Using road topology to improve cyclist path prediction

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

24 Citations (Scopus)
179 Downloads (Pure)


We learn motion models for cyclist path prediction on real-world tracks obtained from a moving vehicle, and propose to exploit the local road topology to obtain better predictive distributions. The tracks are extracted from the Tsinghua-Daimler Cyclist Benchmark for cyclist detection, and corrected for vehicle egomotion. Tracks are then spatially aligned to local curves and crossings in the road. We study a standard approach for path prediction in the literature based on Kalman Filters, as well as a mixture of specialized filters related to specific road orientations at junctions. Our experiments demonstrate an improved prediction accuracy (up to 20% on sharp turns) of mixing specialized motion models for canonical directions, and prior knowledge on the road topology. The new track data complements the existing video, disparity and annotation data of the original benchmark, and will be made publicly available.
Original languageEnglish
Title of host publicationProceedings of the 2017 IEEE Intelligent Vehicles Symposium (IV)
EditorsPetros Ioannou, Wei-Bin Zhang, Meng Lu
Place of PublicationPiscataway, NJ, USA
ISBN (Print)978-1-5090-4804-5
Publication statusPublished - 2017
Event28th IEEE Intelligent Vehicles Symposium (IV2017) - Redondo Beach, United States
Duration: 11 Jun 201714 Jun 2017


Conference28th IEEE Intelligent Vehicles Symposium (IV2017)
CountryUnited States
CityRedondo Beach


  • Roads
  • Tracking
  • Topology
  • Predictive models
  • Benchmark testing
  • Vehicle dynamics
  • Layout

Fingerprint Dive into the research topics of 'Using road topology to improve cyclist path prediction'. Together they form a unique fingerprint.

Cite this