CN116894984B - Image recognition-based access method for home and computer readable storage medium - Google Patents
Image recognition-based access method for home and computer readable storage medium Download PDFInfo
- Publication number
- CN116894984B CN116894984B CN202311152298.3A CN202311152298A CN116894984B CN 116894984 B CN116894984 B CN 116894984B CN 202311152298 A CN202311152298 A CN 202311152298A CN 116894984 B CN116894984 B CN 116894984B
- Authority
- CN
- China
- Prior art keywords
- image
- building
- night scene
- shooting
- recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004891 communication Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000009466 transformation Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
- G06Q50/163—Real estate management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a home access method based on image recognition and a computer readable storage medium. Shooting a night scene photo outside a residential building, and transmitting the night scene photo to a cloud server; the cloud server identifies households with bright windows in night scene photos outside the residential building and generates corresponding residential information; and the cloud server transmits the house information to a communication terminal of a person accessing the house in the field, so that the person can directly access the resident of the person at home. The method can effectively obtain the residence information of the resident of the person in the home in the residential building, and the residence information can be transmitted to the communication terminal of the access person in real time for the access of the access person, so that the situation that whether the resident is in the home or not can not be determined by knocking the door for many times is reduced and avoided.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to a home access method and a computer readable storage medium based on image recognition.
Background
Property personnel or community management personnel need to enter the home to visit or conduct works such as census, economic census and the like, and usually need to make a call in advance for reservation or visit every time the person is knocked out, but the situation that the person is out of home is encountered, and time is delayed. The invention provides the method for improving the accuracy and the efficiency of the access to the home.
Disclosure of Invention
The invention mainly solves the technical problems that in the prior art, the access to the home needs to be contacted by telephone in advance, the access to the home by knocking the door frequently encounters the problems of low access efficiency, long time consumption, inaccuracy and the like of the home when the resident is not at home, and provides a home access method and a computer readable storage medium based on image recognition.
In order to solve the technical problems, the invention adopts a technical scheme that a home access method based on image recognition is provided, which comprises the following steps: 1. the home access method based on image recognition is characterized by comprising the following steps: shooting a night scene photo outside the residential building, and transmitting the night scene photo to a cloud server; the cloud server identifies households with bright windows in the night scene photo outside the residential building and generates corresponding residence information; the residence information is transmitted to a communication terminal of a person accessing the field for the person to directly access the corresponding resident with the bright window.
Further, the method for shooting the night scene photo outside the residential building comprises the following steps: responding to a trigger signal, entering a building night scene shooting mode, firstly entering a shooting preview stage, displaying images in a camera on a display screen, automatically identifying buildings in the shooting preview stage, and when a plurality of buildings exist, respectively framing the buildings by using a selected frame to prompt the selection of the buildings on the display screen; selecting one of the buildings to be accessed by a user, entering an automatic focusing stage, and enabling the camera to realize quick automatic focusing according to the size of the area occupied by the outline of the selected building on the display screen; then entering an automatic shooting stage, automatically adjusting exposure parameters of a night scene of a building shot by a lens, and acquiring images shot at least twice, namely a first night scene building image, on the basis of keeping the same shooting pictureAnd a second night scene building image +.>。
Further, the first night scene building imageThe corresponding image with low exposure parameters has darker overall picture and is used for accurately identifying the bright window of the building; said second night scene building image +.>The corresponding image is a high exposure parameter image, the whole picture is brighter, the high exposure parameter image is used for acquiring the outline of the building, and lines are extracted from the high exposure parameter image to determine floor division.
Further, in the automatic shooting stage, the building is divided into a plurality of shooting areas according to the illumination condition of the building to be shot, and the shooting areas are shot respectively, wherein exposure parameters corresponding to the shooting areas are different; wherein the first night scene building imageAfter split shooting, a first sub-image set +.>Wherein the sub-picture +.>Shooting under different exposure parameters, wherein n represents the number of sub-images in the first sub-image set, and combining and splicing the sub-images in the first sub-image set to obtain a first corrected night scene building image->The method comprises the steps of carrying out a first treatment on the surface of the Said second night scene building image +.>After split shooting, a second sub-image set +.>Wherein the sub-imagesShooting under different exposure parameters, wherein m represents the number of sub-images in the second sub-image set, and combining and splicing the sub-images in the second sub-image set to obtain a second corrected night scene building image。
Further, the method for identifying the resident with the bright window in the night view photo outside the residential building by the cloud server comprises the following steps: based on the first night scene building imageOr said first modified night scene building image +.>Performing image recognition to obtain the position information of the bright window of the building in the image; based on the second night scene building image +.>Or said second modified night scene building image +.>And carrying out image recognition to obtain floor information of the building in the image.
Further, the method for obtaining the position information of the bright window of the building in the image comprises the following steps: converting the first night scene building image or the first corrected night scene building image into a gray level image, performing image binarization processing on the gray level image, setting the gray level value of the bright window serving as an image background of a target identification area to be 0, and setting the gray level value of the bright window of the target identification area to be 1, so as to obtain a two-dimensional matrix with the numerical values of only 0 and 1; traversing the two-dimensional matrix, identifying and judging gray values of 6 adjacent matrix points around the matrix points when the gray values of 1 matrix point are found to be 1, determining whether 1 is connected, further identifying that a set of matrix points occupied by a bright window is an island, and then counting the number and positions of the islands to obtain a bright window identification map.
Further, the method for obtaining the floor information of the building in the image comprises the following steps: reading the second night scene building image or the second corrected night scene building image, converting the second night scene building image or the second corrected night scene building image into a gray level image, and converting the second night scene building image or the second corrected night scene building image into a binarized edge image by adopting an edge detection operator; then carrying out Hough transformation on the binarized edge image; firstly, searching a peak value in the Hough transformation of the binarized edge image by using a peak value detection function, and finding out a Hough transformation unit larger than a threshold value, wherein the local maximum value is a point on a line; and identifying a group of candidate peaks, determining line segments related to the candidate peaks, and starting points and ending points of the line segments, and corresponding to a plurality of transverse and longitudinal line segments to obtain a floor identification map.
Further, the bright window recognition graph and the floor recognition graph are overlapped and synthesized to obtain a mixed recognition graph; and numbering each line segment in the mixed identification graph, and determining the floor and unit position information of the bright window according to the number of the line segment and the range of the numbered section of the line segment of each bright window.
Further, the cloud server also provides a building elevation view of the residential building, and according to the building elevation view, the cloud server is used for comparing the number and the positions of the bright windows in the mixed identification view, and accurately judging whether the residential building belongs to the same resident or different residents.
Further, to achieve the above object, the present invention also provides a computer-readable storage medium having stored therein computer-executable instructions configured to perform and implement the steps of the above-described image recognition-based access method.
The beneficial effects of the invention are as follows: the invention discloses a home access method based on image recognition and a computer readable storage medium. Shooting a night scene photo outside a residential building, and transmitting the night scene photo to a cloud server; the cloud server identifies a resident who lights in a night scene photo outside the residential building, and generates corresponding residential information; and the cloud server transmits the house information to a communication terminal of a person accessing the house in the field, so that the person can directly access the resident of the person at home. The method can effectively obtain the residence information of the resident of the person in the home in the residential building, and the residence information can be transmitted to the communication terminal of the access person in real time for the access of the access person, so that the situation that whether the resident is in the home or not can not be determined by knocking the door for many times is reduced and avoided.
Drawings
FIG. 1 is a flow chart of one embodiment of a method of home access based on image recognition in accordance with the present invention;
FIG. 2 is a schematic view of an application scenario of an embodiment of a home access method based on image recognition according to the present invention;
FIG. 3 is a schematic diagram of identification tags of night scene buildings in another embodiment of a home access method based on image identification according to the present invention;
FIG. 4 is a schematic view of a first night scene building image in another embodiment of a home access method based on image recognition according to the present invention;
FIG. 5 is a schematic view of a second night scene building image in another embodiment of a home access method based on image recognition according to the present invention;
FIG. 6 is a schematic view of capturing different areas of a night scene building image according to another embodiment of an image recognition based access method of the present invention;
FIG. 7 is a schematic diagram of a combination of night scene building images after segmentation shooting in another embodiment of a home access method based on image recognition according to the present invention;
FIG. 8 is a schematic diagram of binarizing a first night scene building image according to another embodiment of an image recognition-based access method of the present invention;
FIG. 9 is a schematic view of bright window recognition after processing and recognizing a first night scene building image according to another embodiment of the image recognition-based access method of the present invention;
FIG. 10 is a schematic diagram of floor recognition after processing and recognizing a second night scene building image according to another embodiment of the image recognition-based access method of the present invention;
FIG. 11 is a composite schematic diagram of a bright window recognition graph and a floor recognition graph in another embodiment of an image recognition based access method according to the present invention;
FIG. 12 is a schematic illustration of a building facade requiring comparative identification in another embodiment of an image identification based access method according to the present invention.
