| (19) |
 |
|
(11) |
EP 4 019 448 A1 |
| (12) |
EUROPEAN PATENT APPLICATION |
| (43) |
Date of publication: |
|
29.06.2022 Bulletin 2022/26 |
| (22) |
Date of filing: 22.12.2020 |
|
| (51) |
International Patent Classification (IPC):
|
| (52) |
Cooperative Patent Classification (CPC): |
|
B66B 5/0012 |
|
| (84) |
Designated Contracting States: |
|
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL
NO PL PT RO RS SE SI SK SM TR |
|
Designated Extension States: |
|
BA ME |
|
Designated Validation States: |
|
KH MA MD TN |
| (71) |
Applicant: Kleemann Hellas SA |
|
61100 Kilkis (GR) |
|
| (72) |
Inventor: |
|
- Georgiadis, Georgios
55135 Thessaloniki (GR)
|
| (74) |
Representative: Chatzara, Viktoria |
|
Rokas Law Firm
Boukourestiou 25A 10671 Athens 10671 Athens (GR) |
|
| |
|
| (54) |
PASSENGER EMERGENCY DETECTION SYSTEM |
(57) The invention refers to a passenger emergency detection system which detects an emergency,
as fainting or any other medical situation that affects the ability to ask for help
by yourself, through a camera that is placed in the elevator cabin. The applied camera
calibration algorithm permits the monitor of any area, regardless its size. Passenger's
fall is detected based on characteristics like vertical velocity and area variance.
The system is connected to the elevator controller so the corresponding signal sets
on the alarm, increases the cabin ventilation and moves the cabin to the ground floor
with the door on the open position. Alongside, the help signal is sent to an emergency
centre.
|

|
[0001] Present invention refers to a passenger emergency detection system in an elevator.
The above-mentioned system is able to detect an emergency situation, such as loss
of conscience of a passenger, heart attack or any other kind of medical situation
that affects the ability to physically act, through a camera that is placed in the
elevator cabin. Following are described further details about the invention.
[0002] Loss of conscience is an unpleasant event that may occur usually amongst the senior
citizens, patients or pregnant women, but it could also occur in cases of heart attack
or a stroke. This event may cause physical injuries or even mental problems, such
as fear and anxiety. Most of the times is crucial the immediate medical treatment.
[0003] According to the statistical committee of European Lift Association the existing
lifts in Europe are more than 6,000,000. In the meantime, in China is estimated that
in 2019 more than 600,000 new installations took place. As it becomes clear people
spend several of minutes everyday in an elevator while going to work, for shopping
or even in their homes. There is also a wide range of people who use the elevators,
they are people of all ages that may face a medical situation at any time, even while
they are in an elevator cabin.
[0004] According to the state of the art, there is always an emergency button or emergency
stop switch in the elevator cabin, that is used in case of emergency. The result is
usually the simplest form of ringing an alarm in the building or even connecting to
a call center for asking help. The main drawback of these solutions is that the passengers
have to act by themselves, while in several cases they are not able to do it before
falling on the floor or even before getting unconscious.
[0005] The presented invention is a passenger emergency detection system. The first part
of the presented invention concerns the presence of a real-time, multi-space, multi-camera
tracking system to a fall detection system with all the deriving qualities, such as
monitoring any cabin area regardless its size by the use of multiple depth sensors
that retain passengers' individual privacy. The detection system is based on key features
that characterize a fall, such as vertical velocity and area variance, while falling
process is modelled by Hidden Markov Models (HMM). Furthermore, the system produces
alarms, or sends a signal, like an auto dialler, that may call for immediate assistance
to the person that is in need. Moreover, the controller manages the immediate cabin
movement to the ground floor (or any other floor that has been declared as the reference
floor) and door opening, so the person in need is visible from outside. In parallel,
the fan speed is increased so to provide the feeling of additional air to the person
that has fainted out in the cabin.
[0006] The description of the invention is supplemented with the following figures. Each
one is described thoroughly.
[0007] In Figure 1 is presented in detail the way that the system works. One of the most
important aspects is to discriminate whether the passenger has actually fainted out
or just bended over, for example picking up something or tie shoes. For that reason,
the detection method extracts data as vertical velocity and area variance. Moreover,
in case that the passenger remains on the floor several acts are going to take place
and they are all presented in the figure.
[0008] Figure 2 visualize better the idea of the passenger emergency detection system. One
of the main parts of the system is the detection camera (1). The applied camera calibration
algorithm permits the use of multiple cameras that refer to a common coordinate system
in the cabin, so that any area, regardless its size, can be monitored. Moreover, possible
constrictions are handled by deploying a virtual top-view camera based on calibration
data, even though the overall detection-tracking procedure is performed on the horizontal
plane. On the left side of the figure the passenger is standing (2a) in the elevator
cabin, while on the right side is presented a fall event and the passenger is laying
(2b) on the cabin floor. The fall is modelled by HMM based on characteristics like
vertical velocity and area variance from top view of the tracked passenger. The system
is connected to the elevator controller so the corresponding signal sets on the alarm,
increases the cabin ventilation and moves the cabin to the ground floor (or any other
reference floor) with the door (3) on the open position. Alongside, the corresponding
signal (digital or through loT) for help is sent to the proper service, that had been
selected as an emergency contact.
[0009] Finally, Figure 3 shows a fall event in an elevator cabin as it is depicted by the
system camera. It is obvious that it is impossible to have a face recognition and
the system does not record any other personal data of the passengers. Therefore, the
system can be used in public buildings since none personal data is violated. The system
recognizes only the outline of the passengers, while the collected data of vertical
velocity and area variance leads to the activation of emergency procedures as they
are presented in Figure 1.
1. The "Passenger emergency detection system" is characterized in that it is an elevator system comprising of at least one depth analysis camera, that is
installed in the cabin, a software for analyzing the input data from the camera and
a control action system, which is connected to the elevator controller.
2. The invention according to Claim 1, is characterized in that it detects elevator passenger's loss of conscience, or any other medical problem,
resulting in inability of passenger to activate pushing emergency buttons (or switch).
3. The invention according to Claims 1 and 2, is characterized in that it analyzes whether passenger's loss of conscience exceeds a predefined time period,
without recovery to normal passenger condition.
4. The invention according to Claims 1 and 3, is characterized in that after the lapse of the predefined time it initiates automatically set of actions,
such as alarm, call to emergency center, digital message to first aid facilities with
data regarding place, building and elevator where the incident took place.
5. The invention according to Claims 1-4, is characterized in that after lapse of the predefined time it sends the elevator to ground floor, open the
doors in order cabin to be accessible to external help and regulates fans inside cabin
to provide increased circulation of air as needed to passenger in emergency condition.