A method and a device for a motor vehicle of adapting safety mechanisms of a vehicle safety system. The method includes acquiring (s101) data to create a representation (113) of a current vehicle surrounding (110), comparing (s102) the created representation to pre-stored representations of vehicle surroundings, with a risk assessment measure (R) associated with it which stipulates whether to trigger the safety mechanism of the vehicle safety system. If there is correspondence between the created representation and one of the pre-stored representations; detecting (s103) a vehicle behavior associated with the current surrounding, and determining (s104), whether to adjust triggering of the safety mechanism associated with the at least one risk assessment measure of the pre-stored representation of the current vehicle surrounding for which there is a match with the created representation.

An impact detection system is disclosed for detecting and identifying an object colliding with a vehicle. The impact detection system comprises a sensor arrangement arranged to measure a characteristic of an impact of the object against the vehicle, a trigger determiner associated with the sensor arrangement for determining whether the characteristic of the 5 impact is greater than a predefined threshold value, and an image capturing device arranged to capture an image of the object. The system is arranged to automatically make the captured image available for inspection in response to the trigger determiner determining that the characteristic of the impact is greater than the predefined threshold value so that the object in the image can be identified substantially in real-time.

In order to detect a vehicle accident in which a vehicle and an object crash into one another, wherein a motion variable assigned to the collision is so low that at least one active occupant protection system provided for accidents in the vehicle is not activated by the crash, it is provided, with respect to the collision event, that signals and/or data formed by sensors of the vehicle are processed in such a manner that the signals and/or data are filtered, feature data are formed based on the filtered signals and/or data, and the collision event is assigned to a classification in a classification database based on the feature data.

A method and system may identify vehicle collisions in real-time or at least near real-time based on statistical data collected from previous vehicle collisions. A user's portable computing device may obtain sensor data from sensors in the portable computing device and compare the sensor data to a statistical model indicative of a vehicle collision, where the statistical model includes sensor data characteristics which correspond to the vehicle collision. The sensor data characteristics may include several threshold sample rate ranges at which another sensor data characteristic is measured and for each of the threshold sample rate ranges, a different threshold value for the other sensor data characteristic. If the portable computing device identifies a vehicle collision based on the comparison, notifications may be sent to emergency contacts and/or emergency personnel to provide assistance to the user.

Disclosed is a method for predicting collision severity, including: establishing a first learning model, and inputting vehicle data and collision accident scene feature data into the first learning model; obtaining a predicted collision acceleration curve outputted by the first learning model, the predicted collision acceleration curve being established based on a plane rectangular coordinate system; establishing a second learning model, and inputting the predicted collision acceleration curve, the occupant feature data and the restraint system feature data into the second learning model; obtaining a plurality of predicted collision kinematics and dynamics curves of human body parts outputted by the second learning model; generating a collision severity parameter according to the plurality of predicted collision kinematics and dynamics curves of the human body parts, the collision severity parameter being configured to evaluate the collision severity.

A collision detection device includes a first acceleration acquisition unit, a second acceleration acquisition unit, and a frontal collision determination unit. The first acceleration acquisition unit acquires longitudinal acceleration output from a left-side sensor and a right-side sensor. The second acceleration acquisition unit acquires the longitudinal acceleration output from a main sensor, which is an acceleration sensor different from the left-side sensor and the right-side sensor. A frontal collision determination unit determines an occurrence of the frontal collision based on a safing determination based on the longitudinal acceleration acquired at the first acceleration acquisition unit and a main determination based on the longitudinal acceleration acquired at the second acceleration acquisition unit.

A method and system for operating restraint devices in a vehicle during a fast roll event or a slow roll event includes a lateral acceleration sensor and an angular rate sensor. When the angular rate and a vertical acceleration of the vehicle predict a vehicle rollover, the system integrates the lateral acceleration from the lateral acceleration sensor to obtain a roll rate velocity. When the lateral acceleration is greater than a fast lateral acceleration threshold and the roll rate velocity is greater than a fast roll rate velocity threshold, the system provides a fast roll event output. When the lateral acceleration is less than the fast lateral acceleration threshold and greater than a slow lateral acceleration threshold while the roll rate velocity is greater than a slow roll rate velocity threshold, the system provides a slow roll event output. The system operates restraint devices based on the roll event.

A method and system for operating restraint devices in a vehicle during a fast roll event or a slow roll event includes a lateral acceleration sensor and an angular rate sensor. When the angular rate and a vertical acceleration of the vehicle predict a vehicle rollover, the system integrates the lateral acceleration from the lateral acceleration sensor to obtain a roll rate velocity. When the lateral acceleration is greater than a fast lateral acceleration threshold and the roll rate velocity is greater than a fast roll rate velocity threshold, the system provides a fast roll event output. When the lateral acceleration is less than the fast lateral acceleration threshold and greater than a slow lateral acceleration threshold while the roll rate velocity is greater than a slow roll rate velocity threshold, the system provides a slow roll event output. The system operates restraint devices based on the roll event.

Techniques for using machine learning-based continuous monitoring to improve crash detection and response system accuracy are provided. In examples, a driving event is detected as it occurs at a first time from driving data collected by a plurality of sensors of a mobile device disposed in a vehicle during a trip. After a second time, a crash prediction model is executed on driving data leading up to the second time to generate a first crash classification. In response to determining that the first crash classification meets first criterion, an escalation action sequence is initiated based on a severity of the crash prediction. After a third time, the crash model is executed on driving data leading up to the third time to generate a second classification, from which it is determined whether to terminate the escalation action sequence prior to an automatic execution of an action.

A system of object detection for a trailer. In one example, the system includes a camera configured to capture images of the trailer, where the images include an object other than the trailer. The system also includes a sensor configured to capture sensor data, a display configured to display images from the perspective of the camera, and a controller on the vehicle. The controller includes an electronic processor configured to receive the image data from the camera, receive the sensor data from the sensor, determine a blind spot, analyze the sensor data for radar data associated with the object, calculate the position of the object relative to the blind spot and the trailer, determine that the object is within the blind spot using an object detection algorithm, and in response to the determining that the object is within the blind spot, generate an augmented image.