Dragon Lake Parking (DLP) Dataset API

The API to work with the Dragon Lake Parking (DLP) Dataset.

The Dragon Lake Parking (DLP) Dataset contains annotated video and data of vehicles, cyclists, and pedestrians inside a parking lot.

Abundant vehicle parking maneuvers and interactions are recorded. To the best of our knowledge, this is the first and largest public dataset designated for the parking scenario (up to April 2022), featuring high data accuracy and a rich variety of realistic human driving behavior. To download trial sample or request full access, please visit the dataset webpage for more infomation.

Note: If you experience connectivity issue to the webpage above, try this backup page.

Authors: Xu Shen (xu_shen@berkeley.edu), Michelle Pan, Vijay Govindarajan, Neelay Velingker, Alex Wong, Yibin Li

Model Predictive Control (MPC) Lab at UC Berkeley

Install

1. Clone this repo
2. With your virtualenv activated, run pip install -e . in the root directory of this repo.
3. Place the JSON data files in the ./data directory

Usage in other projects

Import this dataset API as a package, e.g.

from dlp.dataset import Dataset as DlpDataset

Quick-start tutorials

1. notebooks/tutorial.ipynb explains the structure of the dataset and available APIs
2. notebooks/visualization.ipynb demonstrates the dataset by visualizing it with either matplotlib or PIL

Partner

Source Trajectory and Bounding box data were annotated and gathered with DataFromSky TrafficSurvey - an AI video analytics-based service for gathering advanced traffic data.