Work

Localization in the Crowd with Topological Constraints

Year: 2021

Type: conference-paper

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.

Source: Proceedings of the AAAI Conference on Artificial Intelligence

DOI: 10.1609/aaai.v35i2.16170

Authors: Shahira Abousamra, Minh Hoai, Dimitris Samaras, Chao Chen

Institution: Stony Brook University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: National Science Foundation, State University of New York, Defense Advanced Research Projects Agency, Air Force Research Laboratory

Awards: RI: Medium: Inverse Reinforcement Learning for Human Attention Modeling, G4713059963, RI: Small: Collaborative Research: Topology-Aware Image Understanding using Deep Variational Objectives, AitF: Collaborative Research: Topological Algorithms for 3D/4D Cardiac Images: Understanding Complex and Dynamic Structures