SAVTrack：面向可靠性感知点云跟踪的选择性投票聚合
SAVTrack: Selective Vote Aggregation for Reliability-Aware Point Cloud Tracking
浏览论文内容
中文总结 AI 辅助
针对点云稀疏导致投票不可靠的问题，提出SAVTrack，通过选择性投票聚合估计投票可靠性并过滤低置信度假设，在KITTI和nuScenes上取得领先性能且计算开销小。
中文摘要 AI 辅助
在LiDAR点云中进行3D单目标跟踪（SOT）对于自主系统至关重要，但在稀疏和不完整的观测条件下仍然具有挑战性。在这种情况下，不同的目标点对目标中心提供极不均匀的约束，导致某些点到中心的投票比其他投票的可靠性低得多。现有的基于点的跟踪器通常聚合这些假设而不显式建模其可靠性，使得不准确的投票污染提议聚类并降低定位精度。为解决此问题，我们提出SAVTrack，一种具有选择性投票聚合（SAV）的运动感知跟踪框架。SAVTrack从局部种子特征和帧间运动上下文估计每个候选投票的可靠性，并在提议聚类之前移除低置信度假设。这种聚合前门控防止不可靠的假设影响聚类形成，同时仅引入适度的计算开销。SAVTrack在KITTI和nuScenes上实现了有竞争力的性能，分别达到68.4/87.4和58.44/69.82的成功率/精度，同时以82 FPS运行。它保留的候选投票少于密集聚合所用投票的六分之一，并且在稀疏目标观测下特别有效。
英文摘要
3D single object tracking (SOT) in LiDAR point clouds is essential for autonomous systems, but remains challenging under sparse and incomplete observations. In such cases, different target points provide highly uneven constraints on the object center, causing some point-to-center votes to be substantially less reliable than others. Existing point-based trackers typically aggregate these hypotheses without explicitly modeling their reliability, allowing inaccurate votes to contaminate proposal clustering and degrade localization accuracy. To address this issue, we propose \textbf{SAVTrack}, a motion-aware tracking framework with \textbf{Selective Vote Aggregation (SAV)}. SAVTrack estimates the reliability of each candidate vote from both local seed features and inter-frame motion context, and removes low-confidence hypotheses before proposal clustering. This pre-aggregation gating prevents unreliable hypotheses from affecting cluster formation while introducing only modest computational overhead. SAVTrack achieves competitive performance on KITTI and nuScenes, reaching 68.4/87.4 and 58.44/69.82 Success/Precision, respectively, while running at 82 FPS. It retains fewer than one-sixth of the candidate votes used by dense aggregation and remains particularly effective under sparse target observations.
发表机构
- Southeast University（东南大学）
- Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education（教育部复杂工程系统测量与控制重点实验室）
- University of Pennsylvania（宾夕法尼亚大学）
- Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
机构由 AI 辅助整理，请以论文原文为准。
