 1, wherein The specific method for extracting several high-light regions from the suspected obstacle regions based on the relative brightness of different regions includes: Convert the environmental image in RGB format for each frame into an HSV environmental image, denoted as the HSV environmental image. Use A window of size to divide each suspected obstacle area in each frame of the HSV environmental image into several areas, denoted as equal division areas, where is a preset window parameter. Regarding the difference between the overall V-channel level of each equal division region in any HSV environmental image and the overall V-channel level of the environmental image as the possibility that the equal division region is a high-light region; Using the magnitude of the possibility that the equal division region is a high-light region to screen out several high-light regions.

4. The intelligent path planning system for a medical handling robot according to claim 1, wherein The specific method for obtaining the distribution discreteness of the high-light regions in the suspected obstacle regions is: Taking the vertex at the lower left corner of each frame of the HSV environmental image as the origin, with the horizontal right direction as the positive direction of the horizontal axis and the vertical upward direction as the positive direction of the vertical axis, a rectangular coordinate system is constructed to obtain the rectangular coordinate system of each frame of the HSV environmental image, and the minimum circumscribed circle of each suspected obstacle area in each frame of the HSV environmental image is obtained. For any frame of the HSV environmental image, any highlight area is denoted as the target highlight area, and the highlight area closest to the target highlight area among the highlight areas outside the target highlight area is obtained and denoted as the highlight reference area of the target highlight area. Using the area ratio of the highlight area on the corresponding minimum circumscribed circle of the suspected obstacle area to which it belongs, and the distance between the highlight area and the corresponding highlight reference area, calculate the distribution discreteness of the highlight area in the suspected obstacle area, where the distribution discreteness is negatively correlated with the area ratio and positively correlated with the distance.

5. The intelligent path planning system for a medical handling robot according to claim 1, wherein The specific method for obtaining the regularity degree of the suspected obstacle area is as follows: Using the Canny edge detection algorithm to obtain several edge lines in each suspected obstacle area of each frame of the HSV environmental image, and using the Hough line detection algorithm to perform line detection on each edge line to obtain several line segments in each suspected obstacle area of each frame of the HSV environmental image. Obtain the differences in quantity and length between the edge lines and the corresponding line segments in the suspected obstacle area as the regularity degree of the suspected obstacle area.

6. The intelligent path planning system for a medical handling robot according to claim 1, wherein The specific method for obtaining the obstacle area is as follows: Combining the regularity degree of the suspected obstacle area and the distribution discreteness of the highlight area in the suspected obstacle area, obtain the possibility of the suspected obstacle area, where the possibility is positively correlated with both the regularity degree and the distribution discreteness. If the obstacle possibility of the suspected obstacle area is greater than or equal to the preset obstacle area threshold, then the suspected obstacle area is denoted as the obstacle area.

7. The intelligent path planning system for a medical handling robot according to claim 1, wherein The specific method for using the gradient and gray-scale distribution characteristics corresponding to the edge information in the obstacle area and combining the comprehensive result to perform de-blurring processing on the obstacle area to obtain the enhanced environmental image includes: For the obstacle area in any HSV environmental image, obtain the blurring degree of the obstacle area according to the gradient distribution of the edge pixel points in the obstacle area and the average difference between the gray scale of each edge pixel point and the overall gray scale level of all edge pixel points. Taking the sum value between the blurring degree and the obstacle possibility of each obstacle area in each frame of the HSV environmental image as the sharpening factor, and combining the sharpening factor with the image sharpening algorithm to perform de-blurring operations on each obstacle area in each frame of the HSV environmental image to obtain several frames of enhanced environmental images.

8. The intelligent path planning system for a medical handling robot according to claim 7, characterized in that The specific method for combining the sharpening factor with the image sharpening algorithm to perform de-blurring operations on each obstacle area in each frame of the HSV environmental image includes: Using the USM sharpening algorithm to perform sharpening processing on each obstacle area, and multiplying and adjusting the scaling factor in the USM sharpening algorithm by the sharpening factor corresponding to each obstacle area during the sharpening process.

9. The intelligent path planning system for a medical handling robot according to claim 1, wherein The path planning for the medical handling robot using the enhanced environment image includes the following specific methods: Use SLAM technology to analyze consecutive frames of the enhanced environment image, construct an environmental model of the hospital, and use the Dijkstra algorithm to calculate the travel path of the medical handling robot in the environmental model.

Images