Method and system for monitoring a spatial area in a personnel interlock

Patent metadata

Field	Value
Publication number	US-12026902-B2
Application number	US-202017426098-A
Country	US
Kind code	B2
Filing date	Jan 28, 2020
Priority date	Jan 28, 2019
Publication date	Jul 2, 2024
Grant date	Jul 2, 2024

Abstract

A method and a system for monitoring a spatial area in a personnel interlock are provided. Image data are acquired which represent a plurality of depth images of the spatial area which have been acquired simultaneously and from different positions in the area of the personnel interlock, in each case by a respective 3D image sensor arranged at the corresponding position. For each of the depth images, an associated characteristic depth image value is calculated. A total image value is obtained by combining the characteristic depth image values of the various depth images in accordance with a predetermined monotonic combination rule. An estimation result for the probability that more than one person is present in the spatial area is then determined.

First claim

What is claimed is:

1. A method of monitoring a spatial area in a personnel interlock and for monitoring of a separation of persons with respect to the spatial area, the method comprising:
receiving image data which represent a plurality of depth images of the spatial area which have been acquired simultaneously and from different positions in an area of the personnel interlock, in each case by a respective 3D image sensor arranged at the different positions, wherein each of the depth images indicates, for each of its pixels, a spatial distance of an object or portion thereof imaged thereon from the associated 3D image sensor on a basis of a pixel value assigned thereto;
calculating, for each of the depth images, a characteristic depth image value associated with the respective depth image, on a basis of all of the individual pixel values or on a basis of a subset of the individual pixel values of the respective depth image;
calculating a total image value by combining the characteristic depth image values of the various depth images in accordance with a predetermined monotonic combination rule;
determining an estimation result for a probability that more than one person is present in the spatial area, in dependence upon a result of a comparison of the total image value with at least one predetermined reference total image value, wherein the estimation result is a percentage within a range of probabilities between 0% and 100% to define a quantitative measure of the probability that more than one person is present in the spatial area; and
comparing the estimation result to a predetermined threshold value to determine whether there is only a single person in the spatial area or there are multiple persons in the spatial area,
wherein:
the step of calculating the characteristic depth image value is performed using averaging of the individual pixel values to calculate an average value that is set as the characteristic depth image value associated with the respective depth image;
the step of calculating the total image value is performed by summation or multiplication of the characteristic depth image values such that the total image value is always greater than or equal to each of the characteristic depth image values summed or multiplied using the monotonic combination rule; and
during the step of determining the estimation result, the comparison of the total image value with the at least one predetermined reference total image value is performed by a mathematical calculation that determines both (a) whether these compared values differ from one another, and (b) a measure of how much the compared values differ from one another when unequal.

2. The method in accordance with claim 1 , further comprising:
triggering of a functionality of the personnel interlock in dependence upon the estimation result.

3. The method in accordance with claim 1 , wherein the personnel interlock can be operated as a bidirectional passage interlock and the steps of the method is applied for each of two directions of passage.

4. The method in accordance with claim 1 , wherein the spatial area of the personnel interlock can be closed off at least on one side by a movable restriction of passage, and the method further comprises:
determining the distance of an object located in the spatial area on a basis of at least one of the depth images, and
triggering an opening or a closing of the restriction of passage as a function of the distance that has been determined.

5. The method in accordance with claim 1 , further comprising:
carrying out an image transformation with respect to at least one of the depth images prior to a calculation of its respective characteristic depth image value, wherein the respective depth image is combined with a reference depth image within a framework of the image transformation in accordance with a predetermined transformation rule, by means of which image areas in the respective depth image with respect to which image areas the respective depth image and the reference image match with respect to their respective mutually corresponding pixel values are contrasted, by a predetermined modification of their associated image values, from other areas of the image in which there is no such match.

6. The method in accordance with claim 1 , wherein when the characteristic depth image values are being calculated, the depth image value of at least one of the depth images is calculated on a basis of a subset of the individual pixel values of that depth image, wherein the pixels of the subsets are selected on a basis of their respective pixel value in such a way that all of these pixels each have a pixel value which is beyond a predetermined pixel value threshold or which is within a predetermined pixel value range.

7. The method in accordance with claim 6 , wherein the at least one subset is additionally determined as a function of the respective spatial position of the pixels in the respective depth image.

8. A monitoring system for monitoring a spatial area in a personnel interlock and for monitoring of separation of persons, wherein the system is programmed, with respect to the personnel interlock, to perform a method that comprises:
receiving image data which represent a plurality of depth images of the spatial area which have been acquired simultaneously and from different positions in an area of the personnel interlock, in each case by a respective 3D image sensor arranged at the different positions, wherein each of the depth images indicates, for each of its pixels, a spatial distance of an object or portion thereof imaged thereon from the associated 3D image sensor on a basis of a pixel value assigned thereto;
calculating, for each of the depth images, a characteristic depth image value associated with the respective depth image, on a basis of all of the individual pixel values or on a basis of a subset of the individual pixel values of the respective depth image;
calculating a total image value by combining the characteristic depth image values of the various depth images in accordance with a predetermined monotonic combination rule;
determining an estimation result for a probability that more than one person is present in the spatial area, in dependence upon a result of a comparison of the total image value with at least one predetermined reference total image value, wherein the estimation result is a percentage within a range of probabilities between 0% and 100% to define a quantitative measure of the probability that more than one person is present in the spatial area; and
comparing the estimation result to a predetermined threshold value to determine whether there is only a single person in the spatial area or there are multiple persons in the spatial area,
wherein, in the method that the monitoring system is programmed to perform:
the step of calculating the characteristic depth image value is performed using averaging of the individual pixel values to calculate an average value that is set as the characteristic depth image value associated with the respective depth image;
the step of calculating the total image value is performed by summation or multiplication of the characteristic depth image values such that the total image value is always greater than or equal to each of the characteristic depth image values summed or multiplied using the monotonic combination rule; and
during the step of determining the estimation result, the comparison of the total image value with the at least one predetermined reference total image value is performed by a mathematical calculation that determines both (a) whether these compared values differ from one another, and (b) a measure of how much the compared values differ from one another when unequal.

Assignees

• Muehlbauer Gmbh & Co Kg
• Muhlbauer Gmbh & Co Kg

Inventors

• Niebling Gerhard
• Lehmann-Elle Ralf
• Kumar Deepack

Classifications

• H04N23/90

  Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title

• H04N7/18

  Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title

• G06T2207/30242

  Counting objects in image · CPC title

• G06T2207/30232

  Surveillance · CPC title

• G06T2207/30196

  Human being; Person · CPC title