预训练深度卷积神经网络模型对相机陷阱图像的分类效率

Classification Efficiency of Pre-Trained Deep CNN Models on Camera Trap Images.

作者信息

Stančić Adam, Vyroubal Vedran, Slijepčević Vedran

机构信息

Department of Engineering, Karlovac University of Applied Sciences, Ivana Meštrovića 10, 47000 Karlovac, Croatia.

Department of Wildife Management and Nature Protection, Karlovac University of Applied Sciences, Trg J. J. Strossmayera 9, 47000 Karlovac, Croatia.

出版信息

J Imaging. 2022 Jan 20;8(2):20. doi: 10.3390/jimaging8020020.

DOI:10.3390/jimaging8020020

PMID:35200723

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8879090/

Abstract

This paper presents the evaluation of 36 convolutional neural network (CNN) models, which were trained on the same dataset (ImageNet). The aim of this research was to evaluate the performance of pre-trained models on the binary classification of images in a "real-world" application. The classification of wildlife images was the use case, in particular, those of the Eurasian lynx (lat. "Lynx lynx"), which were collected by camera traps in various locations in Croatia. The collected images varied greatly in terms of image quality, while the dataset itself was highly imbalanced in terms of the percentage of images that depicted lynxes.

摘要

本文展示了对36个卷积神经网络（CNN）模型的评估，这些模型是在相同数据集（ImageNet）上训练的。本研究的目的是评估预训练模型在“现实世界”应用中图像二分类的性能。野生动物图像的分类是应用案例，特别是欧亚猞猁（拉丁语“Lynx lynx”）的图像，这些图像是通过相机陷阱在克罗地亚各地收集的。收集到的图像在图像质量方面差异很大，而数据集本身在描绘猞猁的图像百分比方面高度不平衡。