Skip to Main content Skip to Navigation
Conference papers

Improving Multi-Frame Data Association with Sparse Representations for Robust Near-Online Multi-Object Tracking

Loïc Fagot-Bouquet 1 Romaric Audigier 1 Yoann Dhome 1 Frédéric Lerasle 2
1 LVIC - Laboratoire Vision et Ingénierie des Contenus
DIASI - Département Intelligence Ambiante et Systèmes Interactifs : DRT/LIST/DIASI
2 LAAS-RAP - Équipe Robotique, Action et Perception
LAAS - Laboratoire d'analyse et d'architecture des systèmes
Abstract : Multiple Object Tracking still remains a difficult problem due to appearance variations and occlusions of the targets or detection failures. Using sophisticated appearance models or performing data association over multiple frames are two common approaches that lead to gain in performances. Inspired by the success of sparse representations in Single Object Tracking, we propose to formulate the multi-frame data association step as an energy minimization problem, designing an energy that efficiently exploits sparse representations of all detections. Furthermore, we propose to use a structured sparsity-inducing norm to compute representations more suited to the tracking context. We perform extensive experiments to demonstrate the effectiveness of the proposed formulation , and evaluate our approach on two public authoritative benchmarks in order to compare it with several state-of-the-art methods.
Document type :
Conference papers
Complete list of metadatas

Cited literature [43 references]  Display  Hide  Download

https://hal.laas.fr/hal-01763166
Contributor : Frédéric Lerasle <>
Submitted on : Tuesday, April 10, 2018 - 6:25:31 PM
Last modification on : Monday, February 10, 2020 - 6:13:47 PM

File

camera_ready.pdf
Files produced by the author(s)

Identifiers

Citation

Loïc Fagot-Bouquet, Romaric Audigier, Yoann Dhome, Frédéric Lerasle. Improving Multi-Frame Data Association with Sparse Representations for Robust Near-Online Multi-Object Tracking. European Conference on Computer Vision, Oct 2016, Amsterdam, Netherlands. ⟨10.1007/978-3-319-46484-8_47⟩. ⟨hal-01763166⟩

Share

Metrics

Record views

1112

Files downloads

637