Gesture recognition system

Abstract

The present invention discloses a gesture recognition system comprising: at least one sensor (1) and at least one controller (2) including at least one processor (3). The at least one controller (2) further includes a software. A power source is configured to power the at least one sensor (1) and the at least one controller (2). The gesture recognition system further comprises at least one equipment and / or at least one device and an actuator configured to activate the at least one equipment and / or the at least one device. The at least one sensor (1) is located within an area of use within a static or moving environment or entity and configured to communicate with the at least one controller (2). The number of the at least one sensor (1) is at least one less than the number of the at least one equipment and / or at least one device.

Description

[0001]Gesture recognition system TECHNICAL FIELD The present invention relates to a gesture recognition system that can be used in any area of use such as, for example, buildings and / or vehicles such as, for example, commercial and / or military aircraft where equipment can be activated, for example, by a passenger and / or a crew member. Such a gesture recognition system can be used, for example, for cabin equipment activation and / or device activation in vehicles such as, for example, aircraft. BACKGROUND ART For example, an aircraft cabin hosts several individual equipment and / or individual devices which can be triggered and activated by passengers and / or by crew members. Such equipment and / or devices are generally composed of at least one sensor, which is either a mechanical or an electrical sensor and which triggers an actuator for activating the functionalities of each individual equipment and / or each individual device. Such equipment and / or devices might for example include a reading light integrated into a passenger service unit, or an infrared sensor designed for a water faucet, such as those found in restrooms. PROBLEMS ASSOCIATED WITH THE PRIOR ART Most of the existing individual equipment and / or individual devices in the prior art are stand- alone systems which do not communicate between each other and / or with the cabin management system and which are not even capable to do such a communication. The current products in the prior art include at least one sensor per function of activation of each individual equipment and / or each individual device. These sensors usually only provide simple and limited information, which are simple and limited binary information such as, for example, the mechanical pressure threshold for a mechanical switch. Furthermore, said individual equipment and / or these individual devices of the prior art lack the capability to store any data concerning their usage, for example, frequency of activation, which could be further analyzed for design improvement and / or predictive maintenance. TECHNICAL OBJECTIVES OF THE INVENTION The main technical problems to be solved by the present invention are: - Reducing the number of individual sensors in the currently existing prior art, - Collecting and centralizing the data in a singular system, - Achieving more accurate activation of the equipment and / or device based on real intention of the subject to further improve the passenger and cabin crew experience and comfort, - Collecting the output data of the artificial intelligence algorithm to analyze and further improve the product design of the present invention with respect to economic and ecological aspects such as, for example, reducing unintentional activation of a water faucet and / or a reading light, - Getting more accurate data with further information concerning the behavior and motion of passengers and / or crew members compared to existing limited sensor information such as, for example, the presence or absence of an item, and - Improving hygiene and / or maintenance by using touchless activation and minimizing usage of conventional mechanical switches. SUMMARY OF THE INVENTION A gesture recognition system according to the present invention is capable of solving the above objectives with the described technical features disclosed within these application documents. The gesture recognition system can be used in any kind of static or moving environment or entity as further described below. Such an environment or entity will be described as area of use throughout this application. The gesture recognition system can be used in any area of use such as vehicles such as transport vehicles such as, for example, aircraft, trains, busses, trucks, ships or cars, more particularly, passenger transport vehicles for passenger transportation such as, for example, passenger aircraft, passenger trains, passenger busses, passenger trucks, passenger ships or passenger cars, even more particularly, respective lavatories, cabins, passenger and / or crew rest compartments, galleys and / or kitchenettes on said passenger transport vehicles such as, for example, a lavatory, a cabin and / or a galley of an aircraft, a lavatory, a cabin, a galley and / or a kitchenette of a train, a lavatory, a cabin, a galley and / or a kitchenette on a bus, a lavatory, a cabin, a galley and / or a kitchenette on a truck, a lavatory, a cabin, a galley and / or a kitchenette on a ship or lavatory, a cabin, a galley and / or a kitchenette of a RV (recreational vehicle). The gesture recognition system can also be used in any area of use such as buildings, houses, flats or immobile installations, such as a lavatory, a cabin, a galley and / or a kitchenette thereof. Examples for a device