SegMam: Multi-Scale Deformable Cross-Mamba Attention With Pseudo-LiDAR From Multi-Camera Depth for BEV Segmentation

Bird’s Eye View (BEV) semantic segmentation serves as a critical perception technology for spatially coherent understanding of complex urban environments from multi-camera inputs in autonomous driving and intelligent transportation systems. While recent Transformer-based methods have demonstr...

Полное описание

Библиографические подробности

Главные авторы:	Junhan Kim, Hankyeol Yu, Kyungjae Ahn, Suyeon Kim, Yeonsik Kang
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2026-01-01
Серии:	IEEE Access
Предметы:	Bird’s Eye View semantic segmentation selective state space model depth estimation autonomous driving drivable area
Online-ссылка:	https://ieeexplore.ieee.org/document/11570114/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!