Improving a Real-Time Object Detector with Compact Temporal Information

Abstract

Neural networks designed for real-time object detection have recently improved significantly, but in practice, looking at only a single RGB image at the time may not be ideal. For example, when detecting objects in videos, a foreground detection algorithm can be used to obtain compact temporal data, which can be fed into a neural network alongside RGB images. We propose an approach for doing this, based on an existing object detector, that re-uses pretrained weights for the processing of RGB images. The neural network was tested on the VIRAT dataset with annotations for object detection, a problem this approach is well suited for. The accuracy was found to improve significantly (up to 66%), with a roughly 40% increase in computational time.

Cite

Text

Ahrnbom et al. "Improving a Real-Time Object Detector with Compact Temporal Information." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.31

Markdown

[Ahrnbom et al. "Improving a Real-Time Object Detector with Compact Temporal Information." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/ahrnbom2017iccvw-improving/) doi:10.1109/ICCVW.2017.31

BibTeX

@inproceedings{ahrnbom2017iccvw-improving,
  title     = {{Improving a Real-Time Object Detector with Compact Temporal Information}},
  author    = {Ahrnbom, Martin and Jensen, Morten Borno and Åström, Kalle and Nilsson, Mikael G. and Ardö, Håkan and Moeslund, Thomas B.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {190-197},
  doi       = {10.1109/ICCVW.2017.31},
  url       = {https://mlanthology.org/iccvw/2017/ahrnbom2017iccvw-improving/}
}