arXiv cs.AI· Antonius Bima Murti Wijaya, Paul Henderson, Marwa Mahmoud·· 9 天前AI 评分22
基于动态聚类的密集人群轨迹预测方法
Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering
AI 导读
研究者提出一种基于聚类的即插即用方法用于密集人群轨迹预测，按相似属性随时间对个体分组，以群体质心替代行人输入接入现有轨迹预测器。在多个密集人群场景中，该方法相比 SOTA 方法处理更快、内存占用更低，同时保持精度。
正文 · 原文
Abstract:Crowd trajectory prediction plays a crucial role in public safety and management, where it can help prevent disasters such as stampedes. Recent works address the problem by predicting individual trajectories and considering surrounding objects based on manually annotated data. However, these approaches tend to overlook dense crowd scenarios, where the challenges of automation become more pronounced due to the massiveness, noisiness, and inaccuracy of the tracking outputs, resulting in high computational costs. To address these challenges, we propose and extensively evaluate a novel cluster-based approach that groups individuals based on similar attributes over time, enabling faster execution through accurate group summarisation. Our plug-and-play method can be combined with existing trajectory predictors by using our output centroid in place of their pedestrian input. We evaluate our proposed method on several challenging dense crowd scenes. We demonstrated that our approach leads to faster processing and lower memory usage when compared with state-of-the-art methods, while maintaining the accuracy
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2603.18166 [cs.AI] |
| (or arXiv:2603.18166v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2603.18166 arXiv-issued DOI via DataCite |
Submission history
From: Antonius Bima Murti Wijaya [view email]
[v1]
Wed, 18 Mar 2026 18:04:54 UTC (14,506 KB)
[v2]
Thu, 8 Oct 2026 11:21:49 UTC (396 KB)
来源：arXiv cs.AI · arxiv.org