G
Guillem Palou
Researcher at Polytechnic University of Catalonia
Publications - 8
Citations - 140
Guillem Palou is an academic researcher from Polytechnic University of Catalonia. The author has contributed to research in topics: Image segmentation & Depth perception. The author has an hindex of 5, co-authored 8 publications receiving 138 citations. Previous affiliations of Guillem Palou include Massachusetts Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Hierarchical Video Representation with Trajectory Binary Partition Tree
Guillem Palou,Philippe Salembier +1 more
TL;DR: The proposed algorithm outperforms existing hierarchical video segmentation algorithms and provides more stable and precise regions and relies on different models and associated metrics to deal with color and motion information.
Journal ArticleDOI
Monocular Depth Ordering Using T-Junctions and Convexity Occlusion Cues
Guillem Palou,Philippe Salembier +1 more
TL;DR: A system that relates objects in an image using occlusion cues and arranges them according to depth using a binary partition tree as hierarchical region-based image representation jointly with a new approach for candidate T-junction estimation.
Proceedings ArticleDOI
Occlusion-based depth ordering on monocular images with Binary Partition Tree
Guillem Palou,Philippe Salembier +1 more
TL;DR: This paper proposes a system to relate objects in an image using occlusion cues and arrange them according to depth using the Binary Partition Tree as the segmentation tool jointly with a new approach for T-junction estimation.
Proceedings ArticleDOI
Underwater acoustic MIMO OFDM: An experimental analysis
Guillem Palou,Milica Stojanovic +1 more
TL;DR: In this paper, the performance of multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) is analyzed on an experimental shallow water acoustic channel.
Proceedings ArticleDOI
From local occlusion cues to global monocular depth estimation
Guillem Palou,Philippe Salembier +1 more
TL;DR: It is shown that the system outperforms previously low-level cue based systems, while offering similar results to a priori trained figure/ground labeling algorithms.