WO2021182983A1

WO2021182983A1 - Self-monitoring system for detecting the presence of objects

Info

Publication number: WO2021182983A1
Application number: PCT/RU2020/000133
Authority: WO
Inventors: Сергей Станиславович ЧАЙКОВСКИЙ
Original assignee: Сергей Станиславович ЧАЙКОВСКИЙ
Priority date: 2020-03-13
Filing date: 2020-03-13
Publication date: 2021-09-16
Also published as: RU2742803C1

Abstract

This invention relates to the field of computing and, more specifically, to methods and systems for detecting the presence of objects with a self-monitoring function. A self-monitoring system for detecting the presence of objects, comprising at least one light source, which is able to emit light in a predetermined spectrum, wherein each of the sources has a different predetermined spectrum for each predefined area; at least one means, which is sensitive to light in the predetermined spectrum, is able to detect the light reflected from at least one object if said object is present in a predefined area, and is designed to generate a presence signal on the basis of the detected light; and at least one processor device for determining the presence of an object on the basis of the presence signal generated in the previous step, wherein the processor device draws a conclusion about the presence of an object in the predefined area on the basis of the presence signals.

Description

SELF-CONTROLLED OBJECT DETECTION SYSTEM

FIELD OF TECHNOLOGY

[001] This invention relates to the field of computing, and, in particular, to methods and systems for detecting the presence of objects with a self-monitoring function.

LEVEL OF TECHNOLOGY

[002] Modern access control systems use biometric information about a person to identify registered users and deny access to unauthorized users. [003] One of the features of the development of modern society is the increasing need to restrict access to various objects, such as offices, warehouses, ATMs, military facilities. This is due to the need to ensure the security of these objects, to prevent theft of intellectual property and goods.

[004] Previously widely used security systems based on the presence of a person, for example, a security guard, at the entrance to a protected area or using video surveillance systems, the data from which are also analyzed by a person, become expensive and do not provide the required degree of reliability. It is in connection with these shortcomings in many public and private organizations that systems based on magnetic and smart cards are widely used. The card contains information that identifies the user using it. The scanner located at the entrance to the protected area reads this information and decides to grant the user access to the area.

A significant drawback of such systems is the possibility of using the card by an intruder, for example, he can steal it. [005] Biometric systems are one of the most promising solutions, devoid of these disadvantages. Such systems are based on the analysis of biometric information about the user: facial features, voice, gestures, fingerprints, etc. The biometric parameters of the user, automatically read by the system, are compared with the templates, stored in the database. If one of the templates matches the received data, then the user is considered identified and he is allowed access.

[006] Modern biometric systems are based on the analysis of the following biometric parameters of a person: face, voice, iris, gestures. Other types of parameters either do not provide sufficient accuracy for user identification or require contact with the reader (as is the case with fingerprints).

[007] At the same time, the existing biometric systems have a number of disadvantages that allow unauthorized access to the protected area.

[008] The closest analogue patent No. 2316051 "Method and system for automatically checking the presence of a living person's face in biometric security systems" is known from the prior art, patentee: SAMSUNG ELECTRONICS, published: 27.01.2008.

[009] The invention relates to security and control systems. Its use makes it possible to obtain a technical result in the form of increased reliability and speed in detecting attempts of unauthorized access to an object. This is achieved due to the fact that detection of the face of a living person and detection of unauthorized users present near the registered user are used as the main mechanism. The invention uses methods for tracking a three-dimensional object reduced to the first normalized face shape, using a fast method of measuring and comparing facial expressions with a template, as well as methods for detecting local features and presenting a face in three different normalized forms. In addition, a fast method of measuring and comparing with a template such a behavioral biometric characteristic as a phonemic signature is used, which is obtained as a result of the user's execution of system commands.

[0010] The disadvantage of this technical is that only the presence in the image of a face image and its inherent physical aspects, such as facial expressions, is recorded. This method does not allow to distinguish the generated image from the image of a real living object. [0011] Also known in the art are solutions that propose algorithms and control systems based on the analysis of two-dimensional images of a human face (see US Published Patent Nos. 6,633,655 and 6,681032). These systems use video cameras to capture images of the face, implement the selection of areas of the face and calculate their characteristics, which are compared with the templates stored in the database. Such systems process 2D models of a person's face and thereby allow unauthorized access by providing cameras with a photograph of a registered user.

[0012] From the prior art, the application "WO199702682120.11" A presence detection system and a lighting system "is known (applicant: Ian Robert Fothergill, publication date: 07/31/1997). This patent application discloses a device for monitoring a living body, such as a child, comprising transmitting radiation to the body, receiving radiation transmitted by the body after modification, and processing the received radiation to determine the position and / or state of the body. For example, to determine if the body is breathing or its heart is beating.

[0013] The disadvantage of this system is limited accuracy. In particular, such a system is not able to accurately determine in which part of the area a living body is located.

SUMMARY OF THE INVENTION

[0014] This technical solution is aimed at eliminating the disadvantages known from the prior art.

[0015] The technical problem or technical problem solved in this technical solution is the implementation of a system for detecting the presence of objects with self-control.

[0016] The technical result is to improve the quality of detection of the presence of objects through the use of artificial intelligence, as well as the use of a sensitive means to light of a predetermined spectrum.

[0017] The specified technical result is achieved by implementing a system for detecting the presence of objects with self-monitoring, which contains at least one light source made with the ability to emit light of a predetermined spectrum, each of the sources having a different predetermined spectrum for each predetermined area; at least one light sensing means of a predetermined spectrum, configured to detect light reflected from at least one object, if present in a predetermined area, and to generate a presence signal based on the detected light, and at least one processor a device for determining the presence of an object based on a presence signal generated in a previous step, the processor inferring the presence of an object in a predetermined area based on the presence signals. [0018] In some embodiments, the sensing means comprises a photosensor that is sensitive to light of a predetermined spectrum.

[0019] In some embodiments of the invention, the sensing means comprises a photosensor equipped with a spectral filter for filtering light of a predetermined spectrum.

[0020] In some embodiments, two light sources are contained in one light emitting device, the light emitting device being configured to emit light from at least two different predetermined spectra in two zones.

[0021] In some embodiments, when there are two operable light sources, the first spectrum and the second spectrum do not substantially overlap.

[0022] In some embodiments, the object is a human and the presence signal represents a human vital signal. [0023] In some embodiments, the presence signal represents the vital signals of at least two people present in the same area, and in which the processing device distinguishes the corresponding vital signals from at least two people present in the area.

[0024] In some embodiments of the invention, the target spectrum emitted by the light sources comes from the visible spectrum and / or. [0025] In some embodiments of the invention, each of the photosensors includes a photodiode.

[0026] In some embodiments, the photodiodes are located together in a photodiode array.

BRIEF DESCRIPTION OF DRAWINGS

[0027] The features and advantages of the present technical solution will become apparent from the following detailed description and the accompanying drawings, in which:

[0028] Fig. 1 schematically shows a first exemplary embodiment of a presence detection system in which an area comprises two zones.

[0029] FIG. 2 schematically shows the intensity of presence signals measured by the presence detection system according to FIG. 1. [0030] FIG. 3 schematically shows a second exemplary embodiment of a presence detection system in which an area comprises three zones.

DETAILED DESCRIPTION OF THE INVENTION

[0031] Below will be discussed in detail the terms and their definitions used in the description of this technical solution.

[0032] In this invention, the system means a computer system, a computer (electronic computer), CNC (numerical control), PLC (programmable logic controller), computerized control systems and any other devices capable of performing a given, well-defined sequence of operations. (actions, instructions), centralized and distributed databases, smart contracts.

[0033] By a command processing device is meant an electronic unit or an integrated circuit (microprocessor) executing machine instructions (programs), or the like. A command processor reads and executes machine instructions (programs) from one or more storage devices. Data storage devices can be, but are not limited to, hard disks (HDD), flash memory, ROM (read-only memory), solid state drives (SSD), optical drives.

[0034] A program is a sequence of instructions for execution by a computer control device or command processing device.

[0035] Server (English server) - an electronic device that performs service functions at the request of the client, providing him with access to certain resources. For the purposes of this description, a server is contemplated that has a persistent connection to the internetwork that can transmit data to a client device. The server can process this data and transmit the processing result back to the client device.

