CN112465860B - Method and equipment for checking running state of door - Google Patents
Method and equipment for checking running state of door Download PDFInfo
- Publication number
- CN112465860B CN112465860B CN202011287304.2A CN202011287304A CN112465860B CN 112465860 B CN112465860 B CN 112465860B CN 202011287304 A CN202011287304 A CN 202011287304A CN 112465860 B CN112465860 B CN 112465860B
- Authority
- CN
- China
- Prior art keywords
- door
- image data
- acquiring
- tracking
- target area
- 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 46
- 238000007689 inspection Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000012937 correction Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for checking the operating state of a door, comprising: s1, acquiring image data of a door, and extracting a target area on the door based on the image data; s2, acquiring the image data according to a time sequence, and acquiring a motion trail of the target area based on the image data; s3, checking the motion trail; s4, re-acquiring the image data of the door, and tracking the running state of the door based on the checked movement track. The detection method of the scheme has the advantages of high efficiency, excellent accuracy and good instantaneity.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for checking an operation state of a door.
Background
The elevator is a very popular public facility, is widely applied to scenes such as markets, office areas and residential areas, brings great convenience to daily life of people, and can occasionally fail due to the influence of incorrect use, untimely maintenance and other factors. The door faults are faults with highest frequency in a plurality of faults of the elevator, the types of the door faults are more, the elevator cannot be normally opened after stopping, people can possibly be trapped or passengers can be blocked, the passengers can possibly fall down when the elevator is opened in the running process, therefore, the door motion information can be acquired in real time, the door motion information is analyzed, the elevator with abnormal door motion is timely maintained, and the elevator taking safety problem caused by the door faults can be effectively reduced.
The prior art comprises the following steps: and determining the door edge position by using an identification method, predicting the door edge position by using a door motion model, and obtaining a door motion track by combining the identification and prediction methods. The problems of the prior art are: 1. the edge recognition speed of the elevator door is low, so that real-time is difficult to achieve; 2. false detection is easy to occur when illumination or background color is close to a door, and the result is unstable; 3. when the door is about to be fully opened, there are often multiple edges that occur, often due to specular reflection, and the edge position is difficult to determine.
For example, chinese patent CN107886524a discloses a method for identifying motion trajectories of elevator doors. The method comprises the steps of determining the position of a door edge in an elevator door image sequence in an identification mode; determining an elevator door motion trail model according to the acquired elevator door edge position information; and then determining the motion track of the elevator door by combining the door edge recognition method and the track model. However, the technical scheme has the following disadvantages:
the extracted door edge is easily interfered by the outside, so that the accuracy and stability of a door movement track are affected, and the influence factors mainly comprise the influence of ambient illumination, the outside-elevator background information and the fact that passengers shelter the elevator door edge to cause that the complete door edge cannot be detected; the door edge extraction efficiency is also low, and real-time application is difficult to meet at the camera end.
Disclosure of Invention
The invention aims to provide an operation state checking method and equipment for a door, which solve the problem of low detection efficiency.
To achieve the above object, the present invention provides an operation state checking method for a door, comprising:
S1, acquiring image data of a door, and extracting a target area on the door based on the image data;
s2, acquiring the image data according to a time sequence, and acquiring a motion trail of the target area based on the image data;
s3, checking the motion trail;
S4, re-acquiring the image data of the door, and tracking the running state of the door based on the checked movement track.
According to one aspect of the present invention, in step S2, the motion trajectory is acquired for the start based on the door closing state of the door.
According to one aspect of the present invention, in step S2, in the step of acquiring the motion trail of the target region by the image data, the target region in the image data is searched for according to time sequence, and the positions of the target region are acquired and sequentially arranged according to time sequence to form the motion trail.
According to one aspect of the present invention, in step S2, the step of acquiring a motion trajectory of the target area based on the image data includes:
S21, establishing a coordinate axis parallel to the opening and closing direction of the door based on the image data of the door;
S22, acquiring corresponding nodes of each position on the coordinate axis on the motion track along the direction perpendicular to the coordinate axis;
s23, sequentially acquiring the deviation distances between each position on the motion track and the corresponding node according to the time sequence from the door closing state to the door opening state.
