稀疏 Laneformer

Sparse Laneformer

April 11, 2024

作者: Ji Liu, Zifeng Zhang, Mingjie Lu, Hongyang Wei, Dong Li, Yile Xie, Jinzhang Peng, Lu Tian, Ashish Sirasao, Emad Barsoum

cs.AI

摘要

在自動駕駛中，車道偵測是一項基本任務，隨著深度學習的出現取得了巨大進展。先前基於錨點的方法通常設計密集錨點，這些錨點高度依賴訓練數據集並在推論期間保持不變。我們分析了對於車道偵測來說密集錨點並非必要，並提出了一個基於稀疏錨點機制的基於變壓器的車道偵測框架。為此，我們通過位置感知車道查詢和角度查詢生成稀疏錨點，而非傳統的明確錨點。我們採用水平感知注意力（HPA）沿水平方向聚合車道特徵，並採用車道角度交叉注意力（LACA）在車道查詢和角度查詢之間進行交互作用。我們還提出了基於可變形交叉注意力的車道感知注意力（LPA）來進一步優化車道預測。我們的方法稱為Sparse Laneformer，易於實現並可端對端進行訓練。大量實驗表明Sparse Laneformer在CULane上表現優異，優於最先進的方法，例如在具有相同ResNet-34骨幹網絡的情況下，F1分數比Laneformer高出3.0％，比O2SFormer高出0.7％，並且計算量更少。

English

Lane detection is a fundamental task in autonomous driving, and has achieved great progress as deep learning emerges. Previous anchor-based methods often design dense anchors, which highly depend on the training dataset and remain fixed during inference. We analyze that dense anchors are not necessary for lane detection, and propose a transformer-based lane detection framework based on a sparse anchor mechanism. To this end, we generate sparse anchors with position-aware lane queries and angle queries instead of traditional explicit anchors. We adopt Horizontal Perceptual Attention (HPA) to aggregate the lane features along the horizontal direction, and adopt Lane-Angle Cross Attention (LACA) to perform interactions between lane queries and angle queries. We also propose Lane Perceptual Attention (LPA) based on deformable cross attention to further refine the lane predictions. Our method, named Sparse Laneformer, is easy-to-implement and end-to-end trainable. Extensive experiments demonstrate that Sparse Laneformer performs favorably against the state-of-the-art methods, e.g., surpassing Laneformer by 3.0% F1 score and O2SFormer by 0.7% F1 score with fewer MACs on CULane with the same ResNet-34 backbone.