[0036] A data exchange module is a server module that can represent a receiver of incoming signals, and a converter for further processing, and a translator for further sending.

[0037] A compute module is a server module that is a microprocessor specially adapted for complex signal processing.

[0038] In the following description of preferred embodiments, reference is made to the accompanying drawings, which constitute a portion thereof. Specific embodiments in which the invention may be practiced are shown herein by way of illustration. It is also understood that other embodiments may be used and structural changes may be made without departing from the scope of the present invention. It should be noted that like reference numerals will be used to refer to the same or like parts in several embodiments.

[0039] Fig. 1 is a schematic diagram of a first exemplary embodiment of an object presence detection system according to the invention. In this embodiment, the system comprises two light sources, a first light source 110.1 and a second light source 110.2 for emitting light of predetermined spectra, and two sensing means comprising two photosensors in this embodiment, namely a first photosensor 120.1 and a second photosensor 120.2. In this embodiment, the photosensors are equipped with spectral filters, a first spectral filter 130.1 and a second spectral filter 130.2, respectively, for filtering light of predetermined spectra. The photosensors 120.1, 120.2 are configured to detect light reflected from a person 140 present in the area that has passed through the respective spectral filters 130.1, 130.2, and to generate two presence signals based on the detection results. For example, a detector system can be connected to a system of a type other than a lighting system, such as an HVAC system.

[0040] The photosensor (eg, 120.1 and 120.2) may include various types of optical sensors that provide means for converting the detected optical radiation into an electrical signal, the photosensor may be a broadband sensor or a narrowband sensor. For example, as would be readily understood by one of ordinary skill in the art, the photosensor may be a phototransistor, photosensitive integrated circuit, an off-power LED, a silicon photodiode, or other device. In one embodiment, the broadband sensor is aligned with the filter, and thus a narrow optical detection bandwidth can be provided. One or more photosensors are generally configured to generate electrical signals representative of the respective output radiation of one or more light emitting elements, which can then be used in a controller such as a signal processor or control system (e.g., controller, microcontroller, software and / or device and so on), or other such control means for estimating the output radiation of the light source and, if necessary, adjusting the corresponding output radiation of one or more light-emitting elements. In yet another embodiment, the photosensor may comprise a charge coupled device (CCD, CCD) with spectrally sensitive detectors for converting the energy of the laser beam into digital signals, which can then be processed by a processing unit. subsystem. The charge coupled device can be any device capable of transferring electrical charge from the device to a location where the charge can be processed, such as by converting to a digital value for processing by a processing subsystem, obtained by "displacing" the signals one by one between steps in the device. A charge coupled device can move charge between capacitive cells in a device using bias to transfer charge between cells. By way of example, a CCD device may include n-well / p-sub photodiodes, a capacitive current-controlled voltage amplifier, pixel scanners, and delta-differentiating circuits. Using a charge coupled instrument can eliminate the need for a discrete spectrometer and current-to-voltage converter. [0041] Presence signals are provided to a processor 150, wherein the processor 150 determines the presence or absence of a person 140 based on the provided presence signals 160.1; 160.2. An area can be covered by two zones, a first zone 170.1 and a second zone 170.2. Each of the two light sources, the first light source 110.1 and the second light source 110.2, has a different predetermined spectrum, and each emits light within a different area, the first area 170.1 and the second area 170.2, respectively. Each of the two photosensors, the first photosensor 120.1 and the second photosensor 120.2, is configured to operate with one of the light sources, the first light source 110.1 and the second light source 110.2, respectively, and together with a corresponding spectral filter, the first spectral filter 130.1 and the second spectral filter 130.2 are accordingly configured to detect corresponding light of a predetermined spectrum. Thus, the processor 150 infers the presence of a person 140 by zone. A spectral filter can be additionally installed behind the focusing optics to allow only a certain spectrum of wavelengths to pass through.

[0042] Alternatively, the sensing means comprise photosensors having different spectral sensitivities. Such a photosensor, sensitive to light of a predetermined spectrum, can be use instead of a photosensor equipped with a spectral filter to filter light from a predetermined spectrum. Photosensors must have different spectral sensitivity. In some embodiments, the photosensors may have fundamentally different spectral sensitivities so that they can inherently discriminate between light from different predefined spectra. Substantially different spectral sensitivities can be realized, for example, by using different classes of photosensors, such as photodiodes, CCDs, photomultipliers, etc., without limitation. Alternatively, fundamentally different spectral sensitivities can be realized using photosensors of the same class, such as photodiodes, with different material properties, for example, based on silicon (Si) or based on gallium arsenide (GaAs), different doping levels in silicon, etc. Alternatively, different spectral sensitivities can be realized by adding spectral filters.

