A comparative review of plausible hole filling strategies in the context of scene depth image completion
A Atapour-Abarghouei, TP Breckon - Computers & Graphics, 2018 - Elsevier
Despite significant research focus on 3D scene capture systems, numerous unresolved
challenges remain in relation to achieving full coverage scene depth estimation which is the …
challenges remain in relation to achieving full coverage scene depth estimation which is the …
Self-Supervised Monocular Depth Estimation by Digging into Uncertainty Quantification
Based on well-designed network architectures and objective functions, self-supervised
monocular depth estimation has made great progress. However, lacking a specific …
monocular depth estimation has made great progress. However, lacking a specific …
Recognition and Classification of High Resolution Remote Sensing Image based on Convolutional Neural Network
G Chen, Z Cai, X Li - International Journal of Performability …, 2018 - ijpe-online.com
High resolution remote sensing image data is veritable big data. It is not only massive, multi-
source, and heterogeneous, but also high-dimensional, multi-scale, and non-stationary. In …
source, and heterogeneous, but also high-dimensional, multi-scale, and non-stationary. In …
[PDF][PDF] D2MM-CNN: Difference Depth Motion Map and Convolutional Neural Networks for Human Action Recognition
SS Rani, DGAR Naidu… - International Journal of …, 2019 - mrecacademics.com
ABSTRACT Human Action Recognition has become the most significant research area for
several applications like robotics, healthcare, gaming, smart houses, etc. However, in …
several applications like robotics, healthcare, gaming, smart houses, etc. However, in …