An activity recognition device comprises a port configured to receive a video stream from a video source for a first object and a second object; a memory configured to store instructions and image frames of the video stream; and one or more processors, wherein the one or more processors execute the instructions stored in the memory, the one or more processors configured to: select portions of the image frames based on presence of the first object; determine areas within the portions of image frames, wherein locations of the first object in the video frames are bounded by the determined areas; determine motion of the first object and locations of a second object within the areas of the image frames; and identify an activity according to the determined motion and locations of the second object, and generate an alert according to the identified activity.

A method for recognizing a state of tiredness and/or sleep of a vehicle driver. The method includes reading in a first and second eye opening signal, the first signal representing a degree of eye opening and/or a signal derived therefrom of the left eye of the driver of the vehicle and the second signal representing a degree of eye opening and/or a signal derived therefrom of the right eye of the driver of the vehicle. The method also includes recognizing a validity of the first and/or second signal to recognize the first signal as valid if the first signal corresponds to a first criterion and/or to recognize the second signal as valid if the second eye signal corresponds to a second criterion, and determining the state of tiredness and/or sleep of the driver of the vehicle using the first signal recognized as valid and/or the second signal recognized as valid.

A method on-board vehicles for predicting a plurality of primary signs of driving while impaired or driving while distracted, and preventing running red lights at predefined intersections by a traveling vehicle, the method comprising integrating the autonomous in-vehicle virtual traffic light system with the in-vehicle's cameras and the automatic braking of the vehicle.

Provided is a portable electronic device including: a sensor; and a control unit controlling the sensor so as to obtain movement information of the portable electronic device in order to detect a movement of at least a part of a user's arm, determining whether the user is in a driving state on the basis of the movement information, automatically switching into a driving mode on the basis of the determination, and activating at least one function relating to driving among the functions of the portable electronic device on the basis of the switching into the driving mode.

The present disclosure provides a method for measuring clutch durability of an all wheel drive vehicle. The method includes: a damage degree securing step of accumulating and acquiring a damage degree of a clutch based on a clutch slip amount and clutch transfer torque when the clutch slips by a difference in rotary speed between a front wheel and a rear wheel; and a durability predicting step of predicting current durability of the clutch based on the difference between the accumulated and acquired damage degree and a reference damage degree of the corresponding clutch, an input shaft RPM of rotating the clutch, and a reference durability RPM of the clutch.

Methods, apparatus, and systems are provided for integrated driver expression recognition and vehicle interior environment classification to detect driver condition for safety. A method includes obtaining an image of a driver of a vehicle and an image of an interior environment of the vehicle. Using a machine learning method, the images are processed to classify a condition of the driver and of the interior environment of the vehicle. The machine learning method includes general convolutional neural network (CNN) and CNN with adaptive filters. The adaptive filters are determined based on influence of filters. The classification results are combined and compared with predetermined thresholds to determine if a decision can be made based on existing information. Additional information is requested by self-motivated learning if a decision cannot be made, and safety is determined based on the combined classification results. A warning is provided to the driver based on the safety determination.

A method for correcting a state of charge of a state of charge display of a traction battery of an electrically driven vehicle. The method includes detecting an attentiveness parameter of a driver of the vehicle with respect to the state of charge display, and step correction of the state of charge displayed on the state of charge display if the attentiveness parameter undershoots an attentiveness threshold value.

A drive assisting apparatus includes a running state detection unit which detects a running state of a vehicle, a manipulation detection unit which detects a drive manipulation of a driver on the vehicle, a line-of-sight direction detection unit which detects a line-of-sight direction of the driver, a pattern storage unit which is stored in advance with data indicating combinations of a vehicle running state and a driver drive manipulation and a driver line-of-sight direction pattern, and a warning signal output unit. The warning signal output unit outputs a warning signal if a combination of the running direction detected by the running state detection unit, the drive manipulation detected by the manipulation detection unit, and the line-of-sight direction detected by the line-of-sight direction detection unit is different from any of the combinations of the data stored in the pattern storage unit.

A vehicle display device includes a processor, the processor being configured to acquire a deceleration state of a vehicle achieved by driver assistance and a reason for decelerating the vehicle, and cause a display to display a deceleration image indicating that the vehicle is decelerating and a reason image indicating the reason, based on the acquired deceleration state and the acquired reason.

A remaining fuel amount warning device for a vehicle, the remaining fuel amount warning device giving a warning that an amount of fuel remaining in a fuel tank is smaller than a predetermined value on the basis of output of a fuel gauge measuring the remaining fuel amount, includes combustion state changing device for changing the combustion state of an engine. When the remaining fuel amount becomes smaller than the predetermined value, the remaining fuel amount warning device performs remaining amount warning control that produces vibration different than during normal operation by changing the combustion state of the engine by the combustion state changing device. A starter switch for starting the engine is made to serve also as a warning acknowledging button for stopping the remaining amount warning control for a predetermined time on the basis of an operation by an occupant.