According to an aspect of the present invention, in the step S3, in the step of verifying the motion trajectory, a start point of the motion trajectory is a position of the target area on the image data in a door-closed state.
According to one aspect of the present invention, in step S4, the step of re-acquiring the image data of the door and tracking the running state of the door based on the checked motion trail includes:
S41, re-acquiring the image data of the door, judging whether the door is in a door closing state in the image data, and if so, starting to execute tracking;
s42, acquiring the image data according to the time sequence from the door closing state to the door opening state, and correcting the image data based on the deviation distance;
s43, acquiring the target area in the corrected image data based on a tracking algorithm, and carrying out matching judgment on the target area and a corresponding node on a coordinate axis to realize tracking of the door running state.
According to one aspect of the present invention, in step S2, the motion trajectory is acquired using a KCF tracking algorithm or a tracking algorithm based on deep learning.
According to one aspect of the invention, the target region is extracted from the image data by means of manual and/or automatic analysis.
To achieve the above object, the present invention provides an inspection apparatus comprising:
The image acquisition device is used for acquiring an image data acquisition module and a tracking module of the image data of the door;
The server is used for acquiring the image data, processing and acquiring the motion trail, and sending the motion trail to the tracking module;
the tracking module tracks the running state of the door based on the image data acquired by the image data acquisition module and generates motion information.
According to one aspect of the invention, after the tracking module receives the motion trail, it confirms whether the door is in a door closing state, if so, an algorithm is executed to initialize and tracking is started to be executed.
According to one aspect of the invention, the deviation distance of the corresponding node on the coordinate axis of the motion trail parallel to the opening and closing direction of the door is obtained through the server or obtained through the tracking module.
According to the scheme, the server side and the image acquisition side resources are fused, firstly, a tracking method with high complexity and good effect is used at the server side to obtain an accurate door motion track, then the generated track is sent to the image acquisition side, and the image acquisition side can accurately obtain door motion information in real time by combining the track with a simple tracking algorithm.
According to the scheme of the invention, the calculated amount of the camera end can be effectively reduced, the tracking accuracy is improved, and the door edge position can be well determined through the accurate track of the server end.
According to the scheme of the invention, a tracking method (discriminant) based on feature matching is adopted, and the method has small calculated amount and is suitable for being applied to a camera end.
Drawings
FIG. 1 is a block diagram schematically illustrating steps of a method of status checking according to one embodiment of the present invention;
FIG. 2 is a schematic representation of image data acquired in a condition inspection method according to one embodiment of the invention;
FIG. 3 is a schematic representation of marker locations containing target areas represented in a method of status checking according to one embodiment of the present invention;
FIG. 4 is a schematic representation of a target area at a door-closed state in a state checking method according to an embodiment of the present invention;
Fig. 5 is a view schematically showing a motion trajectory of a door in a state checking method according to an embodiment of the present invention;
Fig. 6 is a view schematically showing a motion trajectory of a door displayed in image data in a state checking method according to an embodiment of the present invention;
Fig. 7 is a correction chart schematically showing a motion trajectory of a door displayed in image data in a state checking method according to an embodiment of the present invention;
FIG. 8 is a schematic representation of a correction trajectory in a state checking method according to one embodiment of the present invention;
fig. 9 is a structural view schematically showing an inspection apparatus according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
In describing embodiments of the present invention, the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer" and the like are used in terms of orientation or positional relationship based on that shown in the drawings, which are merely for convenience of description and to simplify the description, rather than to indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and thus the above terms should not be construed as limiting the present invention.
The present invention will be described in detail below with reference to the drawings and the specific embodiments, which are not described in detail herein, but the embodiments of the present invention are not limited to the following embodiments.
