Real-time dynamic region of interest for sensor fusion on a fixed route.
2022-01-0076
03/29/2022
- Event
- Content
- Sensor fusion is a key technology for enabling the robust operation of automated vehicles. Sensor fusion typically utilizes inputs of cameras, radars, lidar, inertial measurement unit, and global navigation satellite systems to then output robust object detection or positioning data for automated vehicles. This paper will focus on sensor fusion between the camera, radar, and onboard vehicle sensors which is a critical need for near-term realization of sensor fusion benefits. All data collection and experiments were completed on an instrumented autonomous vehicle. The camera is an off-the-shelf computer vision product from MobilEye and the radar is a Delphi/Aptive electronically scanning radar (ESR) both of which are connected to a drive-by-wire capable vehicle platform. We utilize the MobilEye and wheel speed sensors to create a dynamic region of interest (DROI) of the drivable region that changes as the vehicle moves through the environment. The use of the DROI reduces the need for approximately 90% of the input detections, including radar, for processing. This provides not only accurate and robust detections but also has benefits in computational time and power. We then continue to reduce the number of detections in the driveable region using machine learning techniques such as density-based spatial clustering and applications with noise (DBSCAN). This is followed by KMeans clustering to further reduce detections and lastly fused with the extended Kalman filter. Our results show a large reduction in the need for radar detections processing after both fusion with our DROI and further clustering using machine learning techniques for the driveable region. Our proposed technique decreases the amount of fused misdetections, decreases computational power, and increases the reliability of the fused perception model which can greatly benefit current Advanced Driver Assistance System products available on the market today.
- Citation
- Brown, N., Fanas Rojas, J., Alzu'bi, H., Alrousan, Q. et al., "Real-time dynamic region of interest for sensor fusion on a fixed route.," SAE Technical Paper 2022-01-0076, 2022, .