Simultaneous multi-view instance detection with learned geometric soft-constraints

Ahmed Samy Nassar 1, 2 Sébastien Lefèvre 1 Jan D. Wegner 2
1 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 EcoVision Lab
ETH Zürich - Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology in Zürich [Zürich]
Abstract : We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object instance detection difficult are strong changes in viewpoint, lighting conditions, high similarity of neighbouring objects, and strong variability in scale. By turning object detection and instance re-identification in different views into a joint learning task, we are able to incorporate both image appearance and geometric soft constraints into a single, multi-view detection process that is learnable end-to-end. We validate our method on a new, large data set of street-level panoramas of urban objects and show superior performance compared to various baselines. Our contribution is threefold: a large-scale, publicly available data set for multi-view instance detection and re-identification; an annotation tool custom-tailored for multi-view instance detection; and a novel, holistic multi-view instance detection and re-identification method that jointly models geometry and appearance across views.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02343884
Contributor : Sébastien Lefèvre <>
Submitted on : Sunday, November 3, 2019 - 4:24:06 PM
Last modification on : Tuesday, November 5, 2019 - 1:19:27 AM

Links full text

Identifiers

  • HAL Id : hal-02343884, version 1
  • ARXIV : 1907.10892

Citation

Ahmed Samy Nassar, Sébastien Lefèvre, Jan D. Wegner. Simultaneous multi-view instance detection with learned geometric soft-constraints. Internationcal Conference on Computer Vision (ICCV), 2019, Seoul, South Korea. ⟨hal-02343884⟩

Share

Metrics

Record views

20