DSP-SLAM++: 実環境向けマルチクラス・高忠実度オブジェクトSLAMの統合フレームワーク
DSP-SLAM++: A Unified Framework for Multi-Class, High-Fidelity Object SLAM in the Wild
既存のオブジェクト認識SLAMの課題（リアルタイム性、マルチクラス対応、高忠実度モデル生成のトレードオフ）を解決するため、DSP-SLAM++を提案。非同期マッピングパイプラインと魚眼カメラ-LiDARセンサ融合により、処理遅延を最大70%削減し、25Hzのマルチクラスデータセットで頑健なリアルタイム性能を実現した。
著者: Ahmad Kourani, Ghina Daoud, Daniel Asmar, Imad Elhajj
分類: cs.RO, cs.CV
原文アブストラクト
Existing object-aware SLAM systems force a trade-off between real-time performance, multi-class support, and the generation of high-fidelity, semantically coherent object models. To address this trade-off, we present DSP-SLAM++, which extends the DSP-SLAM framework with an asynchronous mapping pipeline for real-time performance and dedicated sensor fusion adaptations for a monocular fisheye-LiDAR suite. Experiments demonstrate that our system generates fine-grained, geometrically-complete shapes for multiple object classes while eliminating severe mapping thread bottlenecks by reducing maximum object processing latency by up to 70\% compared to the state-of-the-art baseline, enabling robust, real-time performance on a challenging 25 Hz multi-class datasets. This work makes high-fidelity, multi-class object SLAM more practical for real-world applications like autonomous driving and robotic manipulation by enabling its use on platforms with common fisheye-LiDAR sensor setups. The open-source code is available at: [github.com/AUBVRL/DSP-SLAMpp].