[0043] In the specific embodiment shown in FIG. 1, the first person 140 is positioned in the first area 170.1 in the area. Thus, only the first photosensor 120.1 detects light emitted from the first light source 110.1, reflected from the first person 140 and is filtered by the first spectral filter 130.1, while the second photosensor 120.2 does not detect any significant light. This means that the processor 150 receives two presence signals 160.1; 160.2, wherein the first presence signal 160.1 indicates the presence of a person in the first zone 170.1, and the second presence signal 160.2 indicates the absence of a person in the second zone 170.2. Therefore, the processing unit 150 detects the presence of a person in the zone 170 and, in particular, the presence in the first zone 170.1.

[0044] Photosensors, such as photodiodes, are capable of measuring vital signals from a person. Photoplethysmography is the monitoring of changes in the blood pulse in the capillaries of a person through the absorption of light by oxydeoxyhemoglobin. Photoplethysmography can be performed using simple photosensors such as photodiodes. A photodiode monitors tiny changes in light intensity caused by cycling the passage of fresh blood in the capillaries of the skin. With such a photodiode, it is possible to dynamically measure the heart rate, heart rate variability, oxygenation of the blood and possibly the blood pressure of a person at a distance of several meters. It is also known that photodiodes are capable of measuring vital signals such as heart rate over a wide range of spectral frequencies. Most preferably, the system uses light in the invisible range of the spectrum, making the measurement completely invisible. Thus, for example, presence signals 160.1; 160.2 can represent a human heart rate signal. This feature provides additional security that the presence of a person is correctly determined, since the known parameters of the heart rate signal can be used by the processor as an additional criterion for inferring the presence of a person.

[0045] Spectral filters can be very simple components, such as deposited thin films, that are located directly on top of the photosensors, ie, photodiodes.

[0046] Alternatively, you can use photodiodes or an array of photodiodes containing spectral filters, as known in the art. Photodiodes can be manufactured using standard semiconductor silicon technology or, alternatively, can be manufactured using amorphous silicon technology, which is used to make LCD displays on glass or flexible plastic substrates. The latter technology mentioned has the advantage of lower cost and larger diode area.

[0047] Light sources 110.1, 110.2 can also emit light in more than one area and instead emit light of relatively high intensity in the main area, and light of relatively low intensity in adjacent areas of the main area. Specifically, in the embodiment shown in FIG. 1, the first light source 110.1 emits light of relatively high intensity in the first zone 170.1, as well as light of relatively low intensity in the second zone 170.2, and similarly, the light source 110.2 emits light of relatively high intensity in the second zone 170.2, as well as a relatively low intensity in the first zone 170.1. Light of the first light source 110.1 continuously decreases from the main area, in this example from the first area 170.1, to areas further away from the main area. Such a feature can be used to determine a relatively more accurate position of the first person 140 within the area. Specifically, in the example shown in FIG. 1, the heartbeat of the first person 140 will be detected by the first photosensor 120.1 relatively strongly and relatively weakly by the second photosensor 120.2. However, for the second person 140.1 shown in the same FIG. 1, the heartbeat of the second person 140.1 being detected by the first photosensor 120.1 as a relatively strong signal, approximately the same intensity as for the first person 140, and as a relatively weak signal detected by the second photosensor 120.2, but still with a higher intensity than the first person 140. This is represented by the table shown in FIG. 2. As already mentioned, this feature can be used to determine a more accurate position of a person in a zone. In this particular example, heart rate measurements for first person 140 and second person 140.1 will indicate that second person 140.1 is closer to second zone 170.2 than first person 140, while it will be apparent that both people are in zone 170.1.

[0048] The number of zones in area 170 can be different, virtually any integer greater than one. Increasing the number of zones can improve the accuracy of the presence detection system. However, the number of zones should also be selected to match the size of the area 170, namely a relatively small area can be very well covered with just two areas, while a relatively large area may require more than 2 areas.