As shown in fig. 1, according to an embodiment of the present invention, an operation state checking method for a door of the present invention includes:
S1, acquiring image data of a door, and extracting a target area on the door based on the image data;
S2, acquiring image data according to a time sequence, and acquiring a motion trail of a target area based on the image data;
S3, checking the motion trail;
s4, re-acquiring the image data of the door, and tracking the running state of the door based on the checked movement track.
As shown in fig. 2, in step S1, image data of an area where a door (e.g., an elevator door) is located is acquired by an image acquisition device, and the acquired data is stored in a server.
As shown in fig. 3, in this embodiment, the position of the target area (such as the area where the tag is located) on the door is manually set according to the acquired image data, and/or the position of the target area (such as the area where the tag is located) in the image data is set by an automatic analysis method, so that the position of the target area is acquired (i.e., a polygon position with a relatively rich texture as shown in fig. 3) in the above manner. Further, a target area having a target on each door is identified based on the position including the target area (see fig. 4).
According to an embodiment of the present invention, in step S2, image data in a server is sequentially extracted in accordance with the timing of the image data and a target area in the image data is acquired (see the square frame position shown in fig. 4). The movement trace of the target area during the door opening and closing process can be formed by changing the position of the target area according to the time sequence (see fig. 5). In this embodiment, a tracking algorithm is used to track the target region and form a motion trajectory. Furthermore, as shown in fig. 5 and 6, the target area in the image data in the server is a tracking target of the tracking algorithm, the data image is extracted according to the time sequence, the target area between two adjacent frames of images (of course, two non-adjacent frames of images) is searched by the tracking algorithm, the similarity between the target areas is compared, the target area with the highest similarity is obtained, and further, continuous tracking of the target area in the image data can be continuously realized, and the purpose of generating a motion track is achieved. In the present embodiment, in the process of generating a motion trajectory by performing the tracking algorithm, if the door in the input image data is in the closed state (see fig. 4), the motion trajectory of the target area may be formed directly through the operation of the door from the closed to the open. If the door in the input image data is in a non-door-closing state, it is difficult to directly acquire a complete motion track through the running state of the door, and then the image data is required to be continuously extracted in time sequence to execute the tracking process of the tracking algorithm until the motion track can be extracted under the closed state of the door. In this embodiment, the process of generating the motion trail is implemented on the server, which belongs to an offline generation process, and the tracking algorithm adopted may be a KCF tracking algorithm or a tracking algorithm based on deep learning, so as to finally obtain the motion trail of the door, and the accuracy of the motion trail is very high. In this embodiment, the target area is lost when the door is fully opened, and the target area position that can be tracked is the door boundary.
According to an embodiment of the present invention, in step S2, the step of acquiring a motion trajectory of a target area based on image data includes:
S21, establishing a coordinate axis parallel to the opening and closing direction of the door based on the image data of the door; in the present embodiment, as shown in fig. 5 to 7, a coordinate axis a parallel to the opening and closing direction of the door is established based on the image data of the door, and the coordinate axis a may be displayed or hidden in the image data, which may be represented by a straight line having a color.
S22, acquiring corresponding nodes of each position on the coordinate axis on the motion track along the direction perpendicular to the coordinate axis; in the present embodiment, as shown in fig. 5 to 7, the corresponding position in the vertical direction with respect to the coordinate axis, that is, the corresponding node is calculated based on the target region in the movement locus.
S23, sequentially acquiring the deviation distances between each position on the motion track and the corresponding node according to the time sequence from the door closing state to the door opening state. In this embodiment, a deviation distance value between the target area on the motion trajectory and the corresponding node b on the coordinate axis is obtained.
In this embodiment, in step S3, in the step of verifying the motion trajectory, both the start point and the end point of the trajectory are in the known target area, and the situation that there is a sudden large change in the slope of the motion trajectory is eliminated. Furthermore, the starting point of the motion trail is the position of the target area on the image data in the door closing state, namely, when the door is closed again through verification, the target area can return to the starting position.
After verification, an accurate motion track for opening and closing the door is obtained and sent to the camera end.
According to an embodiment of the present invention, in step S4, in the step of re-acquiring the image data of the door and tracking the running state of the door based on the checked motion trail, the on-line door running state tracking is directly performed through the camera end, which includes:
S41, re-acquiring the image data of the door, judging whether the door is in a door closing state in the image data, and if so, starting to execute tracking. In this embodiment, the real-time image data of the door is collected again on the camera end line, and it is determined whether the door is in a door-closed state, if so, a tracking algorithm on the camera end is initialized to start tracking.
S42, acquiring the image data according to the time sequence from the door closing state to the door opening state, and correcting the image data based on the deviation distance. Referring to fig. 2 and 3, due to the influence of the installation position and imaging quality of the image acquisition device, when imaging the door operation process, the position of the target area on the door still changes in the horizontal direction and the vertical direction in the opening and closing process, and then the camera end needs to correct the image data in the process of acquiring the image, so that horizontal real-time tracking based on the opening and closing door direction can be realized. In this embodiment, the server has calculated the offset distance δh between each position on the motion track and the horizontal coordinate axis in the vertical direction (see fig. 5) according to the time sequence during the process of collecting the motion track, and these offset distances δh are also sent to the camera end together for correcting the parameters of the target area. Note that δh is equal to the difference in pixel height between the height of the point of each column of the track and the start point of the track (i.e. the vertical distance between the point of each column of the track and the horizontal coordinate axis). In addition, according to another embodiment of the present invention, after the server issues the motion trail to the camera end, the offset distance may be directly calculated and obtained by the camera end.
In this embodiment, the whole image is adjusted at the camera end based on the offset distance value corresponding to each node b on the motion track to implement correction of the image data, as shown in fig. 8, by the above correction method, after image correction is performed in time sequence, a manner that the target areas on each image data are sequentially arranged according to the time sequence and the coordinate axes is actually implemented, so that the displacement in the vertical direction is effectively eliminated, and only the position change along the coordinate axis direction (horizontal direction) is implemented.
Specifically, when the camera end starts to track, the camera acquires a first frame image (such as a door-closed state) according to the time sequence, and corrects each column of nodes (such as pixel points) in the image data based on the deviation distance between the motion track and each node (such as pixel point) on the horizontal coordinate axis in the first frame image data, so that the subsequent matching judgment process can be performed.
Through the correction process, the motion track is converted from the tracking in the two-dimensional direction (horizontal direction and vertical direction) to the tracking in the one-dimensional direction (horizontal direction), so that the calculated amount of a tracking algorithm is greatly reduced, and the efficiency and the effect of on-line tracking are greatly improved.
S43, acquiring a target area in the corrected image data based on a tracking algorithm, and carrying out matching judgment on the target area and a corresponding node on a coordinate axis to realize tracking of the running state of the door. In this embodiment, after correcting the image data, the target area in the image data is obtained, and the actual running position of the door can be obtained only by matching and judging the obtained target area with the corresponding node position on the coordinate axis, so that the actual running position of the door can be completely obtained through continuous time sequence image data (i.e. video stream) correction and position matching judgment, and the tracking of the running state of the door is achieved. In this embodiment, the tracking algorithm adopted by the camera end is a simpler tracking algorithm, such as a tracking algorithm based on hash matching.
In this embodiment, in the process of tracking at the camera end, the manner of acquiring the target area in the image is identical to the foregoing manner, and will not be described herein.
It should be noted that, since the motion trail is generated after continuously collecting and extracting a plurality of pieces of image data, the motion trail may be displayed in different image data in a superimposed manner or may be displayed in a non-superimposed manner.
It should be noted that, when the tracking algorithm is initialized (i.e. the door-closed state), a region of interest is set in a certain frame of image, and the region is the target to be tracked, and after the subsequent target moves, the position after the target moves can be found again near the target of the previous frame by the method.
As shown in fig. 9, according to an embodiment of the present invention, an inspection apparatus of the present invention includes: the image acquisition device and the server connected with the image acquisition device. The image acquisition device and the server can be connected by a wire or a wireless. In this embodiment, the image capturing device may employ a camera, an image data capturing module for capturing image data of the door, and a tracking module; the server is used for acquiring image data, processing and acquiring the motion trail, and sending the motion trail to the tracking module. In this embodiment, the tracking module tracks the running state of the door based on the image data acquired by the image data acquisition module and generates the motion information.
As shown in fig. 1, after receiving the motion trail, the tracking module confirms whether the door is in a door-closed state, if yes, performs algorithm initialization and starts to perform tracking.
In the embodiment, in the process of tracking the door, the motion information can be analyzed, and if the motion information is abnormal, the alarm information is output in real time.
In this embodiment, the offset distance of the corresponding node on the coordinate axis parallel to the opening and closing direction of the door is obtained by the server or obtained by the tracking module.
The foregoing is merely exemplary of embodiments of the invention and, as regards devices and arrangements not explicitly described in this disclosure, it should be understood that this can be done by general purpose devices and methods known in the art.
The above description is only one embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An operational status checking method for a door, comprising:
S1, acquiring image data of a door, and extracting a target area on the door based on the image data;
s2, acquiring the image data according to a time sequence, and acquiring a motion trail of the target area based on the image data;
s3, checking the motion trail;
S4, re-acquiring image data of the door, and tracking the running state of the door based on the checked motion trail;
in step S2, the step of acquiring the motion trail of the target area based on the image data includes:
S21, establishing a coordinate axis parallel to the opening and closing direction of the door based on the image data of the door;
S22, acquiring corresponding nodes of each position on the coordinate axis on the motion track along the direction perpendicular to the coordinate axis;
S23, sequentially acquiring the deviation distances between each position on the motion track and the corresponding node according to the time sequence from the door closing state to the door opening state;
In step S3, in the step of verifying the motion trail, a start point of the motion trail is a position of the target area on the image data in a door closing state of the door;
In step S4, the step of re-acquiring the image data of the door and tracking the running state of the door based on the checked motion trail includes:
S41, re-acquiring the image data of the door, judging whether the door is in a door closing state in the image data, and if so, starting to execute tracking;
s42, acquiring the image data according to the time sequence from the door closing state to the door opening state, and correcting the image data based on the deviation distance;
s43, acquiring the target area in the corrected image data based on a tracking algorithm, and carrying out matching judgment on the target area and a corresponding node on a coordinate axis to realize tracking of the door running state.
2. The running state checking method according to claim 1, wherein in step S2, the motion trajectory is acquired for the start based on the door closing state of the door.
3. The running state checking method according to claim 2, wherein in step S2, in the step of acquiring the movement trace of the target area from the image data, the target areas in the adjacent image data are searched in accordance with a time sequence, and the positions of the target areas are acquired and sequentially arranged in accordance with the time sequence to form the movement trace.
4. A running state checking method according to any one of claims 1 to3, wherein in step S2, the motion trajectory is acquired using a KCF tracking algorithm or a deep learning-based tracking algorithm.
5. A method of checking the operational state according to any one of claims 1 to 3, wherein the target area is extracted from the image data by means of manual and/or automatic analysis.
6. An inspection apparatus for use in the operation state inspection method according to any one of claims 1 to 5, characterized by comprising:
The image acquisition device is used for acquiring an image data acquisition module and a tracking module of the image data of the door;
The server is used for acquiring the image data, processing and acquiring the motion trail, and sending the motion trail to the tracking module;
the tracking module tracks the running state of the door based on the image data acquired by the image data acquisition module and generates motion information.
7. The inspection apparatus of claim 6, wherein the tracking module, upon receiving the motion profile, confirms whether the door is in a closed state, and if so, performs algorithm initialization and begins tracking.
8. The inspection apparatus according to claim 7, wherein the deviation distance of the corresponding node on the coordinate axis of the movement locus parallel to the opening and closing direction of the door is obtained by the server or by the tracking module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011287304.2A CN112465860B (en) | 2020-11-17 | 2020-11-17 | Method and equipment for checking running state of door |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011287304.2A CN112465860B (en) | 2020-11-17 | 2020-11-17 | Method and equipment for checking running state of door |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112465860A CN112465860A (en) | 2021-03-09 |
| CN112465860B true CN112465860B (en) | 2024-05-31 |
Family
ID=74837592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011287304.2A Active CN112465860B (en) | 2020-11-17 | 2020-11-17 | Method and equipment for checking running state of door |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465860B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664552B (en) * | 2023-07-24 | 2023-09-29 | 凯尔菱电（山东）电梯有限公司 | Elevator door abnormity detection method based on video image analysis |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010058665A (en) * | 2008-09-03 | 2010-03-18 | Denso Corp | Vehicular door control system |
| CN104612533A (en) * | 2015-01-09 | 2015-05-13 | 江西百胜门控设备有限公司 | Deviation detection and correction method for automatic door straight-line running |
| CN207092724U (en) * | 2017-06-02 | 2018-03-13 | 瑞高科技（深圳）有限责任公司 | A kind of intelligent electronic lock and intelligent safety door |
| CN107886524A (en) * | 2017-11-20 | 2018-04-06 | 江苏省特种设备安全监督检验研究院 | A kind of elevator door movement locus recognition methods |
| CN108038415A (en) * | 2017-11-06 | 2018-05-15 | 湖南华诺星空电子技术有限公司 | A kind of unmanned plane based on machine vision detects automatically and tracking |
| CN108495775A (en) * | 2016-01-06 | 2018-09-04 | 庞巴迪运输有限公司 | Door gear and the method for operating door gear |
| CN108520531A (en) * | 2018-05-23 | 2018-09-11 | 安徽富煌科技股份有限公司 | A kind of vehicle door status self-adapting detecting system based on video analysis |
| CN108910638A (en) * | 2018-07-18 | 2018-11-30 | 广西烽火信息技术有限公司 | A method of judging whether elevator carries out maintenance based on elevator track |
| CN109296286A (en) * | 2018-09-18 | 2019-02-01 | 惠州拓邦电气技术有限公司 | Railless electric door progress control method, the apparatus and system of view-based access control model |
| CN111680621A (en) * | 2020-06-05 | 2020-09-18 | 浙江新再灵科技股份有限公司 | Elevator door state detection method based on video image |
| CN111731962A (en) * | 2020-06-29 | 2020-10-02 | 浙江新再灵科技股份有限公司 | Opening and closing fault detection method and detection early warning system for door |
| CN111847164A (en) * | 2020-07-02 | 2020-10-30 | 广州广日电梯工业有限公司 | Method and system for monitoring fault recovery condition of elevator |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010098024A1 (en) * | 2009-02-24 | 2010-09-02 | 三菱電機株式会社 | Human tracking device and human tracking program |
-
2020
- 2020-11-17 CN CN202011287304.2A patent/CN112465860B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010058665A (en) * | 2008-09-03 | 2010-03-18 | Denso Corp | Vehicular door control system |
| CN104612533A (en) * | 2015-01-09 | 2015-05-13 | 江西百胜门控设备有限公司 | Deviation detection and correction method for automatic door straight-line running |
| CN108495775A (en) * | 2016-01-06 | 2018-09-04 | 庞巴迪运输有限公司 | Door gear and the method for operating door gear |
| CN207092724U (en) * | 2017-06-02 | 2018-03-13 | 瑞高科技（深圳）有限责任公司 | A kind of intelligent electronic lock and intelligent safety door |
| CN108038415A (en) * | 2017-11-06 | 2018-05-15 | 湖南华诺星空电子技术有限公司 | A kind of unmanned plane based on machine vision detects automatically and tracking |
| CN107886524A (en) * | 2017-11-20 | 2018-04-06 | 江苏省特种设备安全监督检验研究院 | A kind of elevator door movement locus recognition methods |
| CN108520531A (en) * | 2018-05-23 | 2018-09-11 | 安徽富煌科技股份有限公司 | A kind of vehicle door status self-adapting detecting system based on video analysis |
| CN108910638A (en) * | 2018-07-18 | 2018-11-30 | 广西烽火信息技术有限公司 | A method of judging whether elevator carries out maintenance based on elevator track |
| CN109296286A (en) * | 2018-09-18 | 2019-02-01 | 惠州拓邦电气技术有限公司 | Railless electric door progress control method, the apparatus and system of view-based access control model |
| CN111680621A (en) * | 2020-06-05 | 2020-09-18 | 浙江新再灵科技股份有限公司 | Elevator door state detection method based on video image |
| CN111731962A (en) * | 2020-06-29 | 2020-10-02 | 浙江新再灵科技股份有限公司 | Opening and closing fault detection method and detection early warning system for door |
| CN111847164A (en) * | 2020-07-02 | 2020-10-30 | 广州广日电梯工业有限公司 | Method and system for monitoring fault recovery condition of elevator |
Non-Patent Citations (3)
| Title |
|---|
| A Human-Aware Robotic System for Mobile Robot Navigating in Multi-Floor Building with Elevator;Junxin Zhao等;《2019 WRC Symposium on Advanced Robotics and Automation (WRC SARA)》;第178-183页 * |
| 地铁车门系统故障的诊断与维修技术方案分析;董晓婕;《现代制造技术与装备》(第9期);第141+143页 * |
| 基于DSP的智能电梯监控摄像机视频处理算法研究;顾懿超;《中国优秀硕士学位论文全文数据库 工程科技II辑》(第8期);第C038-237页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112465860A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Automatic laser profile recognition and fast tracking for structured light measurement using deep learning and template matching | |
| US11232326B2 (en) | System and process for detecting, tracking and counting human objects of interest | |
| CN110852219B (en) | Multi-pedestrian cross-camera online tracking system | |
| CN109644255B (en) | Method and apparatus for annotating a video stream comprising a set of frames | |
| US7688999B2 (en) | Target detecting system and method | |
| CN109919977B (en) | Video motion person tracking and identity recognition method based on time characteristics | |
| US9953215B2 (en) | Method and system of temporal segmentation for movement analysis | |
| US7003135B2 (en) | System and method for rapidly tracking multiple faces | |
| CN110379050A (en) | A kind of gate control method, apparatus and system | |
| CN110569785B (en) | Face recognition method integrating tracking technology | |
| JP2007334623A (en) | Face authentication device, face authentication method, and access control device | |
| KR100651034B1 (en) | System for detecting targets and method thereof | |
| CN105760846A (en) | Object detection and location method and system based on depth data | |
| CN110750152A (en) | Human-computer interaction method and system based on lip action | |
| CN109754478A (en) | A kind of face intelligent Checking on Work Attendance method of low user's fitness | |
| US20220366570A1 (en) | Object tracking device and object tracking method | |
| KR101023951B1 (en) | motion recognition system and method | |
| CN116030420B (en) | Multi-source data fusion elevator safety operation monitoring method | |
| JP2014059655A (en) | Road situation-monitoring device, and road situation-monitoring method | |
| CN112465860B (en) | Method and equipment for checking running state of door | |
| CN115346155A (en) | Ship image track extraction method for visual feature discontinuous interference | |
| JP4728795B2 (en) | Person object determination apparatus and person object determination program | |
| Xian et al. | Mitfas: Mutual information based temporal feature alignment and sampling for aerial video action recognition | |
| CN112580633B (en) | Public transport passenger flow statistics device and method based on deep learning | |
| CN114037937A (en) | Real-time refrigerator food material identification method based on multi-target tracking |
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 |