Configuring an RF-based sensing system

Abstract

The method involves obtaining (101) visual sensor data related to the environment and detecting (103) a specific object based on the visual sensor data. It further includes calculating (105) a radiofrequency signature for each set of radiofrequency signals transmitted and received while a user is within a threshold distance of the specific object. The method determines (107) an evaluation of each radiofrequency signature and selects (109) one based on the evaluations. Additionally, it selects (111) a node combination corresponding to the chosen radiofrequency signature from a plurality of node combinations. The method configures (113) the radiofrequency-based sensing system to detect events associated with the specific object using the selected node combination.

Description

[0001] Configuring an RF -based sensing system

[0002] FIELD OF THE INVENTION

[0003] The invention relates to a system for configuring a radiofrequency-based sensing system.

[0004] The invention further relates to a method of configuring a radiofrequencybased sensing system.

[0005] The invention also relates to a computer program product enabling a computer system to perform such a method.

[0006] BACKGROUND OF THE INVENTION

[0007] RF (Radio Frequency) sensing is a technology that leverages radio waves to detect and monitor changes in an environment or identify the presence and movements of objects and people without the need for visual or physical contact. This method involves transmitting RF signals and analyzing the way these signals arrive at, e.g., are reflected back to, the receiver, allowing for the sensing of motion, location, and even the material composition of objects within its range. RF sensing is utilized across various applications, including smart homes for automation and security, health monitoring for non-invasive tracking of vital signs, industrial automation for monitoring equipment and processes, and retail environments for customer tracking and inventory management. Its capability to operate in non-line-of-sight conditions and through obstacles like walls makes it particularly valuable in scenarios where traditional sensors might be ineffective.

[0008] In the field of RF sensing, various methods have been proposed for selecting an optimal combination of nodes to achieve the highest detection rate. These methods typically involve conducting walk tests both inside and outside the room to identify nodes and establish the appropriate sensitivity levels for accurately detecting the presence of a person within the room. Additionally, these methods aim to minimize false triggers that may occur when a person is walking outside the room (and causing signal disturbances).

[0009] WO 2022 / 157315 Al describes a radio frequency (RF) sensing system that uses multiple RF sensing nodes (e.g., smart lights) to detect motion and activity in a sensing area. The system has a calibration mode where the controller analyzes metadata about the RF nodes (e.g., names, positions) to select a subset of nodes to use for the sensing. During the calibration, the controller outputs instructions to a user device (e.g., smartphone) to guide the user through activities and movements in the sensing area. This allows the system to analyze the RF signals detected by the selected nodes during the user’s movements to calibrate the sensing.

[0010] WO 2022 / 157315 Al describes that augmented reality (AR) can be used on the user device to provide guided instructions and visualizations to the user during the calibration walkthrough. For example, the AR app can overlay arrows and highlights on the camera view to guide the user’s movements. WO 2022 / 157315 Al further describes that the controller can analyze the impact of certain activities and environmental factors (like turning on appliances) on the RF signals, and instruct the user to perform these activities during calibration to understand their effect on the sensing. However, there is still room for improving the system’s effectiveness in performing event detection within an environment.

[0011] US2021185790A1 relates to a controller, system, method, and computer program product for controlling a wireless network to perform radiofrequency -based motion detection.

[0012] US2022413117A1 relates to a context-sensing control device comprising a pair-assignment device comprising: a sensing-node position ascertainment configured to ascertain position information pertaining to respective positions of external RF-sensing nodes with respect to a predefined sensing volume of a RF context-sensing arrangement; and a pairassigning unit connected to the sensing-node position ascertainment unit.

[0013] US2022172622A1 relates to a system for providing a wireless asymmetric network comprises a hub having one or more processing units and at least one antenna for transmitting and receiving radio frequency (RF) communications in the wireless asymmetric network and a plurality of sensor nodes each having a wireless device with a transmitter and a receiver to enable bi-directional RF communications with the hub in the wireless asymmetric network.

[0014] SUMMARY OF THE INVENTION

[0015] It is advantageous to provide a system and method, which can be used to configure an RF -based sensing system to perform more effective event detection.

[0016] In one aspect, the system for configuring a radiofrequency-based sensing system includes at least one input interface. The system also includes at least one configuration interface. The system furthermore includes at least one processor configured to, for each respective specific object of one or more specific objects in an environment, obtain visual sensor data relating to the environment via the at least one input interface, detect, based on the visual sensor data, the respective specific object in the environment, calculate a radiofrequency signature for each of a plurality of sets of radiofrequency signals, each of the plurality of sets of radiofrequency signals being transmitted and received while an user is within a threshold distance of the respective specific object, each of the plurality of sets of radiofrequency signals being transmitted and received by a different node combination of a plurality of node combinations, determine an evaluation of each of the radiofrequency signatures, select one of the radiofrequency signatures based on the evaluations, select a node combination corresponding to the selected radiofrequency signature from the plurality of node combinations, and configure, via the at least one configuration interface, the radiofrequency -based sensing system to detect events associated with the respective specific object by employing the node combination selected for the respective specific object.

[0017] By detecting an object based on visual sensor data, such as data obtained with a camera or LiDAR scanner, and calculating and evaluating signatures of RF signals transmitted and received while a user is near the object, an optimal combination of nodes may be selected for detecting events associated with the object (e.g., walking through a door) in an effective manner. Machine learning may be used to detect the object based on the visual sensor data.

[0018] The visual sensor data may already be obtained for another purpose, thereby allowing a cost-effective system to be realized. As a first example, the visual sensor data may already be obtained to allow a user to place virtual lighting devices in an AR view of the environment and see in AR the effect of light emitted by these lighting devices on the environment before placing the real lighting devices in the environment. As a second example, the visual sensor data may already be obtained as part of a room scan that a user makes of his home or office (e.g., with the RoomPlan app).

[0019] Another advantage of detecting whether a user is near an object based on visual sensor data is that it is not necessary to install and configure beacons for determining an indoor position of the user’s device and not necessary to have access to a map which identifies the locations of important objects.

[0020] By detecting specific objects in the environment and calibrating RF signatures based on these objects, the system may be able to tailor its sensing capabilities more precisely. This object-specific approach allows for more accurate event detection related to each identified object, reducing the likelihood of false positives or irrelevant detections. By calculating and evaluating RF signatures for different node combinations around each specific object, the system may determine for every important object in the environment the most effective combination of nodes to use for sensing, thereby optimizing the sensing accuracy and efficiency for important areas or items within the sensing zone. The system’s use of visual sensor data to aid in the calibration process represents a multi-modal sensing approach. This integration allows for a more nuanced understanding and interpretation of the environment, leveraging the strengths of both visual and RF sensing to enhance overall system performance.

[0021] Implementations may include one or more of the following:

[0022] The system wherein the at least one processor is configured to identify a space in which the user is located, form the node combinations from a collection of nodes associated with the space, instruct each respective node combination of the plurality of node combinations to transmit and receive a respective set of radiofrequency signals in a time period associated with the respective node combination, and calculate the radiofrequency signature for each respective set of radiofrequency signals of the plurality of sets of radiofrequency signals by calculating a radiofrequency signature for each respective node combination of the plurality of node combinations based on the set of radiofrequency signals as received by at least one receiving node of the respective node combination in the time period associated with the respective node combination.

[0023] The system wherein the least one processor is configured to identify the space based on the visual sensor data.

[0024] The system wherein the at least one processor is configured to configure the radiofrequency -based sensing system to detect events associated with the respective specific object by employing the node combination selected for the respective specific object and the radiofrequency signature selected for the respective specific object.

[0025] The system wherein at least one node out of the plurality of node combinations is attached to or integrated in a luminaire located in the environment.

[0026] The system wherein the at least one processor is configured to instruct the node combination selected for the respective specific object to continuously or periodically transmit radiofrequency signals for the purpose of sensing, obtain radiofrequency signatures of the radiofrequency signals as received by at least one receiver of the node combination selected for the respective specific object, compare each of the radiofrequency signatures with a reference radiofrequency signature associated with the node combination selected for the respective specific object, and detect an event associated with the respective specific object based on the comparisons of the radiofrequency signatures with the reference radiofrequency signature.

[0027] The system wherein the reference radiofrequency signature is the radiofrequency signature selected for the respective specific object and the at least one processor is configured to detect the event associated with the respective specific object upon detecting a match between at least one of the radiofrequency signatures and the radiofrequency signature selected for the respective specific object.

[0028] The system wherein the at least one processor is configured to obtain other visual sensor data relating to the environment via the at least one input interface, and detect, based on the comparisons of the radiofrequency signatures with the reference radiofrequency signature, a first type of event associated with the respective specific object or a second type of event associated with the respective specific object in dependence on the other visual sensor data.

[0029] The system wherein the visual sensor data has been captured by at least one of a camera, a light sensor, and a ranging sensor.

[0030] The system wherein the at least one of the camera, the light sensor, and the ranging sensor is embedded in an augmented reality headset or a mobile phone.

[0031] The system wherein the one or more specific objects comprise at least one of a door, a window, a television screen, stairs, a closet, a couch, and a dining table.

[0032] In one aspect, the method of configuring a radiofrequency-based sensing system includes obtaining visual sensor data relating to the environment. The method also includes detecting, based on the visual sensor data, the respective specific object in the environment. The method furthermore includes calculating a radiofrequency signature for each of a plurality of sets of radiofrequency signals, each of the plurality of sets of radiofrequency signals being transmitted and received while an user is within a threshold distance of the respective specific object, each of the plurality of sets of radiofrequency signals being transmitted and received by a different node combination of a plurality of node combinations. The method in addition includes determining an evaluation of each of the radiofrequency signatures. The method moreover includes selecting one of the radiofrequency signatures based on the evaluations. The method also includes selecting a node combination corresponding to the selected radiofrequency signature from the plurality of node combinations. The method furthermore includes configuring the radiofrequencybased sensing system to detect events associated with the respective specific object by employing the node combination selected for the respective specific object. The method may be performed by software running on a programmable device. This software may be provided as a computer program product.

[0033] Moreover, a computer program for carrying out the methods described herein, as well as a non-transitory computer readable storage-medium storing the computer program are provided. A computer program may, for example, be downloaded by or uploaded to an existing device or be stored upon manufacturing of these systems.

[0034] In one aspect, a non-transitory computer-readable storage medium stores a software code portion, the software code portion, when executed or processed by a computer, being configured to perform the method described above.

[0035] As will be appreciated by one skilled in the art, aspects of the present invention may take the form of a device, a method or a computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware implementation, an entirely software implementation (including firmware, resident software, micro-code, etc.) or an implementation combining software and hardware aspects that may all generally be referred to herein as a "circuit", "module" or "system." Functions described in this disclosure may be implemented as an algorithm executed by a processor / microprocessor of a computer. Furthermore, aspects of the present invention may take the form of a computer program product in one or more computer readable medium(s) having computer readable program code stored thereon.

[0036] Any combination of one or more computer readable medium(s) may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer readable storage medium may include, but are not limited to, the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of the present invention, a computer readable storage medium may be any tangible medium that can contain, or store, a program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable signal medium may include a propagated data signal with computer readable program code included therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0037] Program code on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber, cable, RF, etc., or any suitable combination of the foregoing. Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java(TM), Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0038] Aspects of the present invention are described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to implementations of the present invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor, in particular a microprocessor or a central processing unit (CPU), of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer, other programmable data processing apparatus, or other devices create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0039] These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0040] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0041] The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of devices, methods and computer program products according to various implementations of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0042] BRIEF DESCRIPTION OF THE DRAWINGS

[0043] These and other aspects of the invention are apparent from and will be further elucidated, by way of example, with reference to the drawings, in which:

[0044] Fig. l is a block diagram of an implementation of the system;

[0045] Fig. 2 shows an example of a floor plan of an apartment in which the system of Fig. 1 has been installed;

[0046] Fig. 3 is a flow diagram of a first implementation of the method;

[0047] Fig. 4 is a flow diagram of a second implementation of the method;

[0048] Fig. 5 is a flow diagram of a third implementation of the method;

[0049] Fig. 6 is a flow diagram of a fourth implementation of the method; Fig. 7 is a flow diagram of a fifth implementation of the method;

[0050] Fig. 8 is a flow diagram of a sixth implementation of the method; and

[0051] Fig. 9 is a block diagram of an exemplary data processing system for performing the method.

[0052] Corresponding elements in the drawings are denoted by the same reference numeral.

[0053] DETAILED DESCRIPTION

[0054] Fig. 1 shows an implementation of the system for configuring a radiofrequency -based sensing system. In this implementation, the system 21 comprises a mobile device. The mobile device 21 may be a mobile phone, a tablet, or an augmented reality headset, for example.

[0055] In the implementation of Fig. 1, the mobile device 21 is able to control lighting devices 51, 52, 53, 54, 55, 56 via a bridge 45, e.g. using Zigbee technology. The bridge 45 may be a Hue bridge, for example. The bridge 45 is connected to a wireless LAN access point 33, e.g. via Ethernet or Wi-Fi. In the example of Fig. 1, the mobile device 21 is connected directly to the wireless LAN access point 33. Alternatively, the mobile device 21 may be connected to the Internet 31 remotely, e.g., via an LTE or 5G mobile communication network.

[0056] The bridge 45 is also able to communicate with sensors 41,42, e.g. using Zigbee technology. The bridge, the lighting devices, and the sensors form a lighting system and are also the nodes of the RF-based sensing system. The lighting system may be configured to let one or both of sensors 41,42 trigger one or more of lighting devices 51, 52, 53, 54, 55, 56. The sensors 41,42 may be (Hue) motion sensors, for example. The bridge 45 may also act as the controller of the RF-based sensing system, i.e. instructing other nodes, determining RF signatures, detecting events, and performing actions based on these events (e.g., informing the user). The configuration of the lighting system and of the RF-based sensing system may be stored on the bridge 45, for example.

[0057] In an alternative implementation, the mobile device 21 can alternatively or additionally control one or more of the lighting devices 51, 52, 53, 54, 55, 56 without a bridge, e.g., directly via Bluetooth or via an Internet server 37. The Internet server 37 may be operated by a manufacturer of a lighting company, for example. The Internet server 37 is also connected to the Internet 31. Another device than the bridge 45 may act as the controller of the RF-based sensing system. The mobile device 21 comprises a receiver 23, a transmiter 24, a processor 25, an input interface 26 in the form of a LiDAR scanner, memory 27, an input interface 28 in the form of a camera, and a display 29. The processor 25 is configured to, for each respective specific object of one or more specific objects in an environment, obtain visual sensor data relating to the environment via LiDAR scanner 26 and / or camera 28, detect, based on the visual sensor data, the respective specific object in the environment, and calculate a radiofrequency signature for each of a plurality of sets of radiofrequency signals.

[0058] The one or more specific objects may comprise, for example, one or more of a door, a window, a television screen, stairs, a closet, a couch, and a dining table. Each of the plurality of sets of radiofrequency signals is transmitted and received while a user is within a threshold distance of the respective specific object. Each of the plurality of sets of radiofrequency signals is transmitted and received by a different node combination of a plurality of node combinations. The threshold distance may be a few meters, for example.

[0059] The processor 25 is further configured to determine an evaluation of each of the radiofrequency signatures, select one of the radiofrequency signatures based on the evaluations, select a node combination corresponding to the selected radiofrequency signature from the plurality of node combinations, and configure, via configuration interface 24 (i.e. transmitter 24), the radiofrequency-based sensing system to detect events associated with the respective specific object by employing the node combination selected for the respective specific object.

[0060] The visual sensor data may be captured by one or more of a camera, a light sensor, and a ranging sensor. The visual sensor data may be captured by a camera and / or a LiDAR sensor, for example. The LiDAR sensor may comprise an MPPC, APD, or PIN photodiode, for example. LiDAR is normally more accurate than a camera. However, even with a camera, depth (including distances to objects) may be determined, e.g., by using a dual camera or by taking perspective into account. With regard to LiDAR, current technology (e.g., Apple Lidar scanning on iPhone Pro, VisionPro, and other devices) makes it possible to real-time scan a room and make a floorplan (3D) of that room. At the same time, it is possible to detect important objects in the room, e.g. by using machine learning.

[0061] Certain mobile phones, e.g., Apple’s iPhone Pro, already comprise both a camera and a LiDAR sensor. By utilizing multiple sensor types, the system may gather a comprehensive set of data about the environment. Cameras provide visual imagery and ranging sensors (like LiDAR or ultrasonic sensors) measure distances and spatial layouts. This variety allows for a more detailed and nuanced understanding of the sensing area, leading to more accurate and context-aware event detection. Each type of sensor contributes unique data that can be used to verify or elaborate on the information provided by the others. The integration of these data sources may significantly reduce false positives and false negatives, increasing the system’s reliability.

[0062] A set of RF signals may comprise a single RF signal or a sequence of RF signals (over time). From each RF signal set, the mobile device 21 may extract features that uniquely characterize the behavior of the signal(s) as it interacts with the environment. Features might include signal strength, phase, multipath effects, and temporal variations, for example.

[0063] For instance, the signatures may be calculated based on RS SI information or CSI information (e.g. if the RF signals are Wi-Fi signals) of RF signals transmitted and received at a certain time or during a certain period. For RF signals transmitted and received during a certain period, a sub signature may be created per moment during the certain period and an overall signature may be created for the whole period based on the sub signatures. A (sub)signature may be for an RF signal received by a single receiver or for an RF signal received by multiple receivers, for example.

[0064] To evaluate the signatures, a first signature calculated in relation to a certain node combination while the user is near the object may be compared with one or more second signatures calculated in relation to this same node combination while the user is not near the object. A score may be assigned to the first signature based on how well the first signature can be distinguished from the one or more second signatures.

[0065] Normally, multiple signatures are selected for multiple objects. For each respective specific object, one of the radiofrequency signatures is selected based on the evaluations. A node combination is selected for each signature. A node-combination comprises a transmitter and one or more receivers and is also referred to as a transmitterreceiver combination.

[0066] The connections depicted in Fig. 1 are only schematic representations. For example, it is not required that each lighting device communicates directly with bridge 45. The devices of the lighting system may form a mesh network, and physical communication may be routed over multiple nodes in order to keep the distances of each radio connection short.

[0067] For RF-based sensing, a first node might only be able / configured to transmit a beacon to a second node if it would also transmit network traffic to this second node. Alternatively, the first node may be able / configured to transmit a beacon to the second node even if it would not transmit network traffic to this second node. In the former case, if the nodes are part of a star network, e.g., a Wi-Fi network, the RF signatures may represent multi-path disturbances, e.g., from a lighting device to the wireless LAN access point and from the wireless LAN access point to another lighting device.

[0068] In the implementation of the mobile device 21 shown in Fig. 1, the mobile device 21 comprises one processor 25. In an alternative implementation, the mobile device 21 comprises multiple processors. The processor 25 of the mobile device 21 may be a general-purpose processor, e.g. from ARM or Qualcomm or an application-specific processor. The processor 25 of the mobile device 21 may run an Android or iOS operating system for example. The display 29 may comprise an LCD or OLED display panel, for example. The memory 27 may comprise one or more memory units. The memory 27 may comprise solid state memory, for example.

[0069] The receiver 23 and the transmitter 24 may use one or more wireless communication technologies such as Wi-Fi (IEEE 802.11) to communicate with the wireless LAN access point 33, for example. In an alternative implementation, multiple receivers and / or multiple transmitters are used instead of a single receiver and a single transmitter. In the implementation shown in Fig. 1, a separate receiver and a separate transmitter are used. In an alternative implementation, the receiver 23 and the transmitter 24 are combined into a transceiver. Camera 28 may comprise a CMOS or CCD sensor, for example. The mobile device 21 may comprise other components typical for a mobile device such as a battery and a power connector. The invention may be implemented using a computer program running on one or more processors.

[0070] In the implementation of Fig. 1, the system of the invention comprises a mobile device. In an alternative implementation, the system of the invention alternatively or additionally comprises a different device. In the implementation of Fig. 1, the system comprises a single device. In an alternative implementation, the system comprises a plurality of devices, e.g. the mobile device 21 and bridge 45.

[0071] Fig. 2 shows an example of a floor plan of an apartment in which the system of Fig. 1 has been installed. Apartment 61 comprises an (open) kitchen 63, a living room 64, a bathroom 65, a hallway 66, and a bedroom 67. Lighting device 51 of Fig. 1 has been installed in the (open) kitchen 63, bridge 45 and lighting device 52 of Fig. 1 have been installed in the living room 64, and lighting device 53 and sensor 41 of Fig. 1 have been installed in the bathroom 65. Furthermore, lighting device 54 and sensor 42 of Fig. 1 have been installed in the hallway 66 and lighting devices 55, 56 of Fig. 1 have been installed in the bedroom 67.

[0072] In the example of Fig. 2, sensors 41 and 42 are (part of) separate devices. In another example, sensor 41 may be integrated into lighting device 53 and / or sensor 42 may be integrated into lighting device 54. In the example of Fig. 2, the bridge 45, the lighting devices 51, 52, 53, 54, 55, 56 and the sensors 41, 42 are the nodes of the RF-based sensing system. In another example, other kinds of devices like smart plugs may also be used as nodes, e.g., Hue smart plugs, Nami mesh sensors, and / or Nami Wifi sensors. In the example of Fig. 2, five nodes are integrated into luminaires, i.e., into lighting devices 51, 52, 53, 54, 55, 56. Instead of being integrated into a luminaire, a node may be attached to a luminaire.

[0073] A benefit of integrating nodes of the RF-based system into luminaires or attaching them to luminaires is that luminaires are commonly found in nearly all indoor environments, providing an ideal platform for widespread and discreet deployment of sensing nodes. This ubiquity ensures that the sensing system can have comprehensive coverage of the environment without requiring additional, potentially intrusive equipment installations. Such integration makes the technology more acceptable to users, as it blends seamlessly into the existing infrastructure.

[0074] Furthermore, attaching nodes to luminaires, which are typically positioned at elevated locations in a room, may improve the quality and reach of RF signals used for sensing. The elevated position helps in minimizing obstructions and interference that might otherwise affect signal propagation at lower levels, leading to more accurate and reliable sensing capabilities.

[0075] Moreover, integrating sensing capabilities into existing luminaires may maintain or enhance the aesthetic appeal of the environment. This approach avoids the need for installing additional, potentially unsightly sensing devices. Higher user acceptance is crucial for the widespread adoption of smart environment technologies, as it minimizes perceived intrusiveness and preserves the character of the living or working space.

[0076] Additionally, utilizing luminaires as part of the sensing infrastructure may also contribute to energy efficiency. Luminaires are typically already connected to the power supply, reducing the need for additional power sources for the nodes. This may lead to a more energy-efficient deployment and potentially lower installation and operational costs, as the dual function of lighting and sensing is more cost-effective than separate systems.

[0077] Also, by integrating sensing nodes with luminaires, the installation process may be simplified, leveraging existing electrical connections and placements. This integration may lead to lower installation costs and complexity. Additionally, maintenance of the sensing system may be streamlined with the luminaire’s maintenance, further reducing the system's total cost of ownership and enhancing its reliability.

[0078] Finally, this approach may allow for scalable and flexible system deployment. As the need for more extensive coverage or higher resolution sensing arises, additional luminaires equipped with sensing nodes might be easily integrated into the system. This flexibility supports the gradual expansion of sensing capabilities to meet evolving needs without significant disruption or overhaul of the existing setup.

[0079] In the example of Fig. 2, a window 71 and a door 76 are located in the kitchen 63, a window 72 is located in the living room 64, a door 78 is located in the bathroom 65, and a window 73 and a door 77 are located in the bedroom 67. These are objects that may be detected in the obtained visual sensor data.

[0080] A user 69 located in the bedroom 67 is holding the mobile device 21 of Fig. 1. When door 77 is detected, and the user walks around in the area of door 77, or walks through door 77, and the RF-based sensing system is in configuration mode, signatures of the RSSI / CSI signals may be generated. For example, lighting devices 55 and 56 and optionally one or more of bridge 45, lighting device 52, lighting device 54, and sensor 42 may be transmitting and receiving beacons when the user is detected to be near door 77 based on the visual sensor data from the camera 28 and / or LiDAR scanner 26. Each of the selected nodes may alternately take on the role of transmitter while the other nodes take on the role of receiver, for example.

