ULTRASONIC BASED HUMAN DETECTION SYSTEM AND METHOD - Patent application

Abstract

An ultrasound-based human detection method, the method including: (a) emitting an ultrasonic signal from an emitter, the ultrasonic signal including a component at a first frequency, (b) receiving a reflection of the ultrasonic signal, the received signal including a component at a frequency greater than the first frequency and a component at a frequency less than the first frequency, (c) determining a difference between an upper portion of the received signal including frequencies greater than the first frequency and a lower portion of the received signal including frequencies less than the first frequency, and (d) determining whether a human is present based on the difference between the upper and lower portions.

Description

[Technical field]

[0001] The present invention relates to ultrasonic human detection systems and methods. [Background technology]

[0002] Videoconferencing devices such as collaboration endpoints typically have a standby state, meaning that the device is active when not in use. Advantageously, the standby state reduces power consumption, for example by turning off unnecessary components (e.g., monitors). Another benefit of the standby state is the increased lifespan of components such as camera sensors, projector bulbs, etc.

[0003] A device that has a standby state must have a way to put the device into standby and to wake the device up again. For example, previous videoconferencing devices have operated with a timer and human input method. The device is programmed to go into standby mode after a predefined period of inactivity (e.g., 10 minutes) and is woken up by human input on a control panel or the like. However, this is not intuitive for some users, especially if the control panel is not easily accessible or visible.

[0004] It is also known to use a human detector, where the device is placed in a standby mode when it determines that no human is nearby. One such example is disclosed in US Pat. No. 5,399,433, where ultrasound is transmitted into a spatial region. A controller then receives the reflected ultrasound and calculates an error signal that represents an estimate of the echo-free received ultrasound signal. The controller then calculates a power estimate of the error signal over time and detects the presence of a human based on changes in this power estimate.

[0005] However, a problem with the above-mentioned ultrasonic method is that it can be prone to false positives. The above-mentioned system detects over a relatively narrow frequency range. However, transient noises not generated by an emitter, such as a door closing or clapping hands, have components that are relatively broadband in frequency and therefore fall within the detection range. This can cause false positives where a transient noise detected near a device (but not indicating that someone is in the room) wakes the device from standby mode. Summary of the Invention [Problem to be solved by the invention]

[0006] Therefore, there is a need for more robust human detection methods that are less prone to false positives. [Means for solving the problem]

[0007] Thus, in a first aspect, an embodiment of the present invention provides a method for producing a composition comprising: (a) emitting an ultrasonic signal from an emitter, the ultrasonic signal having a first frequency (outside 1) emitting the component contained in JPEG0007621345000001.jpg10127; (b) receiving a reflection of an ultrasonic signal, the received signal including components at frequencies greater than the first frequency and components at frequencies less than the first frequency; (c) determining a difference between an upper portion of the received signal that includes frequencies higher than the first frequency and a lower portion of the received signal that includes frequencies lower than the first frequency; (d) determining whether a person is present based on a difference between the upper portion and the lower portion. An ultrasound-based human detection method is provided.

[0008] Such a method is more robust in detecting whether a person is actually present by mitigating false positives caused by broadband noise that is not indicative of motion. (outside 2) It is also more robust with respect to other devices that may emit ultrasonic signals, such as those found in JPEG0007621345000002.jpg12127. Additionally, the method does not rely on the emitter and receiver being temporally synchronized.

[0009] The method may have any one of the following optional features, or any compatible combination:

[0010] The determination may be based on the difference between the upper frequency portion and the lower frequency portion.

[0011] The upper portion of the received signal may include higher frequencies immediately surrounding the first frequency, and the lower portion of the received signal may include lower frequencies immediately surrounding the first frequency.

[0012] The method may include dividing the received signal into a number of bins, each bin representing a range of frequencies in the received signal, with the upper portion being upper frequency bins that include portions of the received signal that are at frequencies higher than a first frequency, and the lower portion being lower frequency bins that include portions of the received signal that are at frequencies lower than the first frequency.

[0013] The determination may be based on the difference between the normalized power estimates of the upper and lower frequency bins. The normalization factor may be the sum of the power estimates of the upper and lower frequency bins. The normalization may be performed by subtracting an estimate of the average of the upper and lower frequency bins.

