WO2021190375A1 - 监测自动扶梯的方法和监测自动扶梯的设备 - Google Patents

监测自动扶梯的方法和监测自动扶梯的设备 Download PDF

Info

Publication number
WO2021190375A1
WO2021190375A1 PCT/CN2021/081302 CN2021081302W WO2021190375A1 WO 2021190375 A1 WO2021190375 A1 WO 2021190375A1 CN 2021081302 W CN2021081302 W CN 2021081302W WO 2021190375 A1 WO2021190375 A1 WO 2021190375A1
Authority
WO
WIPO (PCT)
Prior art keywords
pattern
escalator
outline
stored
recognized
Prior art date
Application number
PCT/CN2021/081302
Other languages
English (en)
French (fr)
Inventor
范进泉
陈忠
Original Assignee
通力股份公司
通力电梯有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 通力股份公司, 通力电梯有限公司 filed Critical 通力股份公司
Priority to EP21774349.1A priority Critical patent/EP4131059A4/en
Priority to US17/913,204 priority patent/US20230131405A1/en
Publication of WO2021190375A1 publication Critical patent/WO2021190375A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/26Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/26Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/56Extraction of image or video features relating to colour
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/52Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80Camera processing pipelines; Components thereof
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums

Definitions

  • the present invention relates to a method for monitoring escalators and equipment for monitoring escalators.
  • the present invention provides a method for remotely monitoring an escalator, the method comprising: capturing an image of the escalator through a camera, wherein each step of the escalator is provided with a pattern of a predetermined color, and the pattern The color of the escalator is different from the color of the steps of the escalator; grayscale the captured image; cover the background of the grayscale image to separate the pattern; identify the outline of the pattern; combine the identified pattern outline with the pre-stored pattern outline The comparison is made, and based on the comparison result, it is determined whether the pattern on the steps of the escalator is blocked, and the pre-stored pattern contour is the unblocked pattern contour.
  • the comparison result shows that the recognized pattern outline is different from the pre-stored pattern outline
  • the recognized pattern contour is different from the pre-stored pattern contour, including that the number of recognized unblocked patterns is less than the pre-stored number of unblocked patterns.
  • the comparison result shows that the recognized pattern outline is the same as the pre-stored pattern outline, it is determined that the pattern on the steps of the escalator is not blocked.
  • the identified pattern outline is the same as the pre-stored pattern outline, including the identified number of unshielded patterns equal to the pre-stored number of unshielded patterns.
  • the pattern is arranged on the tread and/or kick surface of each step of the escalator.
  • the pattern is an oval pattern arranged at the center of the tread and/or kick surface of each step.
  • the pattern is a boundary line provided at the perimeter of the tread and/or kick surface of each step.
  • the present invention also provides a device for remotely monitoring an escalator.
  • the device includes a camera that captures an image of the escalator, wherein each step of the escalator is provided with a pattern of a predetermined color, and the color of the pattern The color of the steps of the escalator is different; the gray-scale module, which grays the captured image; the separation module, which covers the background of the gray-scale image, separates the pattern; the recognition module, recognizes the outline of the pattern; the processing module, The recognized pattern outline is compared with the pre-stored pattern outline, and based on the comparison result, it is determined whether the pattern on the steps of the escalator is blocked, and the pre-stored pattern outline is the unobstructed pattern outline.
  • the comparison result shows that the recognized pattern outline is different from the pre-stored pattern outline
  • the recognized pattern contour is different from the pre-stored pattern contour, including that the number of recognized unblocked patterns is less than the pre-stored number of unblocked patterns.
  • the comparison result shows that the recognized pattern outline is the same as the pre-stored pattern outline, it is determined that the pattern on the steps of the escalator is not blocked.
  • the identified pattern outline is the same as the pre-stored pattern outline, including the identified number of unshielded patterns equal to the pre-stored number of unshielded patterns.
  • the pattern is arranged on the tread and/or kick surface of each step of the escalator.
  • the pattern is an oval pattern arranged at the center of the tread and/or kick surface of each step.
