Remote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space
- PDF / 7,795,849 Bytes
- 23 Pages / 595.276 x 790.866 pts Page_size
- 56 Downloads / 197 Views
ORIGINAL ARTICLE
Remote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space Min Wu1 · Xin Jin1
· Qian Jiang1
· Shin-jye Lee2 · Wentao Liang1 · Guo Lin1 · Shaowen Yao1
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Image colorization technique is used to colorize the gray-level image or single-channel image, which is a very significant and challenging task in image processing, especially the colorization of remote sensing images. This paper proposes a new method for coloring remote sensing images based on deep convolution generation adversarial network. The adopted generator model is a symmetrical structure using the principle of auto-encoder, and a multi-scale convolutional module is specially designed to introduce into the generator model. Thus, the proposed generator can enable the whole model to retain more image features in the process of up-sampling and down-sampling. Meanwhile, the discriminator uses residual neural network 18 that can compete with the generator, so that the generator and discriminator can effectively optimize each other. In the proposed method, the color space transformation technique is first utilized to convert remote sensing images from RGB to YUV. Then, the Y channel (a gray-level image) is used as the input of the neural network model to predict UV channels. Finally, the predicted UV channels are concatenated with the original Y channel as a whole YUV that is then transformed into RGB space to get the final color image. Experiments are conducted to test the performance of different image colorization methods, and the results show that the proposed method has good performance in both visual quality and objective indexes on the colorization of remote sensing image. Keywords Image colorization · Multi-scale convolutional · Remote sensing image · Deep convolutional generative adversarial networks
1 Introduction The colorization of gray-level images is hot research in image processing and computer vision; this technique enables people to obtain abundant visual information from the colorized images, which help to distinguish and recognize image content [1]. Image colorization has been widely used in television animation, medical image, infrared image and other fields [2–4]. With the rapid development of satellite technology, remote sensing images are extensive collected to represent Min Wu and Xin Jin have contributed equally to this work
B
Qian Jiang [email protected] Xin Jin [email protected]
1
School of Software,Yunnan University,Kunming, Yunnan, China
2
Institute of Technology Management,National Chiao Tung University,Hsinchu, Taiwan, China
geo-informatics that are significant for many fields [5–7]. To enhance the key features and improve visual effects, this paper introduces a remote sensing image colorization method that is based on the promising generative adversarial networks (GANs). There are some earliest conventional image colorization methods which can be divided into color transfer-based method (or example-ba
Data Loading...
