# US 10,864,911 B2 · Automated detection of hazardous drifting vehicles by vehicle sensors > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,864,911 B2 - Document ID: US10864911B2 - Status: Granted - Kind: B2 - Application number: 15/915,438 - Filed: 2018-03-08 - Published: 2018-09-13 - Granted: 2020-12-15 - Earliest claimed: 2015-09-10 - Assignees: Continental Automotive GmbH - Applicants: Continental Automotive GmbH - Inventors: Razvan-Calin Jurca; Nicolae Pahontu - Web page: https://patentgrep.com/patent/US10864911B2 ## CPC - B60W 30/0956: {the prediction being responsive to traffic or environmental parameters} - B60W 30/095: Predicting travel path or likelihood of collision - B60W 30/0953: {the prediction being responsive to vehicle dynamic parameters} - B60W 40/09: Driving style or behaviour - B60W 50/14: Means for informing the driver, warning the driver or prompting a driver intervention - G01S 7/415: {Identification of targets based on measurements of movement associated with the target} - G01S 13/931: of land vehicles - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road} - B60W 2050/143: {Alarm means} - B60W 2050/146: {Display means} - B60W 2420/403: Image sensing, e.g. optical camera - B60W 2554/804: Relative longitudinal speed - B60W 2555/00: Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00 - B60W 2754/10: Spatial relation or speed relative to objects - B60W 2754/20: Lateral distance - B60W 2754/30: Longitudinal distance - B60W 2754/50: Relative longitudinal speed - G01S 13/867: {Combination of radar systems with cameras} - G01S 2013/9323: {Alternative operation using light waves} - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method and device for determining an anomalous driving pattern of a neighboring vehicle using a vehicle camera and/or other sensor is described. Image data is received and if suitable lane markings are detected, a reference trajectory is derived from the detected lane markers. Otherwise, a reference trajectory is derived from a motion of the present vehicle. A trajectory of the neighboring vehicle is determined, characteristic parameters of the detected trajectory are derived, and the characteristic parameters are compared with predetermined trajectory data. Based on the comparison it is determined if the trajectory of the neighboring vehicle is an anomalous trajectory and in one case an alert signal is generated. ## Claims ### Claim 1 A method for determining an anomalous driving pattern of a neighboring vehicle with a vehicle camera of a present vehicle, comprising: receiving image data from the vehicle camera, the image data comprising image frames; scanning the image data for lane markings; determining if the lane markings are suitable for deriving a trajectory of the neighboring vehicle relative to the lane markings in response to the lane markings being detected in the scanned image data; deriving a reference trajectory from the detected lane markings in response to the detected lane markings being suitable for deriving a trajectory; deriving the reference trajectory from a motion of the present vehicle in response to lane markings not being detected in the scanned image data; determining a trajectory of the neighboring vehicle relative to the reference trajectory; deriving characteristic parameters of the determined trajectory; comparing the characteristic parameters with predetermined trajectory data; determining, based on the comparison, if the trajectory of the neighboring vehicle is an anomalous trajectory; and outputting an alert signal in response to the trajectory of the neighboring vehicle being an anomalous trajectory. ### Claim 2 (depends on 1) The method according to claim 1, wherein the predetermined trajectory data comprise a deviation to the left or to the right with respect to the reference trajectory. ### Claim 3 (depends on 1) The method according to claim 1, wherein the predetermined trajectory data comprise a deviation pattern with respect to the reference trajectory. ### Claim 4 (depends on 3) The method according to claim 3, wherein the deviation pattern is a deviation time sequence with respect to the reference trajectory. ### Claim 5 (depends on 3) The method according to claim 3, wherein the deviation pattern comprises a first lateral deviation in a first direction and a subsequent second lateral deviation in a second direction, wherein the second direction is opposite to the first direction. ### Claim 6 (depends on 5) The method according to claim 5, wherein a duration of the second lateral deviation is shorter than a duration of the first lateral deviation. ### Claim 7 (depends on 2) The method according to claim 2, wherein the reference trajectory is derived from an image sequence of a lane marking. ### Claim 8 (depends on 2) The method according to claim 2, wherein the reference trajectory is derived from motion sensor data of the present vehicle. ### Claim 9 (depends on 1) The method according to claim 1, wherein the neighboring vehicle is a preceding vehicle. ### Claim 10 (depends on 1) The method according to claim 1, comprising triggering an alert action if it is determined that the trajectory of the neighboring vehicle is an anomalous trajectory, wherein the action is selected from slowing down the present vehicle, displaying an alert message on the instrument cluster of the present vehicle, sounding an alert signal inside the present vehicle, flashing the front lights of the present vehicle, sounding the horn of the present vehicle, sending a radio message via a radio transmitter of the present vehicle and forwarding the alert message to a collision warning system. ### Claim 11 An image processing unit for a vehicle, the image processing unit comprising: an input connection for receiving image data from a vehicle camera; and a computation unit which is operative to receive image data from the vehicle camera, the image data comprising image frames, scan the image data for lane markings and lane boundaries, determine, if lane markings are detected in the image frames, if the detected lane markings are suitable for deriving a trajectory of the neighboring vehicle relative to the lane markings and derive a reference trajectory from the detected lane markings, if it is determined that the detected lane markings are suitable, derive a reference trajectory from a motion of the present vehicle, determine a trajectory of the neighboring vehicles relative to the reference trajectory, derive characteristic parameters of the determined trajectory, compare the characteristic parameters with predetermined trajectory data, determine, based on the comparison, if the trajectory of the neighboring vehicle is an anomalous trajectory, and output an alert signal if it is determined that the trajectory of the neighboring vehicle is an anomalous trajectory.