Abstract
Collisions of birds, especially endangered species, with wind turbines is a major environmental concern. Automatic bird monitoring can be of aid in resolving the issue, particularly in environmental risk assessments and real-time collision avoidance. For automatic recognition of birds in images, a clean, detailed, and realistic dataset to learn features and classifiers is crucial for any machine-learning-based method. Here, we constructed a bird image dataset that is derived from the actual environment of a wind farm and that is useful for examining realistic challenges in bird recognition in practice. It consists of high-resolution images covering a wide monitoring area around a turbine. The birds captured in these images are at relatively low resolution and are hierarchically labeled by experts for fine-grained species classification. We conducted evaluations of state-of-the-art image recognition methods by using this dataset. The evaluations revealed that a deep-learning-based method and a simpler traditional learning method were almost equally successful at detection, while the former captures more generalized features. The most promising results were provided by the deep-learning-based method in classification. The best methods in our experiments recorded a 0.98 true positive rate for bird detection at a false positive rate of 0.05 and a 0.85 true positive rate for species classification at a false positive rate of 0.1.