FAR: Fourier Aerial Video Recognition

21 Mar 2022  ·  Divya Kothandaraman, Tianrui Guan, Xijun Wang, Sean Hu, Ming Lin, Dinesh Manocha ·

We present an algorithm, Fourier Activity Recognition (FAR), for UAV video activity recognition. Our formulation uses a novel Fourier object disentanglement method to innately separate out the human agent (which is typically small) from the background. Our disentanglement technique operates in the frequency domain to characterize the extent of temporal change of spatial pixels, and exploits convolution-multiplication properties of Fourier transform to map this representation to the corresponding object-background entangled features obtained from the network. To encapsulate contextual information and long-range space-time dependencies, we present a novel Fourier Attention algorithm, which emulates the benefits of self-attention by modeling the weighted outer product in the frequency domain. Our Fourier attention formulation uses much fewer computations than self-attention. We have evaluated our approach on multiple UAV datasets including UAV Human RGB, UAV Human Night, Drone Action, and NEC Drone. We demonstrate a relative improvement of 8.02% - 38.69% in top-1 accuracy and up to 3 times faster over prior works.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Recognition Drone-Action FAR Top 1 Accuracy 92.7 # 1
Action Recognition NEC Drone FAR Top 1 Accuracy 71.46 # 1
Action Recognition UAV Human FAR Top 1 Accuracy 38.6 # 1

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Action Recognition UAV-Human FAR Top 1 Accuracy 39.1 # 2


No methods listed for this paper. Add relevant methods here