Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach

Published in Arxiv, 2019

Zhenyu Wu, Karthik Suresh, Priya Narayanan, Hongyu Xu, Heesung Kwon and Zhangyang Wang. Arxiv Preprint. To appear in International Conference on Computer Vision (ICCV).



Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful. Despite the great success of the generic object detection methods trained on ground-to-ground images, a huge performance drop is observed when these methods are directly applied to images captured by UAVs. The unsatisfactory performance is owing to many UAV-specific nuisances, such as varying flying altitudes, adverse weather conditions, dynamically changing viewing angles, etc. Those nuisances constitute a large number of fine-grained domains, across which the detection model has to stay robust. Fortunately, UAVs will record meta-data that depict those varying attributes, which are either freely available along with the UAV images, or can be easily obtained. We propose to utilize those free meta-data in conjunction with associated UAV images to learn domain-robust features via an adversarial training framework dubbed Nuisance Disentangled Feature Transforms (NDFT), for the specific challenging problem of object detection in UAV images, achieving a substantial gain in robustness to those nuisances. We demonstrate the effectiveness of our proposed algorithm, by showing both state-of-the-art performance (single model) on two existing UAV-based object detection benchmarks.