Abstract: Methods, systems, and apparatuses to build an explainable user output to receive input feature data by a neural network of multiple layers of an original classifier; determine a semantic function to label data samples with semantic categories; determine a semantic accuracy for each layer of the original classifier within the neural network; compare each layer based on results from the comparison of the semantic accuracy; designate a layer based on an amount of computed semantic accuracy; extend the designated layer by a category branch to the neural network to extract semantic data samples from the semantic content to train a set of new connections of an explainable classifier to compute a set of output explanations with an accuracy measure associated each output explanation for each semantic category of the plurality of semantic categories, and compare the accuracy measure for each output explanation to generate the output explanation in a user understandable format.

Abstract: Vision-based airbag enablement may include capturing two-dimensional images of a passenger, segmenting the image, classifying the image, and determining seated height of the passenger from the image. Enabling or disabling deployment of the airbag may be controlled based at least in part upon the determined seated height.

Abstract: Presented are intelligent vehicle systems for off-road driving incident prediction and assistance, methods for making/operating such systems, and vehicles networking with such systems. A method for operating a motor vehicle includes a system controller receiving geolocation data indicating the vehicle is in or entering off-road terrain. Responsive to the vehicle geolocation data, the controller receives, from vehicle-mounted cameras, camera-generated images each containing the vehicle's drive wheel(s) and/or the off-road terrain's surface. The controller receives, from a controller area network bus, vehicle operating characteristics data and vehicle dynamics data for the motor vehicle. The camera data, vehicle operating characteristics data, and vehicle dynamics data is processed via a convolutional neural network backbone to predict occurrence of a driving incident on the off-road terrain within a prediction time horizon.

Abstract: A system and method for error estimation in an eye gaze tracking system in a vehicle may include an operator monitoring system providing measured eye gaze information corresponding to an object outside the vehicle and an external object monitoring system providing theoretical eye gaze information and an error in the measured eye gaze information based upon the measured eye gaze information and the theoretical eye gaze information.

Abstract: A system in a vehicle includes an image sensor to obtain images in an image sensor coordinate system and a depth sensor to obtain point clouds in a depth sensor coordinate system. Processing circuitry implements a neural network to determine a validation state of a transformation matrix that transforms the point clouds in the depth sensor coordinate system to transformed point clouds in the image sensor coordinate system. The transformation matrix includes rotation parameters and translation parameters.

Abstract: A system includes a seat belt routing module and a user interface device (UID) control module. The seat belt routing module is configured to: determine a routing of a seat belt relative to an occupant in a vehicle seat based on input from a webbing payout sensor; and determine the seat belt routing based on an input from an in-cabin sensor. The in-cabin sensor includes at least one of a camera, an infrared sensor, an ultrasonic sensor, a radar sensor, and a lidar sensor. The UID control module is configured to control a user interface device to indicate that the seat belt is being worn improperly when: the seat belt routing determined using at least one of the webbing payout sensor and the in-cabin sensor is improper; and the seat belt routing determined using the webbing payout sensor corresponds to the seat belt routing determined using the in-cabin sensor.

Abstract: A system and method for error estimation in an eye gaze tracking system in a vehicle may include an operator monitoring system providing measured eye gaze information corresponding to an object outside the vehicle and an external object monitoring system providing theoretical eye gaze information and an error in the measured eye gaze information based upon the measured eye gaze information and the theoretical eye gaze information.

Abstract: A vehicle, system and a computer-implemented method for setting a height of a seat belt in a vehicle. The system includes a computer vision module, a motor and a controller. The computer vision module determines a seatbelt-neck distance (SND) and a seatbelt-shoulder distance (SSD) for an occupant of the vehicle. The motor adjusts the height of the seat belt. The controller control the motor to set the height of the seat belt based on the SND and the SSD.

Abstract: Vision-based airbag enablement may include capturing two-dimensional images of a passenger, segmenting the image, classifying the image, and determining seated height of the passenger from the image. Enabling or disabling deployment of the airbag may be controlled based at least in part upon the determined seated height.

Abstract: Methods, systems, and apparatuses to build an explainable user output to receive input feature data by a neural network of multiple layers of an original classifier; determine a semantic function to label data samples with semantic categories; determine a semantic accuracy for each layer of the original classifier within the neural network; compare each layer based on results from the comparison of the semantic accuracy; designate a layer based on an amount of computed semantic accuracy; extend the designated layer by a category branch to the neural network to extract semantic data samples from the semantic content to train a set of new connections of an explainable classifier to compute a set of output explanations with an accuracy measure associated each output explanation for each semantic category of the plurality of semantic categories, and compare the accuracy measure for each output explanation to generate the output explanation in a user understandable format.

