Jia Liang, Tian Ye, Zhang Junguo
School of Technology, Beijing Forestry University, Beijing 100083, China.
School of Microelectronics and Control Engineering, Changzhou University, Changzhou 213164, China.
Animals (Basel). 2022 Feb 11;12(4):437. doi: 10.3390/ani12040437.
Camera traps provide a feasible way for ecological researchers to observe wildlife, and they often produce millions of images of diverse species requiring classification. This classification can be automated via edge devices installed with convolutional neural networks, but networks may need to be customized per device because edge devices are highly heterogeneous and resource-limited. This can be addressed by a neural architecture search capable of automatically designing networks. However, search methods are usually developed based on benchmark datasets differing widely from camera trap images in many aspects including data distributions and aspect ratios. Therefore, we designed a novel search method conducted directly on camera trap images with lowered resolutions and maintained aspect ratios; the search is guided by a loss function whose hyper parameter is theoretically derived for finding lightweight networks. The search was applied to two datasets and led to lightweight networks tested on an edge device named NVIDIA Jetson X2. The resulting accuracies were competitive in comparison. Conclusively, researchers without knowledge of designing networks can obtain networks optimized for edge devices and thus establish or expand surveillance areas in a cost-effective way.
相机陷阱为生态研究人员观察野生动物提供了一种可行的方法，并且它们经常产生数百万张需要分类的不同物种的图像。这种分类可以通过安装了卷积神经网络的边缘设备自动完成，但由于边缘设备高度异构且资源有限，网络可能需要针对每个设备进行定制。这可以通过能够自动设计网络的神经架构搜索来解决。然而，搜索方法通常是基于基准数据集开发的，这些基准数据集在包括数据分布和宽高比在内的许多方面与相机陷阱图像有很大差异。因此，我们设计了一种新颖的搜索方法，直接在分辨率降低且宽高比保持不变的相机陷阱图像上进行；搜索由一个损失函数引导，该损失函数的超参数是从理论上推导出来的，用于寻找轻量级网络。该搜索应用于两个数据集，并得到了在名为NVIDIA Jetson X2的边缘设备上测试的轻量级网络。相比之下，所得准确率具有竞争力。总之，不具备网络设计知识的研究人员可以获得针对边缘设备优化的网络，从而以具有成本效益的方式建立或扩大监测区域。