  • the pattern is a boundary line provided at the perimeter of the tread and/or kick surface of each step.
  • Fig. 1 shows a flowchart of a method for monitoring an escalator according to the present invention.
  • Fig. 2(a) shows a pattern of a predetermined color provided on an escalator step.
  • Fig. 2(b) shows another predetermined color pattern provided on the escalator steps.
  • Fig. 2(c) shows another pattern of predetermined colors arranged on the steps of the escalator.
  • Fig. 3 shows a schematic diagram of pre-stored oval pattern outlines.
  • Fig. 4 shows a schematic diagram of an image of an escalator captured by a camera.
  • Fig. 5 shows the outline of an elliptical pattern recognized by the method of the present invention.
  • Fig. 6 shows a schematic diagram of a pre-stored border line pattern outline.
  • Fig. 7 shows a schematic diagram of an image of an escalator captured by a camera.
  • FIG. 8 shows the outline of the border line pattern recognized by the method of the present invention.
  • the inventive concept of the present invention is to determine whether there are passengers or other objects on the steps of the escalator by remotely monitoring the escalator, so as to remotely open or close the escalator.
  • FIGS. 1 to 8 the preferred embodiments according to the present invention will be described in detail.
  • step 101 an image of an escalator is captured by a camera.
  • the camera is set so that its field of view covers the entire escalator to capture an image of the entire escalator.
  • One camera can be set to capture the image of the entire escalator, or multiple cameras can be set to capture the image of the escalator. In the case of multiple cameras, the images captured by the multiple cameras are combined to form the image of the entire escalator.
  • a pattern 1 of a predetermined color is provided on each step 2 of the escalator, preferably on the tread 21 and/or the kick surface 22 of each step.
  • the oval pattern or the square pattern is set at the center of the tread and/or the skirting surface, and the pattern in the form of the border line is arranged at the periphery of the tread and/or skirting surface. .
  • the colors of these patterns are different from the colors of the steps of the escalator, so that these patterns can be distinguished in subsequent processing.
  • step 102 the captured image is grayed out to remove color interference for subsequent processing, for example, as shown in FIGS. 4 and 7.
  • step 103 the background of the grayscale image is covered to separate the patterns.
  • step 104 the outline of the pattern is recognized, for example, as shown in FIGS. 5 and 8.
  • the above processing for the image may use an image processing method based on HSV, which is well known to those skilled in the art, and therefore will not be described in detail.
  • step 105 the recognized pattern outline is compared with the pre-stored pattern outline. Based on the comparison result, it is determined whether the pattern on the steps of the escalator is blocked.
  • the pre-stored pattern outlines are shown in Figures 3 and 6.
  • the comparison result shows that the recognized pattern outline is different from the pre-stored pattern outline, then it is determined that the pattern on the steps of the escalator is blocked, so as to determine that there are passengers or objects on the escalator. At this time, the escalator will not be opened or stopped remotely. . For example, if the number of recognized patterns that are not blocked is less than the pre-stored number of patterns that are not blocked, then it indicates that some patterns are blocked. If the comparison result shows that the recognized pattern outline is the same as the pre-stored pattern outline, then it is determined that the pattern on the steps of the escalator is not blocked, so as to confirm that there are no passengers or objects on the escalator. At this time, the escalator can be started or stopped remotely. . For example, the number of recognized patterns that are not blocked is equal to the number of unblocked patterns stored in advance, which indicates that no patterns are blocked.
  • the present invention also provides a device for remotely monitoring escalators.
  • the device includes a camera for capturing an image of the escalator; a grayscale module to grayscale the captured image; a separation module to cover the background of the grayscale image , To separate the pattern; the recognition module to identify the outline of the pattern; the processing module to compare the identified pattern outline with the pre-stored pattern outline, and based on the comparison result, determine whether the pattern on the escalator step is blocked.

Abstract

一种远程监测自动扶梯的方法和设备。所述方法包括:通过相机捕获自动扶梯的图像(101),其中,所述自动扶梯的每个梯级上设置有预定颜色的图案,所述图案的颜色与自动扶梯的梯级的颜色不同;将捕获的图像灰度化(102);遮盖灰度化图像的背景,将图案分离出来(103);识别出图案的轮廓(104);将识别出的图案轮廓与预先存储的图案轮廓进行比较(105),基于比较结果,确定自动扶梯的梯级上的图案是否被遮挡,预先存储的图案轮廓是未被遮挡的图案轮廓。

