当前位置: X-MOL 学术Ecol. Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A systematic study of the class imbalance problem: Automatically identifying empty camera trap images using convolutional neural networks
Ecological Informatics ( IF 5.1 ) Pub Date : 2021-06-10 , DOI: 10.1016/j.ecoinf.2021.101350
Deng-Qi Yang , Tao Li , Meng-Tao Liu , Xiao-Wei Li , Ben-Hui Chen

Camera traps, which are widely used in wildlife surveys, often produce massive images, and many of them are empty images not contain animals. Using the deep learning model to automatically identify the empty camera trap images can reduce the workload of manual classification significantly. However, the performance of deep learning models is easily affected by the class imbalance problem of training datasets, which is a common problem for actual wildlife survey projects. Almost all previous studies on empty image recognition used down-sampling or oversampling methods to eliminate the effect of class imbalance on the performance of deep learning classifiers. The class imbalance problem has been systematically studied in the field of traditional image recognition, yet very limited research is available in the context of identifying camera trap images taken from highly cluttered natural scenes. This study systematically studied the impact of class imbalance on model performance when using a deep learning model to identify empty camera trap images. Then we proposed the construction method of training sets of the deep learning model when the data set has different class imbalance levels. Based on results from our experiments we concluded that (i) the class imbalance showed little effect on the performance of the model when the empty image ratio (EIR) in the data set was between 10% and 70%, so the training sets can be randomly built without changing the class distribution; (ii) we recommended using oversampling to partially eliminate class imbalance to reduce omission errors when the EIR of the data set exceeded 70%; (iii) when the EIRs of the training set and the test set were close, the overall error, omission error, and commission error of the model were relatively smaller, and the model tended to achieve a better overall performance; (iv) the omission and commission errors can be adjusted by changing the percentage of empty images in the training set.



中文翻译:

类不平衡问题的系统研究:使用卷积神经网络自动识别空相机陷阱图像

在野生动物调查中广泛使用的相机陷阱通常会产生大量图像,其中许多是不含动物的空图像。使用深度学习模型自动识别空相机陷阱图像可以显着减少人工分类的工作量。然而,深度学习模型的性能很容易受到训练数据集类别不平衡问题的影响,这是实际野生动物调查项目的常见问题。之前几乎所有关于空图像识别的研究都使用下采样或过采样的方法来消除类不平衡对深度学习分类器性能的影响。类不平衡问题在传统图像识别领域得到了系统的研究,然而,在识别从高度混乱的自然场景中拍摄的相机陷阱图像的背景下,可用的研究非常有限。本研究系统地研究了使用深度学习模型识别空相机陷阱图像时类不平衡对模型性能的影响。然后我们提出了当数据集具有不同类别不平衡程度时深度学习模型训练集的构建方法。根据我们的实验结果,我们得出结论:(i)当数据集中的空图像比率(EIR)在 10% 到 70% 之间时,类不平衡对模型的性能几乎没有影响,因此训练集可以在不改变类分布的情况下随机构建;(ii) 当数据集的 EIR 超过 70% 时,我们建议使用过采样来部分消除类不平衡以减少遗漏错误;(iii) 当训练集和测试集的 EIR 接近时,模型的整体误差、遗漏误差和委托误差相对较小,模型整体性能趋于较好;(iv) 可以通过改变训练集中空图像的百分比来调整遗漏和委托错误。

更新日期:2021-06-21
down
wechat
bug