Newest papers

Real-Time Radar Semantic and Panoptic Scene Understanding

Santosh Parit, Julia Hindel, Rohit Mohan, Georgi Pramatarov, Paul M. Newman, Daniele De Martini, Abhinav Valada · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26816 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La comprensión robusta de la configuración del segmento de red en diferentes condiciones ambientales es esencial para la conducción autónoma segura. Mientras que las cámaras y LiDAR degradan en condiciones meteorológicas adversas y de mala iluminación, el radar de rotación de ondas continuas moduladas por frecuencia 400 (FMCW) proporciona una percepción fiable de 360 ° en intervalos extendidos con un coste de computación mínimo. Sin embargo, la comprensión de la escena del radar FMCW en tiempo real es desafiante debido a los retornos de señales complejos, la resolución temporal limitada y los conjuntos de datos válidos de los decodificadores. Introducimos StreamRPS, un nuevo marco para la segmentación panóptica del radar de FMCW en streaming, que incluye un tubo de codificación de etiquetas

Machine translation (Meta M2M100); the English original follows.

Abstract

Robust scene understanding under varying environmental conditions is essential for safe autonomous driving. While cameras and LiDAR degrade in adverse weather and poor lighting, Frequency-Modulated Continuous-Wave (FMCW) spinning radar provides dependable 360° perception at extended ranges with minimal compute cost. However, real-time FMCW radar scene understanding is challenging due to complex signal returns, limited temporal resolution, and scarce annotated datasets. We introduce StreamRPS, a novel framework for streaming FMCW radar panoptic segmentation, comprising an automated label-generation pipeline via LiDAR scene completion and a real-time streaming network for semantic and panoptic segmentation. Our encoder-decoder streaming architecture comprises a radar-specific hierarchical Transformer encoder and task-specific decoders for semantic or panoptic prediction. Our encoder introduces a stem to capture range-dependent signatures, anisotropic patch embeddings to preserve angular resolution, and axial polar attention to separately model the periodic azimuth and bounded range axes. We further introduce azimuth roll rotation augmentation to simulate ego-vehicle rotation during training. Comprehensive experiments on the SAX and BOREAS datasets validate both our auto-labeling methodology and streaming segmentation network against established baselines. We outperform the strongest baseline by at least 1.4pp while processing sectors at over 400 FPS in a 4-sector streaming setting. We additionally provide manual annotations for 100 SAX radar scans, enabling independent evaluation of the entire framework.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Lidar, Computer vision, Artificial intelligence, Radar, Remote sensing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange