Person Re-identification Dataset with RGB-D Camera in a Top-View Configuration

Liciotti, Daniele; Paolanti, Marina; Frontoni, Emanuele; Mancini, Adriano; Zingaretti, Primo

doi:10.1007/978-3-319-56687-0_1

Cited by 24 publications

(31 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Related Workmentioning

confidence: 99%

“…Multimodal fusion of RGB and depth information is rarely considered in person re-id [18,21,27]. Liciotti et al [18] propose a combination of hand-crafted RGB and depth features to capture both color, texture and anthropometric information. RGB-D based hand-crafted features are also proposed by Wu et al [27] who extract a rotation invariant Eigen-depth feature and fuse it with low-level color and texture features [17].…”

Section: Related Workmentioning

confidence: 99%

“…When evaluating the MAT, we only consider datasets collected from an overhead viewpoint. Three RGB-D based datasets, to our knowledge, have been proposed for overhead person re-id, including the Depth-based Person Identification from Top (DPI-T) [7], Top View Person Re-identification (TVPR) [18] and Overhead Person Reidentification (OPR) [13]. [13] who consider full-frame images, we apply a You Only Look Once (YOLO) detector [22] optimized for person detection, to automatically extract the ROI around persons.…”

Section: Datasets and Protocolsmentioning

confidence: 99%

“…Common for these datasets is the viewpoint which is mostly horizontal, allowing occlusions between persons or persons and objects. Another option is to place the camera overhead, resulting in a vertical viewpoint, an option only considered by few [7,13,18]. This both has the potential of decreasing the probability of occlusions and improve privacy preservation.…”

Section: Introductionmentioning

confidence: 99%

“…Based on extracting features from images captured in an overhead view, it makes sense to include depth information as an additional modality. To that end, previous work on multimodal person re-id has shown RGB and depth based features to complement each other well [10,13,18].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Attention in Multimodal Neural Networks for Person Re-identification

Lejbolle

Krogh²,

Nasrollahi

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

In spite of increasing interest from the research community, person re-identification remains an unsolved problem. Correctly deciding on a true match by comparing images of a person, captured by several cameras, requires extraction of discriminative features to counter challenges such as changes in lighting, viewpoint and occlusion. Besides devising novel feature descriptors, the setup can be changed to capture persons from an overhead viewpoint rather than a horizontal. Furthermore, additional modalities can be considered that are not affected by similar environmental changes as RGB images. In this work, we present a Multimodal ATtention network (MAT) based on RGB and depth modalities. We combine a Convolution Neural Network with an attention module to extract local and discriminative features that are fused with globally extracted features. Attention is based on correlation between the two modalities and we finally also fuse RGB and depth features to generate a joint multilevel RGB-D feature. Experiments conducted on three datasets captured from an overhead view show the importance of attention, increasing accuracies by 3.43%, 2.01% and 2.13% on OPR, DPI-T and TVPR, respectively.

show abstract