Base station acceptance method, device, apparatus and storage medium

Abstract

The application discloses a base station acceptance method, device and equipment and a storage medium. The method comprises the following steps: acquiring a device image of a device to be accepted in a base station collected by a camera device; identifying the device image to obtain device information in the device image; and determining an acceptance result of the device to be accepted according to the device information. The application realizes that an acceptance personnel only needs to collect a device image by a camera device to complete automatic base station acceptance, without coordinating acceptance personnel of all parties to go to the station, thereby greatly saving acceptance time and improving acceptance efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, and particularly relates to a base station acceptance method, device and equipment and a storage medium. BACKGROUND

[0002] A communication base station must pass through an engineering quality acceptance link to be able to be put into a network. A traditional base station acceptance mode mainly relies on manual operation to be completed, and needs to coordinate four parties of personnel, such as an operator engineering supervisor, a maintenance agent, a manufacturer, and an engineering construction party, to jointly participate in acceptance on site, so that the personnel on-site cost is high, coordination is difficult, and the acceptance efficiency is low. SUMMARY

[0003] The main purpose of the present application is to provide a base station acceptance method, device, equipment and storage medium, and aims to solve the technical problem of low acceptance efficiency of the base station acceptance mode relying on manual operation in the prior art.

[0004] To achieve the above purpose, the present application provides a base station acceptance method, which comprises the following steps:

[0005] An equipment image of a to-be-inspected equipment in a base station is acquired by a camera equipment;

[0006] The equipment image is identified to obtain equipment information in the equipment image;

[0007] An acceptance result of the to-be-inspected equipment is determined according to the equipment information.

[0008] Optionally, the step of identifying the equipment image to obtain the equipment information in the equipment image comprises:

[0009] An object detection is performed on the equipment image with various to-be-inspected equipment as a detection object to obtain a detection result, and the detection result is taken as the equipment information in the equipment image, wherein the detection result comprises a quantity of various to-be-inspected equipment in the equipment image;

[0010] The step of determining the acceptance result of the to-be-inspected equipment according to the equipment information comprises:

[0011] Whether the quantity of various to-be-inspected equipment in the equipment image is consistent with a preset quantity is determined according to the equipment information;

[0012] If the quantity of various to-be-inspected equipment in the equipment image is inconsistent with the preset quantity, an unqualified acceptance result of the to-be-inspected equipment is obtained.

[0013] Optionally, the detection result further comprises position information of the to-be-inspected equipment present in the equipment image, and after the step of determining whether the number of each type of the to-be-inspected equipment in the equipment image is consistent with the preset number according to the equipment information, the method further comprises:

[0014] If the number of each type of the to-be-inspected equipment in the equipment image is consistent with the preset number, determining whether the position relationship between the to-be-inspected equipment in the equipment image is consistent with a preset position relationship according to the position information in the equipment information;

[0015] If the position relationship between the to-be-inspected equipment in the equipment image is inconsistent with the preset position relationship, obtaining an unqualified inspection result of the to-be-inspected equipment.

[0016] Optionally, the to-be-inspected equipment comprises an antenna device in the base station, and the step of identifying the equipment image to obtain the equipment information in the equipment image comprises:

[0017] identifying the equipment image with the antenna device as the identification object to obtain an antenna device contour in the equipment image, and taking the antenna device contour as the equipment information in the equipment image;

[0018] The step of determining the inspection result of the to-be-inspected equipment according to the equipment information comprises:

[0019] performing straight line fitting on a side edge in the antenna device contour corresponding to a pixel point on the equipment image to obtain a side edge straight line;

[0020] calculating a visual downtilt angle of the antenna device in the equipment image according to a slope of the side edge straight line;

[0021] determining a relative downtilt angle of the antenna device relative to the ground according to the visual downtilt angle, and taking the relative downtilt angle as the inspection result of the antenna device.

[0022] Optionally, the equipment image comprises a plurality of equipment images obtained by horizontally surrounding the antenna device at different surrounding angles by a camera device, and the step of determining the relative downtilt angle of the antenna device relative to the ground according to the visual downtilt angle comprises:

[0023] determining an amplitude of the visual downtilt angle corresponding to each of the equipment images with respect to the surrounding angle;

[0024] calculating the relative downtilt angle of the antenna device relative to the ground according to the amplitude.

[0025] Optionally, the step of performing linear fitting on the pixel points corresponding to one side of the antenna device contour in the device image to obtain a side line comprises:

[0026] mapping the image coordinates of one side of the antenna device contour in the device image to a pixel coordinate system to obtain pixel points corresponding to the side in the device image;

[0027] performing linear fitting on the pixel points to obtain a side line.

[0028] Optionally, the step of obtaining the device image of the device to be accepted in the base station collected by the camera device comprises:

[0029] obtaining video stream data of the device to be accepted in the base station collected by the camera device;

[0030] extracting key frames from the video stream data to obtain the device image.

[0031] To achieve the above object, the present application further provides a base station acceptance device, wherein the base station acceptance device comprises:

[0032] an acquisition module configured to acquire a device image of a device to be accepted in a base station collected by a camera device;

[0033] an identification module configured to identify the device image to obtain device information in the device image;

[0034] a determination module configured to determine an acceptance result of the device to be accepted according to the device information.

[0035] To achieve the above object, the present application further provides a base station acceptance device, wherein the base station acceptance device comprises a memory, a processor and a base station acceptance program stored in the memory and executable on the processor, and the base station acceptance program implements the steps of the base station acceptance method when executed by the processor.

[0036] In addition, to achieve the above object, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a base station acceptance program, and the base station acceptance program implements the steps of the base station acceptance method when executed by a processor.

[0037] In the present application, by acquiring a device image of a device to be accepted in a base station collected by a camera device, image recognition is performed on the device image to obtain device information in the image, and an acceptance result of the device to be accepted is determined according to the device information, so that an acceptance personnel only needs to collect a device image by a camera device to complete automatic base station acceptance, without coordinating acceptance personnel from all parties to go to the station, thereby greatly saving acceptance time and improving acceptance efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 A flowchart of a first embodiment of the base station acceptance method of the present application;

[0039] Figure 2 A schematic diagram of an antenna device acceptance scenario related to an embodiment of the present application;

[0040] Figure 3 A coordinate system conversion formula related to an embodiment of the present application;

[0041] Figure 4 A schematic diagram of an acceptance process related to an embodiment of the present application;

[0042] Figure 5 A schematic diagram of a base station acceptance system related to an embodiment of the present application;

[0043] Figure 6 A functional module schematic diagram of a preferred embodiment of the base station acceptance device of the present application;

[0044] Figure 7 A structural schematic diagram of a hardware operating environment related to an embodiment of the present application.

[0045] The implementation of the object of the present application, the functional characteristics and the advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0047] The embodiments of the base station acceptance method provided by the embodiments of the present application need to be explained that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in an order different from that described herein.

[0048] Reference Figure 1 , Figure 1 A flowchart of a first embodiment of the base station acceptance method of the present application. In this embodiment, the execution subject of the base station acceptance method of the present application can be a smart phone, a personal computer, a server and the like. For the convenience of description, the following describes each embodiment with the acceptance system as the execution subject.

[0049] In this embodiment, the base station acceptance method comprises:

[0050] Step S10, acquiring a device image of a device to be accepted in the base station collected by a camera device;

[0051] In the embodiment, for a base station to be accepted, an image of the equipment to be accepted in the base station can be collected by a camera device, which is referred to as an equipment image below. According to the acceptance items, the camera device is set to have a shooting angle such that the equipment to be accepted has part or all of its appearance in the equipment image. The equipment image can be a photo directly taken by the camera device, or a video taken by the camera device with video frames as the equipment images. The image collection can be performed by a person holding the camera device, or by a camera device installed on a drone. Regardless of the way, the operation can be completed by one person, and the operator can not need to have professional acceptance experience and ability, but only needs to take photos or videos with clear quality and appropriate angle according to the acceptance items. In some places where climbing is required, for example, when the antenna equipment is accepted, the drone can be used to collect the equipment image to solve the problem of high risk of manual climbing.

[0052] The equipment to be accepted can be any equipment to be accepted in the base station, such as hardware equipment in the machine room, antenna equipment outside the machine room, etc., which can be a single device or a combination of multiple devices. The acceptance items can include the installation position of the equipment, the type of the equipment, the number of the equipment, and other items that can be observed and judged by the human eye to determine whether they are compliant.

[0053] The acceptance system can obtain the equipment image from the camera device in real time or non-real time, and process and analyze the equipment image in real time or non-real time to obtain the acceptance result.

[0054] Further, in an embodiment, the step S10 comprises:

[0055] Step S101, obtaining video stream data of the equipment to be accepted in the base station collected by the camera device;

[0056] Step S102, frame extraction is performed on the video stream data to obtain key frames, and the key frames are taken as the equipment images.

[0057] The video stream data of the base station to be accepted equipment can be collected by the camera equipment, the video stream data collected by the camera equipment is acquired by the acceptance system, the key frame is obtained by frame extraction to the video stream data, and then the key frame is used as the equipment image for subsequent identification. Specifically, in an embodiment, the acceptance equipment can parse the I frame from the video stream data as the key frame. Wherein, the I frame is the key frame in the video stream, which is a full-frame compressed encoded frame, and the amount of data information is large, and only the frame data is needed to reconstruct the complete image when decoding. The I frame is the base frame (the first frame) of the frame group GOP, which can be judged by NALU type. If (NALU type & 0001 1111) = 5, the frame is I frame; the I frame describes the details of the image background and the motion body, and is the reference frame of P frame and B frame, and the quality directly affects the quality of each frame in the same group. In other embodiments, the acceptance system can extract the video frame with clarity above a certain clarity from each video frame in the video stream data as the key frame, so as to improve the accuracy of subsequent image recognition.

[0058] Step S20, identifying the equipment image to obtain the equipment information in the equipment image;

[0059] The acceptance system can identify the equipment image to obtain the equipment information in the equipment image after acquiring the equipment image. Specifically, the information type of the equipment information identified from the equipment image can be set in advance, and different information types can be set according to different types of equipment to be accepted or according to different acceptance items. For example, when the acceptance item is the equipment type, the information type of the equipment information can be set as the information type capable of representing the equipment type appearing in the equipment image. For another example, when the type of the equipment to be accepted is the antenna equipment outside the machine room, and the acceptance item is the downtilt angle of the antenna equipment, the information type of the equipment information can be set as the information type capable of representing the profile of the antenna equipment in the equipment image. For another example, when the type of the equipment to be accepted is the cable installed in the machine room (which can also be regarded as a kind of equipment), and the acceptance item is the cable layout, the information type of the equipment information can be set as the information type capable of representing the position of the cable in the equipment image. It should be noted that the information type of the equipment information is different, and the image recognition algorithm used by the acceptance system is also different. In this embodiment, the image recognition algorithm can use any existing algorithm capable of obtaining the corresponding type of equipment information, and this is not limited.

[0060] Further, in an embodiment, a plurality of device types to be accepted, corresponding acceptance entries of each device type, and image recognition algorithms to be used for each acceptance entry and information types to be output can be pre-set in the acceptance system. The acceptance system determines the device type corresponding to the device image according to the obtained device image, and respectively uses the image recognition algorithm corresponding to each acceptance entry of the device type to perform image recognition on the device image to obtain device information of the information type corresponding to the acceptance entry. Further, the acceptance personnel can note the device type corresponding to the device image or further select the acceptance entry corresponding to the device image when uploading the device image to the acceptance system. The acceptance system can determine the device type and the acceptance entry corresponding to the device image according to the information noted or set by the acceptance personnel.

[0061] In step S30, the acceptance result of the device to be accepted is determined according to the device information.

[0062] After the acceptance system obtains the device information in the device image, the acceptance result of the device to be accepted can be determined according to the device information. The form of the acceptance result can be pre-set according to needs, for example, it can be a direct observation record of the device to be accepted on the acceptance entry, such as device types, device quantity, or installation position of the device, or it can be a result indicating whether the device to be accepted is qualified on the acceptance entry after compliance judgment based on the direct observation record. It should be noted that in some embodiments, when the device information obtained by image recognition can directly obtain an acceptance result meeting the form requirements, the device information can be directly used as the acceptance result without calculation; for example, when the form of the acceptance result is set as a direct observation record, if the device information obtained by image recognition is the type of the device appearing in the image, the recognized device type can be directly used as the acceptance result. In other embodiments, when the device information obtained by image recognition cannot directly obtain an acceptance result meeting the form requirements, the acceptance result can be calculated according to the device information; for example, when the form of the acceptance result is set as a result indicating whether it is qualified, if the device information obtained by image recognition is the type of the device appearing in the image, the device type can be compared with the pre-set compliant device type to determine whether they are consistent, and if they are consistent, the acceptance result of the device to be accepted is qualified, and if they are not consistent, the acceptance result of the device to be accepted is unqualified.

[0063] In the present embodiment, by obtaining the device image of the device to be accepted in the base station collected by the camera device, performing image recognition on the device image to obtain the device information in the image, and determining the acceptance result of the device to be accepted according to the device information, the acceptance personnel only need to collect the device image through the camera device to complete the automatic base station acceptance, without coordinating acceptance personnel from various parties to go to the station, greatly saving the acceptance time and improving the acceptance efficiency.

[0064] Based on the first embodiment, a second embodiment of the base station acceptance method is provided, in which the step S20 comprises:

[0065] In step S201, object detection is performed on the equipment image with each type of the to-be-accepted equipment as a detection object to obtain a detection result, and the detection result is taken as the equipment information in the equipment image, wherein the detection result includes the number of each type of the to-be-accepted equipment in the equipment image.

[0066] In this embodiment, the to-be-accepted equipment can include multiple devices, that is, the acceptance entry is to detect multiple devices as a whole, and at this time, the equipment image can include multiple devices by adjusting the shooting angle. After the acceptance system obtains the equipment image, object detection (or target detection) is performed on the equipment image with each type of the to-be-accepted equipment as a detection object to obtain a detection result, and the detection result includes the number of each type of the to-be-accepted equipment in the equipment image, that is, the number of each type of the to-be-accepted equipment in the image is determined by object detection. The acceptance system can take the detection result as the equipment information in the equipment image.

[0067] It should be noted that the to-be-accepted equipment as a detection object can include a device type that should appear and a device type that should not appear, that is, a counterexample. For example, the type of the to-be-accepted equipment includes a device a and a device b that should appear and a device c that should not appear. After object detection is performed on the image, it is obtained that there is one device a, two devices b, and no device c in the image, that is, there is no device c.

[0068] The object detection can use a conventional object detection algorithm, for example, R-CNN, Fast R-CNN, etc., which is not limited in this embodiment. The algorithm model can be trained in advance by collecting images containing each type of the to-be-accepted equipment, and the trained algorithm model is used for detection during acceptance. In order to improve the detection accuracy of the model, multiple images of different shooting angles and different clarity for each to-be-accepted equipment can be collected to participate in the training.

[0069] The step S30 comprises:

[0070] In step S301, it is determined whether the number of each type of the to-be-accepted equipment in the equipment image is consistent with a preset number according to the equipment information.

[0071] After the acceptance system obtains the device information in the device image, that is, obtains the quantity of each type of device to be accepted in the device image, it can compare whether the quantity of each type of device to be accepted is consistent with the preset quantity. The preset quantity can be the quantity of each type of device to be accepted that should appear, for example, device a should have 2, device b should have 3, and device c should have 0 (that is, device c should not exist). The acceptance system compares the quantity of each type of device to be accepted with the corresponding preset quantity of the type of device to be accepted, and determines whether they are the same. If the quantity of at least one type of device to be accepted is different from the corresponding preset quantity, it is determined that the quantity of each type of device to be accepted in the device image is inconsistent with the preset quantity. If the quantity of each type of device to be accepted is the same as the corresponding preset quantity, it is determined that the quantity of each type of device to be accepted in the device image is consistent with the preset quantity. Alternatively, in other embodiments, according to the compliance condition of the acceptance item, it can also be set that when the quantity of each type of device to be accepted is different from the corresponding preset quantity, it is determined that the quantity of each type of device to be accepted in the device image is inconsistent with the preset quantity.

[0072] In step S302, if the quantity of each type of device to be accepted in the device image is inconsistent with the preset quantity, an unqualified acceptance result of the device to be accepted is obtained.

[0073] If the acceptance system determines that the quantity of each type of device to be accepted in the device image is inconsistent with the preset quantity, it can be determined that the device to be accepted is unqualified, that is, an unqualified acceptance result of the device to be accepted is obtained.

[0074] Further, in an embodiment, if the compliance condition is that the quantity of each type of device to be accepted in the device image is consistent with the preset quantity, then when the acceptance system determines that the quantity of each type of device to be accepted in the device image is consistent with the preset quantity, a qualified acceptance result of the device to be accepted is obtained.

[0075] In this embodiment, by taking each type of device to be accepted as the detection object to perform object detection on the device image, a detection result including the quantity of each type of device to be accepted in the device image is obtained, and then whether the quantity of each type of device to be accepted in the device image is compliant is determined according to the detection result. If not, an unqualified acceptance result is obtained, which realizes automatic detection of the quantity compliance of each type of device of the base station by the object detection algorithm based on artificial intelligence technology, greatly improving the acceptance efficiency compared with manual visual inspection.

[0076] Further, in an embodiment, after step S301, it further includes:

[0077] In step S303, if the number of each type of the to-be-inspected devices in the device image is consistent with the preset number, whether the positional relationship between the to-be-inspected devices in the device image is consistent with the preset positional relationship is determined according to the positional information in the device information.

[0078] The detection result obtained by the inspection device performing object detection on the device image can further include the positional information of each to-be-inspected device present in the device image. The positional information can be represented by pixel coordinates in the device image. Specifically, the position of the to-be-inspected device in the device image can be represented by a pixel point, or the position of the to-be-inspected device in the device image can be represented by a pixel interval.

[0079] When the number of each type of the to-be-inspected devices in the device image is consistent with the preset number, and the positional relationship between the to-be-inspected devices needs to meet specific positional relationship requirements to be determined as compliant, the inspection system can further determine whether the positional relationship between the to-be-inspected devices in the device image is consistent with the preset positional relationship after determining that the number of each type of the to-be-inspected devices in the device image is consistent with the preset number.

[0080] Specifically, the detection result includes the number of each type of the to-be-inspected devices in the device image, and also includes the position of each to-be-inspected device present in the device image. Therefore, the inspection system can determine the type and position of each to-be-inspected device present in the device image. The preset positional relationship can be set according to the compliance condition. The specific preset positional relationship can include the positional relationship that should be met between each two to-be-inspected devices. Correspondingly, the inspection system can determine the positional relationship between each two to-be-inspected devices in the device image according to the detection result, and compare it with the positional relationship that should be met between the two to-be-inspected devices, respectively. If the positional relationship between each two to-be-inspected devices is consistent with the positional relationship that should be met, it is determined that the positional relationship between the to-be-inspected devices is consistent with the preset positional relationship, otherwise, it is determined that the positional relationship between the to-be-inspected devices is not consistent with the preset positional relationship. Alternatively, the preset positional relationship can only include the positional relationship that should be met between a specific plurality of to-be-inspected devices. Correspondingly, the inspection system can determine the positional relationship between the specific plurality of to-be-inspected devices according to the detection result, and compare it with the positional relationship that should be met between the two to-be-inspected devices, respectively. If the positional relationship between the specific plurality of to-be-inspected devices is consistent with the positional relationship that should be met, it is determined that the positional relationship between the to-be-inspected devices is consistent with the preset positional relationship, otherwise, it is determined that the positional relationship between the to-be-inspected devices is not consistent with the preset positional relationship.

[0081] Further, the position relationship that should be met between two to-be-inspected devices can be set according to the compliance condition, for example, one of the to-be-inspected devices must be above the other to-be-inspected device, and then the inspection system can determine whether the up-down relationship is met by comparing the coordinate positions of the two to-be-inspected devices in the image.

[0082] In step S304, if the position relationship between the to-be-inspected devices in the device image is inconsistent with the preset position relationship, an unqualified inspection result of the to-be-inspected devices is obtained.

[0083] If the inspection system determines that the position relationship between the to-be-inspected devices in the device image is inconsistent with the preset position relationship, it can be determined that the to-be-inspected devices are unqualified, that is, an unqualified inspection result of the to-be-inspected devices is obtained. Further, in an embodiment, if the inspection system determines that the position relationship between the to-be-inspected devices in the device image is consistent with the preset position relationship, it can be determined that the to-be-inspected devices are qualified, that is, a qualified inspection result of the to-be-inspected devices is obtained.

[0084] In the present embodiment, the device image is subjected to object detection by taking various to-be-inspected devices as detection objects, a detection result including position information of the to-be-inspected devices in the device image is obtained, and then it is judged whether the position relationship between the to-be-inspected devices in the device image is compliant according to the detection result. If not, an unqualified inspection result is obtained, which realizes automatic detection of the installation positions of various devices of the base station by using an object detection algorithm based on artificial intelligence technology, and greatly improves the inspection efficiency compared with manual visual inspection.

[0085] Further, based on the first and / or second embodiments described above, a third embodiment of the base station inspection method of the present application is proposed. In the present embodiment, the step S20 includes:

[0086] In step S202, the antenna device is taken as the recognition object to recognize the device image and obtain the antenna device contour in the device image, and the antenna device contour is taken as the device information in the device image.

[0087] In the present embodiment, the to-be-inspected devices can include an antenna device in the base station, such as an active antenna device AAU. The inspection item can include the downtilt angle of the antenna device. The antenna device is generally installed at a high place, and in the present embodiment, the device image of the antenna device can be photographed by flying a drone to a height level with the antenna device.

