Abstract: The present disclosure relates to an omnidirectional sensor fusion system and method and a vehicle including the same. The omnidirectional sensor fusion system includes a sensor track processing unit configured to receive recognition information from one or more sensors to generate a sensor track, a sensor track association determination unit configured to determine, based on the generated sensor track being located at an overlapping point of sensing regions of the one or more sensors, an association between a previous sensor fusion track and the sensor track, the sensor track association determination unit further configured to change sensor track information in response to the determined association and output a sensor fusion track, a sensor fusion track tracing unit configured to trace the output sensor fusion track, and a sensor fusion track maintenance unit configured to maintain the traced sensor fusion track.

Abstract: The present disclosure provides an apparatus for associating sensor data in a vehicle. The apparatus includes a plurality of sensors configured to sense an external object and a processor configured to be electrically connected with the plurality of sensors. The processor is configured to obtain a sensor data set for a target located around the vehicle using the plurality of sensors, select at least a portion of sensor data included in the sensor data set based on at least one of target information, a curvature of a road where the vehicle or the target is traveling, or a type of a sensor configured to sense the target, and generate track data for the target by associating at least the portion of the sensor data.

Abstract: Disclosed are an occupancy distance map (ODM) information reliability determination system and method and a vehicle using the same. The system includes a signal conversion unit configured to receive a plurality of sensing signals and to perform signal processing, a calculation unit configured to calculate state information of a nearby vehicle detected from processed signals, a sensor fusion track output unit configured to output sensor fusion track information based on the calculated state information of the nearby vehicle, an ODM output unit configured to output ODM information based on the calculated state information of the nearby vehicle, an ODM fusion unit configured to generate sensor fusion ODM information by performing sensor fusion with respect to the ODM information, and an ODM information reliability determination unit configured to determine reliability of the sensor fusion ODM information by confirming association between the sensor fusion track information and the sensor fusion ODM information.

Abstract: A method of fusing a surrounding vehicle-to-vehicle (V2V) signal and a sensing signal of an ego vehicle includes calculating a position of a surrounding target vehicle and a velocity of the target vehicle based on the ego vehicle using global positioning system (GPS)/vehicle velocity information detected in the ego vehicle and GPS/vehicle velocity information included in a V2V signal detected in the target vehicle, extracting a sensor signal within a predetermined specific distance error from a position of the target vehicle relative to the ego vehicle of the V2V signal as a sensor information candidate group corresponding to the V2V signal, adaptively using a constant velocity model, a kinematic model or a dynamic model according to the extracted situation, and comparing the V2V signal with information on an object tracked using both the sensing signal and the V2V signal to estimate a position and velocity error of the V2V signal.

Abstract: An apparatus and method for identifying a short cut-in vehicle, and a vehicle using the same are disclosed. The apparatus includes a signal conversion unit configured to receive and signal-process a plurality of sensing signals, a computation unit configured to compute state information of a surrounding vehicle detected from the signal-processed signal, a sensor fusion track output unit configured to output a sensor fusion track based on the computed state information of the surrounding vehicle, an occupancy distance map (ODM) output unit configured to output ODM information including a grid map corresponding to a vehicle detection region and an ODM object including a plurality of detection points based on the computed state information of the surrounding vehicle, and a cut-in vehicle identification unit configured to identify a cut-in vehicle based on the output sensor fusion track and ODM information.

Abstract: Disclosed are an occupancy distance map (ODM) information reliability determination system and method and a vehicle using the same. The system includes a signal conversion unit configured to receive a plurality of sensing signals and to perform signal processing, a calculation unit configured to calculate state information of a nearby vehicle detected from processed signals, a sensor fusion track output unit configured to output sensor fusion track information based on the calculated state information of the nearby vehicle, an ODM output unit configured to output ODM information based on the calculated state information of the nearby vehicle, an ODM fusion unit configured to generate sensor fusion ODM information by performing sensor fusion with respect to the ODM information, and an ODM information reliability determination unit configured to determine reliability of the sensor fusion ODM information by confirming association between the sensor fusion track information and the sensor fusion ODM information.

Abstract: A method of fusing a surrounding vehicle-to-vehicle (V2V) signal and a sensing signal of an ego vehicle includes calculating a position of a surrounding target vehicle and a velocity of the target vehicle based on the ego vehicle using global positioning system (GPS)/vehicle velocity information detected in the ego vehicle and GPS/vehicle velocity information included in a V2V signal detected in the target vehicle, extracting a sensor signal within a predetermined specific distance error from a position of the target vehicle relative to the ego vehicle of the V2V signal as a sensor information candidate group corresponding to the V2V signal, adaptively using a constant velocity model, a kinematic model or a dynamic model according to the extracted situation, and comparing the V2V signal with information on an object tracked using both the sensing signal and the V2V signal to estimate a position and velocity error of the V2V signal.

