Machine Learning Algorithms for Image Processing and Recognition of Animal Objects in Photo-DVR Images
УДК 519.6:004.42:004.8:004.93
Abstract
The article is devoted to the development of algorithms and software for processing and analyzing camera traps images to recognize animal objects in them. The algorithms are based on computer vision technologies, image mining, machine learning, and artificial intelligence, which helps increase the speed of image processing photographs and the reliability of object recognition. The software allows processing large amounts of image data, starting from the raw set of camera traps images and up to cataloging the images by types of objects in them. It aims at improving the quality and speed of processing images and increasing the reliability of object recognition. Thus, automatic classification of images with defects (images with damaged pixels, fogged and blurred images) and no defects is essentially the first step of the proposed algorithms. Next, a deep convolutional neural network is used to identify and classify images with animals and images with no animals. Images containing humans, vehicles, and objects of nature are identified and sorted out. The detailed .CSV file report is generated with the file names of images and labels of identified objects in them.
Downloads
Metrics
References
Официальный сайт приложения «WildId ». URL: https://www.wildid.app/ (дата обращения: 15.05.2023).
Официальный сайт приложения «Timelapse: An Image Analyser for Camera Traps». URL: https://saul.cpsc.ucal-gary.ca/timelapse/ (дата обращения: 15.04.2023).
Harris G., Thompson R., Childs J.L., sanderson J.G. Automatic storage and Analysis of Camera Trap Data // Bulletin of the Ecological society of America. 2010. Vol. 91. P. 352-360. DOI: 10.1890/0012-9623-91.3.352
Sundaresan S.R., Riginos C., Abelson E.S. Management and Analysis of Camera Trap Data: Alternative Approaches (Response to Harris et al., 2010) // Bulletin of the Ecological society of America. 2011. Vol. 92. P. 188-195. DOI: 10.1890/00129623-92.2.188
Tobler M.W. Camera Base Version 1.7. User Guide. Botanical Research Institute of Texas. 2015. 38 p.
Niedballa J, Sollmann R, Courtiol A., Wilting A. CamtrapR: an R Package for Efficient Camera Trap Data Management // Methods in Ecology and Evolution. 2016. Vol. 7 (12). P. 1457-1462. DOI: 10.1111/2041-210X.12600
Есипов А.В., Головцов Д.Е., Быкова Е.А. Материалы к фауне млекопитающих и птиц западной части Чаткальского хребта по данным фотоловушек // Вестник Тюменского государственного университета. Экология и природопользование. 2015. Т. 1. № 1 (1). С. 141-150.
Сухоруков Е.Г. Опыт обработки данных фотоловушек в Тигирекском заповеднике // Труды Тигирекского заповедника. 2015. Вып. 7. С. 77-79. DOI: 10.53005/20767390_2015_7_77
Эрнандес-Бланко Х.А., Лукаревский В.С., Найден-ко С.В., Сорокин П.А., Литвинов М.Н., Чистополова М.Д., Котляр А.К., Рожнов В.В. Опыт применения цифровых фотоловушек для идентификации амурских тигров, оценки их активности и использования основных маршрутов перемещений животными // Амурский тигр в Северо-Восточной Азии: проблемы сохранения в XXI веке : материалы научно-практической конференции. Владивосток: Дальнаука. 2010. С. 100-103.
Виткалова А.В., Сторожук В.Б., Матюхина Д.С., Салманова Е.И. Мониторинг популяции дальневосточного леопарда при помощи автоматических фотокамер // Современные технологии в деятельности ООПТ: ГИС, ДЗЗ : Сб. науч. статей. Минск: А.Н. Вараксин. 2015. С. 44-45.
Copyright (c) 2024 Алексей Владимирович Ваганов, Константин Сергеевич Печененко, Любовь Анатольевна Хворова
This work is licensed under a Creative Commons Attribution 4.0 International License.
Izvestiya of Altai State University is a golden publisher, as we allow self-archiving, but most importantly we are fully transparent about your rights.
Authors may present and discuss their findings ahead of publication: at biological or scientific conferences, on preprint servers, in public databases, and in blogs, wikis, tweets, and other informal communication channels.
Izvestiya of Altai State University allows authors to deposit manuscripts (currently under review or those for intended submission to Izvestiya of Altai State University) in non-commercial, pre-print servers such as ArXiv.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