or equipment encompass touchless, pushbutton, mechanical, electromechanical faucets and / or lights, soap dispensers or water dispensers in a lavatory or galley compartment, or disinfection dispensers with a location in the aircraft cabin. Examples for a device or equipment may further encompass cabin attendant call units, seat inclination mechanisms, gasper switches, and / or opening / locking mechanisms of an overhead stowage compartment. The terms “device” and “equipment” are employed interchangeably, their meaning, however, is understood in the conventional understanding of each word and should not be considered as synonyms. TECHNICAL SOLUTIONS AND ADVANTAGEOUS EFFECTS OF THE INVENTION The present invention aims to replace and / or reduce the number of existing sensors of the several individual equipment and / or individual devices by providing at least one gesture recognition system, which can analyze and recognize the gesture of the passengers and / or the crew members and then trigger the at least one actuator to activate the respective individual equipment and / or respective individual device. This gesture recognition system of the present invention is intended to be capable to be integrated, for example, in the locations mentioned above such as, for example, any cabin area of commercial and / or military aircraft. The system of the present invention can further centralize management of the data to sense and trigger several equipment and / or devices simultaneously, therefore reducing the number of individual sensors of the targeted equipment and / or targeted devices. Examples could be operation of a reading light in the cabin, a seat inclination function, and / or activating a water faucet in the lavatory, but the present invention is not limited thereto and relates to any equipment and / or device within the locations mentioned above. Furthermore, this present invention for gesture recognition can differentiate between intentional and non-intentional activation caused by gesture. For example, the present invention can differentiate if an activation through the head of a passenger activating his or her reading light or personal items such as hand bags or if activating the water faucet in the lavatory is intentional or non-intentional. This can be achieved by training an AI method with possible non-intentional motions, which shall not activate the equipment and / or device. The gesture recognition system of the present invention can integrate an artificial intelligence model which can accurately analyze and predict the intention of a passenger and / or a crew member through analysis of their movements and positioning data collected by one or several of the at least one sensor. The at least one controller can trigger signals for activation of one and / or several cabin equipment and / or one and / or several devices simultaneously based on the output of the artificial intelligence algorithm. By implementing this invention, the following aspects can be improved: - Reducing the number of individual sensors in the currently existing prior art, - Collecting and centralizing the data in one system, - Activating more accurately the equipment based on real intention of the subject to further improve the passenger experience and comfort, - Collecting the output data of the artificial intelligence algorithm to analyze and further improve the product design of the present invention with respect to economic and ecological aspects such as, for example, reducing unintentional activation of a water faucet and / or a reading light, - Getting more accurate data with further information concerning the behavior and motion of passengers and / or crew members compared to existing limited sensor information such as, for example, detecting the presence or absence of an item, and - Improving hygiene and / or maintenance by using touchless activation and reducing existing mechanical switches. Efforts have been made in training the artificial intelligence model to accurately classify the input data of the at least one sensor based on the intentions of the subject and remove the unintentional motion for the activation of the equipment and / or device and implement the model in a system to activate various equipment and / or various devices such as, for example, lavatory equipment. The artificial intelligence model of the present invention can identify more complex situations compared to existing solutions in the prior art and therefore can predict more accurately the intention of the passenger and / or the crew member and differentiate between intentional and unintentional activation instances. Moreover, the present invention gives the possibility to collect and record the sensor data and the analysis process of the data. DESCRIPTION OF THE DRAWINGS Fig.1 shows a gesture recognition system architecture for one of the at least one sensor. Fig.2 shows an example of a gesture recognition system architecture in a lavatory environment according to an embodiment of the present invention. Fig.3 shows an example of data provided by a sensor of a gesture recognition system architecture. Fig.4 shows an example of a gesture recognition system architecture in an overhead cabin compartment. DETAILED DESCRIPTION OF THE DRAWINGS Fig.1 shows the gesture recognition system architecture of the present invention for one sensor (1). The motion and / or position of a passenger and / or a crew member is recognized by the sensor (1). The gesture data is transmitted from the sensor (1) to the gesture controller (2), which includes a respective software and / or artificial intelligence capability. Said gesture data