Endoscope collision avoidance alarm device and electronic device

Abstract

The present application belongs to the technical field of endoscope control, and discloses an endoscope anti-collision alarm method and device, equipment and a storage medium. When the first real-time distance between the endoscope and the human tissue is detected to be close by a plurality of specified sensors arranged on the endoscope, the reliability of each specified sensor is calculated, the specified sensor whose reliability reaches a reliability threshold is determined as a target sensor, the second real-time distance between the endoscope and the human tissue is calculated more accurately by using the sensing distance of the reliable target sensor again, and an alarm is given when the second real-time distance is close, so that the sensing distance with low reliability and prone to detection errors can be filtered out through reliability screening, the accuracy of the collected sensing distance is improved, and the misjudgment rate of the endoscope anti-collision alarm is reduced.

Description

Technical Field

[0001] This invention belongs to the field of endoscope control technology, specifically relating to an endoscope anti-collision alarm method, device, equipment, and storage medium. Background Technology

[0002] In minimally invasive surgery, the endoscope is usually supported by an assistant doctor who adjusts its position according to the surgeon's instructions. The long surgical process can cause fatigue for the doctor and affect the surgical outcome. Some complex surgeries require the collaboration of multiple medical staff, which greatly increases medical costs and the unpredictability of surgical results.

[0003] With the development of technology, endoscopic robot-assisted systems have emerged, allowing doctors to control a robotic arm to hold and move the endoscope, greatly improving medical efficiency and precision. However, when observing a specific area of ​​tissue and needing a magnified close-up image, the endoscope tip needs to be brought approximately 2mm close to the mucous membrane to capture the image. At this point, the endoscope tip is very close to the tissue, making it easy to touch and potentially damage it.

[0004] Existing technologies have proposed some anti-collision systems with alarm functions, which will trigger an alarm when the tip of the endoscope comes within a certain distance of human tissue. However, in practice, it has been found that the distance sensor located at the tip of the endoscope is easily interfered with by the complex internal environment (such as mucus, air bubbles, etc.) when detecting the distance between the obstacle (i.e., human tissue) and the tip of the endoscope, resulting in insufficient accuracy in distance detection and a high false alarm rate. Summary of the Invention

[0005] The purpose of this invention is to provide an endoscope anti-collision alarm method, device, equipment, and storage medium, which can reduce the false alarm rate of endoscope anti-collision alarm.

[0006] The first aspect of this invention discloses an endoscope anti-collision alarm method, comprising:

[0007] Acquire the sensing distances of human tissue collected by multiple designated sensors mounted on the endoscope;

[0008] The first real-time distance between the endoscope and human tissue is determined based on multiple sensor distances;

[0009] When the first real-time distance is less than the first safe distance, the reliability of each designated sensor is calculated based on the sensing distance;

[0010] The specified sensor whose reliability reaches the reliability threshold is identified as the target sensor;

[0011] The second real-time distance between the endoscope and human tissue is calculated based on the sensing distance of the target sensor;

[0012] When the second real-time distance is less than the second safe distance, a collision alarm message is issued.

[0013] A second aspect of the present invention discloses an endoscope anti-collision alarm device, comprising:

[0014] The sensing unit is used to acquire the sensing distance of human tissue collected by multiple designated sensors set on the endoscope.

[0015] The distance determination unit is used to determine the first real-time distance between the endoscope and human tissue based on multiple sensor distances;

[0016] The first calculation unit is used to calculate the reliability of each specified sensor based on the sensing distance when the first real-time distance is less than the first safe distance.

[0017] The screening unit is used to identify specified sensors whose reliability reaches the reliability threshold as target sensors.

[0018] The second calculation unit is used to calculate the second real-time distance between the endoscope and human tissue based on the sensing distance of the target sensor.

[0019] An alarm unit is used to issue a collision alarm message when the second real-time distance is less than the second safe distance.

