A method for establishing road signs of a ceiling vision robot and a ceiling vision robot

Abstract

The present invention discloses a method for establishing landmarks using a ceiling vision robot. The method controls the ceiling vision robot to observe existing landmark distribution information in real time while moving, and establishes new landmarks based on this existing landmark distribution information. Based on the ceiling vision robot collecting image information from the ceiling perspective, the method addresses the problem of poor positioning accuracy of conventional visual sensors in complex environments. By observing the existing landmark distribution information in the ceiling image in real time and determining whether to establish new landmarks at the ceiling collection location based on this existing landmark distribution information, the method ensures uniform landmark establishment, thereby improving the reliability of the ceiling vision robot's landmark positioning.

Description

Technical Field

[0001] The present invention relates to the field of road sign positioning, and in particular to a method for establishing road signs using a ceiling vision robot. Background Art

[0002] With the widespread application of mobile robots, researchers have conducted in-depth research on the positioning technology of mobile robots. Currently, the positioning technology of mobile robots is mainly achieved through technologies such as vision, lidar and / or inertial navigation. Among them, vision-based positioning methods are widely used in indoor positioning of mobile robots.

[0003] Vision-based indoor positioning methods require the construction of a highly accurate indoor map first. Indoor maps are currently mainly constructed by using environmental landmarks or artificial landmarks. The method of using artificial landmarks to construct indoor maps requires manual placement of landmarks, which has the disadvantages of complex operation and high cost. If the method of using environmental landmarks to construct indoor maps uses a conventional perspective visual sensor to perceive environmental information, when there are many similar obstacles in the environment, the environmental landmarks are easily confused and the calculation is complex. In addition, there is a problem of inaccurate positioning due to the uneven distribution of environmental landmarks. Summary of the Invention

[0004] To address the above issues, the present invention provides a method for establishing landmarks using a ceiling vision robot. This method, based on the ceiling vision robot's collection of environmental information from the ceiling's perspective, addresses the poor positioning accuracy of conventional vision sensors in complex environments. By observing existing landmark distribution information in real time and establishing new landmarks based on this information, the landmarks are evenly distributed, improving the reliability of the ceiling vision robot's landmark positioning. The specific technical solutions of the present invention are as follows:

[0005] A method for establishing a ceiling vision robot road sign, the method comprising: the ceiling vision robot observes existing road sign distribution information in real time during movement, and establishes new road signs based on the existing road sign distribution information.

[0006] Furthermore, the method for the ceiling vision robot to observe the distribution information of existing landmarks in real time during movement specifically includes: controlling the visual sensor mounted on the body of the ceiling vision robot to collect ceiling images in real time; identifying whether there are existing landmarks in the ceiling image, and obtaining the distribution information of the existing landmarks.

[0007] Furthermore, the method for identifying whether there are existing landmarks in the ceiling image specifically includes: extracting corner point features from the ceiling image, and performing feature matching on the corner point features with the features of all established existing landmarks respectively; if there is an existing landmark that successfully matches the corner point features, then there is an existing landmark in the ceiling image; the existing landmark that successfully matches the corner point features is recorded as an existing landmark in the ceiling image; if there is no existing landmark that successfully matches the corner point features, then there is no existing landmark in the ceiling image.

[0008] Furthermore, the method for obtaining the distribution information of existing landmarks specifically includes: when there are existing landmarks in the ceiling image, respectively calculating the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position as the existing landmark distribution information; when there are no existing landmarks in the ceiling image, respectively calculating the distances between all established existing landmarks and the ceiling image acquisition position, and obtaining the lighting information corresponding to all established existing landmarks when they were established, and using the distances between all established existing landmarks and the ceiling image acquisition position and the lighting information corresponding to all established existing landmarks when they were established as the existing landmark distribution information.

[0009] Furthermore, the method of establishing a new landmark based on the existing landmark distribution information specifically includes: when there are existing landmarks in the ceiling image, determining whether the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position are greater than a first distance threshold; if so, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position; if not, controlling the ceiling vision robot not to establish a new landmark at the ceiling image acquisition position.

[0010] Furthermore, the method of establishing a new landmark based on existing landmark distribution information also includes: when there is no existing landmark in the ceiling image, judging whether there is a landmark whose distance from the ceiling image acquisition position is less than a second distance threshold among all the existing landmarks that have been established based on the acquired existing landmark distribution information; if not, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position; if so, judging whether the lighting information corresponding to the ceiling image is different from the lighting information corresponding to all the existing landmarks in a circular area with the ceiling image acquisition position as the center and a radius of the second distance threshold when the landmarks were established based on the acquired existing landmark distribution information; if so, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position; if not, controlling the ceiling vision robot not to establish a new landmark at the ceiling image acquisition position.

[0011] Furthermore, the method of establishing new landmarks based on existing landmark distribution information also includes: when the ceiling vision robot observes in real time during movement that the duration of the absence of existing landmarks in the ceiling image reaches a first time threshold, the ceiling vision robot is controlled to establish a new landmark at the ceiling image acquisition position.

[0012] Furthermore, the method of controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position specifically includes: controlling the ceiling vision robot to establish landmark structure information corresponding to the new landmark at the ceiling image acquisition position; wherein the landmark structure information includes: the posture information of the ceiling vision robot at the ceiling image acquisition position, the angle information of the ceiling vision robot at the ceiling image acquisition position, the posture information of the new landmark relative to the ceiling vision robot, the lighting information when the ceiling vision robot obtains the ceiling image, and using the corner point features in the ceiling image obtained by the ceiling vision robot as the features of the new landmark.

[0013] Furthermore, the lighting information corresponding to the ceiling image includes: the ceiling image is collected during the day, or the ceiling image is collected at night with lights on.

[0014] Furthermore, the method for obtaining lighting information corresponding to the ceiling image includes: after the ceiling vision robot obtains the ceiling image, using an automatic exposure algorithm to analyze the ceiling image to determine the presence of sunlight in the environment. If there is sunlight in the current environment, it is confirmed that the ceiling image was collected during the day; if there is no sunlight in the environment and the lighting in the ceiling image is normal, it is confirmed that the ceiling image was collected at night with the lights on.

[0015] The present invention also provides a ceiling vision robot, which executes the ceiling vision robot landmark establishment method as described above.

[0016] The present invention collects environmental information from the ceiling perspective based on a ceiling vision robot, solving the problem that the robot's conventional perspective for perceiving the environment is limited by complex environmental conditions. By controlling the ceiling vision robot to observe the distribution information of existing landmarks in real time and establishing new landmarks based on the existing landmark distribution information, the landmarks can be established evenly, thereby improving the reliability of the ceiling vision robot's landmark positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a flow chart of a method for establishing a ceiling vision robot road sign according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described below are only used to explain the present invention and are not intended to limit the present invention. It is also understood that for those of ordinary skill in the art, making some changes in design, manufacturing or production based on the technical content disclosed in the present invention is merely a routine technical means and should not be interpreted as insufficient disclosure of the present application.

[0019] Unless otherwise defined, technical or scientific terms used in the present invention shall have the ordinary meanings understood by those skilled in the art in the art to which this application belongs. The terms "comprise," "include," "have," and any variations thereof used in this application are intended to cover non-exclusive inclusions, such as a process or method comprising a series of steps that is not limited to the listed steps but may also include steps not listed, or may include other steps inherent to the process or method.

[0020] As a preferred embodiment of the present invention, a first embodiment of the present invention provides a method for establishing landmarks for a ceiling vision robot. The method comprises: the ceiling vision robot observes existing landmark distribution information in real time while moving, and establishes new landmarks based on the existing landmark distribution information. Specifically, the ceiling vision robot refers to a mobile robot that uses a visual sensor with a ceiling-oriented viewing angle; the visual sensor can be, but is not limited to, a monocular camera, a binocular camera, a depth camera, or a fisheye camera, etc., which has a ceiling image acquisition function; the landmark refers to an identifier used to provide position reference information for the positioning of the ceiling vision robot.

