Back to Search
Start Over
SpherePHD: Applying CNNs on 360 Images With Non-Euclidean Spherical PolyHeDron Representation
- Source :
- IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:834-847
- Publication Year :
- 2022
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2022.
-
Abstract
- Omni-directional images are becoming more prevalent for understanding the scene of all directions around a camera, as they provide a much wider field-of-view (FoV) compared to conventional images. In this work, we present a novel approach to represent omni-directional images and suggest how to apply CNNs on the proposed image representation. The proposed image representation method utilizes a spherical polyhedron to reduce distortion introduced inevitably when sampling pixels on a non-Euclidean spherical surface around the camera center. To apply convolution operation on our representation of images, we stack the neighboring pixels on top of each pixel and multiply with trainable parameters. This approach enables us to apply the same CNN architectures used in conventional Euclidean 2D images on our proposed method in a straightforward manner. Compared to the previous work, we additionally compare different designs of kernels that can be applied to our proposed method. We also show that our method outperforms in monocular depth estimation task compared to other state-of-the-art representation methods of omni-directional images. In addition, we propose a novel method to fit bounding ellipses of arbitrary orientation using object detection networks and apply it to an omni-directional real-world human detection dataset.
- Subjects :
- Pixel
Orientation (computer vision)
business.industry
Computer science
Applied Mathematics
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Ellipse
Convolutional neural network
Object detection
Convolution
Computational Theory and Mathematics
Kernel (image processing)
Artificial Intelligence
Non-Euclidean geometry
Computer Science::Computer Vision and Pattern Recognition
Distortion
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Computer vision
Computer Vision and Pattern Recognition
Artificial intelligence
Representation (mathematics)
business
Software
Subjects
Details
- ISSN :
- 19393539 and 01628828
- Volume :
- 44
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Accession number :
- edsair.doi...........4243eb69d18b2ec5a84b785fb831ee3d