Improving the accuracy of camera range estimates with automotive radar

Date

2025-5-6

Author

İkiz, Yunus Emre

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

100
views

0
downloads

Cite This

Cars equipped with Advanced Driver Assistance Systems (ADAS) and autonomous driving capabilities are a reality today, thanks to rapid advancements in sensors and the perception algorithms that process their data. These technologies, which enhance road safety and reduce accident-related costs, must also adhere to design budgets while meeting critical safety standards. Automotive-grade radars—also known as millimeter-wave radars—are resilient sensors that perform well in harsh weather conditions. However, they lack the resolution needed to provide detailed perception in static environments, and ambient noise remains a known issue. Cameras, on the other hand, can provide a clear visual representation of the environment but struggle to represent surroundings in 3D with high precision. This thesis explores strategies for improving object tracking by leveraging the complementary strengths of these two sensors. Specifically, we investigate methods to enhance camera-based detections by integrating accurate 3D ranging and Doppler speed measurements from radar with the camera’s unique classification and angular position data. The results demonstrate that combining complementary information from both sensors improves tracking accuracy, as well as the precision of range and velocity estimations.

Subject Keywords

Camera, Millimeter wave radar, Sensor fusion, Kalman filter

URI

https://hdl.handle.net/11511/114634

Collections

Graduate School of Natural and Applied Sciences, Thesis