An ultra-fast human detection method for color-depth camera

Jun Liu, Guyue Zhang, Ye Liu, Luchao Tian, Yan Qiu Chen

Abstract

Highlights • An extremely fast technique to locate positions that are plausibly humans is proposed to quickly reduce searching space. • A novel knowledge based human locator which can deal with partial occlusion and incomplete depth data is proposed. • A stepwise filtering framework enables the system to perform very quickly (80–140 fps). Abstract Real-time human detection is important for a wide range of applications. The task is highly challenging due to occlusions, complex backgrounds, and variation of human poses. We propose a cascade-structured approach to real-time human detection in cluttered and dynamic environments with both color and depth data seamlessly incorporated. The first stage efficiently exploits depth data which generates a set of physically plausible yet over-detected candidates. These candidates are then purified by another two filters: a knowledge based human upper portion locator and a data-driven learning based filter. Experimental results show high detection accuracy achieved by the proposed method at 80–140 fps on a single CPU core (without GPU acceleration).
BibTeX
@article{liu2015ultra,
  author = {Jun Liu and Guyue Zhang and Ye Liu and Luchao Tian and Yan Qiu Chen},
  title = {{An ultra-fast human detection method for color-depth camera}},
  journal = {J. Vis. Commun. Image Represent.},
  year = {2015},
  url = {https://openreview.net/forum?id=TCsL6Goxayr},
}

Loading related content...

Figure