This project hosts the code for implementing the models for Panoptic Segmentation proposed in the following paper:
Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually Impaired,
@inproceedings{mao2021panoptic,
title={Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually Impaired},
author={Mao, Wei and Zhang, Jiaming and Yang, Kailun and Stiefelhagen, Rainer},
booktitle={2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)},
year={2021},
organization={IEEE}
}
This implementation is based on Detectron2. Please refer to INSTALL.md for installation and dataset preparation.
Change to the directory projects for the implementations for VerConv, VerConvSep and Lintention which can be used as a stand-alone module.