[0049] FIG. 3 schematically shows a second exemplary embodiment of a presence detection system in accordance with the invention, in which the system is used to detect the presence of more than one person, in this particular example, the presence of three people, the first person 140, the second person 140.1 and the third person 140.2. The processor 150 will receive three presence signals, a first presence signal 160.1, a second presence signal 160.2, and a third presence signal 160.3. These presence signals will indicate the presence three people. The first presence signal 160.1 will indicate the presence of the first person 140 having a first heart rate. A third presence signal 160.3 will indicate the presence of a second person 140.1 and a third person 140.2 having a second heart rate and a third heart rate. This means that the system according to the invention is capable of detecting more than one person in different areas as well as in the same area. This is possible because the presence signal contains information about different heartbeats found in different people in the same area. To confirm that two or more people are actually present in the same area, any difference in the measured heart rates must be determined, such as different heart rates, heart rate variability, etc.

[0050] To classify and determine signals of the presence of a living object in this technical solution, machine learning algorithms can be used. Below is an example based on an artificial neural network.

[0051] A neural network is a graph of interconnected non-linear processing units (processors) that can be trained to approximate complex mappings between input data and output data. Note that the input data is, for example, a digital presence signal (a set of coordinates of a living object), and the output is, for example, a classification solution (in the simplest case, + 1 / -1, which means "yes", there is a person in the signal, or "no", there is no person in the signal). Each nonlinear processor (or neuron) consists of a weighted linear combination of its inputs, to which a nonlinear activation function is applied.

[0052] A neural network is defined by its connectivity structure, its nonlinear activation function and its weights.

[0053] In the following embodiments, a concept is used that may be called and is called relevance propagation in the following description. It redistributes the evidence (basis) for a particular structure in the data, as modeled by the output neurons, back to the input neurons. So she seeks to explain its own prediction in terms of input variables (e.g. coordinates of a living object). Note that this concept works for any type (no loop) neural network, regardless of the number of layers, type of activation function, etc. Thus, it can be applied to many popular models, since many algorithms can be described in terms of neural networks.

[0054] The following is an illustration of a relevance propagation procedure for a network consisting of convolution / downsampling layers followed by a sequence of fully connected layers.

[0055] In particular, the example below shows an artificial neural network implementation in a simplified exemplary manner. An artificial neural network is made up of neurons. Neurons are interconnected with each other or interact with each other. Typically, each neuron is connected to downstream (downstream) adjacent (or downstream) neurons on one side and upstream (upstream) neighboring (or upstream) neurons on the other side. The terms "upstream", "upstream", "downstream" and "downstream" refer to the general direction of propagation along which the neural network operates when applied to a set of elements to map the set of elements to the output of the network, that is, to perform prediction.

[0056] The set of elements may, for example, be a set of image pixels that form an image by associating each pixel with a pixel value corresponding to the color or intensity of the scene, at a spatial location corresponding to the position of the corresponding pixel in the image pixel array, or for example, presence signal data that contains information about the different heartbeats of people. In this case, the set is an ordered set of items, namely an array of pixels or heart rate data. In this case, the elements will correspond to individual pixel values, i.e. each element will correspond to one pixel. It will be further explained that the present application is not limited to the field of images. Rather, a collection of elements can be a collection of elements without any ordering defined among the elements. Combinations between them can also take place.

[0057] The first or lowest layer of neurons forms a kind of input to the artificial neural network. That is, each neuron of this lower layer takes as input at least a subset of the set of elements, that is, at least a subset of pixel values. The union of subsets of elements from the set, the values of which are entered into some neuron of the lower layer. In other words, for each element of the set, its value is entered into at least one of the neurons of the lower layer.

[0058] On the opposite side of the neural network, that is, on its descending / output side, the network contains one or more output neurons, which differ from neurons in that the former do not have descending neighboring / subsequent neurons. After being applied to the presence signal dataset and after processing is complete, the values stored in each output neuron form the output of the network. That is, the network output can, for example, be a scalar. In this case, only one output neuron will be present, and its value after the network operation will form the network output. Such a network output can, for example, be a measure of the likelihood that a set of elements, that is, a set of numerical values of a presence signal, belongs to a certain class or not. The network output can, however, alternatively be a vector. In this case, there is more than one output neuron, and the value of each of these output neurons, as obtained at the end of the network operation, forms the corresponding component of the network output vector. Each component of the network output is a measure that measures the probability that the set belongs to the corresponding class associated with the corresponding component, for example, to the class of presence signals "human", "cat" and "elephant". Other examples are also possible and will be presented below.

[0059] Thus, to summarize the foregoing, a neural network includes neurons interconnected to map, in feedforward or normal operation, a set of elements to a neural output. Like the output neurons, the value of which at the end of the network operation forms the output of the network, the elements of the set, that is, the numerical the values of the presence signal in an exemplary case can be considered as input neurons of a network with neurons and layers formed in this case, which are intermediate neurons or intermediate layers, respectively. In particular, input neurons can appropriately be considered as ascending adjacent or preceding neurons of interneurons, just as output neurons can form descending adjacent / subsequent neurons of interneurons, forming, for example, the highest intermediate layer of the network or, if one or more output neurons are interpreted as forming the topmost layer of the network, the second highest layer of the network.

[0060] The neural network may be implemented, for example, in the form of a computer program running on a computer or processing device, that is, in software, but implementation in hardware, for example, in the form of an electrical circuit, would also be feasible. Each neuron, when trained, calculates, as described above, activation based on its input values using a neural function, which, for example, is represented as a non-linear scalar function q () of a linear combination of input values. As described, neural functions associated with neurons can be parameterizable functions. For example, in one of the specific examples described below, the neural functions for neuron j are parameterizable using an offset bj and a weight wij for all input values i of the corresponding neuron. These parameters can be obtained by training the network. To this end, the network is, for example, reapplied to the training (training) set for element sets for which the correct network output is known, that is, the training set of labeled presence signals in the illustrative case. However, there may be other possibilities as well. Even a combination can be workable. The embodiments described below are not limited to any source or method for determining parameters. For example, the ascending (front) part of the network, consisting of layers extending from the dataset, i.e. network input, up to the intermediate hidden layer, can be artificially generated or trained to emulate the extraction of the presence signal data feature by means of convolutional filters, for example, so that each the (downstream) neuron of the subsequent layer represents the feature value from feature maps. Each feature map, for example, is associated with a specific characteristic or feature or impulse response or the like. Accordingly, each feature map can, for example, be viewed as a sparse (sub-) sampled filtered version of the presence input, with one feature map differing in the associated feature / characteristic / impulse response of the associated filter from the other feature map. If, for example, a set has CΎ elements, namely, presence signal values, that is, X columns and Y rows of signal values, each neuron will correspond to one feature value of one feature map, the value of which will correspond to a local feature estimate associated with a certain part of the signal presence. In the case of N feature maps with PQ samples of feature estimates, for example, P columns and Q rows of feature values, the number of neurons in the descending subsequent layer of the part will be equal, for example, NPQ, which may be less or more than X Y. To set neural functions or parameterization of the neural functions of neurons within a part, translation (transformation) of feature descriptions or filters underlying feature maps could be used, respectively. Note again, however, that the existence of such a "translated" rather than a "trained" portion of the network is optional for the present application and its embodiments, and that such a portion may alternatively be absent. In any case, establishing that it is possible that the neural functions of neurons can be equal among all neurons, or equal among neurons of the same layer, or the like, the neural function can, however, be parameterizable, and although the parameterizable neural function may be the same among these neurons, the function parameter (s) of that neural function may (may) vary among these neurons. The number of intermediate layers is also arbitrary and can be one or more than one. [0061] To summarize the above, the application of the network in normal operating mode is as follows: a set of numerical values of the presence signal is affected or entered into the network. That is, these values form the input values for the neurons of the first layer. These the values propagate as described along the forward direction of the network and result in the output of the network. In the case of a signal for the presence of a living person, for example, the network output will, for example, indicate that this input signal belongs to the third class, that is, to the class of signals showing a living person. More precisely, while the human output neuron would end up high, other output neurons, illustratively in this case for the cat and elephant classes, would end up at low (lower) values. [0062] However, as described in the introductory part of the specification of the present application, information as to whether or not a presence signal, that is, a dial, a person, or the like, may be insufficient. Rather, it would be preferable to have information at the level of granularity of the presence signal values indicating which numbers, i.e. the elements of the set were relevant to the network's decision and which were not, for example, which values about the heartbeat data display a person and which do not.

[0063] If a photodiode array is used, a one-time system calibration may be required to transform the color of the spectrum detected by the photodiode array into a spatial coordinate. However, since the illumination pattern is fixed and possibly matches the photosensor filters in a 1: 1 ratio, the calibration problem is trivial.

[0064] Light sources can use light of invisible wavelengths, since it is not always desirable to illuminate the space with colored light. For this reason, in a preferred embodiment of the invention, it is proposed to provide a system in which the spectral bandwidth of the light source and the photosensor array filter go beyond the wavelengths of visible light, that is, 350-700 nanometers (nm).

[0065] Light is also strongly absorbed by the bloodstream in human skin at both infrared (IR) wavelengths above 700 nm and ultraviolet (UV) wavelengths below 400 nm. Since the effects of ultraviolet light can be harmful to the skin, it is highly preferred that the spectrum frequencies used are infrared frequencies when the light is still strongly absorbed by the bloodstream in the skin. This IR spectrum is well suited for both sources of infrared radiation, such as LEDs, and for photodiodes, which are readily available over the entire wavelength range of infrared radiation.

[0066] The invention also provides specific concepts whereby either the spectral bandwidth of the light source or the array photodiode filter is reduced. In general, the bandwidth of the light source should be within the passband of the photodiode array filter.

[0067] In addition, such a system may contain a discrete or continuous spectrum of light. It will be apparent to those skilled in the art that such a system can be constructed using broadband light or a series of reduced bandwidth light sources or with single frequency light sources such as lasers and LEDs.

[0068] In addition, it is also possible that each photodiode in the array has a discrete filter.

[0069] The described system has a self-monitoring function to determine when conditions within zones require the activation of photodetectors, and is equipped with adjusting mechanisms that can self-adjust in response to detected conditions in the area for detecting the presence of a person.

[0070] Although the invention has been illustrated and described in detail in the drawings and the foregoing description, such illustrations and description are to be considered as illustrative or exemplary and not restrictive, i. E. the invention is not limited to the disclosed embodiments.

[0071] Other variations of the disclosed embodiments may be understood and practiced by those skilled in the art based on an examination of the drawings, the disclosure, and the appended claims. [0072] All blocks used in the system can be implemented with electronic components used to create digital integrated circuits, which is obvious to a person skilled in the art. Not limited to, microcircuits can be used, the logic of which is determined during manufacture, or programmable logic integrated circuits (FPGA), the logic of which is set through programming. Programmers are used for programming and debugging environments that allow you to set the desired structure of a digital device in the form of a circuit diagram or a program in special hardware description languages: Verilog, VHDL, AHDL, etc. An alternative to FPGAs can be programmable logic controllers (PLC), basic matrix crystals (BMC), which require factory production process for programming; ASICs are specialized custom large integrated circuits (LSI), which are significantly more expensive for small-scale and single-piece production.

[0073] Typically, the FPGA itself consists of the following components:

• configurable logic blocks that implement the required logic function;

• programmable electronic links between configurable logic blocks;

• programmable input / output blocks providing connection of the external output of the microcircuit with the internal logic.

[0074] Blocks can also be implemented using read-only memory devices.

[0075] Thus, the implementation of all the blocks used is achieved by standard means based on the classical principles of the implementation of the foundations of computing.

[0076] As will be understood by a person skilled in the art, aspects of the present technical solution may be implemented as a system, method, or computer program product. Accordingly, various aspects of the present technical solution may be implemented solely as hardware, as software (including application software, and so on), or as an embodiment combining software and hardware aspects, which may generally be referred to as a "module" , "System" or "architecture". In addition, aspects of the present technical solution may take the form of a computer program product implemented on one or more computer-readable media having computer-readable program code that is implemented thereon. [0077] Any combination of one or more computer readable media can also be used. Computer readable media storage can be, without limitation, electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, apparatus, device, or any suitable combination thereof. More specifically, examples (non-exhaustive list) of a computer-readable storage medium include: an electrical connection using one or more wires, a portable computer diskette; hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), fiber optic connection, compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any combination of the above. As used herein, a computer-readable storage medium can be any flexible storage medium that can contain or store a program for use by the system itself, device, apparatus, or in connection therewith.

[0078] Program code embedded in a computer-readable medium can be transmitted using any medium, including, without limitation, wireless, wired, fiber optic, infrared, and any other suitable network or combination of the above.

[0079] Computer program code for performing operations for the steps of the present technical solution may be written in any programming language or combinations of programming languages, including an object-oriented programming language such as Java, Smalltalk, C ++, and so on, and conventional procedural programming languages such as programming language "C" or similar programming languages. The program code can be executed on the user's computer in whole, in part, or as a separate software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer. In the latter case, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN), a wide area network (WAN), or a connection to an external computer (for example, via the Internet using Internet service providers). [0080] Aspects of the present technical solution have been described in detail with reference to block diagrams, schematic diagrams, and / or diagrams of methods, devices (systems), and computer program products in accordance with embodiments of the present technical solution. It should be appreciated that each block from the block diagram and / or diagrams, as well as combinations of blocks from the block diagram and / or diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other data processing device to create a procedure, such that instructions executed by a computer processor or other programmable data processing device create means to implement the functions / actions specified in block or blocks of flowchart and / or diagram.

[0081] These computer program instructions may also be stored on a computer-readable medium that can control a computer other than a programmable data processing device or other devices that function in a particular way, such that the instructions stored on the computer-readable medium create a device including instructions that perform the functions / actions specified in the block diagram and / or diagram.

[0082] The above description includes examples of one or more aspects. Of course, it is not possible to describe every possible combination of components or methodologies in order to represent the aspects described above, but one skilled in the art will understand that many additional combinations and permutations of various aspects are possible. Accordingly, the described aspects are intended to embrace all such changes, modifications and variations that fall within the spirit and scope of the appended claims. In addition, to the extent that the term "includes" is used either in the detailed description of the invention or in the claims, such a term is intended to have an inclusive meaning, similar to the term "comprising" as the term "comprising" is interpreted when it is used as a transition word in the claims.

Claims

FORMULA

1. A self-monitoring system for detecting the presence of objects, comprising:

• at least one light source configured to emit light of a predetermined spectrum, each of the sources having a different predetermined spectrum for each predetermined area;

• at least one light sensing means of a predetermined spectrum, configured to detect light reflected from at least one object, if present in a predetermined area, and to generate a presence signal based on the detected light, which is a heart rate signal a person, and

• at least one processor for determining the presence of an object based on a presence signal generated in the previous step, the processor inferring the presence of an object in a predetermined area based on the presence signals using a trained artificial neural network.

2. A self-monitoring system for detecting the presence of objects according to claim 1, characterized in that the sensing means comprises a photosensor sensitive to light of a predetermined spectrum.

3. A self-monitoring object presence detection system according to claim 1, characterized in that the sensing means comprises a photosensor equipped with a spectral filter for filtering light of a predetermined spectrum.

4. The self-monitoring object presence detection system of claim 1, wherein the two light sources are contained in one light emitting device, the light emitting device being configured to emit light from at least two different predetermined spectra in two zones.

5. The system for detecting the presence of objects with self-monitoring according to claim 1, characterized in that in the case of the presence of two working light sources, the first spectrum and the second spectrum do not substantially overlap.

6. The system for detecting the presence of objects with self-control according to claim 1, characterized by the fact that the object is a person, and the signal of presence is a vital signal of a person.

7. The system for detecting the presence of objects with self-monitoring according to claim 6, characterized in that the presence signal represents vital signals from at least two people present in the same area, and in which the processing device distinguishes the corresponding vital signals from at least at least two people present in the zone.

8. The system for detecting the presence of objects with self-monitoring according to claim 1, characterized in that the specified spectrum of light emitted by the light sources comes from the visible spectrum and / or.

10. System for detecting the presence of objects with self-monitoring according to any paragraph. 1-9, characterized in that each of the photosensors contains a photodiode.

11. The self-monitoring system for detecting the presence of objects according to claim 10, characterized in that the photodiodes are located together in an array of photodiodes.