Abstract | ||
---|---|---|
Due to the various noises, the cloud image segmentation becomes a big challenge for atmosphere prediction. CNN is capable of learning discriminative features from complex data, but this may be quite time-consuming in pixel-level segmentation problems. In this paper we propose superpixel analysis based CNN (SP-CNN) for high efficient cloud image segmentation. SP-CNN employs image over-segmentation of superpixels as basic entities to preserve local consistency. SP-CNN takes the image patches centered at representative pixels in every superpixel as input, and all superpixels are classified as cloud or non-cloud part by voting of the representative pixels. It greatly reduces the computational burden on CNN learning. In order to avoid the ambiguity from superpixel boundaries, SP-CNN selects the representative pixels uniformly from the eroded superpixels. Experimental analysis demonstrates that SP-CNN guarantees both the effectiveness and efficiency in cloud segmentation. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/IWSSIP.2017.7965591 | 2017 International Conference on Systems, Signals and Image Processing (IWSSIP) |
Keywords | Field | DocType |
Cloud image,Superpixel analysis,Convolutional neural networks,Cloud segmentation | Computer vision,Local consistency,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Pixel,Artificial intelligence,Discriminative model,Cloud computing | Conference |
ISSN | ISBN | Citations |
2157-8672 | 978-1-5090-6345-1 | 1 |
PageRank | References | Authors |
0.37 | 10 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lifang Wu | 1 | 82 | 22.35 |
Jiaoyu He | 2 | 1 | 0.37 |
Meng Jian | 3 | 59 | 8.07 |
Jianan Zhang | 4 | 1 | 0.37 |
Yunzhen Zou | 5 | 1 | 0.37 |