Detailed Description
In order that the invention may be readily understood, a more particular description thereof will be rendered by reference to specific embodiments that are illustrated in the appended drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used in this specification includes any and all combinations of one or more of the associated listed items.
FIG. 1 shows a flowchart of one embodiment of a home access method based on image recognition, comprising the steps of:
step S1: shooting a night scene photo outside the residential building, and transmitting the night scene photo to a cloud server;
step S2: the cloud server identifies households with bright windows in the night scene photo outside the residential building and generates corresponding residence information;
step S3: the residence information is transmitted to the communication terminal of the personnel accessing the field for the personnel to directly access the corresponding resident with the bright window.
In combination with the application scene schematic diagram shown in fig. 2, the night view photo outside the residential building 1 mainly can present the on-lamp condition of the resident, if the resident is on, the resident is indicated to be at home, and whether the resident is on can be distinguished through the brightness and the darkness of the window. The photographing terminal 2 that photographs night scenes outside the residential building 1 is typically a User Equipment (UE) having a photographing function and a communication function, a mobile device, a User terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, or the like.
And then, the shot night view photo of one or more residential building external night scenes is transmitted to the cloud server 3, the photo is intelligently identified by the cloud server, and the residential information of the resident with the lighted lamp is identified, wherein the residential information comprises floors, units and house numbers. Generally, the cloud server belongs to a cloud server of a property unit or a community management unit where the residential building is located.
The cloud server 3 then transmits the house information to the communication terminal 4 of the person who accesses the field, so that the person who accesses the house information that can be accessed accurately and directly accesses the resident of the person who has the house. The whole process can be realized within seconds to minutes, and the method has the advantages of high speed and high accuracy.
It can be seen that, through the embodiment of the home access method based on image recognition shown in fig. 1 and 2, the residence information of the resident in the home with a person in the residential building can be effectively obtained, and the residence information can be transmitted to the communication terminal of the access person in real time for accurate home access, so that the situation that whether the resident is in the home or not can not be determined by multiple times of door knocking is reduced and avoided. The application is suitable for community and property managers in home visit, especially in the application with specific requirements of public management, and can greatly improve the efficiency and reduce the labor capacity of the managers.
Specifically, in step S1, the method for capturing a night view photograph outside the residential building includes entering a building night view capturing mode in response to a trigger signal, and displaying an instruction of a receiving processor by a view system, so as to remind that the current capturing mode is the building night view capturing mode.
Then, entering a shooting preview stage, displaying images in a camera on a display screen, automatically identifying the buildings in the camera, and when a plurality of buildings exist, respectively framing the buildings by using a selected frame to prompt the selection of the buildings on the display screen.
As shown in fig. 3, a plurality of buildings are identified in the picture, each Building is surrounded by a feature area, namely a rectangular frame, and is marked as Building, and the display frame and the marking indicate that the buildings and the Building are dynamically tracked along with the transfer of a lens and the change of a focal length.
And selecting one of the buildings needing to be accessed by a user, entering an automatic focusing stage, and enabling the camera to realize quick automatic focusing according to the size of the area occupied by the selected building outline on the display screen, so that the building outline can be completely entered into the display screen, and the largest area and the clearest display effect are obtained.
Specifically, when photographing, the central head-up photographing residential building is mainly performed, that is, photographing is performed at the middle position of the building, and the photographed height is also the position of the middle floor of the building, so that it is generally required to select a proper position opposite to the building for photographing, photographing can be performed by an unmanned aerial vehicle, photographing is performed around the residential building, and then a plurality of photos are synthesized. However, if the condition is not satisfied, the resident building may be photographed in a bottom view.
Then, the automatic shooting stage is further entered, and exposure parameters of the camera lens for shooting the night scene of the building are automatically adjusted, wherein the exposure parameters comprise automatic adjustment sensitivity (ISO), a shutter (S), exposure compensation (EV), a focusing mode (AF) and white balance (AWB). Wherein, the automatic adjusting sensitivity (ISO) is used for setting the sensitivity of the camera, the higher the ISO sensitivity is, the shorter the exposure time is, but the more the noise of the picture is; the shutter (S) is used for setting exposure time, equipment needs to be kept still before the exposure time is over, otherwise, a picture is blurred; exposure compensation (EV) is used to change the recommended exposure value of the camera, making the photo brighter or darker; the focusing mode (AF) is used for supporting single automatic focusing (AF-S), continuous automatic focusing (AF-C) and Manual Focusing (MF), and the continuous automatic focusing is used for automatically focusing again when the view finding picture is changed greatly; white Balance (AWB) can ensure that the imaging color is not affected by the light source color, and can be selected according to the light source type.
Specifically, in the automatic shooting stage, at least two shot images, namely, a first night scene building image, are acquired on the basis of maintaining the same shooting pictureAnd a second night scene buildingObject image->Wherein the first night scene building image +.>Corresponding to the image with low exposure parameters, the exposure compensation (EV) is lower, the whole acquired picture is darker, the purpose is to obtain better contrast between the bright window and the non-bright window, so as to be beneficial to more accurately identifying the window and the resident with the bright lamp, as shown in fig. 4; second night scene building image->Corresponding to the image of the high exposure parameters, where the exposure compensation (EV) is high and the acquired picture is overall bright, the purpose is to determine the floor division in order to acquire the outline of the building, from which lines are extracted, as shown in fig. 5.
Further, in the automatic shooting stage, the building is further divided according to the self-illumination condition of the shot building, the building is divided into a plurality of shooting areas to be shot respectively, exposure parameters corresponding to the shooting areas are different, but shooting effects of the shooting areas are consistent finally, and then the shooting areas are combined into a picture. Thus, the first night scene building imageAfter the split shooting, a first sub-image set can be obtained +.>First sub-picture->Are->Is photographed under different exposure parameters, wherein n represents the number of the sub-images in the first sub-image set, but the first corrected night scene building image finally obtained by combining and splicing the sub-imagesHas the same or very close display effect on the whole; likewise, a second night scene building imageOr after split shooting, a second sub-image set can be obtained>Wherein m represents the number of these sub-images in the second sub-image set, and finally the second corrected night scene building image after merging and stitching by these sub-images of the second sub-image set +.>。
Specifically, as shown in fig. 6, since the lower floor of the night scene building has external light irradiation, the brightness of the outer wall is obviously higher than that of the outer wall of the upper floor, so that the building is divided into an upper area and a lower area for shooting respectively when shooting, shooting is performed according to different exposure parameters, and finally splicing and synthesizing are performed, and fig. 7 shows an effect diagram of actual shooting and splicing.
Further, the method for the cloud server to identify the resident that lights in the night view photo outside the residential building in step S2 includes:
building image based on first night sceneOr first modified night scene building image +.>Performing image recognition to obtain the position information of the bright window resident in the image; based on the second night scene building image +.>Or a second modified night scene building image +.>Proceeding withAnd (5) identifying the image to obtain floor information of the building in the image.
The method for obtaining the position information of the bright window resident in the image comprises the following steps: the first night scene building image or the first corrected night scene building image is converted to a color artwork into a gray scale image, for example, the color artwork is converted into gray scale images (0-255) according to RGB values, white is 0, and black is 255. Then, the gray image is subjected to image binarization processing, for example, the average gray of the whole image is obtained according to the gray value of the current image to be used as a threshold value of gray segmentation (image binarization), the selected image background is basically black or dark gray, the processing is simple, after the image binarization, the gray value of the bright window serving as the image background of the target identification area is set to be 0, the gray value of the bright window of the target identification area is set to be 1, and a two-dimensional matrix with the values of only 0 and 1 is obtained, as shown in fig. 8.
Further preferably, the two-dimensional matrix is traversed, when the gray value of each 1 matrix point is found to be 1, the gray values of 6 adjacent matrix points around the matrix point are identified and judged, whether 1 is connected or not is determined, a set of matrix points occupied by a bright window is identified as an island (namely, pixel points occupied by the bright window) is further identified, and then the number and the positions of the islands are counted, so that a bright window identification chart is obtained, as shown in fig. 9.
