Related Concept Videos
Rise of Liquid in a Capillary Tube
Difference from Background: Limit of Detection
The LOD indicates the presence or absence...
Distillation: Vapor–Liquid Equilibria
Precipitation Titration: Endpoint Detection Methods
In the Volhard method, a standard excess of AgNO3 is first added to the...
Titration in Nonaqueous Solvents
Constant Volume Calorimetry
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Probiotic Properties of Pediococcus acidilactici Z123 and its Intervention Effects and Mechanisms on Hypercholesterolemia in Mice.
Deciphering Platelet Transcriptomic Profiles in Antiphospholipid Syndrome: Insights into Their Role as Immunological Players.
Related Experiment Video
Updated: Jul 19, 2025

Fast Inspection of Quality of Indigo Naturalis by Multiple Light Scattering
Published on: August 18, 2023
Liquid Content Detection In Transparent Containers: A Benchmark.
You Wu1, Hengzhou Ye1, Yaqing Yang1
1Guangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, China.
This study introduces a new dataset (LCDTC) for detecting liquid content in transparent containers. This advances computer vision for applications like service robots by estimating liquid presence and location.
Area of Science:
- Computer Vision
- Robotics
- Artificial Intelligence
Background:
- Liquid detection in transparent containers is crucial for daily life applications.
- Existing methods for transparent container analysis are limited, focusing on detection or complex height estimation.
- There's a need for generalized computer vision solutions for liquid content detection in real-world scenarios.
Purpose of the Study:
- To introduce the Liquid Content Detection in Transparent Containers (LCDTC) dataset.
- To propose an innovative task combining transparent container detection and liquid content estimation.
- To provide a foundation for developing advanced computer vision applications for liquid analysis.
Main Methods:
- Development of the LCDTC dataset with 5916 annotated images.
- Annotation includes axis-aligned bounding boxes for containers and liquid presence.
- Creation of two baseline detectors (LCD-YOLOF and LCD-YOLOX) using identity-preserved human posture detectors.
Main Results:
- The LCDTC dataset offers a novel approach to liquid content detection.
- Baseline detectors demonstrate feasibility for the proposed task.
- The dataset facilitates more informative computer vision analysis beyond simple container localization.
Conclusions:
- The LCDTC dataset and baseline models pave the way for enhanced liquid content detection in transparent containers.
- This work aims to stimulate further research in this challenging and practical computer vision task.
- Potential applications span service robots, security, and industrial monitoring systems.