[0014] Determining the presence of a person may include determining a logit function of the normalized power of the upper frequency bins. Determining the presence of a person may include determining a logit function of the normalized power of the lower frequency bins. Determining the presence of a person may include determining a first logit function of the normalized power of the upper frequency bins and determining a second logit function of the normalized power of the lower frequency bins.

[0015] The logit function is

number

number

number

[0016] Steps (b)-(d) may be repeated at a predetermined rate. Each iteration of (b)-(d) may be performed over a time window of the received signal. The time window may be about 20 ms.

[0017] After it is determined that a person is present, the method may further include determining whether the person is moving towards or away from the receiver. Determining whether the person is moving towards or away from the receiver may be further based on a first log-likelihood ratio test to determine whether the person is moving towards the receiver and a second log-likelihood ratio test to determine whether the person is moving away from the receiver. A log-likelihood ratio may be derived for each likelihood ratio and may be recursively calculated from previous values ​​of the respective log-likelihood ratio. Advantageously, such log-likelihood ratios are simpler to implement and have lower computational complexity, resulting in a computationally cheaper method.

[0018] When it is determined that a person is present, the method may include removing the video conferencing device from a standby mode.

[0019] In some embodiments, there may be a first receiver and a second receiver, where the first receiver receives reflections of ultrasonic signals having frequency components higher than a first frequency, and the second receiver receives reflections of ultrasonic signals having frequency components lower than the first frequency. Thus, the first receiver may receive an upper portion of the received signal, and the second receiver may receive a lower portion of the received signal. Determining the difference between the upper portion of the received signal and the lower portion of the received signal may include determining whether the first receiver and / or the second receiver received the respective signal. If both receivers receive the signal, the received signal may be determined to be a false positive. If only one receiver receives the signal, it may be determined that a person is present.

[0020] In a second aspect, an embodiment of the present invention provides a system for detecting a person, the system comprising: First Frequency (Outside 3) an emitter configured to emit an ultrasonic signal having a component at JPEG0007621345000006.jpg13127; one or more receivers configured to receive reflections of the ultrasonic signals; one or more processors, the processor comprising: In response to the receiver receiving a received signal including components at frequencies greater than a first frequency and components less than the first frequency, (a) determining a difference between an upper portion of the received signal that includes frequencies higher than a first frequency and a lower portion of the received signal that includes frequencies lower than the first frequency; and (b) determining whether a person is present based on the difference between the upper and lower portions It is configured as follows.

[0021] Such a system is more robust in detecting whether a person is actually present by mitigating false positives caused by broadband noise that is not indicative of motion. (outside 4) It is also more robust with respect to other devices that may emit ultrasonic signals at JPEG0007621345000007.jpg12127. Furthermore, the system does not rely on the emitter and receiver being temporally synchronized.

[0022] The system may have any one of the following optional configurations, or any compatible combination:

[0023] The determination may be based on the difference between the upper and lower portions of the received signal.

[0024] The upper portion of the received signal may include higher frequencies immediately surrounding the first frequency, and the lower portion of the received signal may include lower frequencies immediately surrounding the first frequency.

[0025] The processor may be further configured to divide the received signal into a number of bins, each bin representing a range of frequencies in the received signal, the upper portion being upper frequency bins that include portions of the received signal that are at frequencies higher than the first frequency, and the lower portion being lower frequency bins that include portions of the received signal that are at frequencies lower than the first frequency.

[0026] The determination may be based on a difference between a normalized power estimate of the upper frequency bin and a normalized power estimate of the lower frequency bin, and the normalization factor may be the sum of the power estimates of the upper and lower frequency bins.

[0027] Determining the presence of a person may include determining a logit function of the normalized power of the upper frequency bins. Determining the presence of a person may include determining a logit function of the normalized power of the lower frequency bins. Determining the presence of a person may include determining a first logit function of the normalized power of the upper frequency bins and determining a second logit function of the normalized power of the lower frequency bins.

[0028] The logit function is

number

number

number

[0029] The processor may be configured to repeat steps (a)-(b) at a predetermined rate. Each iteration of (a)-(b) may be performed over a time window of the received signal. The time window may be about 20 ms.

