Scipediacontent: Scipediacontent moved page Draft Content 150756171 to Tanaka et al 2019a

2021-01-28T19:25:31Z

Scipediacontent moved page Draft Content 150756171 to Tanaka et al 2019a

Scipediacontent: Created page with " == Abstract == Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. Howev..."

2021-01-28T19:25:27Z

Created page with " == Abstract == Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. Howev..."

New page

== Abstract ==

Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. However, the performance of these networks strongly depends on the training data. An issue with collecting training data is labeling. Labeling by humans is necessary to obtain the ground truth label; however, labeling requires huge costs. Therefore, we propose an automatic labeled data generation pipeline, for which we can change any parameters or data generation environments. Our approach uses a human model named Dhaiba and a background of Miraikan and consequently generated realistic artificial data. We present 500k+ data generated by the proposed pipeline. This paper also describes the specification of the pipeline and data details with evaluations of various approaches.

Comment: Accepted at ICRA2019

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1902.05341 http://arxiv.org/abs/1902.05341]

* [http://arxiv.org/pdf/1902.05341 http://arxiv.org/pdf/1902.05341]

* [http://xplorestaging.ieee.org/ielx7/8780387/8793254/08793916.pdf?arnumber=8793916 http://xplorestaging.ieee.org/ielx7/8780387/8793254/08793916.pdf?arnumber=8793916],
: [http://dx.doi.org/10.1109/icra.2019.8793916 http://dx.doi.org/10.1109/icra.2019.8793916]

* [https://dblp.uni-trier.de/db/journals/corr/corr1902.html#abs-1902-05341 https://dblp.uni-trier.de/db/journals/corr/corr1902.html#abs-1902-05341],
: [https://arxiv.org/abs/1902.05341 https://arxiv.org/abs/1902.05341],
: [https://ieeexplore.ieee.org/document/8793916 https://ieeexplore.ieee.org/document/8793916],
: [http://arxiv.org/pdf/1902.05341.pdf http://arxiv.org/pdf/1902.05341.pdf],
: [https://academic.microsoft.com/#/detail/2969152418 https://academic.microsoft.com/#/detail/2969152418]

← Older revision	Revision as of 19:25, 28 January 2021
(No difference)

Tanaka et al 2019a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 150756171 to Tanaka et al 2019a

Scipediacontent: Created page with " == Abstract == Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. Howev..."