Further, the method for obtaining the floor information of the building in the image comprises the following steps: reading a second night scene building imageOr the second corrected night scene building image is converted into a gray level image, and an edge detection operator (such as Canny) is adopted to convert into a binary edge image; then carrying out Hough transformation on the image; firstly, searching a peak value in the Hough transform of the image by using a peak value detection function, and finding out Hough transform units larger than a threshold value, wherein the local maximum value is the most possible line; the above identified set of candidate peaks requires determining the line segments associated therewith and the start and end points thereof, such as the various transverse and longitudinal line segments shown in FIG. 10, corresponding toTo the floor identification map.
Then, the bright window recognition map shown in fig. 9 and the floor recognition map shown in fig. 10 are superimposed and synthesized to obtain a mixed recognition map. And the line segments in the mixed recognition graph are numbered, and the numbering sequence can be numbered according to the definition and the far-near relation of the image and the sequence from top to bottom and from near to far. Therefore, the floor and unit position information of the bright window can be determined according to the line segment numbers and the line segment number interval range of each bright window.
Further, in order to verify and validate the bright window resident information obtained from the hybrid identification map, the cloud server also provides a building map of the associated residential building, including a building elevation map, as shown in fig. 12. The method is an engineering drawing showing the reality of a building, wherein the setting positions and the numbers of windows of each resident in a residential building are recorded in detail, so that the number and the positions of the bright windows in the mixed identification drawing can be accurately judged whether the resident belongs to the same resident or different resident, and the improvement of the accurate identification of the resident is facilitated.
Therefore, the invention discloses a home access method based on image recognition. Shooting a night scene photo outside a residential building, and transmitting the night scene photo to a cloud server; the cloud server identifies a resident who lights in a night scene photo outside the residential building, and generates corresponding residential information; and the cloud server transmits the house information to a communication terminal of a person accessing the house in the field, so that the person can directly access the resident of the person at home. The method can effectively obtain the residence information of the resident of the person in the home in the residential building, and the residence information can be transmitted to the communication terminal of the access person in real time for the access of the access person, so that the situation that whether the resident is in the home or not can not be determined by knocking the door for many times is reduced and avoided.
In addition, the invention further provides a computer readable storage medium, wherein the storage medium stores computer executable instructions configured to execute and implement the steps of the home access method based on image recognition in the above embodiments.
In the embodiments of the computer readable storage medium of the present invention, all the technical features of the embodiments of the home access method based on image recognition are included, and description and explanation contents are basically the same as those of the embodiments of the home access method based on image recognition, and are not described in detail herein.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part in the form of a software product stored in a computer readable storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above for performing the method according to the embodiments of the present invention.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structural changes made by the present invention and the accompanying drawings, or direct or indirect application in other related technical fields, are included in the scope of the present invention.
Claims (7)
1. The home access method based on image recognition is characterized by comprising the following steps:
shooting a night scene photo outside the residential building, and transmitting the night scene photo to a cloud server;
the cloud server identifies households with bright windows in the night scene photo outside the residential building and generates corresponding residence information;
the residence information is transmitted to a communication terminal of a person accessing in the field, so that the person can directly access the corresponding resident with the bright window;
the method for shooting the night scene photo outside the residential building comprises the following steps of using a shooting terminal:
responding to a trigger signal, entering a building night scene shooting mode, firstly entering a shooting preview stage, displaying images in a camera on a display screen, automatically identifying buildings in the shooting preview stage, and when a plurality of buildings exist, respectively framing the buildings by using a selected frame to prompt the selection of the buildings on the display screen;
selecting one of the buildings to be accessed by a user, entering an automatic focusing stage, and enabling the camera to realize quick automatic focusing according to the size of the area occupied by the outline of the selected building on the display screen;
then entering an automatic shooting stage, automatically adjusting exposure parameters of a night scene of a building shot by a lens, and acquiring images shot at least twice, namely a first night scene building image, on the basis of keeping the same shooting pictureAnd a second night scene building image +.>；
The first night scene building imageThe corresponding image with low exposure parameters has darker overall picture and is used for accurately identifying the bright window of the building; said second night scene building image +.>The corresponding image is an image with high exposure parameters, the whole picture is brighter, and the image is used for acquiring the outline of the building and extracting lines from the outline for determining floor division;
the method for identifying the resident with the bright window in the night scene photo outside the residential building by the cloud server comprises the following steps:
based on the first night scene building imagePerforming image recognition to obtain a bright window recognition graph and position information of a bright window of the building in the image; based on the second night scene building image +.>Performing image recognition to obtain a floor recognition graph and floor information of a building in the image;
superposing and synthesizing the bright window identification chart and the floor identification chart to obtain a mixed identification chart; and numbering each line segment in the mixed identification graph, and determining residence information of the bright window according to the number of the line segment and the range of the numbered section of the line segment of each bright window, wherein the residence information comprises floor and unit position information.
