Localization in the Crowd with Topological Constraints

Abstract

We address the problem of crowd localization, i.e., the prediction of dots corresponding to people in a crowded scene. Due to various challenges, a localization method is prone to spatial semantic errors, i.e., predicting multiple dots within a same person or collapsing multiple dots in a cluttered region. We propose a topological approach targeting these semantic errors. We introduce a topological constraint that teaches the model to reason about the spatial arrangement of dots. To enforce this constraint, we define a persistence loss based on the theory of persistent homology. The loss compares the topographic landscape of the likelihood map and the topology of the ground truth. Topological reasoning improves the quality of the localization algorithm especially near cluttered regions. On multiple public benchmarks, our method outperforms previous localization methods. Additionally, we demonstrate the potential of our method in improving the performance in the crowd counting task.

arXiv commentAAAI 2021

References in corpus (7)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Distribution Matching for Crowd Counting
• Sliced Wasserstein Kernel for Persistence Diagrams
• A Topological Regularizer for Classifiers via Persistent Homology
• Connectivity-Optimized Representation Learning via Persistent Homology
• A Topological Filter for Learning with Label Noise

Cited by in corpus (5)

• Learning Independent Instance Maps for Crowd Localization
• Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Audio-visual Representation Learning for Anomaly Events Detection in Crowds
• Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network