FIELD: measuring.
SUBSTANCE: disclosed invention relates to laboratory studies, data processing in which is based on deep learning, and specifically to a method of changing the level and volume of liquid in transparent containers. Method of changing the level and volume of liquid in transparent containers includes using a graduated cylinder as a liquid container and a chamber with a support, then calibrating the camera, creating a data set with more than 214 images, which are divided into a data set for training (70%), verification (20%) and testing (10%), each of which contains a graduated cylinder filled with a transparent liquid at random levels, on some images the graduated cylinder remains empty without liquid, each image is annotated with three classes using an annotation tool.
EFFECT: providing high-precision and fast measurement of liquid level (and liquid volume) using deep learning technology.
1 cl, 6 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| DEVICE FOR MEASURING DYNAMIC CONTACT ANGLE IN A CHANNEL | 2022 |
|
RU2794420C1 |
| METHOD FOR MEASURING DYNAMIC CONTACT ANGLE IN A CHANNEL | 2021 |
|
RU2776634C1 |
| METHOD FOR DETECTION AND CLASSIFICATION OF COLOR IMAGES OF NUCLEATED BLOOD AND BONE MARROW CELLS WHEN FORMING DIAGNOSTIC CONCLUSION IN ONCOHEMATOLOGY | 2024 |
|
RU2837299C1 |
| TRAINING GAN (GENERATIVE ADVERSARIAL NETWORKS) TO CREATE PIXEL-BY-PIXEL ANNOTATION | 2019 |
|
RU2735148C1 |
| METHOD OF CONTROLLING ON-BOARD SYSTEMS OF UNMANNED VEHICLES USING NEURAL NETWORKS BASED ON ARCHITECTURE OF TRANSFORMERS | 2024 |
|
RU2841111C1 |
| SYSTEM AND METHOD FOR DETECTION OF WEAR AND LOSS OF BIT FOR EARTHWORK | 2022 |
|
RU2825885C1 |
| WAY TO TRAIN DEEP LEARNING NEURAL MODEL USING IMAGES AND DATA FROM POINT CLOUDS AT SAME TIME | 2023 |
|
RU2832583C1 |
| METHOD FOR PROVIDING COMPUTER VISION | 2022 |
|
RU2791587C1 |
| MILK ANALYSER FOR MILK CLASSIFICATION | 2019 |
|
RU2794708C2 |
| SEGMENTATION AND PREDICTION OF TIME PATTERNS OF LOW LEVEL TRAILS | 2020 |
|
RU2783420C1 |
