Method and system for updating indoor map data

Abstract

The embodiment of the application provides a kind of indoor map data updating method and system, it is related to data updating technical field.The method comprises: obtaining indoor video data;According to the indoor video data, obtain the image frame data of target area;According to the image frame data, generate gray image data;Obtain the historical gray image data of the target area;According to the gray image data and the historical gray image data, obtain difference image data;According to the difference image data, obtain the vertex space coordinate of subarea that needs to update indoor map data;According to the vertex space coordinate of subarea, update the indoor map data.The method can realize the technical effect of improving the accuracy and timeliness of updating map data, improve user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data updating, in particular to an indoor map data updating method and system, an electronic device and a computer readable storage medium. BACKGROUND

[0002] At present, outdoor navigation positioning technology is quite mature and can better meet the needs of people's travel, while indoor positioning and navigation technology for large buildings such as hospitals, shopping malls, venues and office buildings cannot meet people's fine navigation needs. Indoor electronic map is the basis of indoor navigation technology.

[0003] In the prior art, indoor electronic maps are mostly generated by manual surveying and mapping; however, large buildings often have complex and variable structures, and once the internal structure or function of the building changes, the previously drawn indoor electronic map needs to be updated in a timely manner. However, the existing technical means rely on manual reporting of positions that need to be updated, which not only has high labor costs, but also causes the indoor electronic map to be updated in a timely manner, affecting the accuracy of indoor navigation and reducing user experience. In addition, the real scene image uploaded by the user can be analyzed by using an algorithm to obtain the position that needs to be updated; however, this method relies heavily on the user's travel trajectory and user's behavior habits, and cannot guarantee timeliness. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide an indoor map data updating method, system, electronic device and computer readable storage medium, which can improve the accuracy and timeliness of updating map data and improve user experience.

[0005] In a first aspect, the embodiments of the present application provide an indoor map data updating method, comprising:

[0006] obtaining indoor video data;

[0007] obtaining image frame data of a target area according to the indoor video data;

[0008] generating grayscale image data according to the image frame data;

[0009] obtaining historical grayscale image data of the target area;

[0010] obtaining difference image data according to the grayscale image data and the historical grayscale image data;

[0011] obtaining sub-area vertex space coordinates of indoor map data that needs to be updated according to the difference image data;

[0012] updating the indoor map data according to the sub-area vertex space coordinates.

[0013] In the implementation process, the indoor map data updating method analyzes and processes indoor video data, obtains gray image data, difference image data and black-and-white image data in sequence, and then obtains corresponding sub-region vertex space coordinates in the indoor map data according to the region vertex pixel coordinates on the black-and-white image data, so as to update the indoor map data. The indoor map data updating method can obtain indoor video data by using an existing monitoring camera, repeatedly use the existing monitoring camera, does not need to increase equipment, saves equipment cost, does not depend on real scene images uploaded by users, reduces the occupation of user traffic, and improves user experience. In addition, the method can quickly judge the region to be updated according to the black-and-white image data, and improves the updating efficiency, accuracy and timeliness of the indoor map data.

[0014] Further, the step of obtaining difference image data according to the gray image data and the historical gray image data comprises:

[0015] performing image feature point matching on the gray image data and the historical gray image data to obtain a transformation matrix;

[0016] processing the gray image data according to the transformation matrix to obtain transformed gray image data;

[0017] obtaining difference image data according to the transformed gray image data and the historical gray image data.

[0018] In the implementation process, the transformation matrix between the gray image data and the historical gray image data is calculated by using an image feature point matching algorithm, and the feature points of the two images can be aligned by the transformation matrix. Therefore, the transformation matrix is applied to the gray image data to obtain transformed gray image data, the pixel points of the transformed gray image data and the historical gray image data correspond to each other, and the difference image data is obtained according to the pixel absolute difference.

[0019] Further, the step of obtaining sub-region vertex space coordinates of indoor map data to be updated according to the difference image data comprises:

[0020] performing binaryzation processing on the difference image data to obtain black-and-white image data, wherein a white region in the black-and-white image data represents that the difference between the historical gray image data and the gray image data is greater than a preset value;

[0021] obtaining all white region contours with an area greater than a preset area threshold in the black-and-white image data, and generating an outer bounding rectangle frame of each white region contour;

[0022] Traverse all the outer rectangular frame, and perform the following processing on the traversed outer rectangular frame: obtaining the corresponding sub-region vertex pixel coordinates in the gray image data according to the vertex pixel coordinates of the outer rectangular frame; obtaining the corresponding sub-region vertex space coordinates in the indoor map data according to the sub-region vertex pixel coordinates.

