Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud Data
Automatic garment size measurement approaches using computer vision algorithms have been attempted in various ways, but there are still many limitations to overcome. One limitation is that the process involves 2D images, which results in constraints in the process of determining the actual distance...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/10/5286 |
_version_ | 1797501687411245056 |
---|---|
author | Seounggeun Kim Haejun Moon Jaehoon Oh Yonghak Lee Hyun Kwon Sunghwan Kim |
author_facet | Seounggeun Kim Haejun Moon Jaehoon Oh Yonghak Lee Hyun Kwon Sunghwan Kim |
author_sort | Seounggeun Kim |
collection | DOAJ |
description | Automatic garment size measurement approaches using computer vision algorithms have been attempted in various ways, but there are still many limitations to overcome. One limitation is that the process involves 2D images, which results in constraints in the process of determining the actual distance between the estimated points. To solve this problem, in this paper, we propose an automated method for measuring garment sizes using computer vision deep learning models and point cloud data. In the proposed method, a deep learning-based keypoint estimation model is first used to capture the clothing size measurement points from 2D images. Then, point cloud data from a LiDAR sensor are used to provide real-world distance information to calculate the actual clothing sizes. As the proposed method uses a mobile device equipped with a LiDAR sensor and camera, it is also more easily configurable than extant methods, which have varied constraints. Experimental results show that our method is not only precise but also robust in measuring the size regardless of the shape, direction, or design of the clothes in two different environments, with 1.59% and 2.08% of the average relative error, respectively. |
first_indexed | 2024-03-10T03:22:09Z |
format | Article |
id | doaj.art-18f0c4bec8924a54ab208ae2f97ee591 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T03:22:09Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-18f0c4bec8924a54ab208ae2f97ee5912023-11-23T10:00:28ZengMDPI AGApplied Sciences2076-34172022-05-011210528610.3390/app12105286Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud DataSeounggeun Kim0Haejun Moon1Jaehoon Oh2Yonghak Lee3Hyun Kwon4Sunghwan Kim5Department of Applied Statistics, Konkuk University, Seoul 05029, KoreaDepartment of Applied Statistics, Konkuk University, Seoul 05029, KoreaDepartment of Applied Statistics, Konkuk University, Seoul 05029, KoreaDepartment of Applied Statistics, Konkuk University, Seoul 05029, KoreaDepartment of Artificial Intelligence and Data Science, Korea Military Academy, Seoul 01819, KoreaDepartment of Applied Statistics, Konkuk University, Seoul 05029, KoreaAutomatic garment size measurement approaches using computer vision algorithms have been attempted in various ways, but there are still many limitations to overcome. One limitation is that the process involves 2D images, which results in constraints in the process of determining the actual distance between the estimated points. To solve this problem, in this paper, we propose an automated method for measuring garment sizes using computer vision deep learning models and point cloud data. In the proposed method, a deep learning-based keypoint estimation model is first used to capture the clothing size measurement points from 2D images. Then, point cloud data from a LiDAR sensor are used to provide real-world distance information to calculate the actual clothing sizes. As the proposed method uses a mobile device equipped with a LiDAR sensor and camera, it is also more easily configurable than extant methods, which have varied constraints. Experimental results show that our method is not only precise but also robust in measuring the size regardless of the shape, direction, or design of the clothes in two different environments, with 1.59% and 2.08% of the average relative error, respectively.https://www.mdpi.com/2076-3417/12/10/5286garment measurementLiDARpoint cloud datadeep leaningconvolutional neural networkskeypoint estimation |
spellingShingle | Seounggeun Kim Haejun Moon Jaehoon Oh Yonghak Lee Hyun Kwon Sunghwan Kim Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud Data Applied Sciences garment measurement LiDAR point cloud data deep leaning convolutional neural networks keypoint estimation |
title | Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud Data |
title_full | Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud Data |
title_fullStr | Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud Data |
title_full_unstemmed | Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud Data |
title_short | Automatic Measurements of Garment Sizes Using Computer Vision Deep Learning Models and Point Cloud Data |
title_sort | automatic measurements of garment sizes using computer vision deep learning models and point cloud data |
topic | garment measurement LiDAR point cloud data deep leaning convolutional neural networks keypoint estimation |
url | https://www.mdpi.com/2076-3417/12/10/5286 |
work_keys_str_mv | AT seounggeunkim automaticmeasurementsofgarmentsizesusingcomputervisiondeeplearningmodelsandpointclouddata AT haejunmoon automaticmeasurementsofgarmentsizesusingcomputervisiondeeplearningmodelsandpointclouddata AT jaehoonoh automaticmeasurementsofgarmentsizesusingcomputervisiondeeplearningmodelsandpointclouddata AT yonghaklee automaticmeasurementsofgarmentsizesusingcomputervisiondeeplearningmodelsandpointclouddata AT hyunkwon automaticmeasurementsofgarmentsizesusingcomputervisiondeeplearningmodelsandpointclouddata AT sunghwankim automaticmeasurementsofgarmentsizesusingcomputervisiondeeplearningmodelsandpointclouddata |