A Novel Multi-View Labelling Network Based on Pairwise Learning

Yue Zhang, Akin Caliskan, Adrian Hilton, Jean-Yves Guillemaut

Abstract

Correct labelling of multiple people from different viewpoints in complex scenes is a challenging task due to occlusions, visual ambiguities, as well as variations in appearance and illumination. In recent years, deep learning approaches have proved very successful at improving the performance of a wide range of recognition and labelling tasks such as person re-identification and video tracking. However, to date, applications to multi-view tasks have proved more challenging due to the lack of suitably labelled multi-view datasets, which are difficult to collect and annotate. The contributions of this paper are two-fold. First, a synthetic dataset is generated by combining 3D human models and panoramas along with human poses and appearance detail rendering to overcome the shortage of real dataset for multi-view labelling. Second, a novel framework named Multi-View Labelling network (MVL-net) is introduced to leverage the new dataset and unify the multi-view multiple people detection, segmentation and labelling tasks in complex scenes. To the best of our knowledge, this is the first work using deep learning to train a multi-view labelling network. Experiments conducted on both synthetic and real datasets demonstrate that the proposed method outperforms the existing state-of-the-art approaches.
BibTeX
@inproceedings{zhang2021novel,
  author = {Yue Zhang and Akin Caliskan and Adrian Hilton and Jean-Yves Guillemaut},
  title = {{A Novel Multi-View Labelling Network Based on Pairwise Learning}},
  booktitle = {ICIP},
  year = {2021},
  doi = {10.1109/icip42928.2021.9506140},
}

Loading related content...

Figure