EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Vision-Based Deep Learning Framework for Monitoring and Recognition of Chemical Laboratory Operations

Chuntao Guo, Jing Lin, Shunxing Bao iD, Xin Liu, Yaru Wang, Yunlin Chen iD

Sensors · 2026

DOI: 10.3390/s26041106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Chuntao Guo und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Physical Science and Engineering, Beijing Jiaotong University, Beijing 100044, China. Hauptthemen laut MEDLINE: Deep Learning, Laboratories. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Provincial Administration for Market Regulation Science and Tech Plan Project, Jiangsu Provincial Administration for Market Regulation Science and Technology Plan Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Standardized operating procedures are essential for ensuring safety and reproducibility in chemical laboratory experiments. However, real-time monitoring of manual laboratory operations, such as pipetting, remains challenging due to complex human–tool interactions, temporal dependencies between procedural steps, and operator variability. In this study, we propose a vision-based deep learning framework that leverages spatiotemporal features for automated monitoring of pipetting operations using non-contact visual sensing. Briefly, human poses and pipette interactions are extracted from video recordings using a YOLO-based perception model, while temporal execution patterns are captured through bidirectional long short-term memory networks. Experimental results demonstrate that the proposed approach can reliably distinguish between standard and non-standard pipetting behaviors across multiple predefined error categories and shows improved robustness compared with static or frame-level analysis. Overall, this work demonstrates the feasibility of vision-based AI systems for objective and scalable monitoring of laboratory pipetting operations, with potential applicability to other manual laboratory procedures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningLaboratoriesHumansDetection AlgorithmsLong Short Term MemoryAlgorithms

Stichwörter der Autor:innen

laboratory quality assurancepipetting behaviorpose estimationspatiotemporal modelingvision-based sensing

Autor:innen und Institutionen

  • School of Physical Science and Engineering, Beijing Jiaotong University, Beijing 100044, China.
  • Beijing Purkinje General Instrument Co., Ltd., Beijing 100081, China.
  • Nanjing Institute of Measurement and Testing Technology, Nanjing 210049, China.
  • Institute of Analysis and Testing, Beijing Academy of Science and Technology (Beijing Center for Physical and Chemical Analysis), Beijing 100089, China.
  • School of Bioengineering, Beijing Polytechnic University, Beijing 100021, China.

ORCID-Profile: Shunxing Bao, Yunlin Chen

Förderung

  • Jiangsu Provincial Administration for Market Regulation Science and Tech Plan Project
  • Jiangsu Provincial Administration for Market Regulation Science and Technology Plan Project

Zitieren

APA

Guo, C., Lin, J., Bao, S., Liu, X., Wang, Y., & Chen, Y. (2026). A Vision-Based Deep Learning Framework for Monitoring and Recognition of Chemical Laboratory Operations. Sensors. https://doi.org/10.3390/s26041106

Vancouver

Guo C, Lin J, Bao S, Liu X, Wang Y, Chen Y. A Vision-Based Deep Learning Framework for Monitoring and Recognition of Chemical Laboratory Operations. Sensors. 2026. doi:10.3390/s26041106

BibTeX
@article{Guo2026,
  author = {Guo, Chuntao and Lin, Jing and Bao, Shunxing and Liu, Xin and Wang, Yaru and Chen, Yunlin},
  title = {A Vision-Based Deep Learning Framework for Monitoring and Recognition of Chemical Laboratory Operations},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26041106}
}
Kostenlos starten →