Description

监测自动扶梯的方法和监测自动扶梯的设备
相关申请的交叉引用
本申请要求于2020年3月24日向中国国家知识产权局提交的中国申请CN 202010211781.4的优先权。
技术领域
本发明涉及一种用于监测自动扶梯的方法和监测自动扶梯的设备。
背景技术
目前,自动扶梯的开启和关闭一般依靠工作人员到现场检查并手动打开或关闭自动扶梯的按钮。这导致在自动扶梯较多的场所,工作人员的劳动量较大。因此,需要能够远程监测自动扶梯,从而确定自动扶梯上是否有乘客或物体,以远程开启或关闭自动扶梯。
发明内容
因此,本发明的提供了一种远程监测自动扶梯的方法,所述方法包括:通过相机捕获自动扶梯的图像,其中,所述自动扶梯的每个梯级上设置有预定颜色的图案,所述图案的颜色与自动扶梯的梯级的颜色不同;将捕获的图像灰度化;遮盖灰度化图像的背景,将图案分离出来;识别出图案的轮廓;将识别出的图案轮廓与预先存储的图案轮廓进行比较,基于比较结果,确定自动扶梯的梯级上的图案是否被遮挡,预先存储的图案轮廓是未被遮挡的图案轮廓。
优选地,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓不同时,确定自动扶梯的梯级上的图案被遮挡。
优选地,识别出的图案轮廓与预先存储的图案轮廓不同包括识别出的未被遮挡的图案数量小于预先存储的未被遮挡的图案数量。
优选地,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓相同时,确定自动扶梯的梯级上的图案未被遮挡。
优选地,识别出的图案轮廓与预先存储的图案轮廓相同包括识别出的未被遮挡的图案数量等于预先存储的未被遮挡的图案数量。
优选地,所述图案设置在自动扶梯的每个梯级的踏面和/或踢面上。
优选地,所述图案是设置在每个梯级的踏面和/或踢面的中心处的椭圆形图案。
优选地,所述图案是设置在每个梯级的踏面和/或踢面的周界处的边界线。
本发明还提供了一种远程监测自动扶梯的设备,所述设备包括:相机,捕获自动扶梯的图像,其中,所述自动扶梯的每个梯级上设置有预定颜色的图案,所述图案的颜色与自动扶梯的梯级的颜色不同;灰度化模块,将捕获的图像灰度化;分离模块,遮盖灰度化图像的背景,将图案分离出来;识别模块,识别出图案的轮廓;处理模块,将识别出的图案轮廓与预先存储的图案轮廓进行比较,基于比较结果,确定自动扶梯的梯级上的图案是否被遮挡,预先存储的图案轮廓是未被遮挡的图案轮廓。
优选地,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓不同时,确定自动扶梯的梯级上的图案被遮挡。
优选地,识别出的图案轮廓与预先存储的图案轮廓不同包括识别出的未被遮挡的图案数量小于预先存储的未被遮挡的图案数量。
优选地,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓相同时,确定自动扶梯的梯级上的图案未被遮挡。
优选地,识别出的图案轮廓与预先存储的图案轮廓相同包括识别出的未被遮挡的图案数量等于预先存储的未被遮挡的图案数量。
优选地,所述图案设置在自动扶梯的每个梯级的踏面和/或踢面上。
优选地,所述图案是设置在每个梯级的踏面和/或踢面的中心处的椭圆形图案。
优选地,所述图案是设置在每个梯级的踏面和/或踢面的周界处的边界线。
附图说明
从下面结合附图详细描述的本发明的优选实施方式中,本发明的优点和目的可以得到更好地理解,附图中:
图1示出根据本发明的监测自动扶梯的方法的流程图。
图2(a)示出设置在自动扶梯梯级上的预定颜色的图案。
图2(b)示出设置在自动扶梯梯级上的另一预定颜色的图案。
图2(c)示出设置在自动扶梯梯级上的又一预定颜色的图案。
图3示出预先存储的椭圆形图案轮廓的示意图。
图4示出利用相机捕获的自动扶梯的图像的示意图。
图5示出利用本发明的方法识别出的椭圆形图案轮廓。
图6示出预先存储的边界线图案轮廓的示意图。
图7示出利用相机捕获的自动扶梯的图像的示意图。
图8示出利用本发明的方法识别出的边界线图案轮廓;
具体实施方式
将参照附图详细描述根据本发明的各个实施例。这里,需要注意的是,在附图中,将相同的附图标记赋予基本上具有相同或类似结构和功能的组成部分,并且将省略关于它们的重复描述。如果没有特别说明,本文中的术语“上”、“下”、“顶部”、“底部”、“内侧”、“外侧”均是相对于本发明的附图描述的。术语“依次包括A、B、C等”仅指示所包括的部件A、B、C等的排列顺序,并不排除在A和B之间和/或B和C之间包括其它部件的可能性。
本发明的发明构思在于,通过远程监测自动扶梯,来确定自动扶梯的梯级上是否有乘客或者其它物体,以远程开启或关闭自动扶梯。
下面,参照图1至图8,详细描述根据本发明的优选实施方式。
如图1所示,示出根据本发明的远程监测自动扶梯的方法的流程图。在步骤101中,通过相机捕获自动扶梯的图像。相机设置成其视场覆盖整个自动扶梯,以捕获整个自动扶梯的图像。可以设置一个相机来捕获整个自动扶梯的图像,也可以设置多个相机来捕获自动扶梯的图像,在多个相机的情况下,多个相机各自捕获的图像组合起来来形成整个自动扶梯的图像。
预定颜色的图案1设置在自动扶梯的每个梯级2上,优选地设置在 每个梯级的踏面21和/或踢面22上。如图2(a)至图2(c)所示,椭圆形图案或方形图案设置在踏面和/或踢面的中心处,边界线形式的图案设置在踏面和/或踢面的周界处。本领域技术人员应明白的是,还可以使用其它任意形式的图案,只要能够实现本发明的目的即可。这些图案的颜色与自动扶梯的梯级的颜色不同,以在后续处理中能够分辨出这些图案。
接着,在步骤102,将捕获的图像灰度化,从而去除颜色的干扰,以便后续的处理,例如图4和7所示。在步骤103,遮盖灰度化图像的背景,以便将图案分离出来。在步骤104,识别出图案的轮廓,例如图5和8所示。上面针对图像的处理可以利用基于HSV的图像处理方法,该图像处理方法是本领域技术人员所熟知的,因此不再赘述。
最后,在步骤105,将识别出的图案轮廓与预先存储的图案轮廓进行比较。基于比较结果,确定自动扶梯的梯级上的图案是否被遮挡。预先存储的图案轮廓如图3和6所示。
如果比较结果表明识别出的图案轮廓与预先存储的图案轮廓不同,那么确定自动扶梯的梯级上的图案被遮挡,从而确定自动扶梯上有乘客或者物体,此时便不会远程开启或停止自动扶梯。例如,识别出的未被遮挡的图案数量小于预先存储的未被遮挡的图案数量,那么表明有些图案被遮挡。如果比较结果表明识别出的图案轮廓与预先存储的图案轮廓相同,那么确定自动扶梯的梯级上的图案未被遮挡,从而确定自动扶梯上没有乘客或者物体,此时便可以远程开启或停止自动扶梯。例如,识别出的未被遮挡的图案数量等于预先存储的未被遮挡的图案数量,这表明没有图案被遮挡。
本发明还提供了一种远程监测自动扶梯的设备,该设备包括相机,用于捕获自动扶梯的图像;灰度化模块,将捕获的图像灰度化;分离模块,遮盖灰度化图像的背景,将图案分离出来;识别模块,识别出图案的轮廓;处理模块,将识别出的图案轮廓与预先存储的图案轮廓进行比较,基于比较结果,确定自动扶梯的梯级上的图案是否被遮挡。
通过本发明的远程监测自动扶梯的方法和设备,可以方便地且可靠地确定自动扶梯上是否有乘客或物体,从而远程地开启或关闭自动扶梯,例如,在早上开启自动扶梯,在晚上关闭自动扶梯,而不用工作人员花费过多的劳动量。
尽管上面参照本发明的优选实施方式具体描述了本发明,但是要理解的是,本发明并不局限于上面描述的实施方式,而是在不背离本发明的精髓的前提下,本领域技术人员可以做出各种修改和变化,而这些修改和变化都应落入所附权利要求及其等价物限定的范围内。

