Skip to Main content Skip to Navigation
Conference papers

Improvement of multiple pedestrians tracking thanks to semantic information

Abstract : This work presents an interacting multiple pedestrian tracking method for monocular systems that incorporates a prior knowledge about the movement and interactions of the targets. We consider 4 cases of pedestrian behaviors: going straight; finding the way; walking around and stand still. Those are combined within an Interacting Multiple Model Particle Filter strategy. We model targets interactions with social forces, included as potential functions in the weighting process of the Particle Filter (PF). We use different social force models in each motion model to handle high level behaviors (collision avoidance, flocking.. .). We evaluate our algorithm on challenging datasets and demonstrate that such semantic information improve the tracker performance.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.laas.fr/hal-01763156
Contributor : Frédéric Lerasle <>
Submitted on : Tuesday, April 10, 2018 - 6:15:59 PM
Last modification on : Friday, January 10, 2020 - 9:10:11 PM

File

paper_1499.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01763156, version 1

Citation

Francisco Madrigal, Jean-Bernard Hayet, Frédéric Lerasle. Improvement of multiple pedestrians tracking thanks to semantic information. International Conference on Pattern Recognition, Aug 2014, Stockholm, Sweden. ⟨hal-01763156⟩

Share

Metrics

Record views

85

Files downloads

45