[0081] In addition to the visual sensor data from the camera 28 and / or LiDAR scanner 26, information received from the mobile device 21 (e.g., geographic coordinates, direction information) may be used to detect whether the user is near door 77 and / or to detect a specific event associated with door 77, e.g., entering the bedroom 67 or leaving the bedroom 67. For example, Apple’s iOS is able to provide geographic coordinates on an iPhone.

[0082] From the determined signatures, it may be determined (e.g., using machine learning) which nodes had the best signature to detect an event associated with the door 77, e.g., a best signature when entering the bedroom 67 or when leaving the bedroom 67. For instance, all signatures determined while scanning a home with camera 28 and LiDAR scanner 26 may be input into a neural network to detect certain behavior in the home. A map of the home may then be made based on the scans and this map may include signatures when the user was at certain positions or moving certain directions in the home. One or more of the following objects may be detectable: a door, a window, a television screen, stairs, a closet, a couch, and / or a dining table. For instance, combinations of nodes may be selected such that movements close to windows, a person sitting down on a couch, activities around the television screen, and / or activities around the dining table may be detected effectively.

[0083] A first implementation of the method of configuring a radiofrequency-based sensing system is shown in Fig. 3. The method may be performed by the mobile device 21 of Fig. 1, for example.

[0084] A step 101 comprises obtaining visual sensor data relating to an environment. A step 103 comprises analyzing the visual sensor data obtained in step 101. A step 104 comprises determining whether an object was detected in the environment in step 103. If not, step 101 is repeated, i.e., new visual sensor data is obtained, and the method proceeds as shown in Fig. 3. If at least one object is detected in step 103, then a step 105 is performed after step 104.

[0085] Step 105 comprises calculating a radiofrequency signature for each of a plurality of sets of radiofrequency signals which is transmitted and received while a user is within a threshold distance of an object detected in step 103. Each of the plurality of sets of radiofrequency signals is transmitted and received by a different node combination of a plurality of node combinations. If multiple objects are detected in step 103, then radiofrequency signatures may be selected which are transmitted and received while the user is within the threshold distance of one of these objects, e.g. the most prominent object.

[0086] Next, a step 107 comprises determining an evaluation of each of the radiofrequency signatures calculated in step 105. A step 109 comprises selecting one of the radiofrequency signatures based on the evaluations determined in step 107. A step 111 comprises selecting a node combination corresponding to the radiofrequency signature selected in step 109 from the plurality of node combinations.

[0087] A step 113 comprises configuring the radiofrequency -based sensing system to detect events associated with the object detected in step 103 by employing the node combination selected for the detected object in step 111. Step 101 is repeated after step 113, and the method proceeds as shown in Fig. 3, until the user stops the configuration process.

[0088] After step 113 has been performed, the calibration / configuration process is completed and the RF -based sensing system may be made operational, as will be described in relation to Figs. 7 and 8. The implementation of Fig. 3 may be combined with the implementation of Fig. 5, Fig. 6, and / or Fig. 7 (or Fig. 8 instead of Fig. 7). A second implementation of the method of configuring a radiofrequencybased sensing system is shown in Fig. 4. The method may be performed by the mobile device 21 of Fig. 1, for example. The implementation of Fig. 4 differs from the implementation of Fig. 3 in that step 113, i.e., the configuration of the radiofrequency-based sensing system, is performed after all the node combinations have been selected, e.g., after the user stops the configuration process.

[0089] A step 121 comprises determining, after a node combination has been selected in step 111, whether the configuration process should continue. If so, step 101 is repeated, and the method proceeds as shown in Fig. 4. If not, step 113 is performed and the radiofrequency-based sensing system is configured to detect events associated with the objects detected in step 103 by employing the node combinations selected for each respective object in step 111. The implementation of Fig. 4 may be combined with the implementation of Fig. 5, Fig. 6, and / or Fig. 7 (or Fig. 8 instead of Fig. 7).

[0090] A third implementation of the method of configuring a radiofrequency -based sensing system is shown in Fig. 5. The method may be performed by the mobile device 21 of Fig. 1, for example. The implementation of Fig. 5 is an extension of the implementation of Fig. 3. In the implementation of Fig. 5, step 105 of Fig. 3 is implemented by a step 147 and steps 141, 143, and 145 are performed after step 103.

[0091] Step 141 comprises identifying a space in which the user is located. The space may be identified based on the type of space, the dimensions of the space, identified objects in the space (e.g., using Al image classification), and the location of the user. In the implementation, step 141 comprises identifying the space based on the visual sensor data (e.g. LiDAR and / or camera data) obtained in step 101, specifically based on the results of the analysis in step 103.

[0092] For example, if a TV is detected in the visual sensor data, the space may be identified as the living room, and if a refrigerator is detected in the visual sensor data, the space may be identified as the kitchen. In an alternative implementation, the space in which the user is located is alternatively or additionally identified in another way, e.g. based on information from motion detectors and / or geographical coordinates from the user’s mobile device.

[0093] Step 143 comprises forming the plurality of node combinations from a collection of nodes associated with the space identified in step 141. For example, if the nodes are integrated into or attached to components (e.g., luminaires) of a lighting system, their locations may have been configured during the commissioning of the lighting system. Preferably, each node combination comprises three to four nodes. This would mean that three to four nodes would be used for detecting an event associated with the object when the RF- based sensing system becomes operational. If the identified space does not comprise at least a minimum number of nodes (e.g., three nodes), one or more nodes from an adjacent space may be included in the node combinations.

[0094] Step 145 comprises instructing each respective node combination of the plurality of node combinations formed in step 143 to transmit and receive a respective set of radiofrequency signals in a time period associated with the respective node combination. If the transmitter role is alternated between nodes in the combination when the RF-based sensing system becomes operational, then the node combination need not specify which node is assigned the transmitter role. In such a node combination, the transmitter role may rotate between nodes in a round-robin fashion.

[0095] If the transmitter role is not alternated between nodes in the combination when the RF-based sensing system becomes operational, then the node combination may specify which node is assigned the transmitter role in the combination, and multiple node combinations may comprise the same nodes. In the calibration phase, different node combinations consisting of the same nodes may be tested in sequence, and the transmitter role may then also be rotated between nodes in a round-robin fashion. In the calibration phase, beacons may be transmitted, for example, every 100 milliseconds. In the operational phase, beacons would typically be transmitted less often than in the calibration phase.