Abstract: An apparatus and method for identifying a short cut-in vehicle, and a vehicle using the same are disclosed. The apparatus includes a signal conversion unit configured to receive and signal-process a plurality of sensing signals, a computation unit configured to compute state information of a surrounding vehicle detected from the signal-processed signal, a sensor fusion track output unit configured to output a sensor fusion track based on the computed state information of the surrounding vehicle, an occupancy distance map (ODM) output unit configured to output ODM information including a grid map corresponding to a vehicle detection region and an ODM object including a plurality of detection points based on the computed state information of the surrounding vehicle, and a cut-in vehicle identification unit configured to identify a cut-in vehicle based on the output sensor fusion track and ODM information.

Abstract: The present disclosure relates to an omnidirectional sensor fusion system and method and a vehicle including the same. The omnidirectional sensor fusion system includes a sensor track processing unit configured to receive recognition information from one or more sensors to generate a sensor track, a sensor track association determination unit configured to determine, based on the generated sensor track being located at an overlapping point of sensing regions of the one or more sensors, an association between a previous sensor fusion track and the sensor track, the sensor track association determination unit further configured to change sensor track information in response to the determined association and output a sensor fusion track, a sensor fusion track tracing unit configured to trace the output sensor fusion track, and a sensor fusion track maintenance unit configured to maintain the traced sensor fusion track.

Abstract: An apparatus and a method are capable of accurately deciding a maneuver of a surrounding vehicle. The apparatus includes a first surrounding vehicle information detector configured to obtain first surrounding vehicle information for a surrounding vehicle of a vehicle by using a front radar device. The apparatus further includes a second surrounding vehicle information detector configured to obtain second surrounding vehicle information for the surrounding vehicle by using a corner radar device. The apparatus also includes a processor configured to decide a motion of the surrounding vehicle by using the first surrounding vehicle information and the second surrounding vehicle information. The processor is also configured to decide a maneuver of the surrounding vehicle by using maneuver decision logic derived by a mechanical training technique. The processor is further configured to decide a final maneuver of the surrounding vehicle by using the two decision results.

Abstract: An apparatus and a method are capable of accurately deciding a maneuver of a surrounding vehicle. The apparatus includes a first surrounding vehicle information detector configured to obtain first surrounding vehicle information for a surrounding vehicle of a vehicle by using a front radar device. The apparatus further includes a second surrounding vehicle information detector configured to obtain second surrounding vehicle information for the surrounding vehicle by using a corner radar device. The apparatus also includes a processor configured to decide a motion of the surrounding vehicle by using the first surrounding vehicle information and the second surrounding vehicle information. The processor is also configured to decide a maneuver of the surrounding vehicle by using maneuver decision logic derived by a mechanical training technique. The processor is further configured to decide a final maneuver of the surrounding vehicle by using the two decision results.

Abstract: The present disclosure provides an apparatus for associating sensor data in a vehicle. The apparatus includes a plurality of sensors configured to sense an external object and a processor configured to be electrically connected with the plurality of sensors. The processor is configured to obtain a sensor data set for a target located around the vehicle using the plurality of sensors, select at least a portion of sensor data included in the sensor data set based on at least one of target information, a curvature of a road where the vehicle or the target is traveling, or a type of a sensor configured to sense the target, and generate track data for the target by associating at least the portion of the sensor data.

Abstract: An apparatus for warning an obstacle of a vehicle includes an image obtaining device configured to take an image around the vehicle through image sensors. An image segmentation device is configured to segment a current reference image obtained in blocks of an object. A motion estimator is configured to estimate two dimensional motion information of the object. A variation estimator is configured to estimate distance information between the object and the vehicle. A relative motion estimator is configured to estimate three dimensional relative motion information of the object by combining the two dimensional motion information and the distance information. A collision time estimator is configured to estimate a collision time between the object and the vehicle by using the three dimensional relative motion information. An image processor is configured to adjust a brightness of a corresponding segmented block. A display is configured to display the image.

Abstract: An apparatus for warning an obstacle of a vehicle includes an image obtaining device configured to take an image around the vehicle through image sensors. An image segmentation device is configured to segment a current reference image obtained in blocks of an object. A motion estimator is configured to estimate two dimensional motion information of the object. A variation estimator is configured to estimate distance information between the object and the vehicle. A relative motion estimator is configured to estimate three dimensional relative motion information of the object by combining the two dimensional motion information and the distance information. A collision time estimator is configured to estimate a collision time between the object and the vehicle by using the three dimensional relative motion information. An image processor is configured to adjust a brightness of a corresponding segmented block. A display is configured to display the image.