Manuscript received August 7, 2024; revised August 21, 2024; accepted September 4, 2024; published February 27, 2025.

Abstract—Image-based individual localization in densely populated scenes offers practical advantages beyond mere head counting, enabling a broader range of high-level tasks in crowd analysis. Crowd image data contain drastic changes in head sizes caused by the perspective effect. This specific challenge has not been addressed in the literature, as existing localization methods do not consider multi-scale features. To alleviate this issue, we propose a novel Multi-Scale Point-to-Point Network (MSP2P) in which a set of experts are in charge of predicting head locations a at different perspective levels. However, the training procedure requires ground-truth scale information for precise one-to-one matching. For this reason, we develop a simple yet effective method that uses neighbor density information to estimate the scale associated with each head location. Extensive experiments demonstrate that our method outperforms most state-of-the-art methods on relevant counting benchmarks without compromising performance.

Keywords—crowd localization, multi-scale, crowd counting

Cite: David Redó Nieto, Mikel Aramburu Retegui, Jorge García Castaño, and Antonio José Sánchez Salmerón, "MSP2P: Multi-Scale Point-based Approach for Optimal Crowd Localization Through Perspective Analysis," Journal of Image and Graphics, Vol. 13, No. 1, pp. 115-122, 2025.

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC-BY-4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.