is analyzed and a gesture recognition takes place that can differentiate between intentional and non-intentional activations caused by a gesture. Based on said gesture recognition the gesture controller (2) can trigger signals for respective equipment and / or respective devices. Fig.2 shows an example of the gesture recognition system of the present invention in a lavatory environment. A sensor (1), for example located at a position 1, and a controller (2), for example located at a position 2, located for example above the ceiling (4), for example located at a position 4, analyze the motion of a passenger or crew member (7), for example located at a position 7. The analysis is directed towards an equipment and / or a device such as, for example, a waste flap (8), which could be located at a position 8. The gesture recognition system comprises at least one sensor (1), for example located at a position 1, and at least one controller (2), for example located at a position 2. Said at least one controller (2) includes a processor (3), for example located at a position 3. Said processor (3) operates with a software using an artificial intelligence algorithm. The type of the at least one sensor (1) is not limited to a specific type and can, for example, be an optical sensor such as, for example, an optical camera, Lidar, a time-of-flight sensor or a camera, a radar sensor, an ultrasonic sensor, a thermal sensor, or a thermal camera. The controller (2), for example located at a position 2, can be electrically powered by an aircraft power system or by a separate power system. It integrates a power module to deliver electrical energy to the at least one sensor (1), for example located at a position 1. The at least one sensor (1) can be integrated in various different locations, for example within a cabin of a vehicle. Examples include within a ceiling (4), for example located at a position 4, in a seat (5), for example located at a position 5 (cf. Fig.4), or in a passenger service unit (6), for example located at a position 6 (cf. Fig.4). This strategy ensures a wide field of view from various locations and accurate information about the position and motion of a passenger and / or a crew member. The at least one sensor (1), for example located at a position 1, can communicate with the controller (2), for example located at a position 2, via wire transmission or wireless communication and can transmit the data concerning the position and motion of a passenger or a crew member (7), for example located at a position 7. The format of the sensor data is not particularly limited and can be for example point cloud data, picture data and / or energy amplitude data that can be analyzed by the processor (3), for example located at a position 3, of the controller (2), for example located at a position 2. The data are first pre-processed in order to remove all redundant information and adjust their input format, for example by reducing dimensions or sizes of the data. The artificial intelligence algorithm developed to analyze the data provided by the at least one sensor (1), for example located at a position 1, integrates either a supervised method or an unsupervised method including a deep learning algorithm (artificial neural network) or both methods in sequence. The artificial intelligence model, which is previously trained using training data in a similar environment, classifies the data in several defined classes depending on the type of equipment to be activated. By using a large quantity of training data, the artificial intelligence algorithm can differentiate between intentional activation and unintentional activation of the equipment and / or the devices, for example, a head of passenger touching the reading light switch. Based on the probability of the different classes, the controller (2), for example located at a position 2, sends a trigger signal to the corresponding equipment and / or device to be activated. The artificial model can be continuously improved during the operational use of the system since the new data collected in the building or vehicle such as, for example, a cabin can be employed to retrain the model. As an additional feature the output of the artificial intelligence algorithm, for example, frequency and / or probability of class activation, can be stored for later design improvement and passenger and crew member behavior analysis. Fig.3 shows an example of the data provided by the at least one sensor (1) where a passenger or a crew member (7), for example located at a position 7, puts his or her hand above a waste flap (8), for example located at a position 8. Fig.4 shows an example of the gesture recognition system in the overhead cabin compartment. The at least one sensor (1), for example located at a position 1, is located above a passenger seat (5) and analyzes the gesture of the passenger and / or the crew member to activate for example a reading light (9), for example located at a position 9. ALTERNATIVE EMBODIMENTS This invention describes a solution for a gesture recognition system in an aircraft, but similar areas of use as stated above could be used for various equipment and / or for various devices. INDUSTRIAL APPLICABILITY This invention can be applied, for example, in vehicles such as, for example, commercial and / or military aircraft. The present invention can be used in any areas of commercial or military aircraft where equipment and / or devices can be activated by passengers and / or crew members. LIST OF REFERENCE NUMERALS 1 sensor 2 controller 3 processor 4 ceiling 5 seat 6 service unit 7 person (passenger or crew member) 8 waste flap 9 light

Claims

AMENDED CLAIMS received by the International Bureau on 26 June 2024 (26.06.2024)1 . A gesture recognition system comprising: at least one sensor (1), at least one controller (2) including at least one processor (3 ), the at least one controller (2) further including a software, a power source configured io power the at least one sensor (1) and the at least one controller (2), at least one equipment and / or at least one device, an actuator configured to activate the at least one equipment and / or the at least one device, wherein the at least one sensor (1 ) is located within an area of use within a static or moving environment or entity and configured to communicate with the at least one controller (2), wherein the number of the at least one sensor (1) is at least one less than the number of the at least one equipment and / or at least one device, characterized in that the software in the at least one controller (2) uses an artificial intelligence algorithm,Wherein sensor data acquired by the at least one sensor (3) are first pre-processed in order to remove all redundant information and adjust their input format, the artificial intelligence model - is previously trained using training data in. a similar environment,- classifies the data in several defined classes depending on the type of equipment to be activated,AMENDED SHEET (ARTICLE 19)- by using a large quantify of training data, can differentiate between intentional activation and unintentional activation of the equipment and / or the devices, the controller, based on the probability of the different classes is configured to send a trigger signal to the corresponding equipment and / or device to be activated,2. A gesture recognition system according to claim 1 wherein tile removal of all redundant information and adjustment of their input format is achieved by reducing dimensions or sizes of the data.

3. A gesturerecognition system according to any of the preceding claims, wherein the output of the artificial intelligence can be stored for later design improvement and passenger and crew member behavior.

4. The gesture recognition system according to claim 1, wherein the gesture recognition system is configured to communicate between the at least one equipment and / or the at least one device and with the cabin management system.

5. The gesture recognition system according to claim 1 or 2, wherein the data of the at least one equipment and / or the at least one device can be stored in the gesture recognitionsystem.

6. The gesture recognition system according to any of the preceding claims, wherein the artificial intelligence algorithm can integrate a supervised method and / or an unsupervised method including a deep learning algorithm: or both methods in sequence.

7. The gesture recognition system according to any of the preceding claims, wherein the data from the at least one sensor (1) to the at least one controller (2) is transmitted via a wire connection.AMENDED SHEET (ARTICLE 19)8. The gesture recognition system according to any of the claims 1 to 5, wherein the data from the at least one sensor (1) to the at least one controller (2) is transmitted via wireless communication.

9. The gesture recognition system according to any of the preceding claims, wherein the format of the data of the at least one sensor (1) can be point cloud data, and / or picture data, and / or energy amplitude data.10 The gesture recognition system according to any of the preceding claims, wherein the at least one sensor (1) is a touchless sensor and replaces mechanical switches in order to improve hygiene and reduce maintenance.

11. The gesture recognition system according to any of the preceding claims, wherein the at least one sensor (I) can be one or more of the following sensors (!): an optical sensor such as, for example, an optical camera, Lidar, a time-of-flight sensor or a camera, and / or a radar sensor, and / or an ultrasonic sensor, and / or a thermal sensor, and / or a thermal camera.

12. The gesture recognition system according to any of the preceding claims, wherein the at least one sensor (1 ) is located at at least one location within the area of use, wherein the at least one location can be a ceiling (4), and / or a seat (5), and / or a service unit (6), and / or a lavatory, and / or a galley, and / or a passenger and / or crew rest compartment.AMENDED SHEET (ARTICLE 19)

Images