Proceedings of the 5th International Conference on Vehicle Technology and Intelligent Transport Systems 2019
DOI: 10.5220/0007678700760085
|View full text |Cite
|
Sign up to set email alerts
|

Evaluation of Embedded Camera Systems for Autonomous Wheelchairs

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
3
1

Relationship

3
1

Authors

Journals

citations
Cited by 4 publications
(9 citation statements)
references
References 0 publications
0
9
0
Order By: Relevance
“…Despite their good performance, CNNs pose high requirements on computational and memory resources, especially for large data amounts as in 3D point clouds. Unfortunately, powered wheelchairs and autonomous robots have severe constraints in terms of power, space, heat dissipation, and hardware resources, 1 meaning that real-time CNN implementations are unfeasible for our application.…”
Section: Introductionmentioning
confidence: 99%
“…Despite their good performance, CNNs pose high requirements on computational and memory resources, especially for large data amounts as in 3D point clouds. Unfortunately, powered wheelchairs and autonomous robots have severe constraints in terms of power, space, heat dissipation, and hardware resources, 1 meaning that real-time CNN implementations are unfeasible for our application.…”
Section: Introductionmentioning
confidence: 99%
“…The camera has a non-visible static infrared (IR) pattern projector to allow measuring the depth at dark-light conditions and also when the scene’s texture is too low. The Intel RealSense D435 camera uses a global shutter enabling robotic navigation and object recognition applications on a moving environment [ 30 ]. It has also a small size, making it suitable to be embedded into a robot or vehicle’s frame easily.…”
Section: Results and Analysismentioning
confidence: 99%
“… Pose alignment. Each synthetic object from the training dataset is aligned using the PCA-STD method described in Vilar et al [ 30 ] before computing the object descriptor in order to achieve rotational invariance. …”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations