2018
DOI: 10.3390/s18082430
|View full text |Cite
|
Sign up to set email alerts
|

Relative Pose Based Redundancy Removal: Collaborative RGB-D Data Transmission in Mobile Visual Sensor Networks

Abstract: In this paper, the Relative Pose based Redundancy Removal (RPRR) scheme is presented, which has been designed for mobile RGB-D sensor networks operating under bandwidth-constrained operational scenarios. The scheme considers a multiview scenario in which pairs of sensors observe the same scene from different viewpoints, and detect the redundant visual and depth information to prevent their transmission leading to a significant improvement in wireless channel usage efficiency and power savings. We envisage appl… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 61 publications
0
3
0
Order By: Relevance
“…The corn leaf images that will be utilised as input in image identification are in the YCbCr colour space. The actual colour displayed is determined by the RGB colourants used to present the corn leaf images, but these RGB are inefficient as a representation for storage and transmission due to their high mutual redundancy (Wang et al, 2018). YCbCr distinguishes between a luma (Y) component that can be stored in high resolution or transmitted at high bandwidth and two chroma components (Cb and Cr) that can be bandwidthreduced, sub-sampled, compressed, or otherwise treated separately to improve algorithm efficiency.…”
Section: 60mentioning
confidence: 99%
“…The corn leaf images that will be utilised as input in image identification are in the YCbCr colour space. The actual colour displayed is determined by the RGB colourants used to present the corn leaf images, but these RGB are inefficient as a representation for storage and transmission due to their high mutual redundancy (Wang et al, 2018). YCbCr distinguishes between a luma (Y) component that can be stored in high resolution or transmitted at high bandwidth and two chroma components (Cb and Cr) that can be bandwidthreduced, sub-sampled, compressed, or otherwise treated separately to improve algorithm efficiency.…”
Section: 60mentioning
confidence: 99%
“…The depth pixels are predicted by searching similar surfaces from the neighboring frame of depth data. Wang et al [14][15] proposed a prediction method for depth data by calculating the camera movement from the neighboring frame. Our previous study [16] predicts the depth pixels through a plane modeling that is an intra-picture prediction method by a plane estimation.…”
Section: Background and Previous Workmentioning
confidence: 99%
“…Therefore, the inter-and intra-picture prediction for depth data should consider the relationship of the adjacent pixels depending on the surface type. The methods for the surface motion estimating between consecutive frames [13] and for calculating the threedimensional motion of the camera [14][15] are proposed to predict adjacent pixels by considering the surface type.…”
Section: Introductionmentioning
confidence: 99%