Tracking both pose and status of a traffic light via an Interacting Multiple Model filter

Abstract : Either for driver assistance systems or autonomous vehicles, detecting traffic lights (status and pose) is required when Intelligent Transport Systems go downtown. As detection algorithms could still have some misclassification on the traffic light status, this paper proposes a solution to nearly avoid this problem. An Interacting Multiple Model filter is used to track both the position and the status of a traffic light through the time and to increase traffic light recognition performances for automation purpose.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01024096
Contributor : Guillaume Trehard <>
Submitted on : Tuesday, July 15, 2014 - 4:07:07 PM
Last modification on : Thursday, February 7, 2019 - 5:54:02 PM
Long-term archiving on : Friday, November 21, 2014 - 6:50:29 PM

File

IMMTracking.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01024096, version 1

Collections

Citation

Guillaume Trehard, Evangeline Pollard, Benazouz Bradai, Fawzi Nashashibi. Tracking both pose and status of a traffic light via an Interacting Multiple Model filter. Fusion 2014 - 17th International Conference on Information Fusion, Jul 2014, Salamanca, Spain. ⟨hal-01024096⟩

Share

Metrics

Record views

419

Files downloads

871