WO2022194015A1

WO2022194015A1 - Area-by-area completeness self-checking method of capsule endoscope, electronic device, and readable storage medium

Info

Publication number: WO2022194015A1
Application number: PCT/CN2022/080076
Authority: WO
Inventors: 杨戴天杙
Original assignee: 安翰科技(武汉)股份有限公司
Priority date: 2021-03-17
Filing date: 2022-03-10
Publication date: 2022-09-22
Also published as: CN113017544A; CN113017544B

Abstract

Provided in the present invention are an area-by-area completeness self-checking method of a capsule endoscope, an electronic device, and a readable storage medium, the method comprising: dividing a working area into multiple sub working areas; establishing a virtual positioning area corresponding to each sub working area; driving a capsule endoscope to move in the working area, photograph images, synchronously execute step A and, when the proportion of voxels marked with a light-up identifier is no less than a preset proportion value, no longer synchronously execute step A; step A comprises: recording in sequence the position in a spatial coordinate system and the field of view orientation of each working point; at each working point in sequence, confirming an intersection area; and marking with a light-up identifier the voxels located in an intersection area and unmarked with a light-up identifier. The present invention can implement completeness self-checking of a capsule endoscope.

Description

Partition completeness self-checking method, device and readable storage medium of capsule endoscope

This application claims the priority of a Chinese patent application with an application date of March 17, 2021, an application number of 202110284699.9, and the invention titled "Sectional Integrity Self-Inspection Method, Device and Readable Storage Medium for Capsule Endoscope", The entire contents of which are incorporated herein by reference.

technical field

The invention relates to the field of medical equipment, and in particular, to a self-checking method, equipment and readable storage medium for partition completeness of a capsule endoscope.

Background technique

Capsule endoscopy is increasingly used for gastrointestinal examination. Capsule endoscopes are taken orally, passed through the mouth, esophagus, stomach, small intestine, large intestine, and finally excreted from the body. Usually, the capsule endoscope runs passively with the peristalsis of the digestive tract, and captures images at a certain frame rate during the process, so that doctors can check the health of each section of the patient's digestive tract.

Compared with traditional intubation endoscopes, capsule endoscopes have the advantages of no risk of cross-infection, no damage to the human body, and good tolerance. However, traditional endoscopes have high controllability, and at the same time, after long-term operation, relatively complete operating procedures have been summarized to ensure the relative completeness of inspection, while the self-inspection scheme of the completeness of new technology capsule endoscopes There is still something missing.

On the one hand, the controllability of the capsule endoscope is poor, which is affected by the peristalsis and movement of the detection space, which leads to the randomness of the capsule endoscope shooting. That is, there is a missed shot. On the other hand, it is also affected by poor maneuverability and lack of position and attitude feedback, so it is difficult to form a good operating procedure to ensure the completeness of the inspection. In addition, the capsule endoscope lacks the function of cleaning the lens, resulting in a significantly lower image resolution than the intubation endoscope, so its image quality cannot be guaranteed to be always clear. The above problems will lead to the lack of completeness of capsule endoscopy.

SUMMARY OF THE INVENTION

In order to solve the above-mentioned technical problems, the purpose of the present invention is to provide a self-checking method, electronic device and readable storage medium for partition completeness of a capsule endoscope.

In order to achieve one of the above purposes of the invention, an embodiment of the present invention provides a method for self-checking the partition completeness of a capsule endoscope, the method includes: acquiring a working area of the capsule endoscope, and dividing the working area into multiple a sub-work area, any line passing through any sub-work area has at most two intersection points with the current sub-work area;

Correspondingly establish a virtual positioning area for each sub-working area, the virtual positioning area and the working area are in the same spatial coordinate system, and the virtual positioning area completely covers the working area;

dividing each of the virtual positioning areas into a plurality of adjacent voxels with the same size, and each of the voxels has a unique identifier and coordinates;

Drive the capsule endoscope to move in the working area, and sequentially record the images captured by the capsule endoscope when it reaches each working point according to a predetermined frequency, and perform step A synchronously to scan the body in each virtual positioning area. The voxel is marked with a lighting mark, and for each virtual positioning area, when the proportion of the voxels marked with the lighting mark in the current virtual positioning area is not less than the preset ratio threshold, step A is no longer performed synchronously;

Among them, in the initial state, each voxel point is not marked with a lighted mark;

Step A includes:

Sequentially record the position and view orientation of each working point in the space coordinate system;

At each work point in turn, confirm the intersection area of the field of view of the capsule endoscope and the virtual positioning area currently located at the current work point according to the position of the current work point and the direction of the field of view;

Marking a lighting mark on the voxel points that are in the intersection area and are not marked with a lighting mark.

As a further improvement of an embodiment of the present invention, the capsule endoscope is driven to move in the working area, and the images captured when the capsule endoscope reaches each working point are sequentially recorded according to a predetermined frequency, and step A is performed synchronously. Lighting flags to label voxels include:

Score the images obtained at each work point. If the score of the image obtained corresponding to the current work point is not less than the preset score, step A is performed synchronously. If the score of the image obtained corresponding to the current work point is less than the preset score, Then, step A is skipped for the current working point.

As a further improvement of an embodiment of the present invention, when step A is performed, the method further includes:

If the virtual positioning area where the capsule endoscope is currently located at any working point is not unique, the virtual positioning area with the smallest volume is used as the virtual positioning area corresponding to the current working point by default.

As a further improvement of an embodiment of the present invention, when step A is performed, marking the voxel points that are in the intersection area and are not marked with a lighting mark includes:

In the intersection area, obtain the line of sight vector of the current working point and each voxel that is not marked with a lighted mark, and at the same time, according to the acquisition order of the intersection area, the line of sight vector corresponding to each voxel is merged into the same vector set. ;

Traverse the vector set, if the number of sight vectors in any one of the vector sets is at least 2, and the included angle between the two sight vectors is greater than the preset angle threshold, mark the voxel corresponding to the current vector set. Bright logo.

If the distance between the two positioning points is less than the preset distance threshold, and the angle between the viewing directions of the two positioning points is smaller than the preset angle threshold, then the vector intersecting within the field of view of the two current positioning points is traversed. When set, the calculation of the angle between each voxel in the intersecting range of the visual field and the two line-of-sight vectors corresponding to the two positioning points is omitted.

As a further improvement of an embodiment of the present invention, the method further includes:

judging in real time whether the proportion of the voxel points marked with the lit logo in each virtual positioning area is not less than the preset proportion threshold,

If so, drive the capsule endoscope to exit the working mode;

If not, drive the capsule endoscope to continue working mode.

When the capsule endoscope runs for a preset working time in the working area, it is judged whether the proportion of the voxel points marked with the lit logo in each virtual positioning area is not less than the preset proportion threshold, and

If so, drive the capsule endoscope to exit the working mode;

If not, drive the capsule endoscope to continue working mode.

As a further improvement of an embodiment of the present invention, each of the virtual positioning areas is configured to be spherical.

In order to solve one of the above objects of the invention, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory stores a computer program that can be executed on the processor, and the processor executes the program At the time, the steps in the self-checking method of the partition completeness of the capsule endoscope as described above are implemented.

In order to solve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the partition completeness of the capsule endoscope as described above is realized. Steps in the Sexual Self-Test Method.

Compared with the prior art, the beneficial effects of the present invention are: the self-checking method, device and readable storage medium for the partition completeness of the capsule endoscope of the present invention divide the working area into sub-working areas composed of convex curved surfaces, corresponding to Each sub-working area establishes a virtual positioning area under the same spatial coordinate system as it, and when the sub-working area intersects with the virtual positioning area, it will be marked and illuminated, which can realize the completeness self-check of the capsule endoscope and improve the detection probability.

Description of drawings

FIG. 1 is a schematic flowchart of a self-checking method for partition completeness of a capsule endoscope according to an embodiment of the present invention.

FIG. 2 is a schematic flowchart of step A in FIG. 1 .

FIG. 3 is a schematic structural diagram of a specific example of the present invention.

FIG. 4 is a schematic structural diagram of another specific example of the present invention.

Detailed ways

The present invention will be described in detail below with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and the structural, method, or functional transformations made by those of ordinary skill in the art according to these embodiments are all included within the protection scope of the present invention.

Referring to FIG. 1 and FIG. 2 , a first embodiment of the present invention provides a self-checking method for the completeness of a partition of a capsule endoscope, and the method includes the following steps.

S1, obtaining the working area of the capsule endoscope, dividing the working area into a plurality of sub-working areas, and a straight line passing through any sub-working area arbitrarily has at most two intersections with the current sub-working area;

A virtual positioning area is correspondingly established for each sub-working area, the virtual positioning area and the working area are in the same space coordinate system, and the virtual positioning area completely covers the working area.

S2. Divide each of the virtual positioning areas into a plurality of adjacent voxels with the same size, and each of the voxels has a unique identifier and coordinates.

S3. Drive the capsule endoscope to move in the working area, and sequentially record the images captured by the capsule endoscope when it reaches each working point according to a predetermined frequency, and perform step A synchronously to locate the images in each virtual positioning area. For each virtual positioning area, when the proportion of the voxels marked with the lighting mark in the current virtual positioning area is not less than the preset ratio threshold, step A is no longer performed synchronously.

Among them, in the initial state, each voxel point is not marked with a lighted mark.

Wherein, step A includes the following specific steps:

For step S1, after the capsule endoscope reaches the working area, it traverses the working area quickly to outline the outline of the working area. Further, the key areas in the work area are retrieved and located according to the specific work environment, the coordinates of key points are obtained in each key area, and after connecting the key points in sequence, the work area composed of key points is formed. . Referring to FIG. 3 , in a specific example of the present invention, a virtual stomach environment is taken as an example for a specific introduction. The key regions of the stomach include: the cardia, fundus, lesser curvature, greater curvature, gastric angle, pylorus and Pyloric sinus area, after the capsule endoscope quickly traverses the working area, the working area composed of curved surfaces can be drawn. Among them, the more sampling points in each key area, the smoother the surface of the work area, and accordingly, the amount of calculation will increase. Further, the coordinates of several working points are acquired in the key area of each stomach, and are connected by straight lines in sequence to form the working area.

In a specific example of the present invention, the Chinese patent application with the extension publication number: CN110335318A, the invention name is "a method for measuring objects in the digestive tract based on a camera system", or the extension publication number: CN110327046A, the invention name is "a kind of The Chinese patent application of "Method for Measuring Objects in Digestive Tract Based on Camera System" can roughly estimate the coordinates of a certain working point in each key area, and then connect the obtained coordinates in a straight line to form the work described in the steps of the present invention. area.

After the work area is determined, the work area is divided into a plurality of sub-work areas. Preferably, the best division method is to take the division method with the fewest sub-work areas. Specifically, any straight line passing through any sub-working area has at most two intersection points with the current sub-working area, that is, each sub-working area is a convex surface structure. With reference to FIG. 4 , in the specific example of the present invention, a sub-working area with any surface protruding to the outside is defined as a sub-working area of a convex curved surface.

Further, after the working area is determined, under the same spatial coordinate system as the working area, a virtual positioning area is correspondingly established for each sub-working area. Preferably, the shapes of the plurality of virtual positioning areas are the same.

In the specific example of the present invention, the virtual positioning area is configured as a sphere. For convenience of illustration, only one section is shown in the example of FIG. 3 . Here, each virtual positioning area covers its corresponding sub-working area.

