Back to AI News
arxiv

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.

AI Brief

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.

arXiv:2611.24352v1 Announce Type: cross Abstract: Trajectory forecasting at urban intersections is often studied assuming that reliable bird's-eye-view (BEV) motion histories are available, which in practice requires costly resources such as LiDAR, aerial views, HD maps, or calibrated infrastructure. We address this upstream perception-to-forecasting problem by reconstructing and predicting agents' BEV trajectories only from paired opposite-corner RGB cameras mounted on existing urban infrastructure at variable heights at inference time. We introduce the Opposite-Corner Trajectory Reconstruction and Anticipation Architecture (OCTR2A), a modular pipeline integrating per-view detection with class refinement, geometric cross-camera matching, transformer-based BEV projection, and egocentric GRU forecasting, trained in cascade and mainly supervised with a soft multi-scale spatial-overlap loss. Since no public benchmark provides this sensing configuration, we introduce R3ST++, a Blender-based synthetic benchmark built from SIND trajectories that provides synchronized opposite-corner views, cross-view correspondences, and BEV ground truth, while also serving as a deployment-support simulator for site-specific fine-tuning. Experiments on these datasets show that, with 12 observed and 12 predicted frames at 10\,Hz, OCTR2A achieves projection~-~forecasting ADE/FDE of 0.144/0.140~-~0.154/0.241~meters in real time on a single consumer GPU. Evaluated on ground-truth BEV histories, the forecasting module improves over the strongest state-of-the-art methods on SIND by 66.7\%/41.7\% ADE/FDE. Transfer experiments on TUMTraf-V2X show that R3ST++ pretraining supports adaptation to real-world roadside domains with different sensing configurations.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!