Dr. Fan-Qiang Kong Profile

Dr. Fan-Qiang Kong

Associate Professor at Nanjing Univ of Aeronautics and Astronautics

SPIE Involvement:

Author

Publications (6)

SPIE Journal Paper | 4 September 2024

End-to-end feature domain residual coding network for multispectral image compression based on interspectral prediction

Fanqiang Kong, Murong Huang, Jiahui Tang, Guanglong Ren

JARS, Vol. 18, Issue 03, 036508, (September 2024) https://doi.org/10.1117/12.10.1117/1.JRS.18.036508

KEYWORDS: Image compression, Multispectral imaging, Image restoration, Feature extraction, Video coding, Image quality, Education and training, Network architectures, Neural networks, Image transmission

Read Abstract +

SPIE Journal Paper | 13 September 2022

End-to-end deep multispectral image compression based on interspectral prediction network

Fanqiang Kong, Yuxin Meng, Dan Li, Kedi Hu

JARS, Vol. 16, Issue 03, 036516, (September 2022) https://doi.org/10.1117/12.10.1117/1.JRS.16.036516

KEYWORDS: Image compression, Multispectral imaging, JPEG2000, Image quality, Computer programming, Image restoration, Video compression, Quantization, Satellites, Convolution

Read Abstract +

SPIE Journal Paper | 28 May 2022

Spatial–spectral feature deep extraction based on a multichannel grouping fusion module for multispectral image compression

Fangqiang Kong, Kang Wang, Dan Li, Kedi Hu

JEI, Vol. 31, Issue 03, 033024, (May 2022) https://doi.org/10.1117/12.10.1117/1.JEI.31.3.033024

KEYWORDS: Image compression, Multispectral imaging, Image fusion, Feature extraction, Computer programming, JPEG2000, Image processing, Convolution, Landsat, Earth observing sensors

Read Abstract +

SPIE Journal Paper | 12 February 2021

End-to-end multispectral image compression framework based on adaptive multiscale feature extraction

Fanqiang Kong, Shunmin Zhao, Yunsong Li, Dan Li

JEI, Vol. 30, Issue 01, 013010, (February 2021) https://doi.org/10.1117/12.10.1117/1.JEI.30.1.013010

KEYWORDS: Image compression, Multispectral imaging, Feature extraction, Computer programming, 3D image reconstruction, Image quality, JPEG2000, Quantization, Convolution, Satellites

Read Abstract +

Multispectral image compression can considerably reduce the volume of data and promote their application. However, conventional single-scale compression schemes, such as JPEG2000 and three-dimensional set partitioning in hierarchical tree (3D-SPIHT), do not accurately preserve the features of images due to the complex features of multispectral images. A compression framework based on adaptive multiscale feature extraction with a convolutional neural network is proposed. First, an adaptive multiscale feature extraction module, which is the basic component of the compression framework, is designed to extract the multiscale spatial–spectral features of the multispectral images and adaptively adjust the weights of the features according to the content of the images. Second, the encoder, which is composed of multiscale feature extraction modules, extracts the multiscale spatial–spectral features of the multispectral images, and the extracted features are quantized and encoded by the quantizer and the entropy coder to generate a compressed bitstream. Third, the decoder, which is structurally similar to the encoder, is utilized to recover the images. The rate-distortion optimizer is embedded in the encoder to control the trade-off between the rate loss and the distortion. The results of these experiments on multispectral images of the Landsat 8 satellite and the WorldView-3 satellite validate the better performance of our compression framework compared with the performances of conventional schemes, including JPEG2000 and 3D-SPIHT. In order to further verify the effectiveness of multiscale features, the framework is compared with a single-scale compression algorithm based on deep learning, the experimental results validate that the performance of the single-scale compression algorithm superior to the conventional schemes but inferior to our multiscale algorithm, which indicates that the multiscale features can significantly improve the performance of the compression algorithm.

Proceedings Article | 5 September 2008 Paper

A new pipelined VLSI architecture for JPEG-LS compression algorithm

Jie Lei, Yunsong Li, Fanqiang Kong, Chengke Wu

Proceedings Volume 7084, 70840O (2008) https://doi.org/10.1117/12.794543

KEYWORDS: Image compression, Computer programming, Error analysis, Very large scale integration, Image processing, Radium, Rubidium, Data processing, Image quality, Image quality standards

Read Abstract +

Proceedings Article | 5 September 2008 Paper

Interferential multi-spectral image compression based on distributed source coding

Xian-yun Wu, Yun-song Li, Cheng-ke Wu, Fan-qiang Kong

Proceedings Volume 7084, 70840R (2008) https://doi.org/10.1117/12.793507

KEYWORDS: Image compression, Computer programming, Data compression, Distortion, Algorithm development, Multispectral imaging, JPEG2000, Image quality, Reconstruction algorithms, Silicon

Read Abstract +

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years