IEEE Access (Jan 2020)

Two-Stream RGB-D Human Detection Algorithm Based on RFB Network

  • Wenli Zhang,
  • Jiaqi Wang,
  • Xiang Guo,
  • Kaizhen Chen,
  • Ning Wang

DOI
https://doi.org/10.1109/ACCESS.2020.3007611
Journal volume & issue
Vol. 8
pp. 123175 – 123181

Abstract

Read online

In order to effectively combine RGB image features with depth image features for human detection, this paper proposes a two-stream RGB-D human detection algorithm based on RFB network. The proposed algorithm mainly contains three parts: RGB-stream, Depth-stream and Channel Weight Fusion (CWF) strategy. (1) The RGB-stream extracts RGB image features using RFB-Net as the backbone network. (2) By analyzing the results of depth features visualization, we build the Depth-stream, which can effectively extract the depth image features. (3) The improved CWF strategy can enhance the effectiveness of important channels in RGB-D fusion features and improve the capability of the network expression. The experimental results show that the proposed algorithm has a significant improvement compared with other algorithms on two common datasets.

Keywords