[0021] This embodiment establishes new landmarks based on the existing landmark distribution information observed in real time by the ceiling vision robot, so that the construction of the new landmarks can refer to the existing landmark distribution information, so that the landmarks can be established evenly, and the rationality of the landmark establishment is improved, thereby improving the reliability of the ceiling vision robot's landmark positioning.

[0022] Based on the above embodiments, as a preferred embodiment of the present invention, the method for a ceiling vision robot to observe existing landmark distribution information in real time while moving, as described in the second embodiment of the present invention, specifically includes: controlling a visual sensor mounted on the ceiling vision robot to capture ceiling images in real time, controlling the ceiling vision robot to identify whether existing landmarks exist in the ceiling images, and obtaining existing landmark distribution information. Specifically, the visual sensor mounted on the ceiling vision robot can be, but is not limited to, a sensor device with image acquisition capabilities, such as a monocular camera or a binocular camera; the visual sensor is mounted on the ceiling vision robot at a ceiling vision angle, that is, the visual image captured by the visual sensor is a ceiling image. This embodiment achieves real-time monitoring of existing landmark distribution information by controlling the visual sensor to capture ceiling images in real time, enabling the ceiling vision robot to establish landmarks more accurately and reasonably.

[0023] Based on the above embodiments, as a preferred embodiment of the present invention, the method for identifying whether existing landmarks exist in a ceiling image, as described in the third embodiment of the present invention, specifically includes: extracting corner features from the ceiling image, and matching the corner features with the features of all established existing landmarks. If an existing landmark successfully matches the corner features, then an existing landmark exists in the ceiling image; the existing landmark successfully matched with the corner features is recorded as an existing landmark in the ceiling image; if no existing landmark successfully matches the corner features, then no existing landmark exists in the ceiling image. Specifically, the method for extracting corner features from the ceiling image can be, but is not limited to, an algorithm with corner feature extraction capabilities, such as the Harris corner detection algorithm. Since the Harris corner detection algorithm is a conventional technical means, the specific method for extracting corner features from this algorithm is not further described in this embodiment. The corner features are features that remain stable for the same scene even when the image acquisition perspective changes. Successful matching of corner point features with existing landmark features occurs when the degree of overlap between the angle features extracted from the ceiling image and the features of the existing landmarks reaches a preset matching threshold. The preset matching threshold is a value set based on the positioning accuracy requirements of the ceiling vision robot to limit the degree of matching between corner point features and existing landmark features. It should be noted that the features of the existing landmark are acquired and recorded when the landmark is created. This embodiment improves the reliability of landmark distribution information in ceiling images through feature matching.

[0024] Based on the above embodiments, as a preferred embodiment of the present invention, the method for obtaining the distribution information of existing landmarks described in the fourth embodiment of the present invention specifically includes: when there are existing landmarks in the ceiling image, the distances between all existing landmarks in the ceiling image and the ceiling vision robot are calculated respectively as the existing landmark distribution information; when there are no existing landmarks in the ceiling image, the distances between all established existing landmarks and the ceiling image acquisition position are calculated respectively, and the lighting information corresponding to all established existing landmarks when they are established is obtained, and the distances between all established existing landmarks and the ceiling image acquisition position and the lighting information corresponding to all established existing landmarks when they are established are used as the existing landmark distribution information. Specifically, based on the presence of existing landmarks in the ceiling image, the distribution information of the existing landmarks corresponding to the ceiling image is obtained accordingly. When there are existing landmarks in the ceiling image, the establishment of new landmarks only needs to refer to the distance between the existing landmarks in the ceiling image and the ceiling vision robot. When there are no existing landmarks in the ceiling image, the establishment of new landmarks needs to refer to the distance between all existing landmarks and the ceiling image acquisition position. This avoids the situation where the existing landmarks near the ceiling image acquisition position cannot be found in the ceiling image due to the limitation of the viewing angle. By counting the distances of all existing landmarks and the ceiling image acquisition position, the distances between all existing landmarks and the ceiling vision robot are mastered. At the same time, the lighting information corresponding to all existing landmarks at the time of establishment is obtained as the existing landmark distribution information. In this method, the lighting information corresponding to the establishment of the landmark is used as a reference factor for the establishment of the new landmark, so as to avoid the situation where the reliability of the overall landmark positioning is affected by the different lighting information of different landmark points during establishment.

