Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-Objects

Monitoring moving bio-objects is currently of great interest for both fundamental and practical research. The advent of deep-learning algorithms has made it possible to automate the qualitative and quantitative analysis of the behavior of bio-objects recorded in video format. When processing such da...

Full description

Saved in:
Bibliographic Details
Main Authors: Marina Barulina, Alexander Andreev, Ilya Kovalenko, Ilya Barmin, Eduard Titov, Danil Kirillov
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/24/3978
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036243871563776
author Marina Barulina
Alexander Andreev
Ilya Kovalenko
Ilya Barmin
Eduard Titov
Danil Kirillov
author_facet Marina Barulina
Alexander Andreev
Ilya Kovalenko
Ilya Barmin
Eduard Titov
Danil Kirillov
author_sort Marina Barulina
collection DOAJ
description Monitoring moving bio-objects is currently of great interest for both fundamental and practical research. The advent of deep-learning algorithms has made it possible to automate the qualitative and quantitative analysis of the behavior of bio-objects recorded in video format. When processing such data, it is necessary to consider additional factors, such as background noise in the frame, the speed of the bio-object, and the need to reflect information about the previous (past) and subsequent (future) pose of the bio-object in one video frame. The preprocessed dataset must be suitable for verification by experts. This article proposes a method for preprocessing data to identify the behavior of a bio-object, a clear example of which is experiments on laboratory animals with the collection of video data. The method is based on combining information about a behavioral event presented in a sequence of frames with the addition of a native image and subsequent boundary detection using the Sobel filter. The resulting representation of a behavioral event is easily perceived by both human experts and neural networks of various architectures. The article presents the results of training several neural networks on the obtained dataset and proposes an effective neural network architecture (F1-score = 0.95) for identifying discrete events of biological objects’ behavior.
format Article
id doaj-art-b4eabc8111a14a148cc8fc4158aef8f2
institution DOAJ
issn 2227-7390
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-b4eabc8111a14a148cc8fc4158aef8f22025-08-20T02:57:14ZengMDPI AGMathematics2227-73902024-12-011224397810.3390/math12243978Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-ObjectsMarina Barulina0Alexander Andreev1Ilya Kovalenko2Ilya Barmin3Eduard Titov4Danil Kirillov5Institute of Physics and Mathematics, Perm State University, 15 Ul. Bukireva, 614068 Perm, RussiaFaculty of Chemistry, Perm State University, 15 Ul. Bukireva, 614068 Perm, RussiaInstitute of Physics and Mathematics, Perm State University, 15 Ul. Bukireva, 614068 Perm, RussiaInstitute of Physics and Mathematics, Perm State University, 15 Ul. Bukireva, 614068 Perm, RussiaInstitute of Physics and Mathematics, Perm State University, 15 Ul. Bukireva, 614068 Perm, RussiaInstitute of Physics and Mathematics, Perm State University, 15 Ul. Bukireva, 614068 Perm, RussiaMonitoring moving bio-objects is currently of great interest for both fundamental and practical research. The advent of deep-learning algorithms has made it possible to automate the qualitative and quantitative analysis of the behavior of bio-objects recorded in video format. When processing such data, it is necessary to consider additional factors, such as background noise in the frame, the speed of the bio-object, and the need to reflect information about the previous (past) and subsequent (future) pose of the bio-object in one video frame. The preprocessed dataset must be suitable for verification by experts. This article proposes a method for preprocessing data to identify the behavior of a bio-object, a clear example of which is experiments on laboratory animals with the collection of video data. The method is based on combining information about a behavioral event presented in a sequence of frames with the addition of a native image and subsequent boundary detection using the Sobel filter. The resulting representation of a behavioral event is easily perceived by both human experts and neural networks of various architectures. The article presents the results of training several neural networks on the obtained dataset and proposes an effective neural network architecture (F1-score = 0.95) for identifying discrete events of biological objects’ behavior.https://www.mdpi.com/2227-7390/12/24/3978deep-learning modelsvideo data preprocessingpose reflectionmoving bio-objectsdata-preprocessing method
spellingShingle Marina Barulina
Alexander Andreev
Ilya Kovalenko
Ilya Barmin
Eduard Titov
Danil Kirillov
Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-Objects
Mathematics
deep-learning models
video data preprocessing
pose reflection
moving bio-objects
data-preprocessing method
title Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-Objects
title_full Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-Objects
title_fullStr Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-Objects
title_full_unstemmed Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-Objects
title_short Method for Preprocessing Video Data for Training Deep-Learning Models for Identifying Behavioral Events in Bio-Objects
title_sort method for preprocessing video data for training deep learning models for identifying behavioral events in bio objects
topic deep-learning models
video data preprocessing
pose reflection
moving bio-objects
data-preprocessing method
url https://www.mdpi.com/2227-7390/12/24/3978
work_keys_str_mv AT marinabarulina methodforpreprocessingvideodatafortrainingdeeplearningmodelsforidentifyingbehavioraleventsinbioobjects
AT alexanderandreev methodforpreprocessingvideodatafortrainingdeeplearningmodelsforidentifyingbehavioraleventsinbioobjects
AT ilyakovalenko methodforpreprocessingvideodatafortrainingdeeplearningmodelsforidentifyingbehavioraleventsinbioobjects
AT ilyabarmin methodforpreprocessingvideodatafortrainingdeeplearningmodelsforidentifyingbehavioraleventsinbioobjects
AT eduardtitov methodforpreprocessingvideodatafortrainingdeeplearningmodelsforidentifyingbehavioraleventsinbioobjects
AT danilkirillov methodforpreprocessingvideodatafortrainingdeeplearningmodelsforidentifyingbehavioraleventsinbioobjects