Abstract: A system and a method for automatic assessment of comparative negligence of vehicle(s) involved in an accident. The system receives one or more of a video input, an accelerometer data, a gyroscope data, a magnetometer data, a GPS data, a Lidar data, a Radar data, a radio navigation data and a vehicle state data for vehicle(s). The system automatically detects an occurrence of an accident and its timestamp. The system then detects an accident type of the accident, and a trajectory of the vehicle(s) based on the received data for the detected timestamp. A scenario of the accident is generated and compared with a parametrized accident guideline to generate a comparative negligence assessment for the vehicle(s) involved in the accident.

Abstract: A system and a method for automatic assessment of comparative negligence of vehicle(s) involved in an accident. The system receives one or more of a video input, an accelerometer data, a gyroscope data, a magnetometer data, a GPS data, a Lidar data, a Radar data, a radio navigation data and a vehicle state data for vehicle(s). The system automatically detects an occurrence of an accident and its timestamp. The system then detects an accident type of the accident, and a trajectory of the vehicle(s) based on the received data for the detected timestamp. A scenario of the accident is generated and compared with a parametrized accident guideline to generate a comparative negligence assessment for the vehicle(s) involved in the accident.

Abstract: System and method for assessing driving behaviour and hard events in a vehicle in a GPS denied environment are disclosed. One or more first driving parameters are recorded using sensors such as accelerometer and gyroscope. A method for numerically reorienting the sensor parameters is also disclosed. The method computes the second driving parameters along the longitudinal, lateral and vertical axes of the vehicle based on the forces acting along the lateral axis of the vehicle is minimum when the vehicle is being driven along a straight path with non-zero acceleration. A method for detecting the hard events is also disclosed which detects the events that are symptomatic of unsafe driving. The detected events are then mapped to a score that can be used to measure safety and comfort of the drive and assess driving behaviour.

Abstract: A deep learning based computer vision system to detect and analyses automobile crash videos comprises a crash detection module and a crash analysis module. The crash detection module uses dashcam video and or telemetry to detect the same. The usage of computer vision algorithm alongside the IMU sensor data make the system robust. The system uses a deep learning model which looks for an anomalous pattern in the video and/or the IMU signal to detect a crash. The system comprises different machine learning and deep learning based computer vision algorithm to analyze the crash detected videos. The system automates the labor-intensive task of reviewing crash videos and generates a crash report comprising accident type, road surface, weather condition and accident scenario among other things. The accident detection and analysis modules can reside on the vehicle as well as on the cloud based on the compute capabilities of the edge device.