This repository contains documentation and software tools for the Novel Sensors for Autonomous Vehicle Perception (NSAVP) dataset. See the project page for links to all resources, including data download.
Additional information is available in the following documentation pages:
- Sensors: Description of the sensor suite.
- Data Format: Description of the data collected and the data format.
- Conversion: Guide to combine H5 files and convert a combined H5 file to a ROS1 rosbag or a folder containing CSV files and PNG images.
- Preprocessing and Visualization: Guide to perform preprocessing operations (e.g., cropping, debayering, rectification) and visualize the data.
- Place Recognition: Tutorial for evaluating a place recognition method on the dataset.
If you have any questions or comments, please create a GitHub issue.
@article{nsavp_2025,
author = {Spencer Carmichael and Austin Buchan and Mani Ramanagopal and Radhika Ravi and Ram Vasudevan and Katherine A Skinner},
title = {Dataset and Benchmark: Novel Sensors for Autonomous Vehicle Perception},
journal = {The International Journal of Robotics Research},
volume = {44},
number = {3},
pages = {355-365},
year = {2025}}