[0020] A third aspect of the present invention discloses an electronic device, including a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the endoscope anti-collision alarm method disclosed in the first aspect, and to realize the various functions of the endoscope anti-collision alarm device disclosed in the second aspect.

[0021] The fourth aspect of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the endoscope anti-collision alarm method disclosed in the first aspect and to realize the various functions of the endoscope anti-collision alarm device disclosed in the second aspect.

[0022] The beneficial effects of this invention are that the provided endoscope anti-collision alarm method, device, equipment, and storage medium calculate the reliability of each designated sensor when multiple designated sensors on the endoscope detect that the first real-time distance between the endoscope and human tissue is close. The designated sensors whose reliability reaches the reliability threshold are selected as target sensors. The sensing distance of the reliable target sensors is then used to calculate a more accurate second real-time distance between the endoscope and human tissue. An alarm is triggered when the second real-time distance is close. Thus, by filtering out sensing distances with low reliability that are prone to detection errors through reliability screening, the accuracy of the collected sensing distances is improved, thereby reducing the false judgment rate of the endoscope anti-collision alarm. Attached Figure Description

[0023] The accompanying drawings illustrate specific examples of the technical solutions described in this invention and, together with the detailed embodiments, form part of the specification, serving to explain the technical solutions, principles, and effects of this invention.

[0024] Unless otherwise specified or defined, the same reference numerals in different figures represent the same or similar technical features, and different reference numerals may be used to represent the same or similar technical features.

[0025] Figure 1 This is a flowchart of an endoscope anti-collision alarm method disclosed in an embodiment of the present invention;

[0026] Figure 2 This is a flowchart of another endoscope anti-collision alarm method disclosed in an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of the structure of an endoscope anti-collision alarm device disclosed in an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention.

[0029] Explanation of reference numerals in the attached figures:

[0030] 301. Sensing unit; 302. Distance measurement unit; 303. First calculation unit; 304. Filtering unit; 305. Second calculation unit; 306. Alarm unit; 401. Memory; 402. Processor. Detailed Implementation

[0031] To facilitate understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0032] Unless otherwise specified or defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. When combined with the technical solutions of the invention in a real-world scenario, all technical and scientific terms used herein may also have meanings corresponding to the purpose of achieving the technical solutions of the invention. The terms "first," "second," etc., used herein are merely for distinguishing names and do not represent a specific number or order. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0033] It should be noted that when a component is considered "fixed" to another component, it can be directly fixed to the other component or there can be an intervening component; when a component is considered "connected" to another component, it can be directly connected to the other component or there can be an intervening component; when a component is considered "mounted" on another component, it can be directly mounted on the other component or there can be an intervening component; when a component is considered "placed" on another component, it can be directly placed on the other component or there can be an intervening component.

[0034] Unless otherwise specified or defined, the terms "described" or "the" as used herein refer to the technical features or technical content mentioned or described prior to the relevant section, which may be the same as or similar to the technical features or technical content mentioned herein. Furthermore, the terms "comprising" and "having," and any variations thereof, as used herein, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0035] Undoubtedly, any technical content or feature that is contrary to or clearly contradicts the purpose of this invention should be excluded.

[0036] like Figure 1 As shown, this invention discloses an endoscope anti-collision alarm method. The subject executing this method can be an electronic device such as a computer, laptop, or tablet, or an endoscope anti-collision alarm device embedded in an electronic device; this invention does not limit this. In this embodiment, an electronic device is used as an example. The method includes the following steps 110-160:

[0037] 110. Electronic devices acquire sensing distances of human tissue collected by multiple designated sensors mounted on an endoscope.

[0038] Endoscopes refer to medical endoscopes such as gastroscopes, colonoscopes, cystoscopes, bronchoscopes, thoracoscopes, or laparoscopes. These endoscopes are held by the robotic arms of a surgical robot. Both the endoscopes and the surgical robot are connected to electronic equipment via wireless or wired networks, allowing them to receive control commands and execute corresponding operations. For example, the endoscope can receive automatic movement commands from the electronic equipment. When the robotic arm of the surgical robot moves its tip to a natural orifice or surgical opening, the automatic movement mode is activated, allowing the endoscope's insertion section to extend and move along the body cavity.

[0039] Multiple environmental sensors can be installed on the endoscope. These sensors can include distance sensors of the same type or combinations of different types, such as image sensors, ultrasonic sensors, or radar sensors. The multiple environmental sensors can be evenly distributed across the insertion portion of the endoscope, generally preferentially located near the tip of the insertion portion. In this embodiment, the multiple designated sensors include all or some of the environmental sensors. Specifically, they can be selected based on the usage status of each environmental sensor. For example, each environmental sensor is associated with a tag indicating whether it is in an aging state.

[0040] Therefore, before performing step 101, the tag information of each environmental sensor set on the endoscope can be obtained first, and several environmental sensors that are not in an aging state can be selected as designated sensors based on the tag information. This allows for the selection of unaged sensors for distance detection, which can improve the accuracy of the collected sensing distance, and at the same time, it eliminates the need to use all sensors for distance detection, thus reducing power consumption.

[0041] In this embodiment of the invention, human tissue includes normal human tissue or abnormal human tissue. Normal human tissue refers to tissue located on the inner wall of human cavities, such as mucosa. Abnormal human tissue can refer to the target lesion located at the end point of the planned path of the endoscope, or it can refer to suspected lesions that may exist on the planned path, i.e., on the inner wall of the cavity, due to lesions of the cavity mucosa.

[0042] In some possible embodiments, specifically, step 110 may include the following steps 1101 to 1104:

[0043] 1101. Control the endoscope to capture images of the current cavity at a specified frequency.

[0044] The endoscope can be controlled to capture images of the current cavity at a specified frequency. The endoscope tip can be equipped with an image sensor. The image sensor can be used to acquire image data to obtain the current cavity image. The current cavity image is used to characterize the cavity environment around the current position of the endoscope. The current position refers to any position on the planned path of the endoscope.

[0045] Optionally, after executing step 1101, the current position corresponding to the current cavity image can be determined, and a preset target image corresponding to the current position can be retrieved; the matching degree between the current cavity image and the preset target image can be calculated. For example, the mean hash algorithm, difference hash algorithm, or perceptual hash algorithm can be used to calculate the similarity between the current cavity image and the preset target image, and the similarity can be used as the matching degree between the two; when the matching degree does not reach the matching threshold, the specified frequency is increased to obtain a new specified frequency, and then the process returns to step 1101 to re-control the endoscope to take pictures at the new specified frequency to obtain the current cavity image.

[0046] The matching threshold can be set to values ​​such as 85%, 90%, or 93%. The preset target image refers to the cavity image corresponding to the current location. If the matching degree is less than the matching threshold, it is considered that the cavity environment near the current location may have changed, i.e., there may be abnormal human tissue. Therefore, the endoscope's imaging frequency can be increased. That is, after adjusting the above-mentioned specified frequency to obtain a new specified frequency, the endoscope is controlled to capture the current cavity image at the new specified frequency. Through the above implementation method, the endoscope's imaging frequency can be adaptively adjusted according to the cavity environment, thereby improving its flexibility and intelligence.

[0047] 1102. Identify the region of interest containing human tissue from the current cavity image.

[0048] Step 1102 may specifically include: normalizing and Gaussian low-pass filtering the current cavity image to obtain a preprocessed image; wherein the preprocessed image is an image with overexposed and / or underexposed noise information removed; then using a pre-built detection and recognition model to detect the preprocessed image to obtain a prediction box; and determining the image region in the current cavity image corresponding to the prediction box as the region of interest where the human tissue is located.

[0049] The pre-built detection and recognition model is trained from a target detection network (such as a target detection network based on the YOLOv3 or YOLOv5 framework). Several sample cavity images can be pre-collected, and human tissue annotations can be performed on each sample cavity image to mark the sample region containing the human tissue. The edges of this sample region are the bounding boxes. Then, the target detection network is trained using each sample cavity image and its bounding box to obtain the detection and recognition model. During training, the loss functions used include, but are not limited to, positional loss functions, angular loss functions, and probability loss functions.

[0050] 1103. Determine the cavity location corresponding to the region of interest as the location of interest.

[0051] After identifying the region of interest from the current cavity image, the cavity location corresponding to the region of interest can be determined as the location of interest, which refers to the location of the cavity where the human tissue is located.

[0052] 1104. Control multiple designated sensors set on the endoscope to measure distances towards the location of interest, and obtain multiple sensing distances.

[0053] In this embodiment of the invention, the ranging direction of multiple designated sensors disposed on multiple endoscopes is adjustable. Therefore, the designated sensors can be controlled to measure distances toward a certain position. After determining the position of interest, the multiple designated sensors can be controlled to measure distances toward the position of interest, thereby obtaining the sensing distance between each designated sensor and the position of interest.

[0054] 120. Electronic devices determine the first real-time distance between the endoscope and human tissue based on multiple sensor distances.

[0055] After acquiring multiple sensing distances in each acquisition cycle, the sensing distance with the smallest value can be determined as the first real-time distance between the endoscope and human tissue.

[0056] 130. When the first real-time distance is less than the first safe distance, the electronic device calculates the reliability of each designated sensor based on the sensing distance.

[0057] When the endoscope is close to the human tissue in the first real-time distance, a reliability test of the designated sensors is initiated. Sensors with a reliability threshold greater than or equal to the threshold are considered reliable. In step 130, the electronic device calculates the reliability of each designated sensor, which may include the following steps 1301-1303:

[0058] 1301. Calculate the average value among the sensing distances of multiple specified sensors.

[0059] It should be noted that, in addition to using the average value of multiple sensing distances as a benchmark reference value, other relevant index values ​​can also be used as benchmark reference values.

[0060] 1302. Determine the degree of deviation between the sensing distance of each specified sensor and the average value.

[0061] 1303. Calculate the reliability of each specified sensor based on the degree of deviation of each specified sensor.

[0062] The degree of deviation of each specified sensor is negatively correlated with its reliability. That is, the greater the deviation of a specified sensor, the lower its reliability; conversely, the smaller the deviation of a specified sensor, the higher its reliability.

[0063] 140. Electronic devices identify a specified sensor whose reliability reaches a reliability threshold as the target sensor.

[0064] It is understandable that if the designated sensor is an environmental sensor whose tag information is not in an aging state, then in step 140, in addition to determining the designated sensor whose reliability reaches the reliability threshold as the target sensor, for the designated sensor whose reliability does not reach the reliability threshold, it is also possible to further determine whether the designated sensor is aging or the measurement error is caused by the obstruction of the cavity by mucus, so as to decide whether to update its tag information.

[0065] The specific method can be as follows: a designated sensor whose reliability has not reached the reliability threshold is identified as the sensor to be tested. The cleaning mechanism of the endoscope is controlled to clean the area corresponding to the sensor to be tested (i.e., the area where the sensor to be tested is located), for example, by spraying water / air. After cleaning, the sensor to be tested is controlled again to collect the distance to be tested against human tissue. If the deviation of the distance to be tested from the above average value is less than a preset value, it is determined that the measurement error of the sensor to be tested is caused by mucus in the cavity, and its label information will not be updated. If the deviation of the distance to be tested from the above average value is greater than or equal to the preset value, it is determined that the sensor to be tested is aging, and its label information is updated.

[0066] This allows for the identification and adaptive labeling of newly aged sensors during each distance measurement process. Once the tag information is updated to indicate an aged state, the aged sensor will not be activated the next time distance sensing is initiated.

[0067] 150. The electronic device calculates the second real-time distance between the endoscope and human tissue based on the sensing distance of the target sensor.