Claims (16)

  1. 一种远程监测自动扶梯的方法,其特征在于,所述方法包括:
    通过相机捕获自动扶梯的图像,其中,所述自动扶梯的每个梯级上设置有预定颜色的图案,所述图案的颜色与自动扶梯的梯级的颜色不同;
    将捕获的图像灰度化;
    遮盖灰度化图像的背景,将图案分离出来;
    识别出图案的轮廓;
    将识别出的图案轮廓与预先存储的图案轮廓进行比较,基于比较结果,确定自动扶梯的梯级上的图案是否被遮挡,预先存储的图案轮廓是未被遮挡的图案轮廓。
  2. 如权利要求1所述的方法,其特征在于,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓不同时,确定自动扶梯的梯级上的图案被遮挡。
  3. 如权利要求2所述的方法,其特征在于,识别出的图案轮廓与预先存储的图案轮廓不同包括识别出的未被遮挡的图案数量小于预先存储的未被遮挡的图案数量。
  4. 如权利要求1所述的方法,其特征在于,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓相同时,确定自动扶梯的梯级上的图案未被遮挡。
  5. 如权利要求4所述的方法,其特征在于,识别出的图案轮廓与预先存储的图案轮廓相同包括识别出的未被遮挡的图案数量等于预先存储的未被遮挡的图案数量。
  6. 如权利要求1所述的方法,其特征在于,所述图案设置在自动扶梯的每个梯级的踏面和/或踢面上。
  7. 如权利要求6所述的方法,其特征在于,所述图案是设置在每个梯级的踏面和/或踢面的中心处的椭圆形图案。
  8. 如权利要求6所述的方法,其特征在于,所述图案是设置在每个梯级的踏面和/或踢面的周界处的边界线。
  9. 一种远程监测自动扶梯的设备,其特征在于,所述设备包括:
    相机,捕获自动扶梯的图像,其中,所述自动扶梯的每个梯级上设置有预定颜色的图案,所述图案的颜色与自动扶梯的梯级的颜色不同;
    灰度化模块,将捕获的图像灰度化;
    分离模块,遮盖灰度化图像的背景,将图案分离出来;
    识别模块,识别出图案的轮廓;
    处理模块,将识别出的图案轮廓与预先存储的图案轮廓进行比较,基于比较结果,确定自动扶梯的梯级上的图案是否被遮挡,预先存储的图案轮廓是未被遮挡的图案轮廓。
  10. 如权利要求9所述的设备,其特征在于,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓不同时,确定自动扶梯的梯级上的图案被遮挡。
  11. 如权利要求10所述的设备,其特征在于,识别出的图案轮廓与预先存储的图案轮廓不同包括识别出的未被遮挡的图案数量小于预先存储的未被遮挡的图案数量。
  12. 如权利要求9所述的设备,其特征在于,当比较结果表明识别出的图案轮廓与预先存储的图案轮廓相同时,确定自动扶梯的梯级上的图案未被遮挡。
  13. 如权利要求12所述的设备,其特征在于,识别出的图案轮廓与预先存储的图案轮廓相同包括识别出的未被遮挡的图案数量等于预先存储的未被遮挡的图案数量。
  14. 如权利要求9所述的设备,其特征在于,所述图案设置在自动扶梯的每个梯级的踏面和/或踢面上。
  15. 如权利要求14所述的设备,其特征在于,所述图案是设置在每个梯级的踏面和/或踢面的中心处的椭圆形图案。
  16. 如权利要求14所述的设备,其特征在于,所述图案是设置在每个梯级的踏面和/或踢面的周界处的边界线。
PCT/CN2021/081302 2020-03-24 2021-03-17 监测自动扶梯的方法和监测自动扶梯的设备 WO2021190375A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21774349.1A EP4131059A4 (en) 2020-03-24 2021-03-17 METHOD AND DEVICE FOR MONITORING AN ESCALER
US17/913,204 US20230131405A1 (en) 2020-03-24 2021-03-17 Method and device for monitoring escalator

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010211781.4 2020-03-24
CN202010211781.4A CN111325188A (zh) 2020-03-24 2020-03-24 监测自动扶梯的方法和监测自动扶梯的设备

Publications (1)

Publication Number Publication Date
WO2021190375A1 true WO2021190375A1 (zh) 2021-09-30

Family

ID=71173393

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/081302 WO2021190375A1 (zh) 2020-03-24 2021-03-17 监测自动扶梯的方法和监测自动扶梯的设备

Country Status (4)

Country Link
US (1) US20230131405A1 (zh)
EP (1) EP4131059A4 (zh)
CN (1) CN111325188A (zh)
WO (1) WO2021190375A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111325188A (zh) * 2020-03-24 2020-06-23 通力电梯有限公司 监测自动扶梯的方法和监测自动扶梯的设备
CN114283305A (zh) * 2020-12-25 2022-04-05 上海商汤智能科技有限公司 图像检测方法及装置、电子设备和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010058903A (ja) * 2008-09-03 2010-03-18 Hitachi Ltd 画像認識装置
CN107665326A (zh) * 2016-07-29 2018-02-06 奥的斯电梯公司 乘客运输装置的监测系统、乘客运输装置及其监测方法
CN110188644A (zh) * 2019-05-22 2019-08-30 广东寰球智能科技有限公司 一种基于视觉分析的扶梯乘客危险行为监控系统及方法
CN111325188A (zh) * 2020-03-24 2020-06-23 通力电梯有限公司 监测自动扶梯的方法和监测自动扶梯的设备

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012180187A (ja) * 2011-03-01 2012-09-20 Toshiba Elevator Co Ltd 乗客コンベア
US9836028B2 (en) * 2013-02-08 2017-12-05 Chuck Fung Method, system and processor for instantly recognizing and positioning an object
US10061058B2 (en) * 2014-05-21 2018-08-28 Universal City Studios Llc Tracking system and method for use in surveying amusement park equipment
EP3211611A1 (de) * 2016-02-24 2017-08-30 Wincor Nixdorf International GmbH Verfahren zum rechnergestützten leer-erkennen eines transportbehälters und vorrichtung zum rechnergestützten leer-erkennen eines transportbehälters
CN107662872B (zh) * 2016-07-29 2021-03-12 奥的斯电梯公司 乘客运输机的监测系统及其监测方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010058903A (ja) * 2008-09-03 2010-03-18 Hitachi Ltd 画像認識装置
CN107665326A (zh) * 2016-07-29 2018-02-06 奥的斯电梯公司 乘客运输装置的监测系统、乘客运输装置及其监测方法
CN110188644A (zh) * 2019-05-22 2019-08-30 广东寰球智能科技有限公司 一种基于视觉分析的扶梯乘客危险行为监控系统及方法
CN111325188A (zh) * 2020-03-24 2020-06-23 通力电梯有限公司 监测自动扶梯的方法和监测自动扶梯的设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4131059A4

Also Published As

Publication number Publication date
EP4131059A4 (en) 2024-03-13
EP4131059A1 (en) 2023-02-08
US20230131405A1 (en) 2023-04-27
CN111325188A (zh) 2020-06-23

Similar Documents

Publication Publication Date Title
WO2021190375A1 (zh) 监测自动扶梯的方法和监测自动扶梯的设备
WO2019052318A1 (zh) 一种电梯轿厢监控方法、装置及系统
JP4548218B2 (ja) 顔認証装置
JP4505362B2 (ja) 赤目検出装置および方法並びにプログラム
CN108960067B (zh) 基于深度学习的实时的列车驾驶员动作识别系统和方法
US7734062B2 (en) Action recognition apparatus and apparatus for recognizing attitude of object
EP1710747A1 (en) Method for extracting person candidate area in image, person candidate area extraction system, person candidate area extraction program, method for judging top and bottom of person image, system for judging top and bottom, and program for judging top and bottom
US20080117020A1 (en) Method of Detecting Presence and Motion for Door Control Devices and Door Control Devices Implementing Such a Demand
JP5730095B2 (ja) 顔画像認証装置
KR100473600B1 (ko) 얼굴 인식 시스템에서의 사진 판별 장치 및 방법
US7460705B2 (en) Head-top detecting method, head-top detecting system and a head-top detecting program for a human face
JP2017214191A (ja) 輸送機器制御システム、及び、輸送機器制御方法
CN104392210A (zh) 一种手势识别方法
CN110008968A (zh) 一种基于图像视觉的机器人结算自动触发方法
JP2018104142A (ja) エレベータドアロック確認システム、エレベータドアロック確認方法およびエレベータドアロック確認用カメラシステム
JP2009237669A (ja) 顔認識装置
JP5766096B2 (ja) 顔画像認証装置
JP4390487B2 (ja) 頭部領域抽出装置
CN110606422B (zh) 一种施工电梯人数控制的方法
TW201907329A (zh) 具備臉部辨識之門禁系統
Syrlybayev et al. Smart door for COVID restricted areas
JPH07311833A (ja) 人物の顔の検出装置
JP2008234619A (ja) 顔認証装置および顔認証方法
KR20180015467A (ko) 시각장애인을 위한 횡단보도 신호등 영상 인식 방법 및 장치
JP4074464B2 (ja) 周期性を有する動きの検出方法および装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21774349

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021774349

Country of ref document: EP

Effective date: 20221024