OCTR2A: Real-Time RGB-to-BEV Trajectory Projection and Forecasting at Urban Intersections
The paper introduces OCTR2A, a modular pipeline that reconstructs bird's-eye-view motion histories and forecasts agent trajectories using only paired opposite-corner RGB cameras mounted on urban infrastructure. It combines per-view detection, geometric cross-camera matching, transformer-based BEV projection, and GRU forecasting, and introduces R3ST++, a Blender-based synthetic benchmark built from SIND trajectories with synchronized views and BEV ground truth. With 12 observed and 12 predicted frames at 10 Hz, the authors report projection-forecasting ADE/FDE of 0.144/0.140 to 0.154/0.241 meters in real time on a single consumer GPU, and 66.7%/41.7% ADE/FDE improvements on SIND when forecasting from ground-truth BEV histories. Transfer experiments on TUMTraf-V2X indicate that R3ST++ pretraining supports adaptation to real-world roadside domains with different sensing configurations.
It presents a concrete perception-to-forecasting pipeline that reduces dependence on LiDAR, HD maps, or calibrated infrastructure while reporting real-time performance and a new benchmark.
Comments & Questions (0)
No comments yet
Be the first to comment!