Extended Gaze Following: Detecting Objects in Videos Beyond the Camera Field of View

Benoit Massé 1 Stéphane Lathuilière 1, 2 Pablo Mesejo 1, 3 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video. Objects can be indistinctly located inside or outside the camera field of view. We refer to this problem as extended gaze following. The contributions of the paper are the followings. First, we propose a novel spatial representation of the gaze directions adopting a top-view perspective. Second, we develop several convolutional encoder/decoder networks to predict object locations and compare them with heuristics and with classical learning-based approaches. Third, in order to train the proposed models, we generate a very large number of synthetic scenarios employing a probabilistic formulation. Finally, our methodology is empirically validated using a publicly available dataset.
Complete list of metadatas

Cited literature [37 references]  Display  Hide  Download

https://hal.inria.fr/hal-02054236
Contributor : Team Perception <>
Submitted on : Friday, March 1, 2019 - 5:14:45 PM
Last modification on : Wednesday, March 6, 2019 - 10:52:44 AM
Long-term archiving on : Thursday, May 30, 2019 - 4:51:14 PM

Identifiers

  • HAL Id : hal-02054236, version 1

Collections

Citation

Benoit Massé, Stéphane Lathuilière, Pablo Mesejo, Radu Horaud. Extended Gaze Following: Detecting Objects in Videos Beyond the Camera Field of View. FG 2019 - 14th IEEE International Conference on Automatic Face and Gesture Recognition, May 2019, Lille, France. pp.1-8. ⟨hal-02054236⟩

Share

Metrics

Record views

135

Files downloads

104