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
2 EcoVision Lab

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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

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⟩