2. The home access method based on image recognition according to claim 1, wherein in the automatic shooting stage, the building is further divided into a plurality of shooting areas according to the illumination condition of the building to be shot, and the shooting areas are respectively shot, wherein exposure parameters corresponding to the shooting areas are different;
wherein the first night scene building imageAfter split shooting, a first sub-image set +.>Wherein the sub-picture +.>Shooting under different exposure parameters, wherein n represents the number of sub-images in the first sub-image set, and combining and splicing the sub-images in the first sub-image set to obtain a first corrected night scene building image->；
The second night scene building imageAfter split shooting, a second sub-image set +.>Wherein the sub-picture +.>Shooting under different exposure parameters, wherein m represents the number of sub-images in the second sub-image set, and combining and splicing the sub-images in the second sub-image set to obtain a second corrected night scene building image->。
3. The image recognition-based home access method of claim 2, wherein the method for the cloud server to recognize a resident of a bright window in a night scene photo outside the residential building further comprises:
based on the first corrected night scene building imagePerforming image recognition to obtain a bright window recognition graph and position information of a bright window of the building in the image; correcting night scene building images based on the secondAnd carrying out image recognition to obtain a floor recognition graph and floor information of the building in the image.
4. The image recognition-based home access method of claim 3, wherein the method for obtaining the bright window recognition map and the position information of the bright window of the building in the image comprises the following steps: converting the first night scene building image or the first corrected night scene building image into a gray level image, performing image binarization processing on the gray level image, setting the gray level value of the bright window serving as an image background of a target identification area to be 0, and setting the gray level value of the bright window of the target identification area to be 1, so as to obtain a two-dimensional matrix with the numerical values of only 0 and 1;
traversing the two-dimensional matrix, identifying and judging gray values of 6 adjacent matrix points around the matrix points when the gray values of 1 matrix point are found to be 1, determining whether 1 is connected, further identifying that a set of matrix points occupied by a bright window is an island, and then counting the number and positions of the islands to obtain the bright window identification map.
5. The image recognition-based access method for a home of claim 4, wherein the method for obtaining floor information of a building in the floor recognition map and the image comprises: reading the second night scene building image or the second corrected night scene building image, converting the second night scene building image or the second corrected night scene building image into a gray level image, and converting the second night scene building image or the second corrected night scene building image into a binarized edge image by adopting an edge detection operator; then carrying out Hough transformation on the binarized edge image; firstly, searching a peak value in the Hough transformation of the binarized edge image by using a peak value detection function, and finding out a Hough transformation unit larger than a threshold value, wherein the local maximum value is a point on a line; and identifying a group of candidate peaks, determining line segments related to the candidate peaks, and starting points and ending points of the line segments, and corresponding to a plurality of transverse and longitudinal line segments to obtain the floor identification map.
6. The method for accessing a home based on image recognition according to claim 5, wherein the cloud server further provides a building elevation view of the residential building, and according to the building elevation view, the number and the positions of the bright windows in the mixed recognition view are compared, so that whether the residential building belongs to the same residence or different residents can be accurately judged.
