People detection and articulated pose estimation framework for crowded scenes

Sohailah Alyammahi, Harish Bhaskar, Dymitr Ruta, Mohammed Al-Mualla

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


In this paper, we propose a novel articulated pose estimation framework for the simultaneous detection of the human as a whole and their constituent body parts in crowded scenes. The model uses a single discriminative classifier that searches for dependent limbs thereby alleviating the independent inference limitation of other state-of-the-art models. The proposed framework is a hierarchical model that detects humans at both macro and micro levels by fusing global and local detectors. The proposed methodology is validated using a publicly available crowd dataset captured indoors in a sports stadium. Detection results are assessed using the percentage of correctly localized parts (PCP) evaluation metric and compared against competing baselines. Our experimental results report mean detection accuracy of 85% for the global upper body, 95% for the head, 82% for the torso, 71% and 60% for upper and lower arms respectively. A systematic analysis of results also verifies that the proposed model outperforms the state-of-the-art models in terms of detection rate, accuracy and computational complexity.

Original languageBritish English
Pages (from-to)83-104
Number of pages22
JournalKnowledge-Based Systems
StatePublished - 1 Sep 2017


  • Crowd scenes
  • Deformable part models
  • Hierarchical model
  • Joint model
  • Percentage of correctly localized parts
  • Support vector machines


Dive into the research topics of 'People detection and articulated pose estimation framework for crowded scenes'. Together they form a unique fingerprint.

Cite this