DCPB: Deformable Convolution Based on the Poincare Ball for Top-view Fisheye Cameras

The accuracy of the visual tasks for top-view fisheye cameras is limited by the Euclidean geometry for pose-distorted objects in images. In this paper, we demonstrate the analogy between the fisheye model and the Poincare ball and that learning the shape of convolution kernels in the Poincare Ball can alleviate the spatial distortion problem. In particular, we propose the Deformable Convolution based on the Poincare Ball, named DCPB, which conducts the Graph Convolutional Network (GCN) in the Poincare ball and calculates the geodesic distances to Poincare hyperplanes as the offsets and modulation scalars of the modulated deformable convolution. Besides, we explore an appropriate network structure in the baseline with the DCPB. The DCPB markedly improves the neural network's performance. Experimental results on the public dataset THEODORE show that DCPB obtains a higher accuracy, and its efficiency demonstrates the potential for using temporal information in fisheye videos.