Method and control unit for detecting a region of interest
AssigneeVisteon Global Technologies, Inc.
InventorsMartin Pfeifle, Niclas Zeller, Markus Mainberger
Life of this patent
Estimating the term…
Abstract
A method for a vehicle includes determining a region of interest based on environment sensor data corresponding an environment of the vehicle and a machine-learned predictor configured to identify, within the environment sensor data, a region as the region of interest that at least statistically coincides with a line of sight of an occupant of the vehicle. The method also includes classifying a detected object within the determined region of interest using an object detection algorithm. The method also includes operating the vehicle in based on at least one of the detected object and the determined region of interest.
Claims17
A system for a vehicle, the system comprising:
- an environment sensor configured to capture environment sensor data corresponding an environment of the vehicle;
- and
- a control unit coupled to the environment sensor and configured to, at a predetermined time:
- determine a region of interest based on the environment sensor data and a machine-learned predictor, wherein the machine-learned predictor is configured to identify, within the environment sensor data, a region as the region of interest that at least statistically coincides with a line of sight of an occupant of the vehicle;
- determine a corresponding sequence of environment sensor data for a sequence of time instants;
- determine a corresponding sequence of regions of interest based on the sequence of environment sensor data and the machine-learned predictor;
- determine a complexity measure indicative of a complexity of a driving situation at the sequence of time instants based on the sequence of regions of interest;
- and
- operate the vehicle in response to the complexity measure based on the determined region of interest.
A system for a vehicle, the system comprising:
- a processor;
- and
- a memory including instructions that, when executed by the processor, cause the processor to:
- determine a region of interest based on environment sensor data corresponding an environment of the vehicle and a machine-learned predictor configured to identify, within the environment sensor data, a region as the region of interest that at least statistically coincides with a line of sight of an occupant of the vehicle;
- classify a detected object within the determined region of interest using an object detection algorithm;
- determine a corresponding sequence of environment sensor data for a sequence of times;
- determine a corresponding sequence of regions of interest based on the sequence of environment sensor data and the machine-learned predictor;
- determine a complexity measure indicative of a complexity of a driving situation at the sequence of time instants based on the sequence of regions of interest;
- and
- operate the vehicle in response to the complexity measure based on at least one of the detected object and the determined region of interest.
A method for a vehicle, the method comprising:
- determining a region of interest based on environment sensor data corresponding an environment of the vehicle and a machine-learned predictor configured to identify, within the environment sensor data, a region as the region of interest that at least statistically coincides with a line of sight of an occupant of the vehicle;
- classifying a detected object within the determined region of interest using an object detection algorithm;
- determining a corresponding sequence of environment sensor data for a sequence of times;
- determining a corresponding sequence of regions of interest based on the sequence of environment sensor data and the machine-learned predictor;
- determining a complexity measure indicative of a complexity of a driving situation at the sequence of time instants based on the sequence of regions of interest;
- and
- operating the vehicle in response to the complexity measure based on at least one of the detected object and the determined region of interest.
Dependencies are inferred from the claim text.