For step S2, the virtual positioning area is discretized, so as to divide the virtual positioning area into multiple adjacent voxels with the same size. In the specific example of the present invention, each voxel is configured as a cube, and the range of its side length is ∈ [1mm, 5mm]. Correspondingly, each voxel has a unique identification and coordinates, and the identification is, for example, a number. The coordinate may be a fixed position coordinate value of each voxel, for example, one of the corner coordinate values. In the specific example of the present invention, the coordinate value of the center point of each voxel is used as the coordinate value corresponding to the current voxel.

It can be understood that in practical applications, a platform can be set up, and after the user is in the monitoring area of the platform, a virtual positioning area is automatically constructed according to the user's position, and during the working process of the capsule endoscope, the user is always in the monitoring area. , in this way, it is ensured that the virtual positioning area and the working area are in the same space coordinate system.

For step S3, after the sub-working area and its corresponding virtual positioning area are determined, after driving the capsule endoscope into the working area, each working point is recorded according to a predetermined frequency, and according to specific requirements, you can Selectively record the image taken at each work point, the spatial coordinate value P(x, y, z) of each work point, and the view direction M. The field of view orientation here is the posture of the capsule endoscope, such as Euler angles (yaw, pitch, roll), or it can be a four-element or vector coordinate of orientation. Through the field of view orientation, you can know the field of view captured by the capsule endoscope in the M direction at the current coordinate point. The field of view is oriented in a cone shape starting from the current coordinate point, and its vector direction is

That is, the extension direction of the axis of the cone. In the prior art, the steps of capturing an image through a capsule endoscope, locating its position coordinates, and the direction of the recorder's field of view are all steps in the prior art, and will not be further described here.

In a preferred embodiment of the present invention, step S3 further includes: scoring the images obtained at each work point, and if the score of the images obtained corresponding to the current work point is not less than the preset score, then step A is performed synchronously. If the score of the acquired image corresponding to the point is less than the preset score, then step A is skipped for the current work point.

Scoring images can be done in a number of ways, which are known in the art. For example: Authorized Announcement No. CN111932532B, the Chinese patent titled "A Method for Evaluation of Capsule Endoscope Without Reference Image, Electronic Device and Medium" is cited in this application. The score of the present invention may be the image quality evaluation score and/or the image content evaluation score and/or the comprehensive score of the extended patent, which will not be repeated here.

Preferably, when each working point is reached, step A is performed synchronously to mark the voxel with a lighted mark. For each virtual positioning area, when the voxel with the lighted mark is marked, the proportion of the voxel in the current virtual positioning area. When it is not less than the preset ratio threshold, step A is no longer performed synchronously. By marking the proportion of the lit logo, the completeness of capsule endoscopy detection can be determined. The higher the proportion, the more comprehensive the capsule detection work area.

For step A, specifically, in the initial state, each voxel point is by default an unmarked lighted mark, and the lighted mark is a general mark. After the mark passes through step A, the voxel point is marked, and its mark There are many ways. For example: identify the same code, the same color, etc. for the corresponding voxel points. After specific operations, different voxel points are illuminated in sequence, and then the detection progress of the working area is determined by the proportion of voxels marked with the illuminated logo. Of course, in other embodiments of the present invention, all voxels may be turned on in an initial state, and each voxel may be turned off in sequence in the order of step A, which will not be repeated here.

It should be noted that each sub-working area is a convex surface. In this way, taking any working point in the current sub-working area as the shooting angle, there is no occlusion in its field of view, so that the shooting field of view formed by taking this working point as the shooting angle, all the voxels inside can be completely photographed .

As shown in FIG. 3 , the working area is divided into two sub-working areas, and the two sub-working areas are respectively covered by a larger virtual positioning area X1 and a smaller virtual positioning area X2. For step A, for each working point, its truncated cone area can be calculated according to its corresponding field of view orientation. Correspondingly, the frustum region and the spherical virtual positioning region have an intersection region. Take the coordinate point P1, whose field of view faces M as an example, and the intersection area is A1. Correspondingly, when the capsule endoscope is at the coordinate point P1, all voxels in the intersection area A1 are marked with lit marks.

Preferably, if the virtual positioning area where the capsule endoscope is currently located at any working point is not unique, the virtual positioning area where the voxel points are not all lit and the volume is the smallest is set as the corresponding current working point by default. the virtual positioning area of

In order to avoid that some sub-working regions are non-convex surface structures due to errors when the sub-working regions are divided, in the second preferred embodiment of the present invention, when step A is performed, the sub-working regions that are in the intersection region and are not marked Marking the lighting mark on the voxel points with the lighting mark includes: in the intersection area, obtaining the line of sight vector of the current working point and each voxel that is not marked with the lighting mark; Merge the line-of-sight vectors corresponding to each voxel into the same vector set; traverse the vector set, if the number of line-of-sight vectors in any of the vector sets is at least 2, and the included angle between the two line-of-sight vectors is greater than the preset folder When the angle threshold is set, the voxel corresponding to the current vector set is marked with a lighted mark.

Preferably, when the second preferred embodiment implements step A, the method further includes: if the distance between the two positioning points is less than a preset distance threshold, and the angle between the viewing directions of the two positioning points is less than Preset the included angle threshold, when traversing the vector set intersecting within the field of view of the current two positioning points, omit the angle between each voxel within the intersecting range of the field of view and the two line-of-sight vectors corresponding to the two positioning points. calculate. When the deviation of the two positioning points is small, the intersection area may be approximately coincident. At this time, the voxel points in the intersection area are likely not to be marked with lit marks. In this way, by adding this step, the calculation amount can be reduced on the premise of ensuring the accuracy of the calculation result.

Under normal circumstances, the two positioning points described here are usually two coordinate points that are located in the same detection area and are obtained in sequence, and details are not described here.

As in step A above, each voxel point in the virtual positioning area will be marked in turn. Ideally, when the capsule endoscope finishes working, each voxel point in the virtual positioning area will be lit up, but in actual operation , the interference of various factors will lead to errors. Therefore, the present invention sets a preset ratio threshold. When the proportion of the voxels marked with the lit logo in the virtual positioning area is not less than the preset ratio threshold, it means that the monitoring range of the capsule endoscope complies with the standard. In this way, the completeness self-check of the capsule endoscope can be assisted by marking the voxels in the virtual positioning area with lit signs.

Further, the detection result is visualized, and the user can assist in verifying the detection area of the capsule endoscope by observing the lighted mark marked in the virtual positioning area, which will not be repeated here.

Preferably, the method further includes: judging in real time whether the proportion of the voxel points marked with the lit logo in the virtual positioning area is not less than a preset proportion threshold, and if so, driving the capsule endoscope to exit the working mode; if not, driving the capsule endoscope. The capsule endoscope continues working mode.

Preferably, the method further includes: when the capsule endoscope runs for a preset working time in the working area, judging whether the proportion of the voxel points marked with the lit logo in the virtual positioning area is not less than a preset proportion threshold, and if so, Drive the capsule endoscope to exit the working mode; if not, drive the capsule endoscope to continue the working mode. By marking the proportion of the voxel points with the lit logo in the virtual positioning area to determine whether to end the working mode, the working area can be observed from multiple perspectives, and the number of images taken in the same area can be increased under the multi-perspective judgment criteria, which not only ensures the shooting quality Completeness, you can also observe the same area from multiple angles in the post-image application to achieve a better observation effect and improve the detection rate.

Further, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory stores a computer program that can run on the processor, and when the processor executes the program, the above-mentioned Describe the steps in the self-checking method of partition completeness of capsule endoscope.

Further, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, realizes the above-mentioned partition completeness self-checking method of a capsule endoscope. A step of.