[0023] Further, after the step of binarizing the difference image data to obtain the black and white image data, the method further comprises:

[0024] Processing the black and white image data using a preset ROI region to obtain processed black and white image data.

[0025] In the above implementation process, the ROI region is used to filter and process the black and white image data, so that the part outside the ROI region in the black and white image is black, improving the image processing accuracy and efficiency.

[0026] Further, before the step of obtaining the contour of all white regions in the black and white image data with an area greater than a preset area threshold, and generating an outer rectangular frame for each white region contour, the method further comprises:

[0027] Performing morphological processing on the processed black and white image data to merge adjacent white regions in the processed black and white image data.

[0028] In the above implementation process, adjacent white regions in the black and white image data are merged to improve the image processing efficiency.

[0029] Further, the step of generating gray image data from the image frame data comprises:

[0030] Processing the image frame data according to a background separation algorithm to obtain background image data;

[0031] Converting the background image data into the gray image data and performing image enhancement processing on the gray image data.

[0032] In the above implementation process, the image frame data is processed using a background separation algorithm to obtain a background image; available technical means include but are not limited to average background method; the background image data is converted into gray image data, and the gray image data is processed using an image enhancement algorithm to obtain an enhanced current gray image.

[0033] Further, after the step of obtaining the contour of all white regions in the black and white image data with an area greater than a preset area threshold, and generating an outer rectangular frame for each white region contour, the method further comprises:

[0034] cutting region image data corresponding to the outer-enclosed rectangular frame from the background image data;

[0035] inputting the region image data into a preset deep learning classification model to generate an update evaluation result of the region image data.

[0036] In the implementation process, for each white region, region image data surrounded by the top vertex pixel coordinates in the current background image data is cut, and the region image data is input into the pre-trained deep learning classification model as an input, and whether the region needs to update the indoor map data is determined by the update evaluation result.

[0037] In a second aspect, an indoor map data update system is provided, and the system comprises:

[0038] a video acquisition module configured to acquire indoor video data;

[0039] an image frame module configured to obtain image frame data of a target region according to the indoor video data;

[0040] a grayscale image module configured to generate grayscale image data according to the image frame data;

[0041] a historical grayscale image acquisition module configured to acquire historical grayscale image data of the target region;

[0042] a difference image module configured to obtain difference image data according to the grayscale image data and the historical grayscale image data;

[0043] a spatial coordinate module configured to acquire spatial coordinates of a sub-region vertex that needs to update indoor map data according to the difference image data;

[0044] an update module configured to update the indoor map data according to the spatial coordinates of the sub-region vertex.

[0045] Further, the difference image module comprises:

[0046] a feature point matching unit configured to perform image feature point matching on the grayscale image data and the historical grayscale image data to obtain a transformation matrix;

[0047] a transformation processing unit configured to process the grayscale image data according to the transformation matrix to obtain transformed grayscale image data;

[0048] a difference image unit configured to obtain difference image data according to the transformed grayscale image data and the historical grayscale image data.

[0049] Further, the spatial coordinate module comprises:

[0050] A black and white image unit is used to perform binarization processing on the difference image data to obtain black and white image data. The white area in the black and white image data indicates that the difference between the historical grayscale image data and the grayscale image data is greater than a preset value.

[0051] The outer rectangular unit is used to obtain the outlines of all white regions in the black and white image data whose area is greater than a preset area threshold, and to generate an outer rectangular frame for each white region outline.

[0052] The traversal unit is used to traverse all the outer bounding rectangles and perform the following processing on the traversed outer bounding rectangles: obtain the corresponding region vertex pixel coordinates in the grayscale image data based on the vertex pixel coordinates of the outer bounding rectangles; obtain the corresponding sub-region vertex spatial coordinates in the indoor map data based on the region vertex pixel coordinates.

[0053] Furthermore, the indoor map data update system also includes:

[0054] The ROI processing module is used to process the black and white image data using a preset ROI region to obtain processed black and white image data.

[0055] Furthermore, the indoor map data update system also includes:

[0056] The morphology processing module is used to perform morphology processing on the processed black and white image data and merge adjacent white regions in the processed black and white image data.

