Results 51 to 60 of about 14,435,990 (306)
Fusion in dissimilarity space for RGB-D person re-identification
Array, 2021 Person re-identification (Re-id) is the task of recognizing people across different non-overlapping sensors of a camera network. Despite the recent advances with deep learning (DL) models for multi-modal fusion, state-of-the-art Re-id approaches fail to ...
Md Kamal Uddin +4 more
doaj +1 more source
RGB-D scene analysis in the NICU
Computers in Biology and Medicine, 2021 Continuity of care is achieved in the neonatal intensive care unit (NICU) through careful documentation of all events of clinical significance, including clinical interventions and routine care events (e.g., feeding, diaper change, weighing, etc.). As a step towards automating this documentation process, we propose a scene recognition algorithm that ...
Yasmina Souley Dosso +3 more
openaire +2 more sources
PL-GM:RGB-D SLAM With a Novel 2D and 3D Geometric Constraint Model of Point and Line Features
IEEE Access, 2021 In the study of RGB-D SLAM (Simultaneous Localization and Mapping), two types of primary visual features, point and line features, have been widely utilized to calculate the camera pose.
Chenyang Zhang
doaj +1 more source
Semantic RGB-D Image Synthesis
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2023 ICCV Workshop on Representation Learning with Very Limited Images ...
Shijie Li 0006, Rong Li, Juergen Gall
openaire +2 more sources
Depth-Adapted CNN for RGB-D Cameras [PDF]
, 2021 Conventional 2D Convolutional Neural Networks (CNN) extract features from an input image by applying linear filters. These filters compute the spatial coherence by weighting the photometric information on a fixed neighborhood without taking into account the geometric information. We tackle the problem of improving the classical RGB CNN methods by using
Wu, Zongwei +3 more
openaire +4 more sources
Absolute and Relative Depth-Induced Network for RGB-D Salient Object Detection
Sensors, 2023 Detecting salient objects in complicated scenarios is a challenging problem. Except for semantic features from the RGB image, spatial information from the depth image also provides sufficient cues about the object.
Yuqiu Kong +5 more
doaj +1 more source
Re-identification with RGB-D Sensors
, 2012 People re-identification is a fundamental operation for any multi-camera surveillance scenario. Until now, it has been performed by exploiting primarily appearance cues, hypothesizing that the individuals cannot change their clothes. In this paper, we relax this constraint by presenting a set of 3D soft-biometric cues, being insensitive to appearance ...
Igor Barros Barbosa +4 more
openaire +4 more sources
Applied Sciences, 2022 A novel method for structural health monitoring (SHM) by using RGB+D data has been recently proposed. RGB+D data are created by fusing image and laser scan data, where the D channel represents the distance, interpolated from laser scanner data.
Josip Peroš +3 more
doaj +1 more source
Low-Cost Three-Dimensional Modeling of Crop Plants
Sensors, 2019 Plant modeling can provide a more detailed overview regarding the basis of plant development throughout the life cycle. Three-dimensional processing algorithms are rapidly expanding in plant phenotyping programmes and in decision-making for agronomic ...
Jorge Martinez-Guanter +7 more
doaj +1 more source