# Dragon Lake Parking Dataset [https://doi.org/10.5061/dryad.tht76hf5b](https://doi.org/10.5061/dryad.tht76hf5b) The [Dragon Lake Parking (DLP) Dataset](https://sites.google.com/berkeley.edu/dlp-dataset) contains annotated video and data of vehicles, cyclists, and pedestrians inside a parking lot. We collected it by flying a drone above a huge 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. ### Statistics #### Raw video * Length: 3.5 hours * Resolution: 4K * Frame rate: 25 fps #### Parking Area * Size: 140 m x 80 m * Number of spots: \~400 #### Agent Types and Count * Vehicles (normal sedan, medium vehicle like SUV, bus): 1216 * Pedestrians: 3904 * Bicycles: 28 * Motorcycles: 5 ## Description of the data and file structure The raw videos are annotated and converted to JSON format. The dataset has a graph structure with the following components * Agent: An agent is an object that has moved in this scene. It contains the object's dimension, type, and trajectory as a list of instances. * Instance: An instance is the state of an agent at a time step, which includes position, orientation, velocity, and acceleration. It also points to the preceding / subsequent instance along the agent's trajectory. * Frame: A frame is a discrete sample from the recording. It contains a list of visible instances at this time step, and points to the preceding / subsequent frame. * Obstacle: Obstacles are vehicles that never move in this recording. * Scene: A scene represents a consecutive video recording with certain length. It points to all frames, agents, and obstacles in this recording. The entire DLP dataset contains 30 scenes, 317,873 frames, 5,188 agents, and 15,383,737 instances. ## Sharing/Access information Two types of data are available: 1. JSONs will provide you all Instances, Agents, Frames, Obstacles, and Scene data so that you can use our Python toolkit. All coordinates are transformed from UTM to the local coordinates of the parking lot. You can download the JSONs directly from Dryad if your research is about trajectory analysis and/or semantic visualization is enough for your computer vision module. 2. Raw video and ground truth annotation. You ONLY need this if you are working on object detection, tracking, semantic segmentation, or end-to-end models with raw bird's eye view camera data. The annotated trajectories are in UTM coordinates. Please understand that we cannot offer software tools for parsing these data. Since the video data is huge, you have to [submit a request](https://forms.gle/Fw5EKy2cKeYCBssF9) if you need raw videos for your research. ## Code/Software We are releasing a Python toolkit, which provides convenient APIs to query and visualize data. [MPC-Berkeley/dlp-dataset: Dragon Lake Parking Dataset by MPC Lab (github.com)](https://github.com/MPC-Berkeley/dlp-dataset)

The Dragon Lake Parking (DLP) Dataset contains annotated video and data of vehicles, cyclists, and pedestrians inside a parking lot. We collected it by flying a drone above a huge 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. The potential applications of this dataset include but are not limited to trajectory prediction, trajectory analysis, traffic analysis, behavior analysis, behavior cloning, and imitation learning.