Scale Mapping and Dynamic Re-Detecting in Dense Head Detection
Zikai Sun, Dezhi Peng, Zirui Cai, Zirong Chen, Lianwen Jin · 2018
Convolutional neural networks (CNNs) have demonstrated a strong ability to extract semantics from images during object detection; however, the extracted semantics are typically have strong scale priors for a specific circumstance. In this paper, we investigate the influence of head scale and contextual information, and then propose a scale-invariant method for head detection. Our method can dynamically detect heads depending on the complexity of the image. It uses an extra feature map to represent the scale information of the spatial relationship, and then uses this feature map for auxiliary detection. Particularly, we exploit several new techniques, including contextual information, scale invariance, and hard example mining. We evaluated our method on three head datasets and achieved state-of-the-art results for the Brainwash dataset, HollywoodHeads dataset, and SCUT-HEAD dataset.