在提取人体数据的问题中,使用合成数据集进行人体的语义细分
Azat Absadyk1, Olzhas Turar1, Darkhan Akhmed-Zaki1
1Department of Science and Innovation, Astana IT University, Astana, Kazakhstan.
Frontiers in artificial intelligence
|August 26, 2024
概括
这项研究开发了一种使用合成数据的语义细分模型,以准确地从图像中提取身体尺寸,改进虚拟配件并减少电子商务回报.
科学领域:
- 计算机视觉 计算机视觉
- 医疗成像医学成像
- 电子商务 技术 技术 电子商务
背景情况:
- 随着COVID-19的流行,电子商务中需要准确的虚拟尺寸来最大限度地减少退货和浪费.
- 目前用于从图像中提取人体测量数据的方法面临重大局限性.
- 从图像中准确地确定身体形状对于有效的虚拟装配解决方案至关重要.
研究的目的:
- 开发一种新的语义细分模型,从图像中精确地提取人体测量数据.
- 使用大规模合成数据集训练模型,考虑服装变化.
- 在真实世界的图像上验证模型的性能,并与实际的身体测量进行比较.
主要方法:
- 使用NVIDIA Omniverse Replicator生成了一组合成数据集,包含超过22,000张图像,其中包括各种人类模型,姿势和服装.
- 训练并评估多个卷积神经网络 (CNN) 架构,包括U-Net,SegNet,DeepLabV3和PSPNet,用于语义细分.
- 通过准确性,精度,回忆和交叉与联盟 (IoU) 度量来评估模型性能,然后对真实实体进行测试.
主要成果:
- 带有EfficientNet骨干的U-Net模型实现了卓越的性能,显示了99.83%的训练准确度和0.977 IoU得分.
- 该模型精确地从真实图像中对身体形状进行细分,有效地处理服装变化.
- 在9名受试者身上进行的测试显示,关键测量的平均偏差很小:部 (-0.24厘米),肩部 (-0.1厘米),胸部 (1.15厘米),体 (-0.22厘米) 和部 (0.17厘米).
结论:
- 开发的语义细分模型,在合成数据上进行训练,能够从真实图像中精确地提取人体识别数据,即使是穿着衣服.
- 这种方法为增强虚拟装配体验和显著降低在线零售的回报率提供了一个有希望的解决方案.
- 未来的研究将专注于改进算法,以提高特定测量的精度,如和部.
相关概念视频
03:36Genome Annotation and Assembly
The genome refers to all of the genetic material in an organism. It can range from a few million base pairs in microbial cells to several billion base pairs in many eukaryotic organisms. Genome assembly refers to the process of taking the DNA sequencing data and putting it all back together in a correct order to create a close representation of the original genome. This is followed by the identification of functional elements on the newly assembled genome, a process called genome annotation.
01:11Genome-wide Association Studies-GWAS
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
01:33Peptide Identification Using Tandem Mass Spectrometry
Tandem mass spectrometry, also known as MS/MS or MS2, is an analytical technique that employs two mass analyzers. Essentially it is a series of mass spectrometers that helps isolate a particular biomolecule and then helps study its chemical properties.
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...