Future Internet (Dec 2022)

Single-Shot Global and Local Context Refinement Neural Network for Head Detection

  • Jingyuan Hu,
  • Zhouwang Yang

DOI
https://doi.org/10.3390/fi14120384
Journal volume & issue
Vol. 14, no. 12
p. 384

Abstract

Read online

Head detection is a fundamental task, and it plays an important role in many head-related problems. The difficulty in creating the local and global context in the face of significant lighting, orientation, and occlusion uncertainty, among other factors, still makes this task a remarkable challenge. To tackle these problems, this paper proposes an effective detector, the Context Refinement Network (CRN), that captures not only the refined global context but also the enhanced local context. We use simplified non-local (SNL) blocks at hierarchical features, which can successfully establish long-range dependencies between heads to improve the capability of building the global context. We suggest a multi-scale dilated convolutional module for the local context surrounding heads that extracts local context from various head characteristics. In comparison to other models, our method outperforms them on the Brainwash and the HollywoodHeads datasets.

Keywords