Vehicle Object Tracking with Pseudo Targets After Detection Loss
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advanced driver assistance systems (ADAS) rely on robust object tracking to ensure safe operation of safety functions like Automatic Emergency Brake (AEB) and Adaptive Cruise Control (ACC). However, if the object tracker fails to detect a target vehicle, these safety functions can fail, potentially leading to collisions.
Innovation Solution
The method involves creating a pseudo object in the field of view (FOV) of a host vehicle when the original object is no longer tracked. This pseudo object is based on the last known position of the original object and is represented in non-drivable portions of the FOV, ensuring that safety functions can still operate effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the object tracker is used to detect and track target vehicles, then the safety functions can operate with accurate target information, but the system fails when the object tracker cannot detect the target vehicle
Solution Approach 1:
The system performs preliminary actions by creating a pseudo object based on the last known position and trajectory of the target vehicle before the object tracker actually fails. This proactive approach ensures that safety functions continue to have target information available, preventing the complete loss of tracking data and maintaining system reliability during tracker failures
Solution Approach 2:
The system creates a pseudo object that is a simplified copy or representation of the original target vehicle. This pseudo object contains essential information (position, trajectory, dimensions) derived from the last known state of the target, allowing safety functions to continue operating with approximate target data even when the original object tracker fails
2Device complexity
If the detection and tracking system is simplified to reduce complexity, then the system cost and complexity are reduced, but the tracking robustness deteriorates
Solution Approach 1:
The system implements self-service by automatically generating pseudo objects when tracking fails, without requiring complex additional sensors or manual intervention. The pseudo object creation uses readily available data (last known position, trajectory) and basic geometric calculations to maintain tracking continuity, providing a self-correcting mechanism that enhances robustness without significantly increasing system complexity
Data Source
AI summary
A computer-implemented method for tracking an object in a field of view (FOV) of a host vehicle. The method includes detecting and tracking, by a detection and tracking system mounted on the host vehicle, an object in the FOV. The method includes, upon failure of tracking the previously detected object in the FOV, creating, based on a last known position of the previously detected object and for a non-drivable portion of the FOV, a pseudo object representing the previously detected object.