[0088] Specifically, the acceptance system can identify the antenna device as the identification object in the device image to obtain the antenna device contour in the device image. Specifically, an image segmentation algorithm, such as a pyramid image segmentation algorithm, can be used to segment the image to obtain the region where the antenna device is located in the image, and the region outside the contour of the antenna device. Alternatively, an image semantic segmentation algorithm can also be used, taking the antenna device as a target category, predicting whether each pixel point in the device image belongs to the target category, and taking the pixel points belonging to the target type as the region where the antenna device is located, and taking the region outside the contour as the antenna device contour.

[0089] The step S30 comprises:

[0090] In step S305, a straight line fitting is performed on the pixel points corresponding to one side of the antenna device contour on the device image to obtain a side straight line.

[0091] After obtaining the antenna device contour, the acceptance system can perform a straight line fitting on the pixel points corresponding to one side of the antenna device contour on the device image to obtain a side straight line. It should be noted that the antenna device is generally a box-shaped device, and its contour is generally rectangular or approximately rectangular, and the side refers to the left and right sides of the rectangle. When performing straight line fitting, one side can be selected for fitting. Specifically, there are multiple pixel points corresponding to the side on the device image, and there are multiple ways to fit a straight line based on the pixel points, which are not limited in this embodiment. For example, a straight line can be selected such that the sum of the distances of each pixel point to the straight line is minimized, and the straight line is taken as the fitted side straight line.

[0092] In step S306, a visual downtilt angle of the antenna device in the device image is calculated according to the slope of the side straight line.

[0093] After fitting the side straight line, the acceptance system can calculate the downtilt angle of the antenna device in the device image (referred to as the visual downtilt angle to distinguish it) according to the side straight line. Specifically, the visual downtilt angle of the antenna device in the device image can be calculated according to the slope of the side straight line, for example, if the slope is k, then the visual downtilt angle θ = arctan(|k|). Alternatively, the visual downtilt angle can be calculated by calculating the angle between the side straight line and the horizontal axis of the device image pixel coordinate system.

[0094] In step S307, a relative downtilt angle of the antenna device relative to the ground is determined according to the visual downtilt angle, and the relative downtilt angle is taken as the acceptance result of the antenna device.

[0095] After obtaining the visual downtilt angle, the acceptance system can determine the downtilt angle of the antenna device relative to the ground (referred to as the relative downtilt angle for the sake of distinction) according to the visual downtilt angle. Specifically, in an embodiment, when the camera device is shooting the side of the antenna device at an angle horizontally flush with the antenna device, and the horizontal axis of the device image pixel coordinate system obtained by shooting is parallel or close to parallel to the horizontal plane, the visual downtilt angle can be directly taken as the relative downtilt angle. In other embodiments, when the horizontal axis of the device image pixel coordinate system obtained by shooting is not parallel to the horizontal plane, the deflection angle of the camera device relative to the horizontal plane at the shooting time can be collected by the level in the camera device, and the visual downtilt angle is corrected by the deflection angle to obtain the relative downtilt angle of the antenna device relative to the ground.

[0096] Further, in an embodiment, as shown in FIG. 6, multiple device images can be obtained by horizontally surrounding the antenna device with the camera device at different surrounding angles, and the contour of the antenna device is identified for each device image. The area of the region where the antenna device is located in each device image is calculated according to the identified contour of the antenna device. The device image with the smallest area of the region where the antenna device is located is taken as the image shot from the side angle, and the relative downtilt angle is finally obtained according to the image through straight line fitting and visual downtilt angle calculation. Figure 2

[0097] Further, a drone can be used to fly around the antenna device at a constant speed to shoot photos at certain time intervals, or directly shoot videos.

[0098] Further, in an embodiment, the step of calculating the relative downtilt angle of the antenna device relative to the ground according to the visual downtilt angle in step S307 includes:

[0099] Step S3071, determining the amplitude of the visual downtilt angle corresponding to each device image changing with the surrounding angle;

[0100] In the embodiment, as shown in FIG. 6, multiple device images can be obtained by horizontally surrounding the antenna device with the camera device at different surrounding angles, and the contour of the antenna device is identified for each device image. The area of the region where the antenna device is located in each device image is calculated according to the identified contour of the antenna device. The device image with the smallest area of the region where the antenna device is located is taken as the image shot from the side angle, and the relative downtilt angle is finally obtained according to the image through straight line fitting and visual downtilt angle calculation. Figure 2

[0101] Step S3072, calculating the relative downtilt angle of the antenna device relative to the ground according to the amplitude. ​​

[0102] After the amplitude is calculated, the acceptance system can calculate the relative downtilt angle of the antenna device relative to the ground according to the amplitude. Specifically, half of the amplitude can be taken as the relative downtilt angle, or after half of the amplitude is taken, a certain angle is floated up and down to obtain a relative downtilt angle range.

[0103] The process of predicting the antenna downtilt angle has the problems of measurement error or frame error, and is easily affected by wind speed, environment, and UAV angular velocity. The amplitude method is adopted in the embodiment to eliminate the influence of wind speed and UAV angle in actual operation.

[0104] Further, in an embodiment, the step S305 includes:

[0105] Step S3051, mapping the image coordinates of a side edge in the antenna device contour in the device image to the pixel coordinate system to obtain the pixel points corresponding to the side edge on the device image;

[0106] Step S3052, performing linear fitting on each of the pixel points to obtain a side edge straight line.

[0107] The pixel coordinate system and the image coordinate system are both on the imaging plane of the antenna image, but their origins and units of measurement are different. The origin of the image coordinate system is the intersection of the camera optical axis and the imaging plane, which is usually the center point of the imaging plane. The unit of the image coordinate system is mm, while the unit of the pixel coordinate system is pixel. When the antenna device contour recognized by the image segmentation algorithm is expressed by coordinate values in the image coordinate system, the image coordinates of a side edge in the antenna device contour in the device image can be mapped to the pixel coordinate system to obtain the pixel points corresponding to the side edge on the device image. After obtaining the pixel points corresponding to the side edge on the device image, the acceptance system can perform linear fitting on each of the pixel points to obtain a side edge straight line.

[0108] The conversion rule of coordinate values in the pixel coordinate system and the image coordinate system can be as shown in Figure 3 where dx and dy represent how many mm each column and each row represents, i.e. 1 pixel = dx mm. u0 and v0 are the horizontal and vertical coordinates of the center point of the image coordinate system, respectively; R is a 3X3 orthogonal matrix; and T is a three-dimensional translation vector.

[0109] Further, in an embodiment, the process of base station acceptance can be as shown in Figure 4As shown. In the acceptance system, the acceptance task is assigned to the on-site engineer, the on-site engineer performs the acceptance task, that is, the on-site engineer shoots the equipment to be accepted in the acceptance task through the handheld terminal APP or the unmanned aerial vehicle, and returns the images or videos obtained by shooting to the acceptance system. After the acceptance system obtains the images or videos, the image or video frames are subjected to object detection and AI intelligent analysis, and the compliance is automatically audited to obtain the acceptance result; if the acceptance is passed, the acceptance is completed; if the acceptance is not passed, the on-site engineer is notified to rectify. The embodiment proposes a set of intelligent acceptance system of base station, realizes remote real-time acceptance and data information management of base station through efficient cooperation of man and machine in the whole process. Further, the acceptance system can obtain the geographic location information of the on-site engineer according to the client APP of the on-site engineer; the selectable to-be-accepted site is limited in the client APP according to the geographic location information, that is, only the site in the region corresponding to the geographic location information is selected as the selectable to-be-accepted site; the on-site engineer selects the to-be-accepted site on the client APP, and uploads the image or video data of the site collected by the APP to the acceptance system; by limiting the selection of the to-be-accepted site on the acceptance APP by using the geographic location information, it is ensured that the uploaded image and video information is consistent with the actual acceptance site.

[0110] Further, in an embodiment, as shown Figure 5 It is a base station acceptance system. In order to ensure the real-time, efficiency and reliability of the actual acceptance work, an intelligent acceptance system is proposed in combination with the actual production demand, and the high availability of the system is realized through complete process design, standard formulation and rule sorting. The base station acceptance system includes a high-definition image acquisition part, a 5G network backhaul part and a cloud platform AI image recognition part. The 5G terminal controls the unmanned aerial vehicle, collects the high-definition images of the base station, implements the backhaul through the 5G network, and completes the AI real-time acceptance based on the high-definition images through the built video server, AI server and application server.

[0111] In addition, the embodiment of the present application also proposes a base station acceptance device, referring to Figure 6 , the base station acceptance device comprises:

[0112] The acquisition module 10 is configured to acquire the equipment image of the to-be-accepted equipment in the base station collected by the camera device.

[0113] The identification module 20 is configured to identify the equipment image to obtain the equipment information in the equipment image.

[0114] The determination module 30 is configured to determine the acceptance result of the to-be-accepted equipment according to the equipment information.

[0115] Further, the identification module 20 comprises:

[0116] The detection unit is configured to perform object detection on the equipment image with each type of the to-be-inspected equipment as a detection object to obtain a detection result, and the detection result is taken as the equipment information in the equipment image, wherein the detection result includes the number of each type of the to-be-inspected equipment in the equipment image.

[0117] The determination module 30 includes:

[0118] The first determination unit is configured to determine whether the number of each type of the to-be-inspected equipment in the equipment image is consistent with a preset number according to the equipment information.

[0119] The second determination unit is configured to obtain an unqualified inspection result of the to-be-inspected equipment if the number of each type of the to-be-inspected equipment in the equipment image is not consistent with the preset number.

[0120] Further, the detection result further includes position information of the to-be-inspected equipment existing in the equipment image, and the determination module 30 further includes:

[0121] The third determination unit is configured to determine whether a position relationship between the to-be-inspected equipment in the equipment image is consistent with a preset position relationship according to the position information in the equipment information if the number of each type of the to-be-inspected equipment in the equipment image is consistent with the preset number.

[0122] The fourth determination unit is configured to obtain an unqualified inspection result of the to-be-inspected equipment if the position relationship between the to-be-inspected equipment in the equipment image is not consistent with the preset position relationship.

[0123] Further, the to-be-inspected equipment includes an antenna equipment in the base station, and the identification module 20 includes:

[0124] The identification unit is configured to perform identification on the equipment image with the antenna equipment as an identification object to obtain an antenna equipment contour in the equipment image, and the antenna equipment contour is taken as the equipment information in the equipment image.

[0125] The determination module 30 includes:

[0126] The fitting unit is configured to perform linear fitting on pixel points corresponding to a side edge of the antenna equipment contour on the equipment image to obtain a side edge straight line.

[0127] The calculation unit is configured to calculate a visual downtilt angle of the antenna equipment in the equipment image according to a slope of the side edge straight line.

[0128] The fifth determination unit is configured to determine a relative downtilt angle of the antenna equipment relative to the ground according to the visual downtilt angle, and take the relative downtilt angle as an inspection result of the antenna equipment.

[0129] Further, the device images include multiple device images taken by horizontally surrounding the antenna device with different surrounding angles, and the fifth determining unit includes:

[0130] A determining subunit is configured to determine an amplitude of the visual downtilt angle corresponding to each of the device images varying with the surrounding angle;

[0131] A calculating subunit is configured to calculate the relative downtilt angle of the antenna device relative to the ground according to the amplitude.

[0132] Further, the fitting unit includes:

[0133] A mapping subunit is configured to map image coordinates of a side edge in the antenna device profile in the device image to a pixel coordinate system to obtain pixel points corresponding to the side edge on the device image;

[0134] A fitting subunit is configured to perform linear fitting on each of the pixel points to obtain a side edge straight line.

[0135] Further, the obtaining module 10 includes:

[0136] An obtaining unit is configured to obtain video stream data of a device to be accepted in a base station collected by a camera device;

[0137] A frame extracting unit is configured to extract key frames from the video stream data to obtain device images.

[0138] The expansion of the specific implementation of the base station acceptance device is basically the same as the above-mentioned base station acceptance method, and will not be repeated here.

[0139] As shown in Figure 7 , the device structure diagram of the hardware running environment involved in the embodiment of the present application is shown. Figure 7

[0140] It should be noted that the base station acceptance device in the embodiment of the present application can be a smart phone, a personal computer, a server and the like, which is not specifically limited here.

[0141] As shown in Figure 7 ​As shown, the base station acceptance equipment can include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to realize the connection communication between the components. The user interface 1003 can include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). The memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory) such as a disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0142] Those skilled in the art can understand that Figure 7 The device structure shown in the figure does not constitute a limitation on the base station acceptance equipment, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0143] As Figure 7 As shown, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and a base station acceptance program. The operating system is a program that manages and controls the hardware and software resources of the equipment, supports the running of the base station acceptance program and other software or programs. In Figure 7 In the device shown, the user interface 1003 is mainly used for data communication with the client; the network interface 1004 is mainly used for establishing a communication connection with the server; and the processor 1001 can be used to call the base station acceptance program stored in the memory 1005 and perform the following operations:

[0144] Obtaining a device image of the equipment to be accepted in the base station collected by the camera equipment;

[0145] Identifying the device image to obtain device information in the device image;

[0146] According to the device information, determining the acceptance result of the equipment to be accepted.

[0147] Further, the step of identifying the device image to obtain device information in the device image includes:

[0148] Object detection is performed on the device image with various types of equipment to be accepted as detection objects to obtain a detection result, and the detection result is used as the device information in the device image, wherein the detection result includes the number of various types of equipment to be accepted in the device image;

[0149] The step of determining the acceptance result of the to-be-accepted equipment according to the equipment information comprises:

[0150] determining whether the number of each type of the to-be-accepted equipment in the equipment image is consistent with a preset number according to the equipment information;

[0151] if the number of each type of the to-be-accepted equipment in the equipment image is inconsistent with the preset number, obtaining the acceptance result that the to-be-accepted equipment is unqualified.

[0152] Further, the detection result further comprises position information of the to-be-accepted equipment existing in the equipment image, and after the step of determining whether the number of each type of the to-be-accepted equipment in the equipment image is consistent with a preset number according to the equipment information, the processor 1001 can further be configured to call a base station acceptance program stored in the memory 1005 to perform the following operations:

[0153] if the number of each type of the to-be-accepted equipment in the equipment image is consistent with the preset number, determining whether the position relationship between the to-be-accepted equipment in the equipment image is consistent with a preset position relationship according to the position information in the equipment information;

[0154] if the position relationship between the to-be-accepted equipment in the equipment image is inconsistent with the preset position relationship, obtaining the acceptance result that the to-be-accepted equipment is unqualified.

[0155] Further, the to-be-accepted equipment comprises an antenna equipment in the base station, and the step of identifying the equipment image to obtain the equipment information in the equipment image comprises:

[0156] identifying the antenna equipment in the equipment image as an identification object to obtain an antenna equipment contour in the equipment image, and taking the antenna equipment contour as the equipment information in the equipment image;

[0157] The step of determining the acceptance result of the to-be-accepted equipment according to the equipment information comprises:

[0158] performing straight line fitting on a pixel point corresponding to one side of the antenna equipment contour on the equipment image to obtain a side straight line;

[0159] calculating a visual downtilt angle of the antenna equipment in the equipment image according to a slope of the side straight line;

[0160] determining a relative downtilt angle of the antenna equipment relative to the ground according to the visual downtilt angle, and taking the relative downtilt angle as the acceptance result of the antenna equipment.

[0161] Further, the device images include multiple device images taken by the camera device horizontally surrounding the antenna device at different surrounding angles, and the step of determining the relative down tilt angle of the antenna device relative to the ground according to the visual down tilt angle includes:

[0162] determining the amplitude of the visual down tilt angle corresponding to each of the device images varying with the surrounding angle;

[0163] calculating the relative down tilt angle of the antenna device relative to the ground according to the amplitude.

[0164] Further, the step of performing linear fitting on the pixel points corresponding to one side of the antenna device profile on the device images to obtain a side linear line includes:

[0165] mapping the image coordinates of one side of the antenna device profile in the device images to pixel coordinates to obtain the pixel points corresponding to the side on the device images;

[0166] performing linear fitting on each of the pixel points to obtain a side linear line.

