使用地图查询库的在线地图生成控制地图分布
Control Map Distribution using Map Query Bank for Online Map Generation
AI总结：
本文提出地图查询库（MQBank）方法，将高精地图分布分解为点表示，并利用低成本SD地图先验为不同场景生成合适的初始地图查询分布，在OpenLaneV2基准上取得新纪录。
摘要：
可靠的自动驾驶系统需要包含详细地图信息的高精地图（HD map）以进行规划与导航。然而，预先构建高精地图需要巨大的成本。基于视觉的在线地图生成（Online Map Generation, OMG）已成为构建局部高精地图的一种低成本替代方案。基于查询的鸟瞰视图（BEV）Transformer 已成为该任务的基础模型。该模型从一个初始地图查询分布中学习高精地图预测，该初始分布通过在训练集上进行离线优化获得。除了 BEV 特征的质量外，该模型的性能还高度依赖于初始地图查询分布的容量。然而，由于查询数量有限，该分布受到限制。为了使地图预测在每个测试样本上达到最优，必须为每个特定场景生成合适的初始分布。本文提出将整个高精地图分布分解为一组点表示，即地图查询库（map query bank, MQBank）。为了构建不同场景的特定地图查询初始分布，引入低成本的标准定义地图（SD map）数据作为一种先验知识。此外，地图解码器网络的每一层学习实例级地图查询特征，这会丢失每个点的详细信息。然而，BEV 特征图是一种点级密集特征。在与 BEV 特征图交互时，保持地图查询中的点级信息非常重要。这也可以通过地图查询库方法解决。最终实验展示了对 SD 地图先验的新见解，并在 OpenLaneV2 基准上创造了新纪录，在车辆车道和行人区域上分别达到 40.5% 和 45.7% 的 mAP。
英文摘要：
Reliable autonomous driving systems require high-definition (HD) map that contains detailed map information for planning and navigation. However, pre-build HD map requires a large cost. Visual-based Online Map Generation (OMG) has become an alternative low-cost solution to build a local HD map. Query-based BEV Transformer has been a base model for this task. This model learns HD map predictions from an initial map queries distribution which is obtained by offline optimization on training set. Besides the quality of BEV feature, the performance of this model also highly relies on the capacity of initial map query distribution. However, this distribution is limited because the limited query number. To make map predictions optimal on each test sample, it is essential to generate a suitable initial distribution for each specific scenario. This paper proposes to decompose the whole HD map distribution into a set of point representations, namely map query bank (MQBank). To build specific map query initial distributions of different scenarios, low-cost standard definition map (SD map) data is introduced as a kind of prior knowledge. Moreover, each layer of map decoder network learns instance-level map query features, which will lose detailed information of each point. However, BEV feature map is a point-level dense feature. It is important to keep point-level information in map queries when interacting with BEV feature map. This can also be solved with map query bank method. Final experiments show a new insight on SD map prior and a new record on OpenLaneV2 benchmark with 40.5%, 45.7% mAP on vehicle lane and pedestrian area.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