[0030] The processor may be further configured to determine whether a person is moving towards or away from the receiver after it is determined that a person is present. Determining whether a person is moving towards or away from the receiver may be further based on a first likelihood ratio test to determine whether a person is moving towards the receiver and a second likelihood ratio test to determine whether a person is moving away from the receiver. A log-likelihood ratio may be derived for each likelihood ratio and may be recursively calculated from previous values ​​of the respective log-likelihood ratio.

[0031] When a user is determined to be present, the processor may be configured to take the video conferencing device out of standby mode.

[0032] In some embodiments, there may be a first receiver and a second receiver, the first receiver configured to receive reflections of ultrasonic signals having frequency components higher than a first frequency, and the second receiver configured to receive reflections of ultrasonic signals having frequency components lower than the first frequency. Thus, the first receiver may receive an upper portion of the received signal, and the second receiver may receive a lower portion of the received signal. Determining the difference between the upper portion of the received signal and the lower portion of the received signal may include determining whether the first receiver and / or the second receiver received the respective signal. If both receivers receive the signal, the received signal may be determined to be a false positive. If only one receiver receives the signal, it may be determined that a person is present.

[0033] Further aspects of the invention provide a computer program comprising code which, when run on a computer, causes the computer to carry out the method of the first aspect, a computer readable medium storing a computer program comprising code which, when run on a computer, causes the computer to carry out the method of the first aspect, and a computer system programmed to carry out the method of the first aspect.

[0034] The optional features of the above-mentioned aspects of the invention are applicable alone or in any combination with any aspect of the invention.

[0035] Embodiments of the invention will now be described, by way of example only, with reference to the accompanying drawings, in which: [Brief description of the drawings]

[0036] [Figure 1] 1 illustrates a system according to an embodiment of the present invention. [Diagram 2]2 shows a spectrogram (time-frequency plot) of a point in space near the microphone of the system of FIG. 1. [Diagram 3] FIG. 2 is a flow diagram of a method according to an embodiment of the present invention. [Figure 4] When receiving a wideband signal

number

number

number

number

number

[0037] Aspects and embodiments of the present invention will now be discussed below with reference to the accompanying drawings. Further aspects and embodiments will be apparent to those skilled in the art.

[0038] FIG. 1 shows a room containing a system of the invention. The system transmits a first frequency (also called a tone). (outside 5) JPEG0007621345000016.jpg10127(outside 6) JPEG0007621345000017.jpg11127 is 22000 Hz, but may take any ultrasonic frequency value (e.g., at least 20 kHz and up to 24 kHz). The emitter emits a tone continuously. In this example, the emitter is a speaker that is also used in a videoconferencing device. The system also includes a receiver 103, which in this example is also a microphone that is part of the videoconferencing device. The receiver: (outer 7) The system is configured to detect reflections of the Doppler shifted signals as well as the ultrasonic signals present in JPEG0007621345000018.jpg12127. The system also includes one or more processors (not shown), which are configured to use the signals received from the receiver 103 to determine whether a person is present in the room.

[0039] As the ultrasonic signal propagates through the room, it reflects off various objects and / or interfaces. For example, after reflecting off a wall, an unshifted reflection 104, i.e. (outside 8) The stationary reflection at JPEG0007621345000019.jpg12127 is returned to the receiver 103. This unshifted reflection is ignored since it provides little information about the presence of a person in the room (indicated by motion). On the other hand, the upwardly shifted reflection 106 is returned to the receiver after reflecting off a person 105 moving towards the receiver 103. The upwardly shifted reflection 106 is (outer 9) JPEG0007621345000020.jpg12127. This upshifted reflection provides information about the presence of a person in the room, and in particular that the person is moving towards the receiver 103. Similarly, a downshifted reflection 108 is returned to the receiver after reflecting off a person 107 moving away from the receiver 103. The downshifted reflection 108 (Outside 10) JPEG0007621345000021.jpg11127. This downshifted reflection also provides information about the presence of people in the room, and in particular that people are moving away from the receiver 103.

[0040] However, as previously mentioned, transient noises 110, such as those generated by a slamming door 109 or clapping hands, have a relatively wide frequency range and may contain components having the same or similar frequencies as the upshifted or downshifted components. These transient noises that do not originate from the emitter 101 can be interpreted by the receiver (or a processor connected to it) as indicative of the presence of a person.

[0041] Figure 2 is a spectrogram (time-frequency plot) of a region of space near a receiver illustrating this principle. A tone is radiated by an emitter at 22000 Hz, thus providing a narrowband signal that extends over a long period of time. At t0, a person walks towards the receiver at a first speed, thus an upshifted signal 201 is received by the receiver. In this example, the person then increases their speed towards the receiver, resulting in a further upshifted signal 202 being received by the receiver. The person then stops, and the upshifted signal is not received. At t1, the person then walks away from the receiver, thus a downshifted signal 203 is received by the receiver.

[0042] Next, at time t2, a transient signal 204 is received by the receiver. This signal is transitory in that it has a finite presence on the "x" axis. However, the transient signal contains components at the same frequencies as the upshifted signal 201, the further upshifted signal 202, and the downshifted signal 203. There is then a risk that a processor connected to the receiver may interpret the transient signal 204 as an indication that a person is present.

[0043] Figure 3 shows a flow diagram of a method according to an embodiment of the invention. In a first step 301, an ultrasonic tone is generated at a frequency (Outside 11) JPEG0007621345000022.jpg13127. Next, in step 302, the signal received by one or more receivers is transformed from microphone frames, i.e. short time frames of the microphone signal, into the time-frequency domain. This is done over a short time window or time frame of the received signal (e.g. 20 ms) and the received signal is transformed into the frequency domain using a filter bank. This

number

number

[0044] Next, in step 303, the logit of the normalized Doppler shift power is calculated. (Outside 13) Let JPEG0007621345000026.jpg15127 denote the frequency bin index that contains the frequency of the radiated tone (e.g., 22000 Hz). Then the logit of the normalized power of the Doppler shift is defined as

number

number

number

number

[0045] this is, (Outside 17) JPEG0007621345000034.jpg11127 means that it is a number between 0 and 1, and can be likened to a probability. In that case, the logit function is (Outside 18) This probability is transformed to take a value between JPEG0007621345000035.jpg12127.

[0046] After this has been calculated over a given time window, the method moves to steps 304 and 307, which are performed simultaneously. In step 304, a first log-likelihood ratio, i.e. log-likelihood ratio 0, is updated based on the calculated logits to indicate how likely it is that there is movement towards the receiver. At the same time, in step 307, a second log-likelihood ratio, i.e. log-likelihood ratio 1, is updated based on the calculated logits to indicate how likely it is that there is movement away from the receiver.

[0047] In general, the likelihood ratio does not have a closed-form expression, and therefore it is computationally expensive to calculate. However, because the values ​​of L(t) are known to be approximately independent and normally distributed, a simple formula for the log-likelihood ratio can be derived.

[0048] A log-likelihood ratio, of a type known per se in the art, has the following general formula:

number

number

number

[0049] Furthermore, the log-likelihood ratios can be recursively calculated using the previous and new values ​​of L(t). Initializing the log-likelihood ratios may include initializing them to zero, which means that the initial likelihood ratios are 1. This means that at initialization, the probability of motion is the same as the probability of no motion.

number

number

number

number

[0050] In these equations, δ is the expected magnitude change, i.e., the expected deviation in the mean of L(t) from its mean zero after the exercise. It is a constant that is set during the initialization phase. The variance of L(t) is (Outside 19) This is denoted as JPEG0007621345000043.jpg9127, which is either set to a fixed value during the initialization phase or estimated as the value of L(t) calculated.

[0051] Once the log-likelihood ratios have been calculated using some or all of the information from the calculated logits, each log-likelihood ratio is compared to a threshold in steps 305 and 308. If one of the likelihood ratios exceeds its threshold, i.e., "yes" in step 305 and / or step 308, movement towards or away from the receiver can be determined in steps 306 and 309, respectively.

[0052] Once motion is detected or not (steps 305 and 308: No), the method returns to step 302 for a new time window. In this way, the motion detection method can operate continuously. In the example discussed below, the value of δ is chosen as 5, (outside 20) JPEG0007621345000044.jpg12127 was estimated from the value of L(t). (outside 21) The estimate for JPEG0007621345000045.jpg10127 is obtained using a maximum likelihood estimator over a time window when it is known that there is no motion. The maximum likelihood estimate is the L(t) over t over a time window when it is known that there is no motion. 2 It can be calculated as the average of

[0053] The logit function described above is particularly suitable for motion detection due to three reasons: (1) its immunity to transient noise, (2) its normally distributed values, and (3) its indication of motion direction.

