SPARK: Low Latency Single-Camera 3D Pose Estimation for Autonomous Racing using Keypoints
For autonomous racing teams, SPARK provides a low-latency, easy-to-deploy vision-based alternative to LiDAR for detecting non-cooperative opponents, enabling safer trajectory planning.
SPARK introduces a monocular 3D pose estimation algorithm for autonomous racing that achieves long-range detection with higher accuracy and lower latency than state-of-the-art monocular methods, while also outperforming LiDAR in speed and deployability.
In autonomous racing, fast detection of other participants' movements is required to plan safe, collision-free trajectories with non-cooperative opponents. LiDAR detection is inherently slower and harder to deploy on edge devices than vision methods, causing delayed detections that limit object tracking performance during high-dynamic maneuvering. Utilizing monocular 3D detection enables an easy-to-deploy, low-latency detection of other participants on the racetrack. We present SPARK, a single-camera pose-estimation algorithm for autonomous racing using keypoint detection. It achieves long-range detection with high accuracy, exceeding the performance of state-of-the-art monocular camera detection algorithms while maintaining lower latency. By employing well-optimized YOLO models and leveraging the fixed geometry in the autonomous racing domain, the algorithm also exhibits low latency and resource usage. We evaluate the performance of our approach on real-world autonomous racing data and compare it to state-of-the-art LiDAR and camera detection algorithms. The source code is available at: https://github.com/TUMFTM/SPARK-camera-det