Localization in the Crowd with Topological Constraints


  • Shahira Abousamra Stony Brook University
  • Minh Hoai Stony Brook University
  • Dimitris Samaras Stony Brook University
  • Chao Chen Stony Brook University




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.




How to Cite

Abousamra, S., Hoai, M., Samaras, D., & Chen, C. (2021). Localization in the Crowd with Topological Constraints. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 872-881. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16170



AAAI Technical Track on Computer Vision I