用深度信息引导查询点，提升交通场景3D目标检测精度
DQ3D: Depth-guided Query for Transformer-Based 3D Object Detection in Traffic Scenarios
- 根据深度图和2D检测结果生成更靠近物体的查询点
- 在nuScenes上mAP提升6.3%，NDS提升4.3%
- 适合处理遮挡目标，适用于自动驾驶感知系统
从多视角图像进行交通场景中的3D目标检测近年来受到广泛关注。现有方法多基于3D参考点生成对象查询以定位目标，但部分参考点常远离真实物体，导致误检。本文提出一种深度引导的查询生成器（DQ3D），利用深度信息和2D检测结果，确保参考点采样于物体表面或内部。为解决当前帧中部分遮挡物体的问题，引入融合历史检测结果与深度引导查询的混合注意力机制，形成混合查询。在nuScenes数据集上的评估表明，该方法相比基线在平均精度（mAP）上提升6.3%，在NuScenes检测得分（NDS）上提升4.3%。
原文摘要 · Abstract (English)
3D object detection from multi-view images in traffic scenarios has garnered significant attention in recent years. Many existing approaches rely on object queries that are generated from 3D reference points to localize objects. However, a limitation of these methods is that some reference points are often far from the target object, which can lead to false positive detections. In this paper, we propose a depth-guided query generator for 3D object detection (DQ3D) that leverages depth information and 2D detections to ensure that reference points are sampled from the surface or interior of the object. Furthermore, to address partially occluded objects in current frame, we introduce a hybrid attention mechanism that fuses historical detection results with depth-guided queries, thereby forming hybrid queries. Evaluation on the nuScenes dataset demonstrates that our method outperforms the baseline by 6.3\% in terms of mean Average Precision (mAP) and 4.3\% in the NuScenes Detection Score (NDS).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。