[0057] Furthermore, the grayscale image module includes:

[0058] The background image unit is used to process the image frame data according to the background separation algorithm to obtain background image data;

[0059] A grayscale image unit is used to convert the background image data into grayscale image data and perform image enhancement processing on the grayscale image data.

[0060] Furthermore, the indoor map data update system also includes:

[0061] The cropping unit is used to crop the region image data corresponding to the outer rectangular frame from the background image data;

[0062] An update evaluation unit is used to input the region image data into a preset deep learning classification model and generate an updated evaluation result for the region image data.

[0063] In a third aspect, an electronic device is provided and includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method of any one of the first aspect when executing the computer program.

[0064] In a fourth aspect, a computer readable storage medium is provided and has instructions stored thereon, and the instructions, when executed on a computer, cause the computer to perform the method of any one of the first aspect.

[0065] In a fifth aspect, a computer program product is provided and, when executed on a computer, causes the computer to perform the method of any one of the first aspect.

[0066] Other features and advantages of the present application will be illustrated in the following description, or can be learned from the description, or can be determined without any doubt, or can be known by implementing the above-mentioned technology disclosed in the present application.

[0067] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0068] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation to the scope, and for those skilled in the art, other related drawings can also be obtained without any creative labor on the basis of these drawings.

[0069] Figure 1 A flowchart of an indoor map data updating method provided by the embodiments of the present application is shown in the figure;

[0070] Figure 2 A flowchart of obtaining a sub-region vertex spatial coordinate provided by the embodiments of the present application is shown in the figure;

[0071] Figure 3 A flowchart of another indoor map data updating method provided by the embodiments of the present application is shown in the figure;

[0072] Figure 4 A structural block diagram of the indoor map data updating method provided by the embodiments of the present application is shown in the figure;

[0073] Figure 5 A structural block diagram of an electronic device provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0075] It should be noted that similar reference numerals and letters refer to like items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are merely used to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0076] The embodiments of the present application provide an indoor map data updating method, system, electronic device and computer readable storage medium, which can be applied to indoor map updating of buildings such as hospitals, shopping malls, stadiums and office buildings. The indoor map data updating method analyzes and processes indoor video data, obtains grayscale image data, difference image data and black-and-white image data in sequence, and then obtains corresponding sub-region vertex space coordinates in the indoor map data according to the region vertex pixel coordinates on the black-and-white image data, so as to realize updating of the indoor map data. The indoor map data updating method can obtain indoor video data by using existing monitoring cameras, repeatedly use existing monitoring cameras, does not need to increase equipment, saves equipment cost, does not depend on real scene images uploaded by users, reduces occupation of user traffic, and improves user experience. In addition, the method can quickly judge the region to be updated according to the black-and-white image data, and improves the updating efficiency, accuracy and timeliness of the indoor map data.

[0077] Please refer to Figure 1 and Figure 2 , Figure 1 FIG. 1 is a flowchart of an indoor map data updating method provided by an embodiment of the present application, Figure 2 FIG. 2 is a flowchart of obtaining sub-region vertex space coordinates provided by an embodiment of the present application; the indoor map data updating method comprises the following steps:

[0078] S100: Obtain indoor video data.

[0079] Exemplarily, the indoor video data can be a monitoring video of a target region shot by a monitoring camera; during the monitoring video, the shooting parameters (such as camera focal length, shooting angle and shooting position) of the monitoring camera do not change.

[0080] S200: Obtain image frame data of the target region according to the indoor video data.

[0081] Exemplarily, the target region is a region monitored by the monitoring camera.

[0082] S300: Generate grayscale image data according to the image frame data.

[0083] Exemplarily, an image processing algorithm is used to convert a frame of image in the monitoring video into a gray image. For example, when the monitoring camera is installed in a shopping mall, a frame of image is obtained at a preset time point outside the business hours every day and converted into a gray image, which can avoid the interference of people flow on subsequent calculation steps.

[0084] S400: Obtain historical gray image data of the target area.

[0085] Exemplarily, the historical gray image data is a historical gray image of the same target area captured by the monitoring camera in the last period and saved.

[0086] S500: Obtain difference image data according to the gray image data and the historical gray image data.

[0087] Exemplarily, an absolute difference value is obtained according to the pixels corresponding to the gray image data and the historical gray image data, to obtain a difference image; wherein the difference value of the difference image is the difference value generated by subtracting the corresponding pixel values of the gray image data and the historical gray image data, to infer the change condition.

[0088] S600: Obtain the spatial coordinates of the vertexes of the sub-area needing to update the indoor map data according to the difference image data.

[0089] S600 includes the following steps:

[0090] S610: Perform binaryzation processing on the difference image data to obtain black and white image data, wherein the white area in the black and white image data represents that the difference between the historical gray image data and the gray image data is greater than a preset value.

[0091] Exemplarily, the black and white image data is obtained by performing binaryzation processing on the difference image data; wherein the white area in the black and white image data represents the part with greater change (difference greater than the preset value) in the historical gray image data and the gray image data; and the black area in the black and white image data represents the part with smaller change (difference less than or equal to the preset value) in the historical gray image data and the gray image data.

[0092] S620: Obtain the contour of all white areas with an area greater than a preset area threshold in the black and white image data, to generate an outer rectangular frame of each white area contour.

[0093] Exemplarily, the contour of each white area with an area greater than the preset threshold is obtained respectively, and the outer rectangular frame of each white area contour is generated by calculation.

[0094] S630: Traverse all the bounding rectangular frames, and perform the following processing on the traversed bounding rectangular frame: obtaining the corresponding sub-region vertex pixel coordinates in the grayscale image data according to the vertex pixel coordinates of the bounding rectangular frame; obtaining the corresponding sub-region vertex space coordinates in the indoor map data according to the sub-region vertex pixel coordinates.

[0095] Exemplarily, the vertex pixel coordinates of the bounding rectangular frame in the black-and-white image are consistent with the vertex pixel coordinates in the grayscale image.

[0096] Exemplarily, the sub-region vertex space coordinates corresponding to the vertex pixel coordinates of the bounding rectangular frame are calculated according to the mutual correspondence relationship between the grayscale image data and the indoor map data.

[0097] Exemplarily, the mutual correspondence relationship between the grayscale image data and the indoor map data is calculated by the spatial coordinates, the shooting angle and the camera focal length of the monitoring camera in the indoor map data.

[0098] S700: Update the indoor map data according to the sub-region vertex space coordinates.

[0099] Exemplarily, for each white region contour in the black-and-white image data, the region surrounded by the sub-region vertex space coordinates corresponding to the vertex pixel coordinates of the bounding rectangular frame of the white region contour is a sub-region that has undergone significant changes; the indoor map data is re-measured and updated for the sub-region that has undergone significant changes, so as to realize automatic updating of the map.

[0100] In some implementation scenarios, the indoor map data updating method analyzes and processes the indoor video data to obtain grayscale image data, difference image data and black-and-white image data in sequence, and then obtains the sub-region vertex space coordinates in the indoor map data according to the region vertex pixel coordinates on the black-and-white image data, so as to realize updating of the indoor map data; the indoor map data updating method can obtain the indoor video data by using the existing monitoring camera, repeatedly use the existing monitoring camera, does not need to increase equipment, saves equipment cost, does not depend on real scene images uploaded by users, reduces occupation of user traffic, and improves user experience; in addition, the method can quickly judge the region that needs to be updated according to the black-and-white image data, and improves the updating efficiency, accuracy and timeliness of the indoor map data.

[0101] Please refer to Figure 3 , Figure 3 Another flowchart of an indoor map data updating method provided by the embodiment of the present application.

[0102] Exemplarily, S500: the step of obtaining the difference image data according to the grayscale image data and the historical grayscale image data comprises:

[0103] S510: image feature point matching is performed on the grayscale image data and the historical grayscale image data to obtain a transformation matrix;

[0104] S520: the grayscale image data is processed according to the transformation matrix to obtain transformed grayscale image data;

[0105] S530: difference image data is obtained according to the transformed grayscale image data and the historical grayscale image data.

[0106] Exemplarily, a transformation matrix between the grayscale image data and the historical grayscale image data is calculated by using an image feature point matching algorithm (such as SIFT), and the feature points of the two images can be aligned through the transformation matrix; thus, the transformation matrix is applied to the grayscale image data to obtain the transformed grayscale image data, the transformed grayscale image data is one-to-one corresponding to the historical grayscale image data, and the difference image data is obtained according to the pixel absolute difference.

[0107] In some implementation scenarios, due to rotation errors of a monitoring camera holder, device tilting and other reasons, the shooting angles of the grayscale image data and the historical grayscale image data have slight deviations, and the above steps can eliminate the shooting angle errors, thereby improving the calculation accuracy of the difference image data.

