HEV-I

Honda Egocentric View-Intersection Dataset

Dataset Information
Modalities
Videos
Introduced
2018
License
Unknown
Homepage

Overview

Honda Egocentric View-Intersection Dataset (HEV-I) is introduced to enable research on traffic participants interaction modelling, future object localization, as well as learning driver action in challenging driving scenarios. The dataset includes 230 video clips of real human driving in different intersections from the San Francisco Bay Area, collected using an instrumented vehicle equipped with different sensors including cameras, GPS/IMU, and vehicle states signals.

Variants: HEV-I

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Trajectory Prediction SGNet Stepwise Goal-Driven Networks for Trajectory … 2021-03-25
Trajectory Prediction FOL-X Unsupervised Traffic Accident Detection in … 2019-03-02

Research Papers

Recent papers with results on this dataset: