Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadata
This addresses the problem of UAV-based object detection suffering from variations due to UAV position, offering a new benchmark with metadata for the computer vision community, though it is incremental as it builds on existing datasets by adding metadata.
The paper introduces Archangel, a hybrid UAV-based human detection dataset with real and synthetic subsets that include position and pose metadata, and demonstrates through experiments that leveraging this metadata improves model evaluation and provides insights for optimization.
Learning to detect objects, such as humans, in imagery captured by an unmanned aerial vehicle (UAV) usually suffers from tremendous variations caused by the UAV's position towards the objects. In addition, existing UAV-based benchmark datasets do not provide adequate dataset metadata, which is essential for precise model diagnosis and learning features invariant to those variations. In this paper, we introduce Archangel, the first UAV-based object detection dataset composed of real and synthetic subsets captured with similar imagining conditions and UAV position and object pose metadata. A series of experiments are carefully designed with a state-of-the-art object detector to demonstrate the benefits of leveraging the metadata during model evaluation. Moreover, several crucial insights involving both real and synthetic data during model optimization are presented. In the end, we discuss the advantages, limitations, and future directions regarding Archangel to highlight its distinct value for the broader machine learning community.