Yang Deng-Qi, Tan Kun, Huang Zhi-Pang, Li Xiao-Wei, Chen Ben-Hui, Ren Guo-Peng, Xiao Wen
Department of Mathematics and Computer Science Dali University Dali China.
Institute of Eastern-Himalaya Biodiversity Research Dali University Dali China.
Ecol Evol. 2021 May 2;11(12):7591-7601. doi: 10.1002/ece3.7591. eCollection 2021 Jun.
Camera traps often produce massive images, and empty images that do not contain animals are usually overwhelming. Deep learning is a machine-learning algorithm and widely used to identify empty camera trap images automatically. Existing methods with high accuracy are based on millions of training samples (images) and require a lot of time and personnel costs to label the training samples manually. Reducing the number of training samples can save the cost of manually labeling images. However, the deep learning models based on a small dataset produce a large omission error of animal images that many animal images tend to be identified as empty images, which may lead to loss of the opportunities of discovering and observing species. Therefore, it is still a challenge to build the DCNN model with small errors on a small dataset. Using deep convolutional neural networks and a small-size dataset, we proposed an ensemble learning approach based on conservative strategies to identify and remove empty images automatically. Furthermore, we proposed three automatic identifying schemes of empty images for users who accept different omission errors of animal images. Our experimental results showed that these three schemes automatically identified and removed 50.78%, 58.48%, and 77.51% of the empty images in the dataset when the omission errors were 0.70%, 1.13%, and 2.54%, respectively. The analysis showed that using our scheme to automatically identify empty images did not omit species information. It only slightly changed the frequency of species occurrence. When only a small dataset was available, our approach provided an alternative to users to automatically identify and remove empty images, which can significantly reduce the time and personnel costs required to manually remove empty images. The cost savings were comparable to the percentage of empty images removed by models.
相机陷阱常常会产生海量图像，而不包含动物的空图像通常占比极大。深度学习是一种机器学习算法，被广泛用于自动识别相机陷阱空图像。现有的高精度方法基于数百万个训练样本（图像），并且需要大量时间和人力成本来手动标注训练样本。减少训练样本数量可以节省手动标注图像的成本。然而，基于小数据集的深度学习模型会产生大量动物图像遗漏错误，许多动物图像往往会被识别为空图像，这可能导致失去发现和观察物种的机会。因此，在小数据集上构建误差较小的深度卷积神经网络（DCNN）模型仍然是一项挑战。利用深度卷积神经网络和小尺寸数据集，我们提出了一种基于保守策略的集成学习方法，以自动识别和去除空图像。此外，我们针对能够接受不同动物图像遗漏错误的用户，提出了三种空图像自动识别方案。我们的实验结果表明，当遗漏错误分别为0.70%、1.13%和2.54%时，这三种方案分别自动识别并去除了数据集中50.78%、58.48%和77.51%的空图像。分析表明，使用我们的方案自动识别空图像不会遗漏物种信息。它只会略微改变物种出现的频率。当只有小数据集可用时，我们的方法为用户提供了一种自动识别和去除空图像的替代方案，这可以显著减少手动去除空图像所需的时间和人力成本。节省的成本与模型去除的空图像百分比相当。