[0108] Exemplarily, after the step of S610: binarization processing is performed on the difference image data to obtain black-and-white image data, the method further includes:

[0109] S611: the black-and-white image data is processed using a preset ROI region to obtain processed black-and-white image data.

[0110] Exemplarily, the black-and-white image data is screened and processed using the pre-set ROI region, so that the part outside the ROI region in the black-and-white image is black, and the image processing accuracy and efficiency are improved.

[0111] In some implementation scenarios, for example, in the visible range of a monitoring camera in a shopping mall, a large area of lighting area is included; the lighting area often hangs various advertising banners and decorations, which are easily identified as having a large change, and thus the lighting area needs to be excluded from the ROI region.

[0112] Exemplarily, in the field of image processing, a region of interest (ROI) is a selected image region from an image, and this region is the focus of your image analysis. The region is circled for further processing; the ROI is used to circle the target you want to read, which can reduce the processing time and increase the accuracy.

[0113] Exemplarily, before the step of S620: obtaining the contour of each white region whose area is greater than the preset area threshold in the black-and-white image data, and generating the outer rectangular frame of each white region contour, the method further comprises:

[0114] S612: performing morphological processing on the processed black-and-white image data, and merging adjacent white regions in the processed black-and-white image data.

[0115] Exemplarily, the adjacent white regions in the black-and-white image data are merged, and the image processing efficiency is improved.

[0116] Exemplarily, the step of S300: generating the gray-scale image data according to the image frame data comprises:

[0117] S310: processing the image frame data according to a background separation algorithm to obtain background image data;

[0118] S320: converting the background image data into gray-scale image data and performing image enhancement processing on the gray-scale image data.

[0119] Exemplarily, the image frame data is processed by using the background separation algorithm to obtain the background image; available technical means include but are not limited to the average background method; the background image data is converted into gray-scale image data, and the gray-scale image data is processed by using an image enhancement algorithm to obtain the enhanced current gray-scale image.

[0120] Optionally, the image enhancement algorithm includes but is not limited to gamma correction, histogram equalization, brightness adjustment, contrast adjustment, etc.; the gray-scale image data can also be denoised and smoothed to make the gray-scale image data and the historical gray-scale image data more easily matched.

[0121] Exemplarily, after the step of S620: obtaining the contour of each white region whose area is greater than the preset area threshold in the black-and-white image data, and generating the outer rectangular frame of each white region contour, the method further comprises:

[0122] S621: cutting the region image data corresponding to the outer rectangular frame in the background image data;

[0123] S622: inputting the region image data into a preset deep learning classification model to generate an update evaluation result of the region image data.

[0124] Exemplarily, for each white region, the region image data surrounded by the region vertex pixel coordinates in the current background image data is cut, and the region image data is input into the pre-trained deep learning classification model as an input, and whether the region needs to update the indoor map data is determined through the update evaluation result.

[0125] In some implementation scenarios, when the update evaluation result is that the objects contained in the region are mainly animals, vehicles, or other movable objects, the indoor map data does not need to be updated; and when the objects contained in the region are mainly walls, barriers, or other artificial obstacles, the indoor map data needs to be updated.

[0126] Exemplarily, in combination with Figures 1 to 3 The specific application process of the indoor map data updating method of the embodiment of the present application is as follows:

[0127] Step 1, obtaining indoor map data, which is a monitoring video of a target region shot by a monitoring camera, and during the monitoring video, the shooting parameters (camera focal length, shooting angle, and shooting position) of the monitoring camera do not change;

[0128] Step 2, judging whether the target region has a significant change according to the indoor map data, and obtaining a sub-region having a significant change, and the steps are as follows:

[0129] Step 2.1, processing the image frames of the indoor map data by using a background separation algorithm to obtain background image data; available technical means include but are not limited to the average background method;

[0130] Step 2.2, converting the background image data into grayscale image data, and processing the grayscale image data by using an image enhancement algorithm to obtain enhanced grayscale image data; available image enhancement methods include but are not limited to gamma correction, histogram equalization, adjusting brightness, adjusting contrast, etc.; the grayscale image data can also be denoised and smoothed to make it easier to match;

[0131] Step 2.3, obtaining historical grayscale image data of the same target region shot in the last period and saved;

[0132] Step 2.4, using an image feature point matching algorithm (such as SIFT) to calculate a transformation matrix between the historical grayscale image data and the grayscale image data; the transformation matrix is used to align the feature points of the two images;

[0133] Step 2.5, applying the transformation matrix to the grayscale image data to obtain transformed grayscale image data;

[0134] Step 2.6, calculating the pixel absolute difference between the transformed grayscale image data and the historical grayscale image data to obtain difference image data;

[0135] Step 2.7, performing binary calculation on the difference image data to obtain black and white image data; the white area in the black and white image data represents the part (image difference greater than a preset value) that has a larger change in the historical grayscale image data and the grayscale image data;

[0136] Step 2.8, using a pre-set ROI region to filter the black and white image data, so that the part of the black and white image data outside the ROI region is black;

[0137] Step 2.9, morphological processing is performed on the black and white image book, and adjacent white regions in the black and white image data are merged.

[0138] Step 2.10, the contour of each white region with an area greater than a pre-set threshold is obtained respectively, and a bounding rectangle frame is calculated.

[0139] Step 2.11, for each white region, the four vertex pixel coordinates of the bounding rectangle frame are calculated using the transformation matrix, and the corresponding region vertex pixel coordinates in the grayscale image data are calculated;

[0140] Step 2.12, for each white region, the region image data surrounded by the region vertex pixel coordinates is intercepted in the background image data, and the region image data is taken as the input of the pre-trained deep learning classification model to determine whether the region needs to update the indoor map data;

[0141] Step 2.13, for each white region, according to the installation position information of the monitoring camera, the shooting angle of the monitoring camera and the camera parameters of the monitoring camera, the corresponding sub-region vertex space coordinates of the region vertex pixel coordinates in the indoor map data are calculated. For example, when the indoor map data is a three-dimensional real scene map, the installation position information of the monitoring camera includes the three-dimensional space coordinates of the monitoring camera in the indoor map data, the installation angle. According to the camera parameters of the monitoring camera and the region vertex pixel coordinates, four rays in the camera coordinate system are calculated; according to the installation angle, the shooting angle of the monitoring camera, and the three-dimensional space coordinates of the monitoring camera, a rotation and translation matrix from the camera coordinate system to the indoor map data coordinate system is calculated. According to the rotation and translation matrix, the four rays are transformed into the coordinate system of the indoor map data, and the intersection points of the four rays and the nearest floor / ground are calculated, that is, the corresponding sub-region vertex space coordinates of the region vertex pixel coordinates in the indoor map data;

[0142] Step 2.14, for each white region, the region surrounded by the corresponding space coordinates of the region vertex pixel coordinates in the indoor map data is a sub-region that has changed significantly;

[0143] Step 3, re-measuring and updating the indoor map data of the sub-region where the significant change occurs. As a feasible solution, the sub-region where the significant change occurs is confirmed by manual, and the point cloud data of the sub-region is collected by a three-dimensional laser scanner, and the indoor map data is updated by using the point cloud data. As another feasible solution, an unmanned vehicle is sent to carry a measuring device to collect the point cloud data of the sub-region, and the indoor map data is updated by using the point cloud data. The specific way of measuring method and updating indoor map data is not limited in the present application.

[0144] Please refer to Figure 4 , Figure 4 The structural block diagram of the indoor map data updating system provided by the embodiment of the present application comprises:

[0145] The video acquisition module 100 is configured to acquire indoor video data.

[0146] The image frame module 200 is configured to obtain image frame data of a target region according to the indoor video data.

[0147] The grayscale image module 300 is configured to generate grayscale image data according to the image frame data.

[0148] The historical grayscale image acquisition module 400 is configured to acquire historical grayscale image data of the target region.

[0149] The difference image module 500 is configured to obtain difference image data according to the grayscale image data and the historical grayscale image data.

[0150] The spatial coordinate module 600 is configured to acquire spatial coordinates of a vertex of a sub-region where the indoor map data needs to be updated according to the difference image data.

[0151] The spatial coordinate module 600 comprises: a black-and-white image unit configured to perform binaryzation processing on the difference image data to obtain black-and-white image data, wherein a white region in the black-and-white image data represents that a difference between the historical grayscale image data and the grayscale image data is greater than a preset value; an outer-enclosing rectangle unit configured to acquire an outline of each white region in the black-and-white image data whose area is greater than a preset area threshold, and generate an outer-enclosing rectangle frame of each white region outline; and a traversal unit configured to traverse all the outer-enclosing rectangle frames, and perform the following processing on the traversed outer-enclosing rectangle frame: acquiring corresponding region vertex pixel coordinates in the grayscale image data according to vertex pixel coordinates of the outer-enclosing rectangle frame; and acquiring corresponding sub-region vertex spatial coordinates in the indoor map data according to the region vertex pixel coordinates.

[0152] The update module 700 is configured to update the indoor map data according to the spatial coordinates of the vertex of the sub-region.

[0153] Exemplarily, the difference image module 500 comprises:

[0154] a feature point matching unit, configured to perform image feature point matching on the grayscale image data and the historical grayscale image data to obtain a transformation matrix;

[0155] a transformation processing unit, configured to perform processing on the grayscale image data according to the transformation matrix to obtain transformed grayscale image data;

[0156] a difference image unit, configured to obtain difference image data according to the transformed grayscale image data and the historical grayscale image data.

[0157] Exemplarily, the indoor map data updating system further comprises:

[0158] a ROI processing module, configured to perform processing on the black-and-white image data using a preset ROI region to obtain processed black-and-white image data.

[0159] Exemplarily, the indoor map data updating system further comprises:

[0160] a morphology processing module, configured to perform morphology processing on the processed black-and-white image data to merge adjacent white regions in the processed black-and-white image data.

[0161] Exemplarily, the grayscale image module 300 comprises:

[0162] a background image unit, configured to perform processing on the image frame data according to a background separation algorithm to obtain background image data;

[0163] a grayscale image unit, configured to convert the background image data into grayscale image data and perform image enhancement processing on the grayscale image data.

[0164] Exemplarily, the indoor map data updating system further comprises:

[0165] a clipping unit, configured to clip region image data corresponding to the outer rectangular frame from the background image data;

[0166] an updating evaluation unit, configured to input the region image data into a preset deep learning classification model to generate an updating evaluation result of the region image data.

[0167] It should be noted that, Figure 4 the indoor map data updating system shown in the embodiments of the present application corresponds to the method embodiments shown in the embodiments of the present application, and thus will not be described herein again to avoid repetition. Figures 1 to 3

[0168] The present application also provides an electronic device, please refer to Figure 5 , Figure 5 ​A structural block diagram of an electronic device is provided in the embodiments of the present application. The electronic device can include a processor 510, a communication interface 520, a memory 530, and at least one communication bus 540. The communication bus 540 is used to realize direct connection communication among the components. The communication interface 520 of the electronic device in the embodiments of the present application is used to communicate signaling or data with other node devices. The processor 510 can be an integrated circuit chip with signal processing capability.

[0169] The processor 510 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; and can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor 510 can also be any conventional processor.

[0170] The memory 530 can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory 530 stores computer readable instructions, which, when executed by the processor 510, can enable the electronic device to perform the above Figures 1 to 3 The method embodiments involve various steps.

[0171] Optionally, the electronic device can further include a storage controller, an input / output unit.

[0172] The memory 530, the storage controller, the processor 510, the peripheral interface, and the input / output unit are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses 540. The processor 510 is used to execute executable modules stored in the memory 530, such as software function modules or computer programs included in the electronic device.

[0173] The input / output unit is used to provide a user with creating a task and creating a selectable period of time or a preset execution time for the task to realize the interaction between the user and the server. The input / output unit can be, but is not limited to, a mouse, a keyboard and the like.

[0174] It can be understood that, Figure 5 The structure shown is only schematic, and the electronic device can further include more or fewer components than those shown, or have a different configuration of components than those shown. Figure 5 The components shown in the figures can be implemented in hardware, software, or a combination thereof. Figure 5 The components shown in the figures can be implemented in hardware, software, or a combination thereof. Figure 5 The components shown in the figures can be implemented in hardware, software, or a combination thereof.

[0175] The embodiments of the present application also provide a storage medium, which has instructions stored thereon, when the instructions are run on a computer, the computer program is executed by a processor to implement the method of the method embodiments. To avoid repetition, it will not be described here.

[0176] The present application also provides a computer program product, which, when run on a computer, causes the computer to execute the method of the method embodiments.

