Graph-Based Classification of Omnidirectional Images

By Pascal Frossard, Renata Khasanova. 2017

72 citations recorded by the source corpus.

Omnidirectional cameras are widely used in such areas as robotics and virtual reality as they provide a wide field of view. Their images are often processed with classical methods, which might unfortunately lead to non-optimal solutions as these methods are designed for planar images that have different geometrical properties than omnidirectional ones. In this paper we study image classification task by taking into account the specific geometry of omnidirectional cameras with graph-based representations. In particular, we extend deep learning architectures to data on graphs; we propose a principled way of graph construction such that convolutional filters respond similarly for the same pattern on different positions of the image regardless of lens distortions. Our experiments show that the proposed method outperforms current techniques for the omnidirectional image classification problem.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network (2018, methodology): “Learning images on the sphere in a rotation invariant way has applications in a wide range of domains from 360 degree video through drone navigation to molecular chemistry [9, 10, 11, 12, 13, 14, 15].”
DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications (2018, methodology): “For example, [35] uses the inverse of the distance instead.”
DeepSphere: a graph-based spherical CNN (2020, methodology): “Figure 2 shows that the weighting scheme (4) from (Khasanova & Frossard, 2017) does indeed not lead to a convolution that is equivariant to all rotations g ∈ SO(3).7 For k = 8 neighbors, selecting the optimal kernel width t improves on (Perraudin et al., 2019) at no cost, highlighting the…”
Learning Spherical Convolution for Fast Features from 360° Imagery (2017, methodology): “Some recent work studies convolution on a sphere [6, 24] using spectral analysis, but those methods require manually annotated spherical images as training data, whereas our method can exploit existing models trained on perspective images as supervision.”
Kernel Transformer Networks for Compact Spherical Convolution (2018, background): “One approach is to apply graph convolution and design the graph structure [24] such that the outputs are rotation invariant.”
SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images (2018, methodology): “[14] and the spherical convolutional model of Cohen et al.”