Abstract: A system and method to adjust an augmented reality (AR) image involve a front-facing camera in a vehicle. The camera obtains an image that includes a road surface ahead of the vehicle. The system also includes a processor to detect lane lines of the road surface in three dimensions, to perform interpolation using the lane lines to determine a ground plane of the road surface, and to adjust the AR image to obtain an adjusted AR image such that all points of the adjusted AR image correspond with points on the ground plane.

Abstract: A system includes a seat belt routing module and a user interface device (UID) control module. The seat belt routing module is configured to: determine a routing of a seat belt relative to an occupant in a vehicle seat based on input from a webbing payout sensor; and determine the seat belt routing based on an input from an in-cabin sensor. The in-cabin sensor includes at least one of a camera, an infrared sensor, an ultrasonic sensor, a radar sensor, and a lidar sensor. The UID control module is configured to control a user interface device to indicate that the seat belt is being worn improperly when: the seat belt routing determined using at least one of the webbing payout sensor and the in-cabin sensor is improper; and the seat belt routing determined using the webbing payout sensor corresponds to the seat belt routing determined using the in-cabin sensor.

Abstract: A system for detecting seatbelt routing includes: a state module configured to, based on a series of images over a period of time from a camera of a vehicle facing a seat, determine and output a routing state of a seatbelt of the seat; and a remediation module configured to, based on the routing state of the seatbelt of the seat, selectively perform at least one remedial action.

Abstract: A seat belt status determining system and method for a vehicle that evaluate a seat belt and determine if it is buckled and if it is properly routed on a passenger. In order to evaluate the seat belt status, the system and method use seat belt sensors and cameras inside the vehicle cabin to generate data that is then analyzed in conjunction with machine learning techniques (e.g., supervised machine learning techniques implemented through the use of neural networks) to classify the seat belt status into one or more categories, such as: passenger not present, passenger present/seat belt not being worn, passenger present/seat belt being worn improperly, passenger present/seat belt being worn properly, and blocked view.

Abstract: A system for detecting seatbelt routing includes: a state module configured to, based on a series of images over a period of time from a camera of a vehicle facing a seat, determine and output a routing state of a seatbelt of the seat; and a remediation module configured to, based on the routing state of the seatbelt of the seat, selectively perform at least one remedial action.

Abstract: Methods and systems involve obtaining information from one or more sources to determine a real-time context. A method includes determining a situational awareness score indicating a level of vigilance required based on the real-time context, obtaining images of eyes of a driver to detect a gaze pattern of the driver, determining a relevant attention score indicating a level of engagement of the driver in the real-time context based on a match between the gaze pattern of the driver and the real-time context, and obtaining images of the driver to detect behavior of the driver. A driver readiness score is determined and indicates a level of readiness of the driver to resume driving the vehicle based on the behavior of the driver. An off-road glance time is obtained based on using the situational awareness score, the relevant attention score, and the driver readiness score.

Abstract: A vehicle, system and a computer-implemented method for setting a height of a seat belt in a vehicle. The system includes a computer vision module, a motor and a controller. The computer vision module determines a seatbelt-neck distance (SND) and a seatbelt-shoulder distance (SSD) for an occupant of the vehicle. The motor adjusts the height of the seat belt. The controller control the motor to set the height of the seat belt based on the SND and the SSD.

Abstract: A vehicle, system and method of adjusting a mirror of a vehicle. A system for adjusting a mirror of a vehicle is disclosed. The system includes a calibration a calibration marker disposed on the vehicle, a camera, a motor and a processor. The calibration marker forms a calibration image onto a face of an occupant of the vehicle via reflection through the mirror. The camera obtains a camera image including the calibration image and the face of the occupant. The processor determines from the camera image an initial location of the calibration image at the face, determines a calibrated setting of the mirror that places the calibration image at a calibration location, and operates the motor to adjust the mirror to the calibrated setting.

Abstract: Systems and methods to mitigate an effect of an errant signal on an image sensor of a vehicle involve collecting light and separating the light to obtain signals at different wavelengths. A method includes determining an intensity of the light at each of the different wavelengths, and identifying the errant signal based on the intensity of the light exceeding a threshold value at an errant signal wavelength among the different wavelengths. The errant signal is mitigated using the controller.

Abstract: An occupant monitoring apparatus is provided. The apparatus includes a laser illuminator configured to emit a laser to illuminate an occupant; and a sensor configured to generate an image of the occupant illuminated by the laser.