Combining Visual Saliency Methods and Sparse Keypoint Annotations to Providently Detect Vehicles at Night
The corresponding paper was submitted to ICRA 2023 and is still under review. The arxiv preprint can be found here. This repository contains the main source code for our context-aware Boolean map saliency approach.
Download the PVDN dataset from Kaggle.
The code was tested on Ubuntu 20.04 and Python 3.8.10. However, it should normally also work fine on other OS and similar Python 3.x versions.
Setup a virtual environment and install the repo as a package:
python3 -m venv venv
source venv/bin/activate
pip install pip --upgrade
pip install -e .
The following notebooks provide examples for basic use cases: