Depthwise Over-Parameterized CNN for Voxel Human Pose Classification

Oddy Virgantara Putra; Riandini; Eko Mulyanto Yuniarno; Mauridhi Hery Purnomo

doi:10.1109/ISITIA59021.2023.10221054

Depthwise Over-Parameterized CNN for Voxel Human Pose Classification

Oddy Virgantara Putra
, Riandini
, Eko Mulyanto Yuniarno
, Mauridhi Hery Purnomo

Institut Teknologi Sepuluh Nopember
Jakarta State Polytechnic
University Center of Excellence on Artificial Intelligence for Healthcare and Society (UCE AIHeS)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Light Detection and Ranging (LiDAR) capture objects and backgrounds using a laser sensor, producing unstructured points in 3-dimensional called point clouds (PC). However, captured human pose PC is limited partially due to the LiDAR scan. The only information in the scanned area exists. Due to the inadequacy of PC data, it is challenging to classify such data. In this paper, we proposed a solution to overcome those problems. It is a novel depthwise over-parameterized (DOConv) embedded into a simple CNN. The raw PCs are converted into a 3D voxel in the input layer. In the convolutional (Conv) layer, the regular Conv is substituted with a-three layered DOConv. Lastly, to assess the performance of our model, we commence an evaluation with multiple classifier algorithms in ModelNet40 and our human pose dataset. Accuracy, loss, recall, precision, F1-scores, and Geometric mean are engaged as performance indicators. To sum up, our model outperformed all compared classifiers in accuracy for the primary dataset by 87.06 % and ModelNet40 by 68.68%.

Original language	English
Title of host publication	2023 International Seminar on Intelligent Technology and Its Applications
Subtitle of host publication	Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	54-59
Number of pages	6
ISBN (Electronic)	9798350313956
DOIs	https://doi.org/10.1109/ISITIA59021.2023.10221054
Publication status	Published - 2023
Event	24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023 - Hybrid, Surabaya, Indonesia Duration: 26 Jul 2023 → 27 Jul 2023

Publication series

Name	2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding

Conference

Conference	24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023
Country/Territory	Indonesia
City	Hybrid, Surabaya
Period	26/07/23 → 27/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Depthwise Convolution
Human Pose
Lightweight CNN
Over-parameterization
Point Cloud

Access to Document

10.1109/ISITIA59021.2023.10221054

Cite this

Putra, O. V., Riandini, Yuniarno, E. M., & Purnomo, M. H. (2023). Depthwise Over-Parameterized CNN for Voxel Human Pose Classification. In 2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding (pp. 54-59). (2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISITIA59021.2023.10221054

Putra, Oddy Virgantara ; Riandini, ; Yuniarno, Eko Mulyanto et al. / Depthwise Over-Parameterized CNN for Voxel Human Pose Classification. 2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 54-59 (2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding).

@inproceedings{63a517523abc4636a7d212b8ecfd3aa6,

title = "Depthwise Over-Parameterized CNN for Voxel Human Pose Classification",

abstract = "Light Detection and Ranging (LiDAR) capture objects and backgrounds using a laser sensor, producing unstructured points in 3-dimensional called point clouds (PC). However, captured human pose PC is limited partially due to the LiDAR scan. The only information in the scanned area exists. Due to the inadequacy of PC data, it is challenging to classify such data. In this paper, we proposed a solution to overcome those problems. It is a novel depthwise over-parameterized (DOConv) embedded into a simple CNN. The raw PCs are converted into a 3D voxel in the input layer. In the convolutional (Conv) layer, the regular Conv is substituted with a-three layered DOConv. Lastly, to assess the performance of our model, we commence an evaluation with multiple classifier algorithms in ModelNet40 and our human pose dataset. Accuracy, loss, recall, precision, F1-scores, and Geometric mean are engaged as performance indicators. To sum up, our model outperformed all compared classifiers in accuracy for the primary dataset by 87.06 \% and ModelNet40 by 68.68\%.",

keywords = "Depthwise Convolution, Human Pose, Lightweight CNN, Over-parameterization, Point Cloud",

author = "Putra, \{Oddy Virgantara\} and Riandini and Yuniarno, \{Eko Mulyanto\} and Purnomo, \{Mauridhi Hery\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023 ; Conference date: 26-07-2023 Through 27-07-2023",

year = "2023",

doi = "10.1109/ISITIA59021.2023.10221054",

language = "English",

series = "2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "54--59",

booktitle = "2023 International Seminar on Intelligent Technology and Its Applications",

address = "United States",

}

Putra, OV, Riandini, , Yuniarno, EM & Purnomo, MH 2023, Depthwise Over-Parameterized CNN for Voxel Human Pose Classification. in 2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding. 2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding, Institute of Electrical and Electronics Engineers Inc., pp. 54-59, 24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023, Hybrid, Surabaya, Indonesia, 26/07/23. https://doi.org/10.1109/ISITIA59021.2023.10221054

Depthwise Over-Parameterized CNN for Voxel Human Pose Classification. / Putra, Oddy Virgantara; Riandini, ; Yuniarno, Eko Mulyanto et al.
2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2023. p. 54-59 (2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Depthwise Over-Parameterized CNN for Voxel Human Pose Classification

AU - Putra, Oddy Virgantara

AU - Riandini,

AU - Yuniarno, Eko Mulyanto

AU - Purnomo, Mauridhi Hery

PY - 2023

Y1 - 2023

N2 - Light Detection and Ranging (LiDAR) capture objects and backgrounds using a laser sensor, producing unstructured points in 3-dimensional called point clouds (PC). However, captured human pose PC is limited partially due to the LiDAR scan. The only information in the scanned area exists. Due to the inadequacy of PC data, it is challenging to classify such data. In this paper, we proposed a solution to overcome those problems. It is a novel depthwise over-parameterized (DOConv) embedded into a simple CNN. The raw PCs are converted into a 3D voxel in the input layer. In the convolutional (Conv) layer, the regular Conv is substituted with a-three layered DOConv. Lastly, to assess the performance of our model, we commence an evaluation with multiple classifier algorithms in ModelNet40 and our human pose dataset. Accuracy, loss, recall, precision, F1-scores, and Geometric mean are engaged as performance indicators. To sum up, our model outperformed all compared classifiers in accuracy for the primary dataset by 87.06 % and ModelNet40 by 68.68%.

AB - Light Detection and Ranging (LiDAR) capture objects and backgrounds using a laser sensor, producing unstructured points in 3-dimensional called point clouds (PC). However, captured human pose PC is limited partially due to the LiDAR scan. The only information in the scanned area exists. Due to the inadequacy of PC data, it is challenging to classify such data. In this paper, we proposed a solution to overcome those problems. It is a novel depthwise over-parameterized (DOConv) embedded into a simple CNN. The raw PCs are converted into a 3D voxel in the input layer. In the convolutional (Conv) layer, the regular Conv is substituted with a-three layered DOConv. Lastly, to assess the performance of our model, we commence an evaluation with multiple classifier algorithms in ModelNet40 and our human pose dataset. Accuracy, loss, recall, precision, F1-scores, and Geometric mean are engaged as performance indicators. To sum up, our model outperformed all compared classifiers in accuracy for the primary dataset by 87.06 % and ModelNet40 by 68.68%.

KW - Depthwise Convolution

KW - Human Pose

KW - Lightweight CNN

KW - Over-parameterization

KW - Point Cloud

UR - https://www.scopus.com/pages/publications/85171199440

U2 - 10.1109/ISITIA59021.2023.10221054

DO - 10.1109/ISITIA59021.2023.10221054

M3 - Conference contribution

AN - SCOPUS:85171199440

T3 - 2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding

SP - 54

EP - 59

BT - 2023 International Seminar on Intelligent Technology and Its Applications

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023

Y2 - 26 July 2023 through 27 July 2023

ER -

Putra OV, Riandini , Yuniarno EM , Purnomo MH. Depthwise Over-Parameterized CNN for Voxel Human Pose Classification. In 2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding. Institute of Electrical and Electronics Engineers Inc. 2023. p. 54-59. (2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding). doi: 10.1109/ISITIA59021.2023.10221054

Depthwise Over-Parameterized CNN for Voxel Human Pose Classification

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this