[0068] It is understood that the target sensor may include all or some of the specified sensors, or may not include any of the specified sensors at all. That is, it is possible that the reliability of all specified sensors is less than the reliability threshold. Therefore, preferably, after determining the specified sensor with the reliability threshold as the target sensor in step 140 and before executing step 150, it can be determined whether the number of target sensors is greater than or equal to one, that is, whether the number is at least one. If the number of target sensors is greater than or equal to one, then step 150 is executed.

[0069] In some possible embodiments, if the number of target sensors is not greater than or equal to one, it is considered that the number of target sensors is 0. This triggers an emergency stop on the endoscope and switches its operation mode from the current state to manual control mode, awaiting user intervention. In manual control mode, the user manually controls the surgical robot to move the endoscope.

[0070] In step 150, the sensing distance with the smallest value among all the sensing distances of the target sensors can be determined as the second real-time distance between the endoscope and the human tissue.

[0071] 160. When the second real-time distance is less than the second safe distance, the electronic device issues a collision alarm.

[0072] The second safety distance and the first safety distance mentioned above are both specified thresholds, and their specific values ​​can be specified in advance by the developers. The second safety distance can be less than or equal to the first safety distance.

[0073] When the second real-time distance is less than the second safe distance, the electronic device can issue a collision alarm through interactive methods such as LED lights, voice and / or text to alert the user that there is a risk of collision with the endoscope, thereby facilitating timely manual intervention by the user to ensure safety.

[0074] After the electronic device issues a collision alarm, it can also predict the dangerous area where the endoscope may collide and output the location of the dangerous area in the real-time cavity image on the display screen of the electronic device. This allows users to intuitively understand the possible collision situation of the endoscope and react in time to manually control the surgical robot to drag the endoscope to avoid the dangerous area.

[0075] As can be seen, by implementing the embodiments of the present invention, the reliability screening can be used to filter out sensing distances with low reliability that are prone to detection errors, thereby improving the accuracy of the collected sensing distances and reducing the false alarm rate of endoscope anti-collision alarms.

[0076] Furthermore, to avoid increasing power consumption due to frequent calculations, the designated sensor can be controlled to acquire data only when the endoscope is close to the local tissue to be observed. Based on this, the embodiments of the present invention are disclosed as follows. Figure 2 Another endoscope anti-collision alarm method shown includes the following steps 210-280:

[0077] 210. When the endoscope moves along the planned path, the electronic device acquires the duration of the endoscope's movement.

[0078] It should be noted that "endoscope moving automatically along the planned path" refers to the endoscope moving automatically in automatic control mode. By recording the duration after the endoscope starts at the beginning of the planned path, the movement duration corresponding to each current moment can be obtained. This movement duration is the time between the current moment and the endoscope's start time at the beginning of the planned path.

[0079] 220. The electronic device determines the stopping node located on the planned path and obtains the preset duration corresponding to the stopping node.

[0080] The preset duration refers to the time required for the endoscope to move from the starting point of the planned path to the stopping point. Multiple stopping points can be pre-specified on the planned path. These stopping points are typically located in a cavity segment where abnormal human tissue is pre-identified. Whenever the endoscope moves near a stopping point, it pauses briefly at that point to observe the surrounding human tissue.

[0081] 230. When the ratio of the movement time to the preset time reaches a specified ratio, the electronic device acquires the sensing distance of the human tissue collected by multiple specified sensors set on the endoscope.

[0082] When the ratio of the endoscope's movement time to the preset time reaches a specified ratio (such as 60%, 70%, 80%), it is considered that the endoscope has moved to the vicinity of the stopping point.

[0083] It should be noted that if there are multiple designated stop points on the planned path, the dwell time of the endoscope after reaching the previous stop point should not be included in the travel time of the endoscope to the next stop point. In other words, the travel time recording will stop when the endoscope stops at any stop point. This avoids errors in the endoscope travel time caused by different dwell times at different stop points.

[0084] 240-280. For the description of steps 240-280, please refer to the explanation of steps 120-160 above; the present invention will not repeat it here.

[0085] In steps 210-280, the endoscope can be compared with the preset duration corresponding to the dwell node by monitoring the movement time of the endoscope. This can determine whether the endoscope has moved to the vicinity of the dwell node. At this time, the designated sensor is controlled to collect the sensing distance and acquire the data. This can further reduce the power consumption of computing and prevent the endoscope tip from overheating and burning the human tissue in the cavity due to frequent data acquisition.

[0086] like Figure 3 As shown, this embodiment of the invention discloses an endoscope anti-collision alarm device, including a sensing unit 301, a distance determination unit 302, a first calculation unit 303, a filtering unit 304, a second calculation unit 305, and an alarm unit 306, wherein...

[0087] The sensing unit 301 is used to acquire the sensing distance of human tissue collected by multiple designated sensors set on the endoscope.

[0088] The distance determination unit 302 is used to determine the first real-time distance between the endoscope and human tissue based on multiple sensor distances;

[0089] The first calculation unit 303 is used to calculate the reliability of each specified sensor based on the sensing distance when the first real-time distance is less than the first safe distance.

[0090] The screening unit 304 is used to identify a specified sensor whose reliability reaches the reliability threshold as the target sensor.

[0091] The second calculation unit 305 is used to calculate the second real-time distance between the endoscope and human tissue based on the sensing distance of the target sensor.

[0092] The alarm unit 306 is used to issue a collision alarm message when the second real-time distance is less than the second safe distance.

[0093] Optionally, the first calculation unit 303 is specifically used to calculate the average value among the sensing distances of multiple specified sensors when the first real-time distance is less than the first safe distance, determine the degree of deviation of the sensing distance of each specified sensor from the average value, and calculate the reliability of each specified sensor based on the degree of deviation of each specified sensor.

[0094] As an optional implementation, the endoscope anti-collision alarm device may further include a judgment unit (not shown) for determining whether the number of target sensors is greater than or equal to one after the screening unit 304 determines the designated sensor whose reliability reaches the reliability threshold as the target sensor, and before the second calculation unit 305 calculates the second real-time distance between the endoscope and human tissue based on the sensing distance of the target sensor; if it is determined that the number of target sensors is greater than or equal to one, the second calculation unit 305 is triggered to perform the operation of calculating the second real-time distance between the endoscope and human tissue based on the sensing distance of the target sensor.

[0095] Further optionally, the endoscope anti-collision alarm device may also include a braking unit (not shown) for controlling the endoscope to trigger emergency braking when the judgment unit determines that the number of target sensors is not greater than or equal to one.

[0096] In some embodiments, the sensing unit 301 may include the following sub-units not shown:

[0097] The imaging subunit is used to control the endoscope to capture images of the current cavity at a specified frequency.

[0098] The recognition subunit is used to identify the region of interest where human tissue is located from the current cavity image;

[0099] The positioning subunit is used to determine the cavity position corresponding to the region of interest as the location of interest.

[0100] The ranging subunit is used to control multiple designated sensors set on the endoscope to measure distances toward the location of interest, thereby obtaining multiple sensing distances.

[0101] In some embodiments, the sensing unit 301 may further include the following sub-units not shown:

[0102] The retrieval subunit is used to determine the current position corresponding to the current cavity image after the imaging subunit controls the endoscope to capture the current cavity image at a specified frequency, and retrieve the preset target image corresponding to the current position.

[0103] The matching subunit is used to calculate the matching degree between the current cavity image and the preset target image;

[0104] The adjustment subunit is used to increase the specified frequency to obtain a new specified frequency when the matching degree does not reach the matching threshold.

[0105] Correspondingly, the aforementioned imaging subunit is also used to control the endoscope to capture images of the current cavity at a new specified frequency.

[0106] Further optionally, the aforementioned identification subunit may include the following modules not shown:

[0107] The preprocessing module is used to normalize and Gaussian low-pass filter the current cavity image to obtain a preprocessed image;

[0108] The detection module is used to detect pre-processed images using a pre-built detection and recognition model to obtain predicted bounding boxes;

[0109] The prediction module is used to identify the image region in the current cavity image that corresponds to the prediction box as the region of interest where the human tissue is located.

[0110] As an optional implementation, the endoscope anti-collision alarm device may also include (not shown):

[0111] The recording unit is used to acquire the movement time of the endoscope when it is detected that the endoscope moves automatically according to the planned path. The movement time is the time between the current time and the start time of the endoscope at the starting point of the planned path.

[0112] The node acquisition unit is used to determine the stopping nodes located on the planned path and acquire the preset duration corresponding to the stopping nodes. The preset duration is the time required for the endoscope to move from the starting point of the planned path to the stopping node.

[0113] The triggering unit is used to trigger the sensing unit to perform the operation of acquiring the sensing distance collected by multiple designated sensors on the endoscope for human tissue when the ratio of the movement time to the preset time reaches a specified ratio.

[0114] As an optional implementation, the endoscope anti-collision alarm device may also include (not shown):

[0115] The selection unit is used to acquire the tag information of each environmental sensor set on the endoscope before the sensing unit 301 acquires the sensing distance collected by multiple designated sensors on the endoscope for human tissue. The tag information is used to characterize whether the environmental sensor is in an aging state. The selection unit is used to select multiple environmental sensors that are not in an aging state as designated sensors based on the tag information.

[0116] Correspondingly, the endoscope anti-collision alarm device may also include (not shown):

[0117] The cleaning unit is used to determine the designated sensors whose reliability has not reached the reliability threshold as the sensors to be tested after the first calculation unit 303 calculates the reliability of each designated sensor according to the sensing distance, and controls the cleaning mechanism of the endoscope to clean the area corresponding to the sensor to be tested. After cleaning, the cleaning unit controls the sensor to be tested to collect the distance to be tested from the human tissue again.

[0118] The update unit is used to determine that the sensor under test is aging when the deviation of the distance to be tested from the above average value is greater than or equal to a preset level, and to update its tag information.

[0119] like Figure 4 As shown, an embodiment of the present invention discloses an electronic device, including a memory 401 storing executable program code and a processor 402 coupled to the memory 401;

[0120] The processor 402 calls the executable program code stored in the memory 401 to execute the endoscope anti-collision alarm method described in the above embodiments.

[0121] This invention also discloses a computer-readable storage medium storing a computer program that causes a computer to execute the endoscope anti-collision alarm method described in the above embodiments.

[0122] The purpose of the above embodiments is to reproduce and derive the technical solution of the present invention by way of example, and to fully describe the technical solution, purpose and effect of the present invention. The purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosure of the present invention, and not to limit the scope of protection of the present invention.

[0123] The above embodiments are not an exhaustive list based on the present invention, and there may be many other embodiments not listed. Any substitutions and improvements made without departing from the concept of the present invention are within the protection scope of the present invention.

Claims

1. An endoscope anti-collision alarm device, characterized in that, include: The sensing unit is used to acquire the sensing distance of human tissue collected by multiple designated sensors set on the endoscope. The distance unit is used to take the smallest value among multiple sensing distances as the first real-time distance between the endoscope and human tissue. The first calculation unit is used to calculate the reliability of each specified sensor based on the sensing distance when the first real-time distance is less than the first safe distance. A screening unit is used to identify a specified sensor whose reliability reaches a reliability threshold as a target sensor. The second calculation unit is used to take the sensing distance with the smallest value among all the sensing distances of the target sensors as the second real-time distance between the endoscope and the human tissue. An alarm unit is used to issue a collision alarm message when the second real-time distance is less than the second safe distance; When the first real-time distance is less than the first safe distance, the reliability of each designated sensor is calculated based on the sensing distance, including: When the first real-time distance is less than the first safe distance, calculate the average value of the sensing distances of multiple designated sensors, determine the degree of deviation of the sensing distance of each designated sensor from the average value, and calculate the reliability of each designated sensor based on the degree of deviation of each designated sensor.