To sum up, the self-checking method, device and readable storage medium of the partition completeness of the capsule endoscope of the present invention divide the working area into sub-working areas composed of convex curved surfaces, and each sub-working area is established in the same space as the sub-working area. The virtual positioning area under the coordinate system is marked and illuminated when the sub-working area intersects with the virtual positioning area, which can realize the completeness self-check of the capsule endoscope and improve the detection probability. At the same time, the visualization of the detection effect can also be realized, and the convenience of the operation of the capsule endoscope can be improved.

It should be understood that although this specification is described in terms of embodiments, not every embodiment only includes an independent technical solution, and this description in the specification is only for the sake of clarity, and those skilled in the art should take the specification as a whole, and each The technical solutions in the embodiments can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

The series of detailed descriptions listed above are only specific descriptions for the feasible embodiments of the present invention, and they are not used to limit the protection scope of the present invention. Changes should all be included within the protection scope of the present invention.

Claims

A self-checking method for partition completeness of a capsule endoscope, characterized in that the method comprises:

Obtaining the working area of the capsule endoscope, dividing the working area into a plurality of sub-working areas, and a straight line passing through any sub-working area arbitrarily has at most two intersections with the current sub-working area;

Correspondingly establish a virtual positioning area for each sub-working area, the virtual positioning area and the working area are in the same spatial coordinate system, and the virtual positioning area completely covers the working area;

dividing each of the virtual positioning areas into a plurality of adjacent voxels with the same size, and each of the voxels has a unique identifier and coordinates;

Drive the capsule endoscope to move in the working area, and sequentially record the images captured by the capsule endoscope when it reaches each working point according to a predetermined frequency, and perform step A synchronously to scan the body in each virtual positioning area. The voxel is marked with a lighting mark, and for each virtual positioning area, when the proportion of the voxels marked with the lighting mark in the current virtual positioning area is not less than the preset ratio threshold, step A is no longer performed synchronously;

Among them, in the initial state, each voxel point is not marked with a lighted mark;

Step A includes:

Sequentially record the position and view orientation of each working point in the space coordinate system;

At each work point in turn, confirm the intersection area of the field of view of the capsule endoscope and the virtual positioning area currently located at the current work point according to the position of the current work point and the direction of the field of view;

Marking a lighting mark on the voxel points that are in the intersection area and are not marked with a lighting mark.
The self-checking method for partition completeness of a capsule endoscope according to claim 1, wherein the capsule endoscope is driven to move in the working area, and the arrival of the capsule endoscope is recorded in sequence according to a predetermined frequency. An image taken at a working point, and step A is performed synchronously to label the voxel with the lit logo, including:

Score the images obtained at each work point. If the score of the image obtained corresponding to the current work point is not less than the preset score, step A is performed synchronously. If the score of the image obtained corresponding to the current work point is less than the preset score, Then, step A is skipped for the current working point.
The self-checking method for partition completeness of a capsule endoscope according to claim 1, wherein when step A is performed, the method further comprises:

If at any working point, the virtual positioning area where the capsule endoscope is currently located is not unique, the virtual positioning area with not all the voxels lit and the smallest volume will be defaulted as the virtual positioning corresponding to the current working point area.
The self-checking method for partition completeness of a capsule endoscope according to claim 1, characterized in that, when step A is performed, a lighting mark is marked on the voxel points in the intersection area and not marked with a lighting mark include:

In the intersection area, obtain the line of sight vector of the current working point and each voxel that is not marked with a lighted mark, and at the same time, according to the acquisition order of the intersection area, the line of sight vector corresponding to each voxel is merged into the same vector set. ;

Traverse the vector set, if the number of sight vectors in any one of the vector sets is at least 2, and the included angle between the two sight vectors is greater than the preset angle threshold, mark the voxel corresponding to the current vector set. Bright logo.
The self-checking method for partition completeness of a capsule endoscope according to claim 4, wherein when step A is performed, the method further comprises:

If the distance between the two positioning points is less than the preset distance threshold, and the angle between the viewing directions of the two positioning points is smaller than the preset angle threshold, then the vector intersecting within the field of view of the two current positioning points is traversed. When set, the calculation of the angle between each voxel in the intersecting range of the visual field and the two line-of-sight vectors corresponding to the two positioning points is omitted.
The self-checking method for partition completeness of a capsule endoscope according to claim 1, wherein the method further comprises:

judging in real time whether the proportion of the voxel points marked with the lit logo in each virtual positioning area is not less than the preset proportion threshold,

If so, drive the capsule endoscope to exit the working mode;

If not, drive the capsule endoscope to continue working mode.
The self-checking method for partition completeness of a capsule endoscope according to claim 1, wherein the method further comprises:

When the capsule endoscope runs for a preset working time in the working area, it is judged whether the proportion of the voxel points marked with the lit logo in each virtual positioning area is not less than the preset proportion threshold, and

If so, drive the capsule endoscope to exit the working mode;

If not, drive the capsule endoscope to continue working mode.
The self-checking method for partition completeness of a capsule endoscope according to claim 1, wherein each of the virtual positioning regions is configured to be spherical.
An electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein the processor implements a partition of a capsule endoscope when the processor executes the program Steps in a completeness self-checking method, the method comprising:

Obtaining the working area of the capsule endoscope, dividing the working area into a plurality of sub-working areas, and a straight line passing through any sub-working area arbitrarily has at most two intersections with the current sub-working area;

Correspondingly establish a virtual positioning area for each sub-working area, the virtual positioning area and the working area are in the same spatial coordinate system, and the virtual positioning area completely covers the working area;

Dividing each of the virtual positioning areas into multiple adjacent voxels with the same size, and each of the voxels has a unique identifier and coordinates;

Drive the capsule endoscope to move in the working area, and sequentially record the images captured by the capsule endoscope when it reaches each working point according to a predetermined frequency, and perform step A synchronously to scan the body in each virtual positioning area. The voxel is marked with a lighting mark, and for each virtual positioning area, when the proportion of the voxels marked with the lighting mark in the current virtual positioning area is not less than the preset ratio threshold, step A is no longer performed synchronously;

Among them, in the initial state, each voxel point is not marked with a lighted mark;

Step A includes:

Sequentially record the position and view orientation of each working point in the space coordinate system;

At each work point in turn, confirm the intersection area of the field of view of the capsule endoscope and the virtual positioning area currently located at the current work point according to the position of the current work point and the direction of the field of view;

Marking a lighting mark on the voxel points that are in the intersection area and are not marked with a lighting mark.
A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps in a self-checking method for partition integrity of a capsule endoscope are implemented, the method comprising: :

Obtaining the working area of the capsule endoscope, dividing the working area into a plurality of sub-working areas, and a straight line passing through any sub-working area arbitrarily has at most two intersections with the current sub-working area;

Correspondingly establish a virtual positioning area for each sub-working area, the virtual positioning area and the working area are in the same spatial coordinate system, and the virtual positioning area completely covers the working area;

dividing each of the virtual positioning areas into a plurality of adjacent voxels with the same size, and each of the voxels has a unique identifier and coordinates;

Drive the capsule endoscope to move in the working area, and sequentially record the images captured by the capsule endoscope when it reaches each working point according to a predetermined frequency, and perform step A synchronously to scan the body in each virtual positioning area. The voxel is marked with a lighting mark, and for each virtual positioning area, when the proportion of the voxels marked with the lighting mark in the current virtual positioning area is not less than the preset ratio threshold, step A is no longer performed synchronously;

Among them, in the initial state, each voxel point is not marked with a lighted mark;

Step A includes:

Sequentially record the position and view orientation of each working point in the space coordinate system;

At each work point in turn, confirm the intersection area of the field of view of the capsule endoscope and the virtual positioning area currently located at the current work point according to the position of the current work point and the direction of the field of view;

Marking a lighting mark on the voxel points that are in the intersection area and are not marked with a lighting mark.