Abstract: EYEN-P-003-PCT The present invention relates generally to the technological field of autonomous driving and advanced driver assistance. More specifically, the present invention relates to preventing occurrence of collisions and dangerous driving situations. The invention may be directed to a method of predicting driver behavior by at least one computing device. The method may include receiving a plurality of motion data elements, characterizing motion of at least one vehicle in at least one specific driving situation; based on the plurality of motion data elements, constructing a behavioral model representing expected driver behavior in the at least one specific driving situation; and inferring the behavioral model on at least one incoming motion data element, to predict expected driver behavior in the specific driving situation.

Abstract: The present invention relates generally to systems and methods of tagging (annotating) data for further use in supervised or semi-supervised machine learning. More specifically, the present invention relates to facilitating the tagging of data, in which the object of tagging is not presented in a detailed way. The invention represents a technical solution which provides effective detection and correction of incorrectly tagged data and helps tagging specialists to reduce the number of tagging mistakes. The invention represents method of facilitating data tagging for machine learning purposes and thereby increases training dataset quality and, consequently, increases reliability of ML model prediction or classification outputs.

Abstract: A system and method for determining a geographical location of one or more computing devices may include coupling a first computing device with one or more second computing devices, obtaining two or more position data elements representing geographical locations of the computing devices, and calculating a refined position data element of the first computing device based on the received position data elements. The system may include a non-transitory memory device, where modules of instruction code are stored, and at least one processor associated with the memory device, configured to execute the modules of instruction code. The method may include associating the at least one processor with a vehicle module of a vehicle and sending the refined position data element to the vehicle module, where the vehicle module may be configured to, for example, control a steering system of the vehicle.

Abstract: A method and system for producing a vulnerable vehicle awareness notification by a server device may include, on a server side: receiving, from a first client device, a location data element, representing current geographical location of the first client device; repeatedly receiving, from one or more second client devices, a corresponding position sample data element associated with a current timestamp; for at least one second client device, identifying a condition of geographical vicinity between the first client device and the at least one second client device; and based on said identified condition, sending the subset of position samples to the first client device. The first client device may, in turn, produce the vulnerable vehicle awareness notification based on the received subset of position samples.

Abstract: A multi-spectral vehicular system for providing pre-collision alerts, comprising two pairs of stereoscopic infrared (IR) and visible light (VL) sensors, each of which providing acquired image streams from a mutual field of view, which are synchronized to provide stereoscopic vision; a data fusion module for mutually processing the data streams, to detect objects within the field of view and calculating distances to detected objects; a cellular based communication module for allowing communication between the sensors and mobile phones/Infotainment systems of the vehicle. The module runs a dedicated background application that is adapted to monitor the vicinity of the vehicle to detect other vehicles having a similar system; calculate speed and heading azimuth of each of the other vehicles; and provide alerts to the driver of the vehicle whenever other vehicles having a similar system are in a path of collision with the vehicle, based on the calculation and on the speed of the vehicle.

Abstract: A multi-spectral vehicular system for providing pre-collision alerts, comprising two pairs of stereoscopic infrared (IR) and visible light (VL) sensors, each of which providing acquired image streams from a mutual field of view, which are synchronized to provide stereoscopic vision; a data fusion module for mutually processing the data streams, to detect objects within the field of view and calculating distances to detected objects; a cellular based communication module for allowing communication between the sensors and mobile phones/Infotainment systems of the vehicle. The module runs a dedicated background application that is adapted to monitor the vicinity of the vehicle to detect other vehicles having a similar system; calculate speed and heading azimuth of each of the other vehicles; and provide alerts to the driver of the vehicle whenever other vehicles having a similar system are in a path of collision with the vehicle, based on the calculation and on the speed of the vehicle.

Abstract: A system for predicting and preventing car accidents and collisions between vehicles and pedestrians, which comprises a plurality of mobile devices each carried by a pedestrian user or a user riding in a vehicle; a dedicated software application installed on each of the mobile devices adapted to detect the location of the mobile device; one or more geographic servers, each geographic server assigned to a geographic territory and adapted to communicate position and motion information with mobile devices in its geographic territory; and a bridge module adapted to register and sign-in users to the system, and establish and maintain a connection between mobile devices and geographic servers. The geographic server of each territory receives ongoing position and motion updates from all of the mobile devices in its territory and transmits ongoing position and motion updates associated with position and motion of other mobile devices to mobile devices in its territory.

Abstract: A system for predicting and preventing car accidents and collisions between vehicles and pedestrians, which comprises a plurality of mobile devices each carried by a pedestrian user or a user riding in a vehicle; a dedicated software application installed on each of the mobile devices adapted to detect the location of the mobile device; one or more geographic servers, each geographic server assigned to a geographic territory and adapted to communicate position and motion information with mobile devices in its geographic territory; and a bridge module adapted to register and sign-in users to the system, and establish and maintain a connection between mobile devices and geographic servers. The geographic server of each territory receives ongoing position and motion updates from all of the mobile devices in its territory and transmits ongoing position and motion updates associated with position and motion of other mobile devices to mobile devices in its territory.