7. A computer-readable storage medium having stored therein computer-executable instructions configured to perform the steps of the image recognition-based home access method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311152298.3A CN116894984B (en) | 2023-09-07 | 2023-09-07 | Image recognition-based access method for home and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311152298.3A CN116894984B (en) | 2023-09-07 | 2023-09-07 | Image recognition-based access method for home and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116894984A CN116894984A (en) | 2023-10-17 |
| CN116894984B true CN116894984B (en) | 2023-12-26 |
Family
ID=88311082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311152298.3A Active CN116894984B (en) | 2023-09-07 | 2023-09-07 | Image recognition-based access method for home and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116894984B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127424A (en) * | 2016-09-19 | 2016-11-16 | 湖南优图信息技术有限公司 | A kind of medium-sized and small enterprises visiting tour method and system |
| CN208607703U (en) * | 2018-07-18 | 2019-03-15 | 王全胜 | A kind of supervisory systems visited of visiting |
| CN110636227A (en) * | 2019-09-24 | 2019-12-31 | 合肥富煌君达高科信息技术有限公司 | High dynamic range HDR image synthesis method and high-speed camera integrating same |
| WO2020038069A1 (en) * | 2018-08-22 | 2020-02-27 | Oppo广东移动通信有限公司 | Exposure control method and device, and electronic apparatus |
| CN111726532A (en) * | 2020-06-30 | 2020-09-29 | 北京环境特性研究所 | Windowing alarm detection system and method |
| CN112911243A (en) * | 2021-02-01 | 2021-06-04 | 江苏开拓信息与系统有限公司 | Method for analyzing vacancy rate of house by aid of high-altitude parabolic monitoring |
| CN113179374A (en) * | 2021-04-22 | 2021-07-27 | 深圳传音控股股份有限公司 | Image processing method, mobile terminal and storage medium |
| CN113888437A (en) * | 2021-10-15 | 2022-01-04 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN115620029A (en) * | 2022-10-08 | 2023-01-17 | 北京惠朗时代科技有限公司 | Smart city-oriented owner actual living big data detection method and system |
-
2023
- 2023-09-07 CN CN202311152298.3A patent/CN116894984B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127424A (en) * | 2016-09-19 | 2016-11-16 | 湖南优图信息技术有限公司 | A kind of medium-sized and small enterprises visiting tour method and system |
| CN208607703U (en) * | 2018-07-18 | 2019-03-15 | 王全胜 | A kind of supervisory systems visited of visiting |
| WO2020038069A1 (en) * | 2018-08-22 | 2020-02-27 | Oppo广东移动通信有限公司 | Exposure control method and device, and electronic apparatus |
| CN110636227A (en) * | 2019-09-24 | 2019-12-31 | 合肥富煌君达高科信息技术有限公司 | High dynamic range HDR image synthesis method and high-speed camera integrating same |
| CN111726532A (en) * | 2020-06-30 | 2020-09-29 | 北京环境特性研究所 | Windowing alarm detection system and method |
| CN112911243A (en) * | 2021-02-01 | 2021-06-04 | 江苏开拓信息与系统有限公司 | Method for analyzing vacancy rate of house by aid of high-altitude parabolic monitoring |
| CN113179374A (en) * | 2021-04-22 | 2021-07-27 | 深圳传音控股股份有限公司 | Image processing method, mobile terminal and storage medium |
| CN113888437A (en) * | 2021-10-15 | 2022-01-04 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN115620029A (en) * | 2022-10-08 | 2023-01-17 | 北京惠朗时代科技有限公司 | Smart city-oriented owner actual living big data detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116894984A (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108419023B (en) | Method for generating high dynamic range image and related equipment | |
| CN107977940B (en) | Background blurring processing method, device and equipment | |
| CN110248096B (en) | Focusing method and device, electronic equipment and computer readable storage medium | |
| EP3520390B1 (en) | Recolorization of infrared image streams | |
| CN107948538B (en) | Imaging method, imaging device, mobile terminal and storage medium | |
| CN109767467A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| KR101155406B1 (en) | Image processing apparatus, image processing method and computer readable-medium | |
| CN110149482A (en) | Focusing method, device, electronic equipment and computer readable storage medium | |
| CN105578063A (en) | Image processing method and terminal | |
| JP6553624B2 (en) | Measurement equipment and system | |
| CN109844804B (en) | Image detection method, device and terminal | |
| CN110536068A (en) | Focusing method and device, electronic equipment, computer readable storage medium | |
| CN105245863A (en) | Image processing device that performs white balance control, method of controlling the same, and image pickup apparatus | |
| CN110022469A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN110349163B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN107404647A (en) | Camera lens condition detection method and device | |
| KR20120007948A (en) | Electronic camera, image processing apparatus, and image processing method | |
| CN108616700B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN109712177A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN110191287A (en) | Focusing method and device, electronic equipment, computer readable storage medium | |
| CN108322651A (en) | Image pickup method and device, electronic equipment, computer readable storage medium | |
| CN107682611B (en) | Focusing method and device, computer readable storage medium and electronic equipment | |
| CN106469442A (en) | A kind of enhancement method of low-illumination image based on array image | |
| CN113989387A (en) | Camera shooting parameter adjusting method and device and electronic equipment | |
| CN113674303A (en) | Image processing method, image processing device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |