Identifying Habitat Elements from Bird Images Using Deep Convolutional Neural Networks

SIMPLE SUMMARY: To assist researchers in processing large amounts of bird image data, many algorithms have been proposed, but almost all of them aim at solving the problems of bird identification and counting. We turn our attention to the recognition of habitat elements in bird images, which will help with automatically extracting habitat information from such images. To achieve this goal, we formed a dataset and implemented our proposed method with four kinds of deep convolutional neural networks, and the recognition rate reached a minimum of 89.48% and a maximum of 95.52%. The use of this method will supplement the extraction of bird image information and promote the study of the relationships between birds and habitat elements. ABSTRACT: With the rapid development of digital technology, bird images have become an important part of ornithology research data. However, due to the rapid growth of bird image data, it has become a major challenge to effectively process such a large amount of data. In recent years, deep convolutional neural networks (DCNNs) have shown great potential and effectiveness in a variety of tasks regarding the automatic processing of bird images. However, no research has been conducted on the recognition of habitat elements in bird images, which is of great help when extracting habitat information from bird images. Here, we demonstrate the recognition of habitat elements using four DCNN models trained end-to-end directly based on images. To carry out this research, an image database called Habitat Elements of Bird Images (HEOBs-10) and composed of 10 categories of habitat elements was built, making future benchmarks and evaluations possible. Experiments showed that good results can be obtained by all the tested models. ResNet-152-based models yielded the best test accuracy rate (95.52%); the AlexNet-based model yielded the lowest test accuracy rate (89.48%). We conclude that DCNNs could be efficient and useful for automatically identifying habitat elements from bird images, and we believe that the practical application of this technology will be helpful for studying the relationships between birds and habitat elements.