Analysis of object detection techniques for bird species identification

Abstract

The birdwatching community in India is extensive. Wildlife enthusiasts often face difficulty in identifying a particular bird. There exist, separately, object detection Machine Learning models as well as online directories for manual bird identification, but there is no approach combining the two for easy identification of birds in India. We present a technique that uses object detection algorithms such as Faster R-CNN and YOLOv5 to solve this challenge. Our dataset includes a total of 60 species of birds found in Maharashtra. Furthermore, these methods have been tested on datasets of various sizes to provide a thorough comparison of the two techniques and to better understand their behaviour as the dataset size and classes grow. The YOLOV5 model trained on 100 epochs for 3000 images achieved a mAP score of 0.78 whereas Detectron2 when trained on the same dataset achieved an IOU score of 0.001. These methods have not been tested on a dataset containing birds from peninsular India, particularly Maharashtra. As a result, we intend to extend the dataset and make bird identification easier for birdwatchers.