Multi-Perspective Vehicle Detection and Tracking: Challenges, Dataset, and Metrics

Jacob Velling Dueholm, Miklas Strøm Kristoffersen, Ravi K. Satzoda, Eshed Ohn-Bar, Thomas B. Moeslund, Mohan M. Trivedi

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

8 Citations (Scopus)


The research community has shown significant improvements
in both vision-based detection and tracking of vehicles,
working towards a high level understanding of on-road
maneuvers. Behaviors of surrounding vehicles in a highway
environment is found as an interesting starting point, of
why this dataset is introduced along with its challenges
and evaluation metrics. A vision-based multi-perspective
dataset is presented, containing a full panoramic view from
a moving platform driving on U.S. highways capturing
2704x1440 resolution images at 12 frames per second. The
dataset serves multiple purposes to be used as traditional
detection and tracking, together with tracking of vehicles
across perspectives. Each of the four perspectives have
been annotated, resulting in more than 4000 bounding boxes
in order to evaluate and compare novel methods.
Original languageEnglish
Title of host publication2016 IEEE 19th International Conference on Intelligent Transportation Systems
Publication date26 Dec 2016
Article number575
ISBN (Electronic)978-1-5090-1889-5
Publication statusPublished - 26 Dec 2016
EventInternational Conference on Intelligent Transportation Systems - Convention Center, Windsor Oceanico Hotel, Rio de Janeiro, Brazil
Duration: 1 Nov 20164 Nov 2016
Conference number: 19


ConferenceInternational Conference on Intelligent Transportation Systems
LocationConvention Center, Windsor Oceanico Hotel
CityRio de Janeiro


Dive into the research topics of 'Multi-Perspective Vehicle Detection and Tracking: Challenges, Dataset, and Metrics'. Together they form a unique fingerprint.

Cite this