Advanced search
1 file | 21.17 MB Add to list

Deep learning fusion of RGB and depth images for pedestrian detection

Zhixin Guo (UGent) , Wenzhi Liao (UGent) , Yifan Xiao (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
In this paper, we propose an effective method based on the Faster-RCNN structureto combine RGB and depth images for pedestrian detection. During the training stage,we generate a semantic segmentation map from the depth image and use it to refine theconvolutional features extracted from the RGB images. In addition, we acquire moreaccurate region proposals by exploring the perspective projection with the help of depthinformation. Experimental results demonstrate that our proposed method achieves thestate-of-the-art RGBD pedestrian detection performance on KITTI [12] datase

Downloads

  • 0847-paper.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 21.17 MB

Citation

Please use this url to cite or link to this publication:

MLA
Guo, Zhixin, et al. “Deep Learning Fusion of RGB and Depth Images for Pedestrian Detection.” 30th British Machine Vision Conference (BMVC), Proceedings, 2019, pp. 1–13.
APA
Guo, Z., Liao, W., Xiao, Y., Veelaert, P., & Philips, W. (2019). Deep learning fusion of RGB and depth images for pedestrian detection. In 30th British Machine Vision Conference (BMVC), Proceedings (pp. 1–13). Cardiff, United Kingdom.
Chicago author-date
Guo, Zhixin, Wenzhi Liao, Yifan Xiao, Peter Veelaert, and Wilfried Philips. 2019. “Deep Learning Fusion of RGB and Depth Images for Pedestrian Detection.” In 30th British Machine Vision Conference (BMVC), Proceedings, 1–13.
Chicago author-date (all authors)
Guo, Zhixin, Wenzhi Liao, Yifan Xiao, Peter Veelaert, and Wilfried Philips. 2019. “Deep Learning Fusion of RGB and Depth Images for Pedestrian Detection.” In 30th British Machine Vision Conference (BMVC), Proceedings, 1–13.
Vancouver
1.
Guo Z, Liao W, Xiao Y, Veelaert P, Philips W. Deep learning fusion of RGB and depth images for pedestrian detection. In: 30th British Machine Vision Conference (BMVC), Proceedings. 2019. p. 1–13.
IEEE
[1]
Z. Guo, W. Liao, Y. Xiao, P. Veelaert, and W. Philips, “Deep learning fusion of RGB and depth images for pedestrian detection,” in 30th British Machine Vision Conference (BMVC), Proceedings, Cardiff, United Kingdom, 2019, pp. 1–13.
@inproceedings{8667041,
  abstract     = {In this paper, we propose an effective method based on the Faster-RCNN structureto combine RGB and depth images for pedestrian detection.  During the training stage,we generate a semantic segmentation map from the depth image and use it to refine theconvolutional features extracted from the RGB images.  In addition,  we acquire moreaccurate region proposals by exploring the perspective projection with the help of depthinformation.  Experimental results demonstrate that our proposed method achieves thestate-of-the-art RGBD pedestrian detection performance on KITTI [12] datase},
  author       = {Guo, Zhixin and Liao, Wenzhi and Xiao, Yifan and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {30th British Machine Vision Conference (BMVC), Proceedings},
  language     = {eng},
  location     = {Cardiff, United Kingdom},
  pages        = {1--13},
  title        = {Deep learning fusion of RGB and depth images for pedestrian detection},
  url          = {https://bmvc2019.org/wp-content/uploads/papers/0847-paper.pdf},
  year         = {2019},
}