[0054] First, taking point (1), FIG. 4 shows the lower frequency bins when a transient wideband signal is received.

number

number

number

[0055] The upper graph in Figure 4 shows the

number

number

[0056] Thus, as can be seen in the lower graph of FIG. 4, which is a plot of L(t), the approximately equal contributions in the upper and lower parts of the signal are cancelled out by their ratio in L(t), and thus the logit function has noise immunity to transient wideband noise or signals.

[0057] Referring now to point (2), which is a normally distributed value, FIG. 5 shows a plot of L(t) along with the corresponding histogram when no motion is occurring. In the absence of motion, and therefore no Doppler shift, the values ​​of L(t) over t=0, 1, 2, ... follow a distribution similar to a normal distribution. This is verified by experiments, the results of which are shown in the histogram plot at the bottom of FIG. 5. It is also expected that the values ​​are largely independent of each other. As mentioned above, since these values ​​are independent of each other and normally distributed, a simple formula for the log-likelihood ratio can be derived.

[0058] Next, regarding point (3), detection of motion, Figure 6 shows the motion detection results when motion is occurring.

number

number

[0059] FIG. 7 shows a plot of L(t) and corresponding plots of log-likelihood ratio and detection threshold. The upper plot of FIG. 7 is of L(t) and corresponds to the lower plot of FIG. 6. The lower plot of FIG. 7 is a plot of log-likelihood ratio versus detection threshold for detecting motion towards or away from the receiver. Line 701 represents the time-domain motion of the receiver as discussed above.

number

number

[0060] As can be seen, line 701 rises above threshold 703 between 4 and 5 seconds, indicating movement towards the receiver. At about 7 seconds, line 702 rises above threshold 703 while line 701 falls below threshold 703, indicating movement away from the receiver.

[0061] Fig. 8 is a flow diagram of a modified method according to an embodiment of the present invention. Where Fig. 8 shares structure with the flow diagram shown in Fig. 3, equivalent structure is indicated by equivalent reference numerals. In contrast to the method shown in Fig. 3, the method of Fig. 8 utilizes two logit functions, a first logit function L1(t) adjusted to better detect motion towards the video system and a second logit function L2(t) adjusted to better detect motion away from the video system.

[0062] The logit function discussed with respect to FIG. 3 can be improved based on the following observation: During the movement towards the videoconferencing device in the room, reflections from moving objects will cause higher received frequencies. However, reflections that hit the back wall, then hit a moving object, then hit the back wall again before being received by the receiver in the videoconferencing device will have lower received frequencies. Note that the received frequencies then constitute a range of Doppler shifts. With the movement towards the videoconferencing device, most of these Doppler shifts are at higher frequencies, but some are at lower frequencies.

[0063] Therefore, L(t) can be formulated as follows:

number

number

number

number

number

number

number

[0064] This is shown in steps 303a-309a and 303b-309b, with both logit functions running in parallel.

[0065] While the present invention has been described in conjunction with the exemplary embodiments above, many equivalent modifications and variations will be apparent to those skilled in the art given this disclosure. Accordingly, the exemplary embodiments of the present invention described above are considered to be illustrative and not limiting. Various changes may be made to the described embodiments without departing from the spirit and scope of the invention. [Prior art documents] [Patent documents]

[0066] [Patent Document 1] U.S. Patent No. 9,319,633B1

Claims

1. 1. An ultrasound-based human detection method, comprising: (a) emitting an ultrasonic signal from an emitter, the ultrasonic signal having a first frequency [0010] and irradiating the component comprising: (b) receiving a reflection of the ultrasonic signal, the received signal including components at frequencies greater than the first frequency and components at frequencies less than the first frequency; (c) determining a difference between an upper portion of the received signal that includes frequencies higher than the first frequency and a lower portion of the received signal that includes frequencies lower than the first frequency; (d) determining whether a person is present based on a difference between the upper portion and the lower portion; (e) dividing the received signal into a plurality of bins, each bin representing a range of frequencies in the received signal, the upper portion being upper frequency bins that include portions of the received signal that are at frequencies higher than the first frequency, and the lower portion being lower frequency bins that include portions of the received signal that are at frequencies lower than the first frequency; determining the presence of a person in step (d) includes determining a logit function of the normalized power of the upper frequency bins; method.

2. The method of claim 1 , wherein the determination is based on a difference between the upper frequency portion and the lower frequency portion.

3. 3. The method of claim 1, wherein the upper portion of the received signal includes higher frequencies immediately adjacent to the first frequency, and the lower portion of the received signal includes lower frequencies immediately adjacent to the first frequency.

4. The method of claim 1 , wherein the determination is made based on a difference between a normalized power estimate of the upper frequency bin and a normalized power estimate of the lower frequency bin.

5. The method of claim 4 , wherein the normalization factor is a sum of power estimates of the upper and lower frequency bins.

6. The logit function is [0025] It takes the form of Where: [0030] is a coefficient representing the upper frequency bin at time t, [0045] is a coefficient representing the lower frequency bin at time t; The method of claim 1.

7. The method of any one of claims 1 to 6, wherein steps (b) to (d) are repeated at a predetermined rate.

8. 8. The method of claim 1, further comprising the step of determining, after it has been determined that a person is present, whether the person is moving towards or away from the receiver.

9. Determining whether the person is moving towards or away from the receiver includes: A comparison of a first log-likelihood ratio indicative of a likelihood of a person moving towards the receiver with a predetermined threshold; and 10. The method of claim 8, further based on comparing a second log-likelihood ratio, indicative of a likelihood of a person moving away from the receiver, to a predetermined threshold.

10. The method described in claim 9, wherein the first log-likelihood ratio is derived based on a ratio of the likelihood that the person is moving towards the receiver to the likelihood that the person is not moving, and the second log-likelihood ratio is derived based on a ratio of the likelihood that the person is moving away from the receiver to the likelihood that the person is not moving, and each of the first log-likelihood ratio and the second log-likelihood ratio is recursively calculated from previous values.

11. The method according to any one of claims 1 to 10, wherein when it is determined that a person is present, the method comprises the step of taking the video conferencing device out of standby mode.

12. A system for detecting a person, comprising: First Frequency [0050] an emitter configured to emit an ultrasonic signal having a component at one or more receivers configured to receive reflections of the ultrasonic signals; one or more processors, the processor comprising: in response to the receiver receiving a received signal including components at frequencies greater than the first frequency and components below the first frequency, (a) determining a difference between an upper portion of the received signal that includes frequencies higher than the first frequency and a lower portion of the received signal that includes frequencies lower than the first frequency; (b) determining whether a person is present based on a difference between the upper portion and the lower portion; (c) dividing the received signal into a number of bins; It is configured as follows: each bin represents a range of frequencies in the received signal, the upper portion being upper frequency bins that include portions of the received signal that are at higher frequencies than the first frequency, and the lower portion being lower frequency bins that include portions of the received signal that are at lower frequencies than the first frequency; determining the presence of a person in the configuration of (b) includes determining a logit function of the normalized power of the upper frequency bins; system.

13. The system of claim 12 , wherein the determination is based on a difference between the upper and lower portions of the received signal.

14. 14. The system of claim 12 or 13, wherein the upper portion of the received signal includes higher frequencies immediately adjacent to the first frequency, and the lower portion of the received signal includes lower frequencies immediately adjacent to the first frequency.

15. The system of claim 12 , wherein the determination is made based on a difference between a normalized power estimate of the upper frequency bin and a normalized power estimate of the lower frequency bin.

16. The system of claim 15 , wherein the normalization factor is a sum of the power estimates of the upper and lower frequency bins.

17. The logit function is [006] It takes the form of Where: [0070] is a coefficient representing the upper frequency bin at time t, [0080] is a coefficient representing the lower frequency bin at time t; The system of claim 12.

18. A system according to any one of claims 12 to 17, wherein the processor is configured to repeat steps (a)-(b) at a predetermined rate.

19. The system of any one of claims 12 to 18, wherein the processor is further configured to determine, after it has been determined that a person is present, whether the person is moving towards or away from the receiver.

20. 20. The system of claim 19, wherein determining whether the person is moving toward or away from the receiver is further based on comparing a first log-likelihood ratio indicating a likelihood that the person is moving toward the receiver with a predetermined threshold, and comparing a second log-likelihood ratio indicating a likelihood that the person is moving away from the receiver with a predetermined threshold.

21. The system of any one of claims 12 to 20, wherein the processor is configured to take the video conferencing device out of standby mode when it is determined that a user is present.

Images