Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering

Antonius Bima Murti Wijaya, Paul Henderson, Marwa Mahmoud

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

Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering

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
Paper Structure (16 sections, 6 equations, 3 figures, 5 tables, 1 algorithm)

This paper contains 16 sections, 6 equations, 3 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Pedestrian Tracking
  4. Pedestrian Trajectory Prediction
  5. Dynamic Clustering for Pedestrians
  6. Method
  7. Clustering Strategy
  8. Centroid Calculation
  9. Experiments
  10. Evaluation Metrics
  11. Implementation Details
  12. Datasets and Track Extraction
  13. Clustering Quality Results
  14. Trajectory Prediction Results
  15. Conclusion
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Our proposed dynamic clustering for dense crowds. The process starts with initialisation with a nested agglomerative cluster, evaluating the direction every 10 frames with LOF (Local Outlier Factor), and calculating the centroids. If LOF identifies outliers, then each outlier will be assigned to another cluster nearby or stored on an unassigned list. The process will execute the nested cluster again when a member of the unassigned list reaches a certain value. The Centroid Trajectory Calculation section shows how the cluster calculates its centroid trajectory accelerations based on the average deviation value from its membership value. The Cluster Assignment section illustrates the dynamic processing of clustering by the algorithm.
  • Figure 2: All images illustrate how our clustering method reduces the number of agents in the tracking results while preserving the overall trajectory patterns. The trajectories shown correspond to frames 70–400 for scenes 2, 3, and 4 of the HT21 dataset. The occurrence of each trajectory could vary depending on the frame.
  • Figure 3: Section A shows how the pedestrian numbers in the cluster keep up with the real pedestrian numbers in scenario 03 from the dataset. Section B shows the data distribution of the CMDD score, where the spike shows the cluster member direction noise. Sections C and D show how smooth trajectories are between the raw average calculation (C) and our proposed delta methods(D).