Skip to content

The dataset includes quantities vehicle trajectories at several sites. The dataset is extracted from aerial videos. Human work is used to ensure accuracy.

Notifications You must be signed in to change notification settings

Ku-Buqi/Ubiquitous-Traffic-Eye

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 

Repository files navigation

Ubiquitous-Traffic-Eye

Trajectory data introduction

My data publication is on the way, star me for latest publication.

These datasets include quantities vehicle trajectories at several sites. The dataset is extracted from aerial videos. Labor work is used to ensure accuracy. Each file is a group of sample, extracted on different sites and time, also in dynamic traffic conditions.

Data available for download from this website include: video files with object identification box, raw track data and data format description. The original vehicle track data includes vehicle number, position coordinates, lane number, vehicle length, vehicle width, driving speed, time headway, space headway, plus/minus speed and other parameters, with a time accuracy of 0.1 second and a position accuracy of 0.01 m.

Data can be obtianed now

SQM1 Dataset

Road Condition: The length of the study road section is 427 meters, east-west direction, including two-way ten Lane East end and two-way six Lane West end. There are two roads merging in the east-west direction, and two roads diverging in the west-east direction, and the number of lanes changes intensively.

Video Condition: This video was captured by a UAV at 310m altitude for 4 minutes and 15 seconds.

Accuracy: The open data can realize 100% vehicle recognition and tracking rate.

Traffic Condition: Video capture covers the whole evolution process of traffic flow from free flow operation to congestion.

Data Information: This data provides the precise vehicle position coordinates with a time accuracy of 0.1s, and contains the information of each vehicle’s speed, acceleration, spacing, time distance, lane, etc.

SQM1

YT Avenue Dataset

Road Condition: The length of the study road section is 362 meters, east-west direction; including two-way ten Lane East end and two-way six Lane West end. There are four roads merging in the east-west direction, and the number of lanes changes intensively in the east-west direction.

Video Condition: This video was captured by a UAV at 200m altitude for 9 minutes and 5 seconds

Accuracy: the open data can realize 100% vehicle recognition and tracking rate

Traffic Condition: Video capture covers the whole evolution process of traffic flow from free flow operation to congestion.

Data Information: Data contains the information of each vehicle’s speed, acceleration, spacing, time distance, lane, etc.

路网2

Learn more about our work

UTE only includes my core work here, other teams share the results and related paper work to understand that you can visit: http://seutraffic.com/#/

About

The dataset includes quantities vehicle trajectories at several sites. The dataset is extracted from aerial videos. Human work is used to ensure accuracy.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published