[0167] Further, the step of obtaining the device images of the base station device to be accepted collected by the camera device includes:

[0168] obtaining the video stream data of the base station device to be accepted collected by the camera device;

[0169] performing frame extraction on the video stream data to obtain key frames, and taking the key frames as the device images.

[0170] In addition, an embodiment of the present application further provides a computer readable storage medium, wherein the storage medium stores a base station acceptance program, and the base station acceptance program is executed by a processor to implement the steps of the base station acceptance method.

[0171] The embodiments of the base station acceptance device and the computer readable storage medium can refer to the embodiments of the base station acceptance method and the device, and details are not described herein.

[0172] It should be noted that, in the present document, the terms “comprising”, “containing” or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement “comprising a” does not exclude the presence of another identical element in the process, method, article or device including the element.

[0173] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0174] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0175] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A base station acceptance method, characterized in that, The base station acceptance method includes the following steps: Acquire equipment images of the equipment to be inspected in the base station, captured by camera equipment; The device information in the device image is obtained by recognizing the device image. The acceptance result of the equipment to be inspected is determined based on the equipment information; The equipment to be inspected includes the antenna equipment in the base station, and the step of identifying the equipment image to obtain equipment information from the equipment image includes: The antenna device is used as the identification object to identify the device image and obtain the antenna device outline in the device image. The antenna device outline is used as the device information in the device image. The step of determining the acceptance result of the equipment to be inspected based on the equipment information includes: A straight line is obtained by performing a straight line fitting on the pixel points corresponding to one side of the antenna device outline in the device image; The visual downtilt angle of the antenna device in the device image is calculated based on the slope of the side straight line; The relative downtilt angle of the antenna device relative to the ground is determined based on the visual downtilt angle, and the relative downtilt angle is used as the acceptance result of the antenna device.

2. The base station acceptance method as described in claim 1, characterized in that, The step of identifying the device image to obtain device information from the device image includes: Using the various types of equipment to be inspected as inspection objects, object detection is performed on the equipment image to obtain inspection results. The inspection results are used as equipment information in the equipment image, wherein the inspection results include the number of various types of equipment to be inspected in the equipment image. The step of determining the acceptance result of the equipment to be inspected based on the equipment information includes: Based on the equipment information, determine whether the quantity of each type of equipment to be inspected in the equipment image is consistent with the preset quantity; If the number of each type of equipment to be inspected in the equipment image is inconsistent with the preset number, then the inspection result is that the equipment to be inspected is unqualified.

3. The base station acceptance method as described in claim 2, characterized in that, The detection result also includes the location information of the devices to be inspected in the device image. After the step of determining whether the number of each type of device to be inspected in the device image is consistent with the preset number based on the device information, the method further includes: If the number of each type of equipment to be inspected in the equipment image is consistent with the preset number, then the positional relationship between the equipment to be inspected in the equipment image is determined according to the positional information in the equipment information to see if it is consistent with the preset positional relationship. If the positional relationship between the devices to be inspected in the equipment image is inconsistent with the preset positional relationship, then the acceptance result of the devices to be inspected is that they are unqualified.

4. The base station acceptance method as described in claim 1, characterized in that, The device images include multiple images of the antenna device taken by a camera device horizontally around the antenna device at different surround angles. The step of determining the relative downtilt angle of the antenna device relative to the ground based on the visual downtilt angle includes: Determine the amplitude of the visual downtilt angle corresponding to each of the device images as a function of the surround angle; The relative downtilt angle of the antenna device relative to the ground is calculated based on the amplitude.

5. The base station acceptance method as described in claim 1, characterized in that, The step of performing line fitting on the pixel points corresponding to one side of the antenna device outline in the device image to obtain the side line includes: Map the image coordinates of one side of the antenna device outline in the device image to the pixel coordinate system to obtain the pixel point corresponding to the side in the device image. The side lines are obtained by fitting each pixel with a straight line.

6. The base station acceptance method as described in any one of claims 1 to 5, characterized in that, The step of acquiring equipment images of the equipment to be inspected in the base station through camera equipment includes: Acquire video stream data of the equipment to be inspected in the base station, collected by camera equipment; The video stream data is processed to extract keyframes, which are then used as device images.

7. A base station acceptance device, characterized in that, The base station acceptance device includes: The acquisition module is used to acquire equipment images of the equipment to be inspected in the base station through the camera equipment; The recognition module is used to recognize the device image to obtain device information in the device image; The determination module is used to determine the acceptance result of the equipment to be inspected based on the equipment information. The equipment to be accepted includes the antenna equipment in the base station, and the identification module includes: The identification unit is used to identify the antenna device as the identification object in the device image to obtain the antenna device outline in the device image, and to use the antenna device outline as the device information in the device image. The determining module includes: The fitting unit is used to perform straight line fitting on the pixel points corresponding to one side of the antenna device outline on the device image to obtain the side straight line. A calculation unit is used to calculate the visual downtilt angle of the antenna device in the device image based on the slope of the side straight line; The fifth determining unit is used to determine the relative downtilt angle of the antenna device relative to the ground based on the visual downtilt angle, and to use the relative downtilt angle as the acceptance result of the antenna device.

8. A base station acceptance testing device, characterized in that, The base station acceptance device includes: a memory, a processor, and a base station acceptance program stored in the memory and executable on the processor. When the base station acceptance program is executed by the processor, it implements the steps of the base station acceptance method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a base station acceptance program, which, when executed by a processor, implements the steps of the base station acceptance method as described in any one of claims 1 to 6.

Images