|
COMPARISON OF THE PERFORMANCE OF DIFFERENT NEURAL NETWORK ARCHITECTURES AND PRE-TRAINED NEURAL NETWORKS FOR THE CLASSIFICATION OF FOREST FLORA AND FAUNA
|
|
|
Witold Prusak; Aleksander Skrzypiec; Tymoteusz Turlej
|
|
|
||
|
10.5593/sgem2023/2.1
|
|
|
1314-2704
|
|
|
||
|
English
|
|
|
23
|
|
|
2.1
|
|
|
• Prof. DSc. Oleksandr Trofymchuk, UKRAINE
• Prof. Dr. hab. oec. Baiba Rivza, LATVIA |
|
|
||
|
The aim of this project is to compare the effectiveness of different neural network architectures and pre-trained models for the classification of forest flora and fauna. Experiments were conducted on a dataset containing images of selected plants and animals found in the forest. The project covers the basics of convolutional neural networks, and compares the architectures of the networks used in the study. The results of the experiments compare the effectiveness of different convolutional neural network architectures and pre-trained models, such as EfficientNet or ResNet50. The study includes the training times of selected neural networks, classification times of individual images, and their effectiveness. Additionally, the impact of pre-training networks on the ImageNet dataset on the quality of neural network classification was compared. The purpose of this project was to determine the neural network with the most optimal parameters for use in our robot, “Rumcajs”, which is to be used for monitoring and mapping forest flora and fauna by classifying the segmented images with Segment Anything Model from our advanced camera systems.
|
|
|
||
|
||
|
conference
|
|
|
||
|
||
|
Proceedings of 23rd International Multidisciplinary Scientific GeoConference SGEM 2023
|
|
|
23rd International Multidisciplinary Scientific GeoConference SGEM 2023, 03 - 09 July, 2023
|
|
|
Proceedings Paper
|
|
|
STEF92 Technology
|
|
|
International Multidisciplinary Scientific GeoConference SGEM
|
|
|
SWS Scholarly Society; Acad Sci Czech Republ; Latvian Acad Sci; Polish Acad Sci; Russian Acad Sci; Serbian Acad Sci and Arts; Natl Acad Sci Ukraine; Natl Acad Sci Armenia; Sci Council Japan; European Acad Sci, Arts and Letters; Acad Fine Arts Zagreb Croatia; Croatian Acad Sci and Arts; Acad Sci Moldova; Montenegrin Acad Sci and Arts; Georgian Acad Sci; Acad Fine Arts and Design Bratislava; Russian Acad Arts; Turkish Acad Sci.
|
|
|
35-40
|
|
|
03 - 09 July, 2023
|
|
|
website
|
|
|
|
|
|
9085
|
|
|
Nature, Segment Anything Model, Neural Network, Classification, Data Science
|
|