TDFANet: 軌道誘導型変形可能特徴集約による4Dレーダー点群の逐次符号化に基づく場所認識
TDFANet: Encoding Sequential 4D Radar Point Clouds Using Trajectory-Guided Deformable Feature Aggregation for Place Recognition
悪天候に強い4Dレーダーの逐次スキャンから動的点除去と自己速度推定を行い、BEV特徴を軌道で位置合わせして時空間特徴を集約する場所認識手法を提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Shouyi Lu, Guirong Zhuo, Haitao Wang, Quan Zhou, Huanyu Zhou, Renbo Huang, Minqing Huang, Lianqing Zheng, Qiang Shu
分類: cs.RO
原文アブストラクト
Place recognition is essential for achieving closed-loop or global positioning in autonomous vehicles and mobile robots. Despite recent advancements in place recognition using 2D cameras or 3D LiDAR, it remains to be seen how to use 4D radar for place recognition - an increasingly popular sensor for its robustness against adverse weather and lighting conditions. Compared to LiDAR point clouds, radar data are drastically sparser, noisier and in much lower resolution, which hampers their ability to effectively represent scenes, posing significant challenges for 4D radar-based place recognition. This work addresses these challenges by leveraging multi-modal information from sequential 4D radar scans and effectively extracting and aggregating spatio-temporal features.Our approach follows a principled pipeline that comprises (1) dynamic points removal and ego-velocity estimation from velocity property, (2) bird's eye view (BEV) feature encoding on the refined point cloud, (3) feature alignment using BEV feature map motion trajectory calculated by ego-velocity, (4) multi-scale spatio-temporal features of the aligned BEV feature maps are extracted and aggregated.Real-world experimental results validate the feasibility of the proposed method and demonstrate its robustness in handling dynamic environments. Source codes are available.