[0025] Based on the above embodiments, as a preferred embodiment of the present invention, the method for establishing new landmarks based on existing landmark distribution information in the fifth embodiment of the present invention specifically includes: when there are existing landmarks in the ceiling image, judging whether the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position are greater than a first distance threshold based on the acquired existing landmark distribution information; specifically, the first distance threshold is a value set according to the ceiling vision robot's requirements for landmark positioning accuracy to make the landmark establishment more uniform, and by judging the distance between the existing landmarks in the ceiling image and the ceiling image acquisition position, supplemented by distance limitations, to determine whether new landmarks need to be established, the ceiling vision robot can have more uniform and reliable landmarks to achieve precise positioning.

[0026] If the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position are greater than the first distance threshold, the ceiling vision robot is controlled to establish new landmarks at the ceiling image acquisition position; specifically, when the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position are greater than the first distance threshold, it means that there are no landmarks in the circular range with the ceiling image acquisition position as the center and the radius of the first distance threshold to provide positioning assistance for the ceiling vision robot. Therefore, new landmarks need to be established to reduce the area not covered by landmarks and improve the reliability of the ceiling vision robot using landmarks for positioning.

[0027] If there is at least one existing landmark among all the existing landmarks in the ceiling image and the distance between it and the ceiling vision robot is less than or equal to the first distance threshold, the ceiling vision robot is controlled not to establish a new landmark at the ceiling image acquisition position; specifically, when there is at least one existing landmark among all the existing landmarks in the ceiling image and the distance between it and the ceiling image acquisition position is less than or equal to the first distance threshold, it means that there is an existing landmark within a circular range with the ceiling image acquisition position as the center and the radius of the first distance threshold to provide positioning assistance for the ceiling vision robot, so there is no need to establish a new landmark, avoiding the situation where some areas are densely distributed and some areas are less distributed due to uneven landmark establishment.

[0028] In the case where existing landmarks exist in the ceiling image, this embodiment determines the distribution of the existing landmarks within a circular range centered on the ceiling image acquisition position and with a radius of a first distance threshold, and determines whether to establish new landmarks based on the distribution, thereby avoiding the problem of uneven landmark establishment.

[0029] Based on the above embodiments, as a preferred embodiment of the present invention, in the sixth embodiment of the present invention, the method of establishing new landmarks based on existing landmark distribution information also includes: when there are no existing landmarks in the ceiling image, judging whether there are landmarks in all the established existing landmarks whose distance from the ceiling image acquisition position is less than a second distance threshold based on the acquired existing landmark distribution information; specifically, the second distance threshold is a value set according to the ceiling vision robot's requirements for landmark positioning accuracy to make the landmark establishment more uniform. It should be noted that the second distance threshold is less than or equal to the first distance threshold.

[0030] If there is no landmark among all the existing landmarks that have been established, the distance from the ceiling image acquisition position to which is less than the second distance threshold is not present, the ceiling vision robot is controlled to establish a new landmark at the ceiling image acquisition position; specifically, when there is no existing landmark in the ceiling image, when there is no landmark among all the existing landmarks that have been established, the distance from the ceiling image acquisition position to which is less than the second distance threshold is not present, it means that there is no existing landmark to provide positioning assistance to the ceiling vision robot within the circular range centered on the ceiling image acquisition position and with the second distance threshold as the radius. In order to make the landmark establishment more uniform and to provide better positioning assistance to the ceiling vision robot, the ceiling vision robot is controlled to establish a new landmark at the ceiling image acquisition position.

[0031] If a landmark exists among all the existing landmarks whose distance from the ceiling image acquisition position is less than a second distance threshold, then, based on the acquired existing landmark distribution information, it is determined whether the lighting information corresponding to the ceiling image differs from the lighting information corresponding to all the existing landmarks within a circular area centered at the ceiling image acquisition position and with a radius of the second distance threshold at the time of establishment. If so, the ceiling vision robot is controlled to establish a new landmark at the ceiling image acquisition position. Specifically, if no existing landmark exists in the ceiling image, and if a landmark exists among all the existing landmarks whose distance from the ceiling image acquisition position is less than the second distance threshold, then the main reference factor for establishing the new landmark is converted from distance to lighting information. By determining whether the lighting information corresponding to the ceiling image and the lighting information corresponding to the landmark whose distance from the ceiling vision robot is less than the second distance threshold are all the same, if there is a difference, a new landmark is established to improve the reliability of the landmark.

[0032] Based on the above embodiments, as a preferred embodiment of the present invention, the method for establishing new landmarks based on existing landmark distribution information in the seventh embodiment of the present invention further includes: when the ceiling vision robot observes in real time during movement that the ceiling image does not contain existing landmarks for a duration that reaches a first time threshold, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition location. Specifically, the first time threshold is used to limit the maximum duration that the ceiling vision robot cannot observe existing landmarks, and can be, but is not limited to, 3 seconds, 5 seconds, or 10 seconds. In this embodiment, when the ceiling vision robot observes in real time during movement that the ceiling image does not contain existing landmarks for a duration that reaches the first time threshold, a new landmark is established at the ceiling image acquisition location when the first time threshold is reached, in order to make landmark establishment more uniform and reduce the area of ​​landmark coverage.

[0033] Based on the above embodiments, as a preferred embodiment of the present invention, the method of controlling a ceiling vision robot to establish a new landmark at a ceiling image acquisition position in the eighth embodiment of the present invention specifically includes: controlling the ceiling vision robot to establish landmark structure information corresponding to the new landmark at the ceiling image acquisition position; wherein, it should be noted that the landmark structure information includes: the position information of the ceiling vision robot at the ceiling image acquisition position, the angle information of the ceiling vision robot at the ceiling image acquisition position, the position information of the new landmark relative to the ceiling vision robot, the corresponding lighting information when the ceiling vision robot acquires the ceiling image at the ceiling image acquisition position, and the features of the new landmark; the features of the new landmark refer to the corner features in the ceiling image acquired by the ceiling vision robot. This embodiment establishes a landmark at a specified location by constructing landmark structure information, and achieves the purpose of landmark-assisted positioning of the ceiling vision robot through the position information contained in the landmark structure information.

[0034] It should be noted that in the above embodiment, the landmark establishment method for the ceiling vision robot must be executed under normal ambient lighting conditions. Normal lighting conditions refer to conditions in which image feature points can be clearly distinguished in the visual image captured by the visual sensor to extract corner features. Normal lighting conditions include daytime and nighttime with the lights on. Therefore, the lighting information corresponding to the ceiling image in the above embodiment includes: the ceiling image being captured during the daytime and the ceiling image being captured at night with the lights on.

[0035] Based on the above embodiments, as a preferred embodiment of the present invention, in a ninth embodiment of the present invention, the method for obtaining lighting information corresponding to a ceiling image is as follows: after the ceiling vision robot obtains the ceiling image, it uses an automatic exposure algorithm to analyze the ceiling image and determine the presence of sunlight in the environment. If sunlight is present in the current environment, it is determined that the ceiling image was acquired during the day; conversely, if sunlight is not present in the current environment, it is determined that the ceiling image was acquired at night with the lights on. This embodiment analyzes the presence of sunlight in the environment based on the automatic exposure algorithm and determines the lighting information corresponding to the ceiling image based on the presence of sunlight in the environment. This enables the ceiling vision robot to use the lighting information as a reference condition for establishing new landmarks, indirectly improving the reliability of landmark establishment.

[0036] Based on the above embodiments, as a preferred embodiment of the present invention, the tenth embodiment of the present invention provides a method for establishing a ceiling vision robot road sign, such as Figure 1 As shown, the ceiling vision robot landmark establishment method specifically includes:

[0037] Step 1: Control the visual sensor mounted on the ceiling vision robot to collect ceiling images in real time, and proceed to step 2; specifically, the visual sensor can be, but is not limited to, a monocular camera, a binocular camera, or a fisheye camera with the image acquisition direction facing the ceiling.

[0038] Step 2: Extract corner features from the ceiling image and perform feature matching between the corner features and the features of existing landmarks. If the features of the existing landmark successfully match the corner features, proceed to step 31; if the features of the existing landmark successfully match the corner features, proceed to step 41. Specifically, the method for extracting corner features from the ceiling image may be, but is not limited to, using an algorithm with corner feature extraction function, such as the Harris corner detection algorithm, to identify and extract corner features from the ceiling image. The features of the existing landmark refer to the corner features in a ceiling image corresponding to the existing landmark recorded when the landmark was established.

[0039] Step 31: Confirm that there are existing landmarks in the ceiling image, calculate the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position as existing landmark distribution information, and proceed to step 32; specifically, when the corner point features in the ceiling image successfully match the features of the existing landmarks, it is preliminarily determined that there are existing landmarks in the ceiling image, and the existence of the existing landmarks in the ceiling image is determined by feature matching. Then, the existing landmark distribution information in the ceiling image is further calculated based on the existing landmarks in the ceiling image, so that the ceiling vision robot can confirm whether to establish a new landmark at the ceiling image acquisition position based on the existing landmark distribution information.

[0040] Step 32: Determine whether the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position are greater than the first distance threshold based on the existing landmark distribution information. If so, proceed to step 5; if not, proceed to step 6. Specifically, calculate the distances between all existing landmarks and the ceiling image acquisition position of the ceiling vision robot to determine whether there are existing landmarks that are not within the ceiling image acquisition range of the ceiling vision robot but exist within the first distance threshold range from the ceiling image acquisition position of the ceiling vision robot, so as to avoid the failure to observe existing landmarks near the ceiling vision robot due to the limitation of the ceiling image acquisition range of the ceiling vision robot, resulting in repeated landmark establishment.

[0041] Step 41: Confirm that there are no existing landmarks in the ceiling image, calculate the distances between all the existing landmarks and the ceiling image acquisition position, and obtain the lighting information corresponding to all the existing landmarks when they were established. The distances between all the existing landmarks and the ceiling image acquisition position and the lighting information corresponding to all the existing landmarks when they were established are used as the existing landmark distribution information. At the same time, determine whether the duration during which the ceiling vision robot observes that there are no existing landmarks in the ceiling image reaches a first time threshold. If not, proceed to step 42; if so, proceed to step 5. Specifically, this step limits the maximum duration during which the ceiling vision robot observes that there are no existing landmarks in the ceiling image to the first time threshold, so as to achieve direct establishment of new landmarks when no existing landmarks are observed in the ceiling image for a long time, thereby ensuring the rationality of landmark establishment.

[0042] Step 42: Based on the existing landmark distribution information, determine whether there is a landmark among all the existing landmarks whose distance from the ceiling image acquisition position is less than the second distance threshold. If not, proceed to step 5; if so, proceed to step 43. Specifically, this step calculates the distance between all the existing landmarks and the ceiling image acquisition position and compares it with the second distance threshold to determine whether there is a landmark that is not observed by the ceiling image near the position where the ceiling vision robot collects the ceiling image, and determines whether a new landmark needs to be established based on the distance, so that the distribution of the landmarks is uniform.

[0043] Step 43: Determine, based on the existing landmark distribution information, whether the lighting information corresponding to the ceiling image is different from the lighting information corresponding to all existing landmarks within a circular area centered on the ceiling image acquisition position and with a radius of the second distance threshold. If so, proceed to step 5; if not, proceed to step 6. Specifically, this step uses lighting information as a condition for determining whether to establish a new landmark, so that when there are existing landmarks nearby, different landmarks can be established for different lighting information, thereby making the ceiling vision robot's positioning based on landmarks more accurate and reliable.

[0044] Step 5: Control the ceiling vision robot to establish a new landmark at the ceiling image acquisition position and record the landmark structure information corresponding to the new landmark. Specifically, the landmark structure information includes, but is not limited to: the position information of the ceiling vision robot at the ceiling image acquisition position, the angle information of the ceiling vision robot at the ceiling image acquisition position, the position information of the new landmark relative to the ceiling vision robot, the corresponding lighting information when the ceiling vision robot acquires the ceiling image at the ceiling image acquisition position, and the features of the new landmark. The features of the new landmark refer to the corner features in the ceiling image acquired by the ceiling vision robot. The landmark structure information listed above is only the information required in the above steps. In the actual application of this method, the landmark structure information may also include other information.

[0045] Step 6: Control the ceiling vision robot not to establish a new landmark at the ceiling image acquisition position.

[0046] The ceiling vision robot landmark construction method provided in this embodiment solves the problem of complex environment and easy confusion of landmarks caused by the current use of conventional perspectives to construct environmental landmarks by using ceiling images. It also controls the ceiling vision robot to observe the existing landmark distribution information in real time and establish new landmarks based on the existing landmark distribution information, so that the landmarks can be established evenly, thereby improving the reliability of the ceiling vision robot's landmark positioning.

[0047] Based on the above embodiments, as a preferred embodiment of the present invention, the eleventh embodiment of the present invention provides a ceiling vision robot, wherein the ceiling vision robot is equipped with a visual sensor with a viewing angle facing the ceiling. The visual sensor can be, but is not limited to, a monocular camera, a binocular camera, a depth camera, or a fisheye camera, etc., which has a visual image acquisition function. The ceiling vision robot executes the ceiling vision robot landmark construction method described in the above embodiments based on the ceiling-facing visual sensor, thereby achieving uniform landmark construction and improving the positioning accuracy and reliability of the ceiling vision robot based on landmark positioning.

[0048] Obviously, the above-mentioned embodiments are only some embodiments of the present invention, rather than all embodiments, and the technical solutions between the various embodiments can be combined with each other. In the above-mentioned embodiments of the present invention, the descriptions of the various embodiments have different focuses. For the parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed technical contents can be implemented in other ways. It should also be noted that the various specific technical features described in the above-mentioned specific embodiments can be combined in any suitable way unless there is any contradiction. In order to avoid unnecessary repetition, the various possible combinations will not be described separately in the embodiments of the present invention.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for establishing a ceiling vision robot road sign, characterized in that: The ceiling vision robot landmark creation method comprises: the ceiling vision robot observes existing landmark distribution information in real time during movement, and creates new landmarks based on the existing landmark distribution information; The method for the ceiling vision robot to observe the distribution information of existing road signs in real time during movement specifically includes: Control the visual sensor mounted on the ceiling vision robot to collect ceiling images in real time; Identify whether there are existing landmarks in the ceiling image and obtain the distribution information of existing landmarks; The method for obtaining existing road sign distribution information specifically includes: When there are existing landmarks in the ceiling image, the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position are calculated as the existing landmark distribution information; When there are no existing landmarks in the ceiling image, the distances between all existing landmarks and the ceiling image acquisition position are calculated respectively, and the lighting information corresponding to all existing landmarks when they were established is obtained. The distances between all existing landmarks and the ceiling image acquisition position and the lighting information corresponding to all existing landmarks when they were established are used as the existing landmark distribution information.

2. The method for establishing a ceiling vision robot road sign according to claim 1, characterized in that: The method for identifying whether there are existing landmarks in a ceiling image specifically includes: extracting corner point features from the ceiling image, and performing feature matching on the corner point features with features of all established existing landmarks; if an existing landmark successfully matches the corner point features, then an existing landmark exists in the ceiling image; and recording the existing landmark successfully matched with the corner point features as an existing landmark in the ceiling image; if no existing landmark successfully matches the corner point features, then no existing landmark exists in the ceiling image.

3. The method for establishing a ceiling vision robot road sign according to claim 2, characterized in that: The method for establishing a new landmark based on existing landmark distribution information specifically includes: when there are existing landmarks in the ceiling image, judging whether the distances between all existing landmarks in the ceiling image and the ceiling image acquisition position are greater than a first distance threshold based on the acquired existing landmark distribution information; if so, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position; if not, controlling the ceiling vision robot not to establish a new landmark at the ceiling image acquisition position.

4. The method for establishing a ceiling vision robot road sign according to claim 3, characterized in that: The method for establishing a new landmark based on existing landmark distribution information also includes: when there is no existing landmark in the ceiling image, judging whether there is a landmark whose distance from the ceiling image acquisition position is less than a second distance threshold among all the existing landmarks that have been established based on the acquired existing landmark distribution information; if not, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position; if so, judging whether the lighting information corresponding to the ceiling image is different from the lighting information corresponding to all the existing landmarks that exist in a circular area centered on the ceiling image acquisition position and with a radius of the second distance threshold when the landmarks are established based on the acquired existing landmark distribution information; if so, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position; if not, controlling the ceiling vision robot not to establish a new landmark at the ceiling image acquisition position.

5. The method for establishing a ceiling vision robot road sign according to claim 4, characterized in that: The method for establishing a new landmark based on existing landmark distribution information also includes: when the ceiling vision robot observes in real time during movement that the duration of the absence of existing landmarks in the ceiling image reaches a first time threshold, controlling the ceiling vision robot to establish a new landmark at the ceiling image acquisition position.

6. The method for establishing a ceiling vision robot road sign according to claim 5, characterized in that: The method for controlling a ceiling vision robot to establish a new landmark at a ceiling image acquisition position specifically includes: controlling the ceiling vision robot to establish landmark structure information corresponding to the new landmark at the ceiling image acquisition position; wherein the landmark structure information includes: posture information of the ceiling vision robot at the ceiling image acquisition position, angle information of the ceiling vision robot at the ceiling image acquisition position, posture information of the new landmark relative to the ceiling vision robot, lighting information corresponding to when the ceiling vision robot acquires the ceiling image, and using corner point features in the ceiling image acquired by the ceiling vision robot as features of the new landmark.

7. The method for establishing a ceiling vision robot road sign according to claim 6, characterized in that: The lighting information corresponding to the ceiling image includes: the ceiling image is collected during the day, or the ceiling image is collected at night with lights on.

8. The method for establishing a ceiling vision robot road sign according to claim 7, characterized in that: The method for obtaining lighting information corresponding to the ceiling image includes: after the ceiling vision robot obtains the ceiling image, using an automatic exposure algorithm to analyze the ceiling image to determine the presence of sunlight in the environment. If sunlight exists in the current environment, it is confirmed that the ceiling image was collected during the day; if there is no sunlight in the environment and the lighting in the ceiling image is normal, it is confirmed that the ceiling image was collected at night with the lights on.

9. A ceiling vision robot, characterized in that: The ceiling vision robot executes the ceiling vision robot landmark establishment method according to any one of claims 1 to 8.

Images