A fall detector device (102) for mounting on a wall for monitoring an environment (100), comprising: a motion sensor (204) for detecting motion of a person (106) within a first field of view of the motion sensor; an active reflective wave sensor (206) for detecting the presence of a person within a second field of view of the active reflective wave sensor using wave reflections from the environment, the first and second fields of views at least partially overlapping one another, and a processor coupled to the motion sensor and active reflective wave sensor for receiving output from each of the motion sensor and active reflective wave sensor, wherein operation of the active reflective wave sensor is dependent on a detection of motion of a person within at least a portion of the first field of view by the motion sensor.

A fall detector device (102) for mounting on a wall for monitoring an environment (100), comprising: a motion sensor (204) for detecting motion of a person (106) within a first field of view of the motion sensor; an active reflective wave sensor (206) for detecting the presence of a person within a second field of view of the active reflective wave sensor using wave reflections from the environment, the first and second fields of views at least partially overlapping one another, and a processor coupled to the motion sensor and active reflective wave sensor for receiving output from each of the motion sensor and active reflective wave sensor, wherein operation of the active reflective wave sensor is dependent on a detection of motion of a person within at least a portion of the first field of view by the motion sensor.

The present invention provides navigation assistance that is for small ships and that enables clear depiction of a radar image. An administrative server in a ship navigation assistance system, the server being equipped with: a communication means that performs, via a network, data transmission/reception with a user terminal which is connected to a device for detecting a target; and a vertex information management means that, of a plurality of target vertices extracted on the basis of detection result information of the target, identifies vertices moving together as a group as belonging to the same target, wherein, on the basis of the vertices that have been identified as belonging to the same target, the communication means transmits an instruction to the user terminal to display a rough outline of said target.

An automatic wall climbing type radar photoelectric robot system for damages of a bridge and tunnel structure, mainly including a control terminal, a wall climbing robot and a server. The wall climbing robot generates a reverse thrust by rotor systems, moves flexibly against the surface of a rough bridge and tunnel structure by adopting an omnidirectional wheel technology, and during inspection by the wall climbing robot, bridges and tunnels do not need to be closed, and the traffic is not affected. Bridges and tunnels can divide into different working regions only by arranging a plurality of UWB base stations, charging and data receiving devices on the bridge and tunnel structure by means of UWB localization, laser SLAM and IMU navigation technologies, a plurality of wall climbing robots supported to work at the same time, automatic path planning and automatic obstacle avoidance realized, and unattended regular automatic patrolling can be realized.

A system includes a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: receive, from a radar sensor of a vehicle, radar data indicative of a stationary object proximate to the radar sensor; receive, from a non-radar sensor of the vehicle, vehicle state data indicative of a vehicle state, the vehicle state data indicative of at least a longitudinal velocity and a yaw rate of the vehicle; determine an orientation estimate and an offset estimate of the radar sensor based on the radar data and the vehicle state data; and determine whether to actuate a vehicle system based on at least one of the orientation estimate or the offset estimate.

A radar-based fill-level measuring device that operates, for example, according to the FMCW principle or the pulse time-of-flight principle comprises a temperature sensor. Thus, the measurement rate at which the fill level is determined can be controlled according to the measured temperature in such a way that, at least above a defined limit temperature, the measurement rate is reduced as the temperature increases further. Furthermore, the measurement can be completely stopped if the measured temperature exceeds a predefined maximum temperature, in particular 150° C. The development of heat in the fill-level measuring device is counteracted by the reduction of the measurement rate. The measurement rate is thereby adaptively adjusted with respect to the ambient temperature such that, even at elevated ambient temperatures, which can occur in the case of cleaning processes, the fill-level measuring device remains at least conditionally fit for use.

The invention relates to a method for detecting at least one road user on a traffic route by means of a radar sensor and an optical detector, wherein with said method radar radiation is emitted by at least one radar transmitter of the radar sensor and reflected by the at least one road user, the reflected radar radiation is detected by means of at least one radar receiver of the radar sensor, the detected radar radiation is evaluated in such a way that at least one distance and one radial velocity of the at least one road user relative to the radar sensor is determined, an optical image of the at least one road user is detected by means of the optical detector, and the optical image is evaluation,
wherein at least one parameter of the at least one road user is determined both from the detected radar radiation and the optical image.

An object information acquisition unit acquires object information including an object distance between a radar device and a reflection object and an object azimuth angle at which the reflection object is located. A roadside object extraction unit extracts roadside object information on a roadside object from the object information. An axis deviation angle estimation unit estimates a vertical axis deviation angle from the roadside object information. The vertical axis deviation angle is an angle of deviation of an actual mounting direction from a reference mounting direction in a vertical direction. The actual mounting direction is an actual direction of the radar device, and the reference mounting direction is a direction of the radar device when the radar device is mounted in a reference state.

The described aspects and implementations enable fast and accurate object identification in autonomous vehicle (AV) applications by combining radar data with camera images. In one implementation, disclosed is a method and a system to perform the method that includes obtaining a radar image of a first hypothetical object in an environment of the AV, obtaining a camera image of a second hypothetical object in the environment of the AV, and processing the radar image and the camera image using one or more machine-learning models MLMs to obtain a prediction measure representing a likelihood that the first hypothetical object and the second hypothetical object correspond to a same object in the environment of the AV.

A system and method for predicting mild cognitive impairment (MCI) related diagnosis and prognosis utilizing hybrid machine learning. More specifically, the system and method produce predictions of MCI conversions to dementia and prognosis related thereof. Using available medical imaging and non-imaging data a diagnosis and prognosis model is trained using transfer learning. A platform may then receive a request from a clinician for a target patient's diagnosis or prognosis. The target patient's medical data is retrieved and used to create a model for the target patient. Then details of the target patient's model and the diagnosis and prognosis model are compared, a prediction is generated, and the prediction is returned to the clinician. As new medical data becomes available it is fed into the respective model to improve accuracy and update predictions.