JP2008046734A - Elevator passenger detection device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an elevator passenger detection device for detecting the presence/absence of a passenger in a cage. <P>SOLUTION: This elevator passenger detection device is provided with image division means 61 to 64 for dividing images D and E obtained by difference image calculation means 61 to 64 into a plurality of images and luminance difference block image calculating means 61 to 64 for calculating a luminance difference to the image of each of those divided blocks, and configured to determine the presence/absence of a passenger by comparing the luminance differences of the respective blocks calculated by the luminance difference block image calculation means 61 to 64. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an elevator passenger detection device, and more particularly to an elevator passenger detection device suitable for detecting passengers in a car using an image.

  As an apparatus for detecting passengers in a car, an apparatus for detecting an abnormality of passengers in a car is known (see Patent Document 1).

An apparatus for detecting passengers by comparing images is known (see Patent Document 2).
JP-A-61-1119580 Japanese Patent Laid-Open No. 05-039175

  As a means for detecting passengers in an elevator car, a method of determining a passenger by installing a camera in the car and analyzing data received from the car is known from many known examples. However, there is a problem that the image by the camera is easily influenced by noise due to the influence of peripheral devices such as an elevator control panel and erroneously detects passengers in the elevator car.

  An object of the present invention is to provide an elevator passenger detection device that detects the presence or absence of passengers in a car without error even when noise is generated in an image of a camera in the elevator car.

  The present invention relates to a camera for capturing an image in an elevator car, a difference image calculation means for recording an image in an elevator car without passengers and calculating a difference between a current image in the elevator car and an image without passengers. And an elevator passenger detection device for determining the presence of passengers in the car from the difference image, an image dividing means for dividing the image obtained by the difference image calculating means into a plurality of images, and for each of the divided blocks The luminance difference block image calculation means for calculating the luminance difference with respect to the image is compared with the luminance difference of each block calculated by the luminance difference block image calculation means to determine the presence or absence of a passenger.

  According to the present invention, the image processed by the difference image calculation means is divided into a plurality of parts, and the brightness of each of the divided images is compared. Even in the situation of receiving a car, the presence or absence of passengers in the car can be detected without error.

  FIG. 1 is a hardware configuration diagram which is one embodiment of the present invention.

  In FIG. 1, 1 is a floor surface of a building, 2 is an elevator main rope, 3 is a passenger, 4 is an elevator car, 5 is a camera for photographing an elevator car, and 6 is a passenger detection device. Also, 61 is an analog / digital conversion circuit for converting a video signal from the camera into a digital signal, 62 is a CPU that performs image processing, 63 is a RAM that is used to record image information, and 64 is an execution program. The ROM 63 is an output device that outputs the result of the presence or absence of passengers.

  FIG. 2 is a flowchart for explaining the details of the detection process by the passenger detection device 6, which is executed by the CPU 62 in accordance with a program stored in the ROM 63. The CPU 62 enters this process upon receiving a command.

  First, in the flow 101, the image A, which is an internal image of the elevator car 4 when there is no passenger, is captured, and the internal image of the elevator car 4 is transmitted to the passenger detection device 6 via the camera 5 to detect the passenger. In the apparatus 6, the received image is converted into image data by the A / D conversion 61 and stored as an image A in the RAM 64. Here, FIG. 3 is an example of a basic image A that is a basic image obtained by photographing the inside of the elevator car 4 stored in the flow 101.

  Next, the image B which is an internal image of the elevator car 4 is captured at the time of detecting the presence or absence of a passenger in the flow 102, and the internal image of the elevator car 4 is transmitted to the passenger detection device 6 via the camera 5 to detect the passenger. In the device 6, the received image is converted into image data by the A / D conversion 61 and stored as an image B in the RAM 64. Here, FIG. 4 is an example of an image B obtained by photographing the inside of the elevator car 4 when the passenger 3 is present in the flow 102.

  FIG. 5 is an example of an image C obtained by photographing the interior of the elevator car 4 when the passenger 3 is absent and noise occurs in the flow 102.

  Next, in the flow 103, the image 1 captured in the flow 101 and the image 2 captured in the flow 102 are taken out, and a difference image D between the basic image A and the image B extracted by comparison with the data is obtained.

  Further, FIG. 7 obtains a difference image E between the image A and the image C extracted by comparing the data when there is no passenger 3 and noise occurs in the flow 103.

  Next, in the flow 104, the image D, which is the difference image extracted in the flow 103, is divided to obtain a divided image F shown in FIG.

  FIG. 9 is a divided image G obtained by dividing the image E, which is a difference image when there is no passenger 3 and noise occurs in the flow 104.

Also, in flow 105, the light / dark ratio calculation for each block of the divided image F and the divided image G created in flow 104 is performed, and the result is compared in each divided image. Here, if the light / dark ratio of each divided image increases and the ratio varies, the flow proceeds to flow 106 and it is determined that there is a passenger. If the light and darkness of each divided data is equal to or less than a certain ratio, the flow proceeds to flow 107. Judging by the impact of.
The divided image F shown in FIG. 8 is a divided image obtained by dividing the difference image when the passenger 3 is present in the flow 105, but the light / dark ratio of the image of each divided data is greatly different, and the ratio varies. Therefore, the process proceeds to the flow 106 and it is determined that there are passengers.

  The divided image G shown in FIG. 9 is a divided image obtained by dividing the difference image when there is no passenger 3 and noise occurs in the flow 105, but the brightness ratio of each divided data is a substantially constant rate. Therefore, it proceeds to the flow 107 and determines that there is no passenger.

  Next, both the flow 106 and the flow 107 proceed to the flow 108, and the presence / absence of the passenger 3 is transmitted via the output device 65. After a predetermined time, the flow proceeds to the flow 102, and the passenger presence / absence detection operation is executed again.

It is a hardware block diagram of one Embodiment in the elevator passenger detection apparatus of this invention. It is a flowchart explaining operation | movement of one Embodiment in the elevator passenger detection apparatus of this invention. It is a figure which shows the basic image of the difference comparison in embodiment of this invention. It is a figure which shows the image of the passenger who image | photographed in embodiment of this invention. It is a figure which shows the image of the noise in embodiment of this invention. It is a figure which shows the image after implementation of the difference image of FIG. 3 and FIG. 4 in embodiment of this invention. It is a figure which shows the image after implementation of the difference image of FIG. 3 and FIG. 5 in embodiment of this invention. It is a figure which shows the image which divided | segmented FIG. 6 in embodiment of this invention. It is a figure which shows the image which divided | segmented FIG. 7 in embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Floor surface 2 Rope 3 Passenger 4 Elevator car 5 Security camera 6 Passenger detection apparatus A Basic image B, C image D, E Difference image F, G Division image

Claims (1)

A camera that captures images in the elevator car, a difference image calculation means that records an image in the elevator car without passengers, and calculates a difference between the current image in the elevator car and an image without passengers, and the difference In the elevator passenger detection device that determines the presence of passengers in the car from the image,
Image dividing means for dividing the image obtained by the difference image calculating means into a plurality of images, luminance difference block image calculating means for calculating a luminance difference with respect to the image of each divided block, and the luminance difference block image calculating means An elevator passenger detection apparatus characterized in that the presence or absence of a passenger is determined by comparing the luminance difference of each block calculated in (1).

Images