A getting-off support device of a vehicle continues to issue an alarm for a predetermined time when a physical body condition indicating that a physical body that obstructs getting-off of an occupant in the vehicle exists around the vehicle and a getting-off condition indicating that the occupant in the vehicle intends to get off the vehicle are satisfied, and prolongs the time of issuing the alarm when both of the physical body condition and the getting-off condition are further satisfied while the issuing of the alarm is continued.

A vehicle operation detection device includes a storage unit configured to store a trained model obtained by machine learning using training data in which an image captured in advance and a body part used for a gesture of a user are associated with each other, an entry determination unit configured to determine whether, based on a position of the body part in the image obtained by inputting a newly captured image into the trained model, the body part enters a recognition area set in an imaging area of a camera, and a gesture determination unit configured to calculate a displacement vector of the body part based on images captured at a time interval after it is determined that the body part enters the recognition area, and determine, in accordance with whether a direction of the displacement vector is a direction corresponding to the gesture, whether the gesture is made.

A vehicle operation detection device includes a storage unit configured to store a trained model obtained by machine learning using training data in which an image captured in advance and a body part used for a gesture of a user are associated with each other, an entry determination unit configured to determine whether, based on a position of the body part in the image obtained by inputting a newly captured image into the trained model, the body part enters a recognition area set in an imaging area of a camera, and a gesture determination unit configured to calculate a displacement vector of the body part based on images captured at a time interval after it is determined that the body part enters the recognition area, and determine, in accordance with whether a direction of the displacement vector is a direction corresponding to the gesture, whether the gesture is made.

The present invention relates to a refrigerator and, more specifically, a refrigerator which enables a user to easily open a door thereof. The present invention relates to a refrigerator and method for controlling the same, which can prevent a door thereof from opening by itself due to a malfunction. According to an embodiment of the present invention, a refrigerator may comprise: a cabinet having a storage chamber; a door for closing or opening the storage chamber; a sensor provided to sense whether a user is within or out of a sensing distance, to enable discrimination between sensing-on and sensing-off; a door opening device provided to automatically open the door; and a control unit for determining an operation condition of the door opening device on the basis of a time interval from the sensing-on to the sensing-off and a duration for which the sensing-on continues in the sensor, so as to control the operation of the door opening device.

The present invention relates to a refrigerator and, more specifically, a refrigerator which enables a user to easily open a door thereof. The present invention relates to a refrigerator and method for controlling the same, which can prevent a door thereof from opening by itself due to a malfunction. According to an embodiment of the present invention, a refrigerator may comprise: a cabinet having a storage chamber; a door for closing or opening the storage chamber; a sensor provided to sense whether a user is within or out of a sensing distance, to enable discrimination between sensing-on and sensing-off; a door opening device provided to automatically open the door; and a control unit for determining an operation condition of the door opening device on the basis of a time interval from the sensing-on to the sensing-off and a duration for which the sensing-on continues in the sensor, so as to control the operation of the door opening device.

An entrance system is disclosed which has a movable door member having a door leaf with a first vertical edge and a second vertical edge. A sensor unit monitors a zone at or near the door leaf for presence or activity of a person or object, and captures an image of an external object at the first vertical edge of the door leaf, and processing the captured image to identify an optical code and recognize a learning mode trigger instruction encoded therein. Triggered by the recognizing of the learning mode trigger instruction, a learning mode of the sensor unit is automatically entered into, in which a distance between the sensor unit and the external object at the first vertical edge is automatically measured and a field width parameter value of the sensor unit is set based on the measured distance.

An entrance system is disclosed which has a movable door member having a door leaf with a first vertical edge and a second vertical edge. A sensor unit monitors a zone at or near the door leaf for presence or activity of a person or object, and captures an image of an external object at the first vertical edge of the door leaf, and processing the captured image to identify an optical code and recognize a learning mode trigger instruction encoded therein. Triggered by the recognizing of the learning mode trigger instruction, a learning mode of the sensor unit is automatically entered into, in which a distance between the sensor unit and the external object at the first vertical edge is automatically measured and a field width parameter value of the sensor unit is set based on the measured distance.

A system and method for self-learning operation of gate paddles is disclosed. Opening and closing of the gate paddles requires timing and other settings to avoid injury and fare evasion. Self-learning allows a machine learning model to adapt to new data dynamically. The new data captured at a fare gate improves the machine learning model, which can be shared the other similar fare gates within a transit system so that learning disseminates.

A package delivery system includes a door access panel that is moveable between an open position and a closed position, and a frame configured to be carried by a door adjacent a passageway and configured to movably mount the door access panel. The system includes an actuator, a motor, and a controller to control selective actuation of the door access panel. The system also includes a wireless communication interface to communicatively couple the controller and a smart device for receiving a remote input to actuate the door access panel between the closed and opened positions. The system further includes a user interface configured to receive local input for actuation of the door access panel. A sensing unit is also included and has a position sensor to generate position signals to the controller. A scanning unit is coupled to the controller to scan packages delivered through the passageway.

A package delivery system includes a door access panel that is moveable between an open position and a closed position, and a frame configured to be carried by a door adjacent a passageway and configured to movably mount the door access panel. The system includes an actuator, a motor, and a controller to control selective actuation of the door access panel. The system also includes a wireless communication interface to communicatively couple the controller and a smart device for receiving a remote input to actuate the door access panel between the closed and opened positions. The system further includes a user interface configured to receive local input for actuation of the door access panel. A sensing unit is also included and has a position sensor to generate position signals to the controller. A scanning unit is coupled to the controller to scan packages delivered through the passageway.