[0096] Step 147 comprises calculating a radiofrequency signature for each respective node combination of the plurality of node combinations formed in step 143 based on the set of radiofrequency signals as received by at least one receiving node of the respective node combination in the time period associated with the respective node combination.

[0097] In step 147, RF signatures are only calculated for sets of RF signals which are transmitted and received while the user is within the threshold distance of the object detected in step 103. In order to evaluate the RF signatures calculated in step 107, RF signatures may need to be calculated for sets of RF signals which are transmitted and received while the user is not within the threshold distance of the object detected in step 103. This step is not shown in Fig. 5. The implementation of Fig. 6 may be combined with the implementation of Fig. 4, Fig. 6, and / or Fig. 7 (or Fig. 8 instead of Fig. 7).

[0098] By identifying the space in which the user is located and forming node combinations from nodes associated specifically with that space, the method may ensure a highly context-aware setup. This spatial awareness may allow the method to focus its sensing capabilities on relevant areas, improving detection accuracy and reducing the likelihood of irrelevant data processing. It may align system resources with the actual layout and use of the environment, enhancing the overall effectiveness of event detection related to specific objects within those spaces.

[0099] A fourth implementation of the method of configuring a radiofrequency-based sensing system is shown in Fig. 6. The method may be performed by the mobile device 21 of Fig. 1, for example. The implementation of Fig. 6 is an extension of the implementation of Fig. 3. In the implementation of Fig. 6, step 113 of Fig. 3 has been implemented by a step 151.

[0100] Step 151 comprises configuring the radiofrequency -based sensing system to detect events associated with the respective specific object by employing not only the node combination selected for the respective specific object in step 111 but also the radiofrequency signature selected for the respective specific object in step 109. Since the employed node combination was selected in step 111 due to the usefulness of the RF signature calculated for this node combination, it is beneficial to employ this same RF signature as a reference signature in the operational phase.

[0101] However, in an alternative implementation, a standard RF signature (i.e., not customized for a specific household, e.g., pre-configured in the RF -based sensing system by the system’s manufacturer) may be employed, at least initially, and this standard RF signature may then be refined based on learning during the operational phase to obtain a similar signature as the signature selected in step 109.

[0102] In the implementation of Fig. 6, the RF signature selected in step 109 may be employed during the entire operational phase, e.g., until the calibration phase is repeated. Alternatively, the RF signature selected in step 109 may be used initially and then refined based on learning during the operational phase. The implementation of Fig. 6 may be combined with the implementation of Fig. 4, Fig. 5, and / or Fig. 7 (or Fig. 8 instead of Fig. 7).

[0103] A fifth implementation of the method of configuring a radiofrequency-based sensing system is shown in Fig. 7. The method may be performed by the mobile device 21 and the bridge 45 of Fig. 1, for example. The implementation of Fig. 7 is an extension of the implementation of Fig. 3. In the implementation of Fig. 7, step 113 of Fig. 3 has been implemented by a step 171 and steps 173, 175, and 177 are performed after step 171.

[0104] Step 171 comprises instructing the node combination selected in step 111 for the object detected in step 103 to continuously or periodically transmit radiofrequency signals for the purpose of sensing. After step 171 has been performed, the calibration / configuration process is completed, and the RF-based sensing system is made operational. Steps 173, 175, and 177 are part of the operational phase.

[0105] Step 173 comprises obtaining radiofrequency signatures of the radiofrequency signals as received by at least one receiver of the node combination instructed in step 171. Step 175 comprises comparing each of the radiofrequency signatures with a reference radiofrequency signature associated with the node combination instructed in step 171, which was selected in step 111 for the object detected in step 103.

[0106] The reference RF signature may be, for example, the RF signature selected in step 109. This approach may simplify the calibration and configuration process of the system by aligning the reference RF signature with the one selected for the specific object in step 109. This alignment means that there may be no need to generate or maintain a separate set of reference signatures, streamlining system setup and maintenance. This simplification may reduce the technical overhead and potentially lower the barriers to deployment and operation.

[0107] Step 177 comprises detecting an event associated with the object detected in step 103 based on the comparisons, as performed in step 175, of the radiofrequency signatures with the reference radiofrequency signature. Step 173 is repeated after step 177, and the method proceeds as shown in Fig. 7 until stopped. Steps 173, 175, and 177 may be performed in parallel for multiple node combinations, which have been configured in multiple iterations of step 113 to detect events associated with multiple objects.

[0108] Optionally, step 101 is repeated after step 177 to repeat the calibration phase. By recalculating RF signatures based on current conditions and objects' positions, the system may be able to adapt to environmental changes or the introduction of new objects into the environment. This adaptability ensures the system remains effective over time, even as the layout or usage of the space changes. The implementation of Fig. 7 may be combined with the implementation of Fig. 4, Fig. 5, Fig. 6, and / or Fig. 8. Steps 173, 175, and 177 may be performed by the bridge 45 of Fig. 1, for example. In that case, the bridge 45 is the controller of the RF-based sensing system.

[0109] The ability to instruct node combinations to continuously or periodically transmit RF signals for sensing purposes enables the method to monitor the environment in real or near-real-time. This continuous or periodic approach may allow for the immediate detection of changes or events related to specific objects, providing timely responses or alerts. This real-time monitoring capability may be a significant advantage in applications where timely information is crucial. By comparing each obtained RF signature with a reference RF signature associated with the selected node combination, the system may be able to more accurately detect events associated with specific objects. This comparative analysis helps to distinguish between normal environmental variations and significant events that merit attention. The use of reference RF signatures as a benchmark improves the system’s accuracy and reliability in event detection, reducing false positives and false negatives.

[0110] The methodology of comparing obtained signatures with reference signatures may allow the method to adapt and potentially update its reference signatures over time. This dynamic adaptation may accommodate changes in the environment or the specific object’s context, enhancing the RF-based sensing system's long-term effectiveness and reducing the need for recalibration.

[0111] The selective instructing of specific node combinations to transmit signals based on the need for sensing in relation to specific objects may be used to optimize the use of sensing resources. This targeted sensing approach may reduce energy consumption and minimize potential interference with other devices or networks, leading to more efficient system operation.

[0112] The focused approach on comparing RF signatures for the detection of events associated with specific objects may enhance both the sensitivity and specificity of the sensing system. By tailoring the method’s operation to the nuances of each object’s RF signature, the method may more accurately identify events that are truly significant, improving its utility and effectiveness in practical applications.

[0113] The described methodology may enable the RF-based sensing system's capabilities to be extended to additional objects or environments. As the RF-based sensing system may be tailored to specific objects through the selection of node combinations and reference signatures, it may easily be adapted or expanded to cover new objects or areas without a complete system overhaul.

[0114] A sixth implementation of the method of configuring a radiofrequency-based sensing system is shown in Fig. 8. The method may be performed by the mobile device 21 and the bridge 45 of Fig. 1, for example. The implementation of Fig. 8 is an extension of the implementation of Fig. 7. In the implementation of Fig. 8, step 177 of Fig. 7 is implemented by a step 183, and a step 181 is performed before step 183.

[0115] Step 181 comprises obtaining other visual sensor data relating to the environment. Step 183 comprises detecting, based on the comparisons of step 175, a first type of event associated with the respective specific object (e.g., entering a room through a detected door) or a second type of event associated with the respective specific object (e.g., leaving the room through the detected door) in dependence on the other visual sensor data obtained in step 181. The implementation of Fig. 8 may be combined with the implementation of Fig. 4, Fig. 5, and / or Fig. 6.

[0116] By leveraging other visual sensor data, the RF-based sensing system may gain the ability to differentiate between types of events associated with a specific object, distinguishing a first type of event from a second. This multi-modal sensing approach may allow for a richer interpretation of the environment and activities within it, enabling more nuanced responses or actions to be taken by the RF-based sensing system. For example, it could distinguish between the object being moved by a person versus being knocked over by a pet, based on the combination of RF signature changes and visual data.

[0117] The inclusion of visual sensor data may provide an additional layer of verification for event detection, improving the system’s overall accuracy and reliability. Visual data may help confirm events suggested by RF signature changes, reducing false positives (incorrectly identifying non-events as events) and false negatives (missing actual events). This is particularly valuable in complex environments where RF signals alone might be susceptible to interference or ambiguous interpretations.

[0118] Visual sensor data may introduce a level of contextual awareness that RF signatures alone might not provide. This context may include the presence of people or animals, changes in lighting conditions, or other environmental factors that could influence the interpretation of RF data. Understanding the context around an event may lead to more appropriate and effective responses by the RF-based sensing system.

[0119] Fig. 9 depicts a block diagram illustrating an exemplary data processing system that may perform the method as described with reference to the flow charts.

[0120] As shown in Fig. 9, the data processing system 900 may include at least one processor 902 coupled to memory elements 904 through a system bus 906. As such, the data processing system may store program code within memory elements 904. Further, the processor 902 may execute the program code accessed from the memory elements 904 via a system bus 906. In one aspect, the data processing system may be implemented as a computer that is suitable for storing and / or executing program code. It should be appreciated, however, that the system 900 may be implemented in the form of any system including a processor and a memory that is capable of performing the functions described within this specification. The data processing system may be an Internet / cloud server, for example. The memory elements 904 may include one or more physical memory devices such as, for example, local memory 908 and one or more bulk storage devices 910. The local memory may refer to random access memory or other non-persistent memory device(s) generally used during actual execution of the program code. A bulk storage device may be implemented as a hard drive or other persistent data storage device. The processing system 900 may also include one or more cache memories (not shown) that provide temporary storage of at least some program code in order to reduce the quantity of times program code must be retrieved from the bulk storage device 910 during execution. The processing system 900 may also be able to use memory elements of another processing system, e.g. if the processing system 900 is part of a cloud-computing platform.

[0121] Input / output (I / O) devices depicted as an input device 912 and an output device 914 optionally can be coupled to the data processing system. Examples of input devices may include, but are not limited to, a keyboard, a pointing device such as a mouse, a microphone (e.g. for voice and / or speech recognition), or the like. Examples of output devices may include, but are not limited to, a monitor or a display, speakers, or the like. Input and / or output devices may be coupled to the data processing system either directly or through intervening VO controllers.

[0122] The input and the output devices may be implemented as a combined input / output device (illustrated in Fig. 9 with a dashed line surrounding the input device 912 and the output device 914). An example of such a combined device is a touch sensitive display, also sometimes referred to as a “touch screen display” or simply “touch screen”. In such an implementation, input to the device may be provided by a movement of a physical object, such as e.g. a stylus or a finger of a user, on or near the touch screen display.

[0123] A network adapter 916 may also be coupled to the data processing system to enable it to become coupled to other systems, computer systems, remote network devices, and / or remote storage devices through intervening private or public networks. The network adapter may comprise a data receiver for receiving data that is transmitted by the systems, devices and / or networks to the data processing system 900, and a data transmitter for transmitting data from the data processing system 900 to the systems, devices and / or networks. Modems, cable modems, and Ethernet cards are examples of different types of network adapter that may be used with the data processing system 900.

[0124] As pictured in Fig. 9, the memory elements 904 may store an application 918. The application 918 may be stored in the local memory 908, the one or more bulk storage devices 910, or separate from the local memory and the bulk storage devices. It should be appreciated that the data processing system 900 may further execute an operating system (not shown in Fig. 9) that can facilitate execution of the application 918. The application 918, being implemented in the form of executable program code, can be executed by the data processing system 900, e.g., by the processor 902. Responsive to executing the application, the data processing system 900 may be configured to perform one or more operations or method steps described herein.

[0125] The invention may be implemented as a program product for use with a computer system, where the program(s) of the program product define functions. The program(s) may be contained on a variety of non-transitory computer-readable storage media, where, as used herein, the expression “non-transitory computer readable storage media” comprises all computer-readable media, with the sole exception being a transitory, propagating signal. The program(s) may also be contained on a variety of transitory computer-readable storage media. Illustrative computer-readable storage media include, but are not limited to: (i) non-writable storage media (e.g., read-only memory devices within a computer such as CD-ROM disks readable by a CD-ROM drive, ROM chips or any type of solid-state non-volatile semiconductor memory) on which information is permanently stored; and (ii) writable storage media (e.g., flash memory, floppy disks within a diskette drive or hard-disk drive or any type of solid-state random-access semiconductor memory) on which alterable information is stored. The computer program may be run on the processor 902 described herein.

[0126] The terminology used herein is for the purpose of describing particular implementations only and is not intended to be limiting of the invention. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0127] The corresponding structures, materials, acts, and equivalents of all means or step plus function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed. The detailed description has been presented for purposes of illustration, but is not intended to be exhaustive or limited to the implementations in the form disclosed.

Claims

CLAIMS:

1. A system (21, 900) for configuring a radiofrequency -based sensing system, the system (21, 900) comprising at least one input interface (26, 28), at least one configuration interface (24), and at least one processor (25, 902) configured to, for each respective specific object of one or more specific objects in an environment, obtain visual sensor data relating to the environment via the at least one input interface (26, 28), detect, based on the visual sensor data, the respective specific object in the environment, calculate a radiofrequency signature for each of a plurality of sets of radiofrequency signals, each of the plurality of sets of radiofrequency signals being transmitted and received while a user (69) of the system (21, 900) is within a threshold distance of the respective specific object such that an impact of the presence of the user close to the respective specific object is reflected in the received radiofrequency signals, each of the plurality of sets of radiofrequency signals being transmitted and received by a different node combination of a plurality of node combinations, determine an evaluation of each of the radiofrequency signatures, select one of the radiofrequency signatures based on the evaluations, select a node combination corresponding to the selected radiofrequency signature from the plurality of node combinations, and configure, via the at least one configuration interface (24), the radiofrequency -based sensing system to detect events associated with the respective specific object by employing the node combination selected for the respective specific object; wherein a node combination represents a pair of a transmitting node and a receiving node, and a corresponding radiofrequency signature is calculated for each node combination based on RS SI information or CSI information of a radiofrequency signal received by the receiving node from the transmitting node.

2. A system (21, 900) as claimed in claim 1, wherein the at least one processor (25, 902) is configured to identify a space in which the user (69) is located,form the node combinations from a collection of nodes associated with the space, instruct each respective node combination of the plurality of node combinations to transmit and receive a respective set of radiofrequency signals in a time period associated with the respective node combination, and calculate the radiofrequency signature for each respective set of radiofrequency signals of the plurality of sets of radiofrequency signals by calculating a radiofrequency signature for each respective node combination of the plurality of node combinations based on the set of radiofrequency signals as received by at least one receiving node of the respective node combination in the time period associated with the respective node combination.

3. A system (21, 900) as claimed in claim 2, wherein the least one processor (25, 902) is configured to identify the space based on the visual sensor data.

4. A system (21, 900) as claimed in any one of claims 1-3, wherein the at least one processor (25, 902) is configured to configure the radiofrequency-based sensing system to detect events associated with the respective specific object by employing the node combination selected for the respective specific object and the radiofrequency signature selected for the respective specific object.

5. A system (21, 900) as claimed in any one of claims 1-4, wherein at least one node out of the plurality of node combinations is attached to or integrated in a luminaire located in the environment.

6. A system (21, 900) as claimed in any one of claims 1-5, wherein the at least one processor (25, 902) is configured to instruct the node combination selected for the respective specific object to continuously or periodically transmit radiofrequency signals for the purpose of sensing, obtain radiofrequency signatures of the radiofrequency signals as received by at least one receiver of the node combination selected for the respective specific object, compare each of the radiofrequency signatures with a reference radiofrequency signature associated with the node combination selected for the respective specific object, anddetect an event associated with the respective specific object based on the comparisons of the radiofrequency signatures with the reference radiofrequency signature.

7. A system (21, 900) as claimed in claim 6, wherein the reference radiofrequency signature is the radiofrequency signature selected for the respective specific object and the at least one processor (25, 902) is configured to detect the event associated with the respective specific object upon detecting a match between at least one of the radiofrequency signatures and the radiofrequency signature selected for the respective specific object.

8. A system (21, 900) as claimed in claim 6 or 7, wherein the at least one processor (25, 902) is configured to obtain other visual sensor data relating to the environment via the at least one input interface (26, 28), and detect, based on the comparisons of the radiofrequency signatures with the reference radiofrequency signature, a first type of event associated with the respective specific object or a second type of event associated with the respective specific object in dependence on the other visual sensor data.

9. A system (21, 900) as claimed in any one of claims 1-8, wherein the visual sensor data has been captured by at least one of a camera (28), a light sensor, and a ranging sensor.

10. A system (21, 900) as claimed in claim 9, wherein the at least one of the camera (28), the light sensor, and the ranging sensor is embedded in an augmented reality headset or a mobile phone.

11. A system (21, 900) as claimed in any one of claims 1-10, wherein the one or more specific objects comprise at least one of a door (76, 77, 78), a window (71, 72, 73), a television screen, stairs, a closet, a couch, and a dining table.

12. A method of a system (21, 900) for configuring a radiofrequency-based sensing system, the method comprising, for each respective specific object of one or more specific objects in an environment,obtaining (101) visual sensor data relating to the environment, detecting (103), based on the visual sensor data, the respective specific object in the environment, calculating (105) a radiofrequency signature for each of a plurality of sets of radiofrequency signals, each of the plurality of sets of radiofrequency signals being transmitted and received while a user of the system (21, 900) is within a threshold distance of the respective specific object such that an impact of the presence of the user close to the respective specific object is reflected in the received radiofrequency signals, each of the plurality of sets of radiofrequency signals being transmitted and received by a different node combination of a plurality of node combinations, determining (107) an evaluation of each of the radiofrequency signatures, selecting (109) one of the radiofrequency signatures based on the evaluations, selecting (111) a node combination corresponding to the selected radiofrequency signature from the plurality of node combinations, and configuring (113) the radiofrequency-based sensing system to detect events associated with the respective specific object by employing the node combination selected for the respective specific object; wherein a node combination represents a pair of a transmitting node and a receiving node, and a corresponding radiofrequency signature is calculated for each node combination based on RSSI information or CSI information of a radiofrequency signal received by the receiving node from the transmitting node.

13. A computer program product for a computing device, the computer program product comprising computer program code to perform the method of claim 12 when the computer program product is run on a processing unit of the computing device.

Images