[0177] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only schematic, for example, the flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the devices, methods and computer program products according to the embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders from those shown in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for executing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0178] In addition, each functional module in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0179] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0180] The above merely provides an example of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0181] The above merely provides an example of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0182] It should be noted that, in the present document, the relationship terms such as first and second are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the processes, methods, articles or devices including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

Claims

1. A method for updating indoor map data, characterized in that, include: Acquire indoor video data; Image frame data of the target area is obtained based on the indoor video data; Generate grayscale image data based on the image frame data; Obtain historical grayscale image data of the target area; The difference image data is obtained based on the grayscale image data and the historical grayscale image data; Based on the difference image data, obtain the spatial coordinates of the sub-region vertices that need to be updated in the indoor map data; The indoor map data is updated based on the spatial coordinates of the vertices of the sub-region; The step of obtaining the spatial coordinates of the sub-region vertices that need to be updated in the indoor map data based on the difference image data includes: The difference image data is binarized to obtain black and white image data. The white area in the black and white image data indicates that the difference between the historical grayscale image data and the grayscale image data is greater than a preset value. Obtain the outlines of all white regions in the black and white image data whose area is greater than a preset area threshold, and generate an outer rectangle for each white region outline; Traverse all the bounding rectangles and perform the following processing on the traversed bounding rectangles: obtain the corresponding sub-region vertex pixel coordinates in the grayscale image data based on the vertex pixel coordinates of the bounding rectangles; obtain the corresponding sub-region vertex spatial coordinates in the indoor map data based on the sub-region vertex pixel coordinates.

2. The method for updating indoor map data according to claim 1, characterized in that, The step of obtaining the difference image data based on the grayscale image data and the historical grayscale image data includes: Image feature point matching is performed on the grayscale image data and the historical grayscale image data to obtain the transformation matrix; The grayscale image data is processed according to the transformation matrix to obtain the transformed grayscale image data; The difference image data is obtained based on the transformed grayscale image data and the historical grayscale image data.

3. The method for updating indoor map data according to claim 1, characterized in that, Before the step of obtaining the outlines of all white regions in the black and white image data whose area is greater than a preset area threshold, and generating the bounding rectangle of each white region outline, the method further includes: The processed black and white image data is subjected to morphological processing to merge adjacent white regions in the processed black and white image data.

4. The method for updating indoor map data according to claim 1, characterized in that, The step of generating grayscale image data based on the image frame data includes: The image frame data is processed according to the background separation algorithm to obtain background image data; The background image data is converted into grayscale image data, and image enhancement processing is performed on the grayscale image data.

5. The method for updating indoor map data according to claim 4, characterized in that, After the step of obtaining the outlines of all white regions in the black and white image data whose area is greater than a preset area threshold, and generating the bounding rectangle of each white region outline, the method further includes: Extract the region image data corresponding to the outer rectangular frame from the background image data; The image data of the region is input into a preset deep learning classification model to generate an updated evaluation result of the image data of the region.

6. An indoor map data updating system, characterized in that, include: The video acquisition module is used to acquire indoor video data; The image frame module is used to obtain image frame data of the target area based on the indoor video data; A grayscale image module is used to generate grayscale image data based on the image frame data; A historical grayscale image acquisition module is used to acquire historical grayscale image data of the target area; The difference image module is used to obtain difference image data based on the grayscale image data and the historical grayscale image data; The spatial coordinate module is used to obtain the spatial coordinates of the vertices of the sub-regions that need to be updated in the indoor map data based on the difference image data. The update module is used to update the indoor map data based on the spatial coordinates of the vertices of the sub-region; The spatial coordinate module includes: A black and white image unit is used to perform binarization processing on the difference image data to obtain black and white image data. The white area in the black and white image data indicates that the difference between the historical grayscale image data and the grayscale image data is greater than a preset value. The outer rectangular unit is used to obtain the outlines of all white regions in the black and white image data whose area is greater than a preset area threshold, and to generate an outer rectangular frame for each white region outline. The traversal unit is used to traverse all the outer bounding rectangles and perform the following processing on the traversed outer bounding rectangles: obtain the corresponding region vertex pixel coordinates in the grayscale image data based on the vertex pixel coordinates of the outer bounding rectangles; obtain the corresponding sub-region vertex spatial coordinates in the indoor map data based on the region vertex pixel coordinates.

7. The indoor map data updating system according to claim 6, characterized in that, The difference image module includes: The feature point matching unit is used to perform image feature point matching on the grayscale image data and the historical grayscale image data to obtain a transformation matrix; A transformation processing unit is used to process the grayscale image data according to the transformation matrix to obtain transformed grayscale image data; The difference image unit is used to obtain difference image data based on the transformed grayscale image data and the historical grayscale image data.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method for updating indoor map data as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the method for updating indoor map data as described in any one of claims 1 to 5.

Images