Saved in:
Bibliographic Details
Main Authors: Li, Mingyue, Yang, Xin, Yan, Shilin, Ran, Jinye, Zhu, Morui, Peng, Zirui, Peng, Huanqing, Peng, Wei, Zhang, Guanghua, Li, Shuo, Zhang, Hao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.10782
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911506172477440
author Li, Mingyue
Yang, Xin
Yan, Shilin
Ran, Jinye
Zhu, Morui
Peng, Zirui
Peng, Huanqing
Peng, Wei
Zhang, Guanghua
Li, Shuo
Zhang, Hao
author_facet Li, Mingyue
Yang, Xin
Yan, Shilin
Ran, Jinye
Zhu, Morui
Peng, Zirui
Peng, Huanqing
Peng, Wei
Zhang, Guanghua
Li, Shuo
Zhang, Hao
contents Reliable visual monitoring of chemical experiments remains challenging in transparent glassware, where weak phase boundaries and optical artifacts degrade conventional segmentation. We formulate laboratory phenomena as the time evolution of phase interfaces and introduce the Chemical Transparent Glasses dataset 2.0 (CTG 2.0), a vessel-aware benchmark with 3,668 images, 23 glassware categories, and five multiphase interface types for phase-interface instance segmentation. Building on YOLO11m-seg, we propose LGA-RCM-YOLO, which combines Local-Global Attention (LGA) for robust semantic representation and a Rectangular Self-Calibration Module (RCM) for boundary refinement of thin, elongated interfaces. On CTG 2.0, the proposed model achieves 84.4% AP@0.5 and 58.43% AP@0.5-0.95, improving over the YOLO11m baseline by 6.42 and 8.75 AP points, respectively, while maintaining near real-time inference (13.67 FPS, RTX 3060). An auxiliary color-attribute head further labels liquid instances as colored or colorless with 98.71% precision and 98.32% recall. Finally, we demonstrate continuous process monitoring in separatory-funnel phase separation and crystallization, showing that phase-interface instance segmentation can serve as a practical visual sensor for laboratory automation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10782
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Phase-Interface Instance Segmentation as a Visual Sensor for Laboratory Process Monitoring
Li, Mingyue
Yang, Xin
Yan, Shilin
Ran, Jinye
Zhu, Morui
Peng, Zirui
Peng, Huanqing
Peng, Wei
Zhang, Guanghua
Li, Shuo
Zhang, Hao
Computer Vision and Pattern Recognition
Reliable visual monitoring of chemical experiments remains challenging in transparent glassware, where weak phase boundaries and optical artifacts degrade conventional segmentation. We formulate laboratory phenomena as the time evolution of phase interfaces and introduce the Chemical Transparent Glasses dataset 2.0 (CTG 2.0), a vessel-aware benchmark with 3,668 images, 23 glassware categories, and five multiphase interface types for phase-interface instance segmentation. Building on YOLO11m-seg, we propose LGA-RCM-YOLO, which combines Local-Global Attention (LGA) for robust semantic representation and a Rectangular Self-Calibration Module (RCM) for boundary refinement of thin, elongated interfaces. On CTG 2.0, the proposed model achieves 84.4% AP@0.5 and 58.43% AP@0.5-0.95, improving over the YOLO11m baseline by 6.42 and 8.75 AP points, respectively, while maintaining near real-time inference (13.67 FPS, RTX 3060). An auxiliary color-attribute head further labels liquid instances as colored or colorless with 98.71% precision and 98.32% recall. Finally, we demonstrate continuous process monitoring in separatory-funnel phase separation and crystallization, showing that phase-interface instance segmentation can serve as a practical visual sensor for laboratory automation.
title Phase-Interface Instance Segmentation as a Visual Sensor for Laboratory Process Monitoring
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.10782