A tracking system for tracking an expanded state of an object is provided. The tracking system comprises at least one processor and a memory having instructions stored thereon that, when executed by the at least one processor, cause the tracking system to execute a probabilistic filter that iteratively tracks a belief on the expanded state of the object, wherein the belief is predicted using a motion model of the object and is further updated using a compound measurement model of the object. The compound measurement model includes multiple probabilistic distributions constrained to lie on a contour of the object with a predetermined relative geometrical mapping to the center of the object. Further, the tracking system tracks the expanded state of the object based on the updated belief on the expanded state.

Techniques and apparatuses are described that implement a smart-device-based radar system capable of detecting user gestures in the presence of saturation. In particular, a radar system 104 employs machine learning to compensate for distortions resulting from saturation. This enables gesture recognition to be performed while the radar system 104's receiver 304 is saturated. As such, the radar system 104 can forgo integrating an automatic gain control circuit to prevent the receiver 304 from becoming saturated. Furthermore, the radar system 104 can operate with higher gains to increasing sensitivity without adding additional antennas. By using machine learning, the radar system 104's dynamic range increases, which enables the radar system 104 to detect a variety of different types of gestures having small or large radar cross sections, and performed at various distances from the radar system 104.

Techniques and apparatuses are described that implement a smart-device-based radar system capable of detecting user gestures in the presence of saturation. In particular, a radar system 104 employs machine learning to compensate for distortions resulting from saturation. This enables gesture recognition to be performed while the radar system 104's receiver 304 is saturated. As such, the radar system 104 can forgo integrating an automatic gain control circuit to prevent the receiver 304 from becoming saturated. Furthermore, the radar system 104 can operate with higher gains to increasing sensitivity without adding additional antennas. By using machine learning, the radar system 104's dynamic range increases, which enables the radar system 104 to detect a variety of different types of gestures having small or large radar cross sections, and performed at various distances from the radar system 104.

An ultra-wideband-based system and method for detecting properties associated with a movable object in an environment such as an indoor environment. The method includes transmitting ultra-wideband radar signals to an environment, using an ultra-wideband transmitter, and receiving signals reflected from the environment as a result of the transmission of the first ultra-wideband radar signals using an ultra-wideband receiver. The method also includes processing the reflected signals and determining properties associated with a movable object in an environment based on the processed reflected signals, using the processor.

An ultra-wideband-based system and method for detecting properties associated with a movable object in an environment such as an indoor environment. The method includes transmitting ultra-wideband radar signals to an environment, using an ultra-wideband transmitter, and receiving signals reflected from the environment as a result of the transmission of the first ultra-wideband radar signals using an ultra-wideband receiver. The method also includes processing the reflected signals and determining properties associated with a movable object in an environment based on the processed reflected signals, using the processor.

A sensor device for measuring a motion of a vehicle includes a light source for radiating light on a region on a ground below the vehicle in temporal intervals and to produce a spot of increased temperature; a heat detection unit, which is mountable at an underside of the vehicle for detecting a position of the spot on the ground at the temporal intervals; and a control unit for receiving data about a measured time of the spot and the position of the spot from the heat detection unit and to estimate a change of the position of the spot in vehicle coordinates.

An exercise machine can include sensors to detect objects proximate to and/or moving towards the exercise machine. For example, a treadmill, or a control system associated with the treadmill, can determine an object is moving towards or is already proximate to a deck of the treadmill (e.g., a front area, middle area, or rear area of the deck of the treadmill) and modify operations of the treadmill in response to the determined or detected object or object movement. The treadmill can utilize various detection mechanisms when determining an object is within a proximity to the treadmill, such as time-of-flight (ToF) sensors or cameras, millimeter wave (mmWave) sensors, computer vision (CV) technology, and so on, to detect the proximity of the object (or movement of the object).

Apparatus and methods for contact-minimized automated teller machine (“ATM”) use and transaction processing using Doppler-radar based gesture recognition and authentication. The apparatus and methods may include an ATM including a millimeter-wave radar transmitter and receiver. Movement of one or more objects, including fingers, within a radar field may be analyzed and translated into gestures and authentication passcode(s). By utilizing the radar field instead of physical buttons or a touchscreen, contact with the ATM may be minimized.

A railroad crossing obstacle detection system including: a laser radar device that includes an irradiator and a light receiver, the irradiator applying laser light at irradiation angles set every prescribed angle, and the light receiver receiving the laser light reflected; and a controller, wherein the laser radar device is configured to be supported by an object such that the laser radar device is located above a detection area of an obstacle in railroad crossing, and to apply the laser light from above to the detection area, and the controller is configured to detect an obstacle on the basis of measurement result representing a distance to an object having reflected the laser light, and an irradiation angle for the object; and monitor a change of at least one of a position or a direction of the laser radar device on the basis of the measurement result by the laser radar device.

A railroad crossing obstacle detection system including: a laser radar device that includes an irradiator and a light receiver, the irradiator applying laser light at irradiation angles set every prescribed angle, and the light receiver receiving the laser light reflected; and a controller, wherein the laser radar device is configured to be supported by an object such that the laser radar device is located above a detection area of an obstacle in railroad crossing, and to apply the laser light from above to the detection area, and the controller is configured to detect an obstacle on the basis of measurement result representing a distance to an object having reflected the laser light, and an irradiation angle for the object; and monitor a change of at least one of a position or a direction of the laser radar device on the basis of the measurement result by the laser radar device.