2. The endoscope anti-collision alarm device as described in claim 1, characterized in that, Also includes: The judgment unit is used to determine whether the number of target sensors is greater than or equal to one after the screening unit determines the specified sensor whose reliability reaches the reliability threshold as the target sensor, and before the second calculation unit calculates the second real-time distance between the endoscope and human tissue based on the sensing distance of the target sensor; if it is determined that the number of target sensors is greater than or equal to one, the second calculation unit is triggered to perform the operation of calculating the second real-time distance between the endoscope and human tissue based on the sensing distance of the target sensor.

3. The endoscope anti-collision alarm device as described in claim 2, characterized in that, Also includes: The braking unit is used to control the endoscope to trigger emergency braking when the judgment unit determines that the number of target sensors is not greater than or equal to one.

4. The endoscope anti-collision alarm device as described in any one of claims 1 to 3, characterized in that, The sensing unit includes: The imaging subunit is used to control the endoscope to capture images of the current cavity at a specified frequency. The identification subunit is used to identify the region of interest where human tissue is located from the current cavity image; A positioning subunit is used to determine the cavity position corresponding to the region of interest as the location of interest. The ranging subunit is used to control multiple designated sensors mounted on the endoscope to measure distances toward the location of interest, thereby obtaining multiple sensing distances.

5. The endoscope anti-collision alarm device as described in claim 4, characterized in that, The sensing unit further includes: The retrieval subunit is used to determine the current position corresponding to the current cavity image after the imaging subunit controls the endoscope to capture the current cavity image at a specified frequency, and retrieve the preset target image corresponding to the current position; A matching subunit is used to calculate the matching degree between the current cavity image and the preset target image; An adjustment subunit is used to increase the specified frequency to obtain a new specified frequency when the matching degree does not reach the matching threshold. Furthermore, the imaging subunit is also used to control the endoscope to capture images of the current cavity at a new specified frequency.

6. The endoscope anti-collision alarm device as described in any one of claims 1 to 3, characterized in that, Also includes: The recording unit is used to acquire the movement time of the endoscope when it is detected that the endoscope moves automatically according to the planned path. The movement time is the time between the current time and the start time of the endoscope at the starting point of the planned path. The node acquisition unit is used to determine the stopping node located on the planned path and acquire the preset duration corresponding to the stopping node. The preset duration is the time required for the endoscope to move from the starting point of the planned path to the stopping node. The triggering unit is used to trigger the sensing unit to perform the operation of acquiring the sensing distance collected by multiple designated sensors on the endoscope for human tissue when the ratio of the movement time to the preset time reaches a specified ratio.

7. The endoscope anti-collision alarm device as described in claim 1, characterized in that, Also includes: The selection unit is used to acquire the tag information of each environmental sensor set on the endoscope before the sensing unit acquires the sensing distance collected by multiple designated sensors on the endoscope for human tissue. The tag information is used to characterize whether the environmental sensor is in an aging state. Additionally, based on the label information, several environmental sensors that are not in an aging state are selected as designated sensors.

8. The endoscope anti-collision alarm device as described in claim 7, characterized in that, Also includes: The cleaning unit is used to determine the designated sensors whose reliability has not reached the reliability threshold as the sensors to be tested after the first calculation unit calculates the reliability of each designated sensor according to the sensing distance. It controls the cleaning mechanism of the endoscope to clean the area corresponding to the sensor to be tested, and controls the sensor to be tested to collect the distance to be tested against human tissue again after cleaning. The updating unit is used to determine that the sensor under test is aging when the deviation between the distance to be tested and the average value is greater than or equal to a preset degree, and to update the tag information of the sensor under test.

9. An electronic device, characterized in that, It includes a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to implement the various functions of the endoscope anti-collision alarm device as described in any one of claims 1 to 8.

Images