POLO -- Point-based, multi-class animal detection
This work addresses the tedious and expensive annotation process in conservation biology for automated wildlife surveys, offering a practical improvement for researchers and practitioners.
The paper tackles the problem of reducing annotation effort for wildlife detection in drone imagery by introducing POLO, a multi-class object detection model trained on point labels instead of bounding boxes, which achieves improved accuracy in counting animals at the same annotation cost.
Automated wildlife surveys based on drone imagery and object detection technology are a powerful and increasingly popular tool in conservation biology. Most detectors require training images with annotated bounding boxes, which are tedious, expensive, and not always unambiguous to create. To reduce the annotation load associated with this practice, we develop POLO, a multi-class object detection model that can be trained entirely on point labels. POLO is based on simple, yet effective modifications to the YOLOv8 architecture, including alterations to the prediction process, training losses, and post-processing. We test POLO on drone recordings of waterfowl containing up to multiple thousands of individual birds in one image and compare it to a regular YOLOv8. Our experiments show that at the same annotation cost, POLO achieves improved accuracy in counting animals in aerial imagery.