.png){kind=icon}
.png){kind=icon}
Return
Hyperspectral image compression based on multiple priors
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jfranklin.2024.107056.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The existing hyperspectral image data contain significant local and non-local spatial redundancy, as well as a large amount of spectral redundancy. However, current algorithms inadequately explore these redundant information, limiting the compression performance. To address this issue, this paper introduces a lossy compression algorithm for hyperspectral images, named THSIC(Transformer-based HyperSpectral Image Compression). This algorithm first utilizes a channel-spatial attention module to fully exploit spatial and spectral redundancies in hyperspectral images, resulting in a better latent representation. Subsequently, the Transformer and CNN-based hyperprior branches are employed to extract non-local and local redundant information from the latent representation, respectively. These two hyperprior information, along with the locally contextual prior extracted from the local context, are fused to construct multiple hyperprior information. Then, a more accurate entropy model is built using these priors, thereby enhancing the rate-distortion performance of lossy compression for hyperspectral images.
Keywords:
Hyperspectral image compression
Learned image compression
Multiple prior
Journal
J
IF:
3.7
Papers:
6.3K
Citations:
1.5W