Semantic Segmentation of Panoramic Images Using a Synthetic Dataset
arXiv:1909.00532
Abstract
Panoramic images have advantages in information capacity and scene stability due to their large field of view (FoV). In this paper, we propose a method to synthesize a new dataset of panoramic image. We managed to stitch the images taken from different directions into panoramic images, together with their labeled images, to yield the panoramic semantic segmentation dataset denominated as SYNTHIA-PANO. For the purpose of finding out the effect of using panoramic images as training dataset, we designed and performed a comprehensive set of experiments. Experimental results show that using panoramic images as training data is beneficial to the segmentation result. In addition, it has been shown that by using panoramic images with a 180 degree FoV as training data the model has better performance. Furthermore, the model trained with panoramic images also has a better capacity to resist the image distortion.
arXiv comment15 pages, 12 figures, SPIE Security + Defence International Symposium
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras
- Panoramic Annular Localizer: Tackling the Variation Challenges of Outdoor Localization Using Panoramic Annular Images and Active Deep Descriptors
- ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation
- Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective
- Orientation-aware Semantic Segmentation on Icosahedron Spheres
- Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems